From 19cb6ccc6b0682bc7dbb6a138c38b442a1a6b2a0 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Thu, 1 Jan 2026 01:26:30 -0500 Subject: [PATCH 01/16] ~update code, small changes --- .env | 11 + CODE_OF_CONDUCT.md | 3 + MIR.egg-info/PKG-INFO | 34 +- MIR.egg-info/SOURCES.txt | 22 +- mir/mir.json | 13254 +------------------------------------ 5 files changed, 35 insertions(+), 13289 deletions(-) create mode 100644 .env diff --git a/.env b/.env new file mode 100644 index 0000000..74c2435 --- /dev/null +++ b/.env @@ -0,0 +1,11 @@ +# Should Not Change +LOGO_BASE_URL="https://raw.githubusercontent.com/darkshapes/entity-statement/refs/heads/main/png/" +DOC_PATH="darkshapes.github.io/public/docs" + +# May Change +VENV=".venv" +DOC_REPO_CLONE="${HOME}/Documents/GitHub/darkshapes/" +SKIP_DOCS=0 + +# Change Every Time +LOGO_PATH="mir/mir75_dark.png" \ No newline at end of file diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index 0242a25..5d216f1 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -25,6 +25,9 @@ Version = 0.0.5_2025-22-12 | Creepy Vibes... | Unacceptable. Words and flirts CAN hurt. End coercion. | | Users vs Developers | Everyone involved, anywhere. Skill DIVERSITY, not division. | +\*More behavior guidelines +https://www.recurse.com/social-rules + ## Constructive Criticism Guide: - Ask consent first. Don't forget to wait for the answer! diff --git a/MIR.egg-info/PKG-INFO b/MIR.egg-info/PKG-INFO index 970ed4f..678b0bd 100644 --- a/MIR.egg-info/PKG-INFO +++ b/MIR.egg-info/PKG-INFO @@ -70,10 +70,10 @@ This repo is an example development implementation of autogenerated model infere > > ## Example: > -> ## mir : model . transformer . clip-l : stable-diffusion-xl +> ## mir : // model . vit . clip-l : stable-diffusion-xl > > ``` -> mir : model . lora . hyper : flux-1 +> mir : // model . lora . hyper : flux-1 > ↑ ↑ ↑ ↑ ↑ > [URI]:[Domain].[Architecture].[Series]:[Compatibility] > ``` @@ -132,27 +132,28 @@ Meant to be created by standards community, derived from code and file analysis | Abbreviation | Description | | ------------------------------------- | ----------------------------------------- | +|
AET
| Autoencoding Transformer | +|
ART
| Autoregressive Transformer | +|
BRNN
| Bi-directional Recurrent Neural Network | +|
CNN
| Convolutional Neural Network | +|
CONTROLNET
| Controlnet | +|
DETR
| Detection Transformer | +|
GAN
| Generative Adversarial Model | |
GRU
| Gated recurrent unit | -|
RBM
| Restricted Boltzmann machine | -|
TAE
| Tiny Autoencoder | -|
VAE
| Variable Autoencoder | +|
LORA
| Low-Rank Adaptation | |
LSTM
| Long Short-Term Memory | -|
RESNET
| Residual Network | -|
CNN
| Convolutional Neural Network | +|
MOE
| Mixture of Experts | +|
RBM
| Restricted Boltzmann machine | |
RCNN
| Region-based Convolutional Neural Network | +|
RESNET
| Residual Network | |
RNN
| Recurrent Neural Network | -|
BRNN
| Bi-directional Recurrent Neural Network | -|
GAN
| Generative Adversarial Model | |
SSM
| State-Space Model | -|
DETR
| Detection Transformer | -|
VIT
| Vision Transformer | -|
MOE
| Mixture of Experts | -|
AET
| Autoencoding Transformer | |
STST
| Sequence-to-Sequence Transformer | -|
ART
| Autoregressive Transformer | -|
LORA
| Low-Rank Adaptation | -|
CONTROLNET
| Controlnet | +|
TAE
| Tiny Autoencoder | |
UNCLASSIFIED
| Unknown | +|
VAE
| Variable Autoencoder | +|
VLA
| Vision Language Action | +|
VIT
| Vision Transformer | -- @@ -196,6 +197,7 @@ MIR is inspired by: +[![mir pytest](https://github.com/darkshapes/MIR/actions/workflows/mir.yml/badge.svg)](https://github.com/darkshapes/MIR/actions/workflows/mir.yml) ![commits per month](https://img.shields.io/github/commit-activity/m/darkshapes/MIR?color=indigo)
![code size](https://img.shields.io/github/languages/code-size/darkshapes/MIR?color=navy)
[](https://discord.gg/VVn9Ku74Dk)
diff --git a/MIR.egg-info/SOURCES.txt b/MIR.egg-info/SOURCES.txt index 101d0c4..23176a9 100644 --- a/MIR.egg-info/SOURCES.txt +++ b/MIR.egg-info/SOURCES.txt @@ -1,4 +1,5 @@ .gitignore +CODE_OF_CONDUCT.md LICENSE README.md pyproject.toml @@ -10,25 +11,6 @@ MIR.egg-info/dependency_links.txt MIR.egg-info/entry_points.txt MIR.egg-info/requires.txt MIR.egg-info/top_level.txt -docs/index.html -docs/mir.html -docs/search.js -docs/mir/automata.html -docs/mir/config.html -docs/mir/doc_parser.html -docs/mir/indexers.html -docs/mir/inspect.html -docs/mir/maid.html -docs/mir/run.html -docs/mir/tag.html -docs/mir/config/constants.html -docs/mir/config/conversion.html -docs/mir/config/json_io.html -docs/mir/inspect/classes.html -docs/mir/inspect/metadata.html -docs/mir/inspect/parenting.html -docs/mir/inspect/pipes.html -docs/mir/inspect/tasks.html mir/__init__.py mir/__main__.py mir/automata.py @@ -38,10 +20,10 @@ mir/maid.py mir/mir.json mir/tag.py mir/config/__init__.py +mir/config/console.py mir/config/constants.py mir/config/conversion.py mir/config/json_io.py -mir/config/logging.py mir/inspect/__init__.py mir/inspect/classes.py mir/inspect/metadata.py diff --git a/mir/mir.json b/mir/mir.json index 2cba92d..59ae13b 100644 --- a/mir/mir.json +++ b/mir/mir.json @@ -1,13255 +1,3 @@ { - "info.dit.allegro": { - "*": { - "repo": "rhymes-ai/Allegro", - "pkg": { - "0": { - "diffusers": "AllegroPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "guidance_scale": 7.5, - "max_sequence_length": 512, - "num_inference_steps": 100 - } - } - }, - "file_256": [ - "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" - ], - "layer_b3": [ - "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" - ], - "layer_256": [ - "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "allegro" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "allegro" - ], - "transformer": [ - "AllegroTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.amused-512": { - "*": { - "repo": "amused/amused-512", - "pkg": { - "0": { - "diffusers": "AmusedInpaintPipeline" - } - }, - "pipe_names": { - "vqvae": [ - "VQModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "amused-512" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "transformer": [ - "UVit2DModel" - ], - "scheduler": [ - "ops.scheduler.amused", - "scheduler" - ] - } - } - }, - "info.lora.animatediff-motion-adapter-v1-5-2": { - "*": { - "repo": "guoyww/animatediff-motion-adapter-v1-5-2", - "pkg": { - "0": { - "diffusers": "AnimateDiffVideoToVideoPipeline" - } - } - } - }, - "info.lora.animatediff-motion-adapter-sdxl": { - "*": { - "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", - "pkg": { - "0": { - "diffusers": "AnimateDiffSDXLPipeline" - } - } - } - }, - "info.controlnet.animatediff-sparsectrl-scribble": { - "*": { - "repo": "guoyww/animatediff-sparsectrl-scribble", - "pkg": { - "0": { - "diffusers": "SparseControlNetModel" - } - } - } - }, - "info.controlnet.animatelcm": { - "*": { - "repo": "wangfuyun/AnimateLCM", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.unet.audioldm-s-v2": { - "*": { - "repo": "cvssp/audioldm-s-full-v2", - "pkg": { - "0": { - "diffusers": "AudioLDMPipeline" - } - }, - "file_256": [ - "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ClapTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "SpeechT5HifiGan" - ] - } - } - }, - "info.unet.audioldm2": { - "*": { - "repo": "cvssp/audioldm2", - "pkg": { - "0": { - "diffusers": "AudioLDM2Pipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" - ], - "layer_b3": [ - "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" - ], - "layer_256": [ - "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ClapModel" - ], - "text_encoder_2": [ - "T5EncoderModel", - "VitsModel" - ], - "projection_model": [ - "AudioLDM2ProjectionModel" - ], - "language_model": [ - "GPT2LMHeadModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "audioldm2" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "audioldm2" - ], - "feature_extractor": [ - "ClapFeatureExtractor" - ], - "unet": [ - "AudioLDM2UNet2DConditionModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "SpeechT5HifiGan" - ] - } - } - }, - "info.dit.auraflow": { - "*": { - "repo": "fal/AuraFlow", - "pkg": { - "0": { - "diffusers": "AuraFlowPipeline" - } - }, - "identifiers": [ - [ - 8192, - 3072 - ], - "mlpX.c_fc2.weight", - "joint_transformer_blocks.2.ff_context.linear_2.weight" - ], - "file_256": [ - "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", - "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", - "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", - "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" - ], - "layer_b3": [ - "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", - "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", - "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", - "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" - ], - "layer_256": [ - "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", - "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", - "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", - "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "auraflow" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "AuraFlowTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - }, - "tasks": [ - "AuraFlowPipeline" - ] - } - }, - "info.unet.blipdiffusion": { - "*": { - "repo": "Salesforce/blipdiffusion", - "pkg": { - "0": { - "diffusers": "BlipDiffusionPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "blipdiffusion" - ], - "text_encoder": [ - "ContextCLIPTextModel" - ], - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - "ops.scheduler.pndm", - "scheduler" - ], - "qformer": [ - "Blip2QFormerModel" - ], - "image_processor": [ - "BlipImageProcessor" - ] - } - } - }, - "info.dit.chroma": { - "*": { - "repo": "lodestones/Chroma", - "pkg": { - "0": { - "diffusers": "ChromaPipeline" - }, - "1": { - "generation": { - "neg_text": "", - "num_steps": "28", - "latent_size": [ - 64, - 64 - ] - } - } - }, - "file_256": [ - "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", - "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", - "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", - "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" - ], - "layer_b3": [ - "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" - ], - "layer_256": [ - "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "ChromaPipeline" - ] - }, - "chroma1-hd": { - "repo": "lodestones/Chroma1-HD", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 40 - } - } - }, - "file_256": [ - "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", - "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", - "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc" - ] - }, - "chroma1-flash": { - "repo": "lodestones/Chroma1-Flash", - "pkg": { - "0": { - "diffusers": "ChromaPipeline", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.0, - "num_images_per_prompt": 1 - } - } - }, - "file_256": [ - "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", - "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", - "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "ChromaPipeline" - ] - } - }, - "info.dit.cogvideox": { - "*": { - "repo": "zai-org/CogVideoX-2b", - "pkg": { - "0": { - "diffusers": "CogVideoXPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_videos_per_prompt": 1, - "num_inference_steps": 50, - "num_frames": 49, - "guidance_scale": 6 - } - } - }, - "file_256": [ - "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" - ], - "layer_b3": [ - "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" - ], - "layer_256": [ - "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogvideox" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "transformer": [ - "CogVideoXTransformer3DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - } - } - }, - "info.controlnet.cogvideox-fun-v-pose": { - "*": { - "repo": "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", - "pkg": { - "0": { - "diffusers": "CogVideoXFunControlPipeline" - } - } - } - }, - "info.dit.cogvideox-i2v": { - "*": { - "repo": "zai-org/CogVideoX-5b-I2V", - "pkg": { - "0": { - "diffusers": "CogVideoXImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogvideox-i2v" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.cogvideox", - "cogvideox-i2v" - ], - "transformer": [ - "CogVideoXTransformer3DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - } - } - }, - "info.dit.cogview3": { - "*": { - "repo": "zai-org/CogView3-Plus-3B", - "pkg": { - "0": { - "diffusers": "CogView3PlusPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "guidance_scale": 7.0, - "num_images_per_prompt": 1, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogview3" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "CogView3PlusTransformer2DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - }, - "tasks": [ - "CogView3PlusPipeline" - ] - } - }, - "info.dit.cogview4": { - "*": { - "repo": "zai-org/CogView4-6B", - "pkg": { - "0": { - "diffusers": "CogView4Pipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogview4" - ], - "text_encoder": [ - "GlmModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "CogView4Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - }, - "tasks": [ - "CogView4ControlPipeline", - "CogView4Pipeline" - ] - } - }, - "info.controlnet.cogview4-control": { - "*": { - "repo": "zai-org/CogView4-6B-Control", - "pkg": { - "0": { - "diffusers": "CogView4ControlPipeline" - } - } - } - }, - "info.dit.consisid": { - "*": { - "repo": "BestWishYsh/ConsisID-preview", - "pkg": { - "0": { - "diffusers": "ConsisIDPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "consisid" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "transformer": [ - "ConsisIDTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - } - } - }, - "info.unet.diffusers-cd-imagenet64-l2": { - "*": { - "repo": "openai/diffusers-cd_imagenet64_l2", - "pkg": { - "0": { - "diffusers": "ConsistencyModelPipeline" - } - } - } - }, - "info.controlnet.sd-controlnet-canny": { - "*": { - "repo": "lllyasviel/sd-controlnet-canny", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.blipdiffusion-controlnet": { - "*": { - "repo": "Salesforce/blipdiffusion-controlnet", - "pkg": { - "0": { - "diffusers": "BlipDiffusionControlNetPipeline" - } - } - } - }, - "info.controlnet.control-v11p-sd15-inpaint": { - "*": { - "repo": "lllyasviel/control_v11p_sd15_inpaint", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-canny-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-canny-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-depth-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-depth-sdxl-1.0-small", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-union-sdxl-1": { - "*": { - "repo": "xinsir/controlnet-union-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetUnionModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-canny": { - "*": { - "repo": "InstantX/SD3-Controlnet-Canny", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-inpainting": { - "*": { - "repo": "alimama-creative/SD3-Controlnet-Inpainting", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sd2-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SD2.1-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sdxl-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SDXL-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.dit.cosmos-predict2-text2image": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Text2Image", - "pkg": { - "0": { - "diffusers": "Cosmos2TextToImagePipeline" - } - }, - "file_256": [ - "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", - "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", - "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", - "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", - "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", - "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", - "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", - "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", - "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", - "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", - "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", - "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", - "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" - ], - "layer_b3": [ - "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", - "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", - "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", - "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", - "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", - "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", - "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", - "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", - "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", - "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", - "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", - "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", - "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" - ], - "layer_256": [ - "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", - "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", - "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", - "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", - "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", - "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", - "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", - "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", - "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", - "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", - "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", - "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", - "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" - ], - "pipe_names": { - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-text2image" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-predict2-video2world": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Video2World", - "pkg": { - "0": { - "diffusers": "Cosmos2VideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-text2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Text2World", - "pkg": { - "0": { - "diffusers": "CosmosTextToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-text2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-video2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Video2World", - "pkg": { - "0": { - "diffusers": "CosmosVideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.unet.if-i-xl-v1": { - "*": { - "repo": "DeepFloyd/IF-I-XL-v1.0", - "pkg": { - "0": { - "diffusers": "IFPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "if-i-xl-v1" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ] - }, - "tasks": [ - "IFImg2ImgPipeline", - "IFInpaintingPipeline", - "IFPipeline" - ] - } - }, - "info.dit.easyanimatev5-zh": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimatePipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - "BertModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.controlnet.easyanimatev5-zh-control": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-Control-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateControlPipeline" - } - } - } - }, - "info.dit.easyanimatev5-zh-inp": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-InP-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateInpaintPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - "BertModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh-inp" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.flux1-schnell": { - "*": { - "repo": "black-forest-labs/FLUX.1-schnell", - "pkg": { - "0": { - "diffusers": "FluxInpaintPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 0.0, - "num_inference_steps": 4, - "max_sequence_length": 256 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "num_inference_steps": 4 - } - } - }, - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "file_256": [ - "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", - "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" - ], - "layer_b3": [ - "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", - "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", - "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" - ], - "layer_256": [ - "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", - "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", - "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-schnell" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-schnell" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline", - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - }, - "shuttle-3-aesthetic": { - "repo": "shuttleai/shuttle-3.1-aesthetic", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", - "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" - ], - "layer_256": [ - "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", - "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a" - ], - "layer_b3": [ - "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", - "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c" - ] - }, - "shuttle-3-diffusion": { - "repo": "shuttleai/shuttle-3-diffusion", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", - "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", - "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", - "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8" - ], - "layer_256": [ - "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", - "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", - "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c" - ], - "layer_b3": [ - "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", - "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", - "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd" - ] - }, - "shuttle-jaguar": { - "repo": "shuttleai/shuttle-jaguar", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", - "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f" - ], - "layer_b3": [ - "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", - "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672" - ] - } - }, - "info.dit.flux1-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-dev", - "pkg": { - "0": { - "diffusers": "FluxPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 3.5, - "num_inference_steps": 50, - "max_sequence_length": 512 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "gudance": 3.5, - "num_inference_steps": 25 - } - } - }, - "file_256": [ - "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", - "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", - "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", - "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", - "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" - ], - "layer_b3": [ - "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", - "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", - "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" - ], - "layer_256": [ - "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", - "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", - "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" - ], - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-dev" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline", - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - }, - "mystic": { - "repo": "enhanceaiteam/Mystic", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 16, - "guidance_scale": 7.5, - "width": 768, - "height": 1024 - } - } - }, - "file_256": [ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" - ], - "layer_256": [ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" - ], - "layer_b3": [ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" - ] - }, - "flux1-lite": { - "repo": "freepik/flux.1-lite-8b", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 28 - } - } - }, - "file_256": [ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" - ], - "layer_256": [ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" - ], - "layer_b3": [ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" - ] - }, - "f-lite": { - "repo": "freepik/f-lite", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "f-lite-texture": { - "repo": "freepik/f-lite-texture", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "flux": { - "repo": "TencentARC/flux-mini", - "file_256": [ - "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" - ], - "layer_256": [ - "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" - ], - "layer_b3": [ - "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" - ] - }, - "flex2": { - "repo": "ostris/Flex.2-preview", - "file_256": [ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" - ], - "layer_256": [ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" - ], - "layer_b3": [ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" - ] - }, - "flex1-alpha": { - "repo": "ostris/Flex.1-alpha", - "file_256": [ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" - ], - "layer_256": [ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" - ], - "layer_b3": [ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" - ] - } - }, - "info.controlnet.flux1-canny-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Canny-dev", - "pkg": { - "0": { - "diffusers": "FluxControlPipeline" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny": { - "*": { - "repo": "InstantX/FLUX.1-dev-controlnet-canny", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny-alpha": { - "*": { - "repo": "InstantX/FLUX.1-dev-Controlnet-Canny-alpha", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.dit.flux1-fill-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Fill-dev", - "pkg": { - "0": { - "diffusers": "FluxFillPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ] - } - }, - "info.dit.flux1-kontext-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Kontext-dev", - "pkg": { - "0": { - "diffusers": "FluxKontextInpaintPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ] - } - }, - "info.dit.hidream-i1": { - "*": { - "repo": "HiDream-ai/HiDream-I1-Full", - "pkg": { - "0": { - "diffusers": "HiDreamImagePipeline" - } - }, - "file_256": [ - "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" - ], - "layer_b3": [ - "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" - ], - "layer_256": [ - "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_2": [ - "CLIPTextModelWithProjection" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_3": [ - "T5EncoderModel" - ], - "tokenizer_3": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_4": [ - "LlamaForCausalLM" - ], - "tokenizer_4": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "transformer": [ - "HiDreamImageTransformer2DModel" - ] - } - } - }, - "info.dit.hunyuanvideo": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo", - "pkg": { - "0": { - "diffusers": "HunyuanVideoPipeline" - } - }, - "file_256": [ - "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" - ], - "layer_b3": [ - "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" - ], - "layer_256": [ - "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" - ], - "pipe_names": { - "text_encoder": [ - "LlamaModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "CLIPTextModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ] - } - } - }, - "info.dit.hunyuanvideo-i2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-I2V", - "pkg": { - "0": { - "diffusers": "HunyuanVideoImageToVideoPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "LlavaForConditionalGeneration" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "CLIPTextModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "image_processor": [ - "CLIPImageProcessor" - ] - } - } - }, - "info.dit.hunyuandit-v1": { - "diffusers": { - "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", - "pkg": { - "0": { - "diffusers": "HunyuanDiTPipeline", - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "extra_embedder", - "model.blocks", - "skip_norm.weight" - ], - "file_256": [ - "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", - "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", - "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" - ], - "layer_b3": [ - "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", - "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", - "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" - ], - "layer_256": [ - "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", - "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", - "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "BertModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuandit-v1" - ], - "transformer": [ - "HunyuanDiT2DModel" - ], - "scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuandit-v1" - ] - }, - "tasks": [ - "HunyuanDiTPipeline" - ] - } - }, - "info.unet.i2vgen-xl": { - "*": { - "repo": "ali-vilab/i2vgen-xl", - "pkg": { - "0": { - "diffusers": "I2VGenXLPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "i2vgen-xl" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ], - "unet": [ - "I2VGenXLUNet" - ], - "scheduler": [ - "ops.scheduler.ddim", - "scheduler" - ] - } - } - }, - "info.unet.kandinsky-2-1": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-1-prior", - "pkg": { - "0": { - "diffusers": "KandinskyPriorPipeline" - } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-1" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "Kandinsky3Img2ImgPipeline", - "Kandinsky3Pipeline", - "KandinskyCombinedPipeline", - "KandinskyImg2ImgCombinedPipeline", - "KandinskyImg2ImgPipeline", - "KandinskyInpaintCombinedPipeline", - "KandinskyInpaintPipeline", - "KandinskyPipeline", - "KandinskyV22CombinedPipeline", - "KandinskyV22Img2ImgCombinedPipeline", - "KandinskyV22Img2ImgPipeline", - "KandinskyV22InpaintCombinedPipeline", - "KandinskyV22InpaintPipeline", - "KandinskyV22Pipeline" - ] - } - }, - "info.unet.kandinsky-2-2": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-2-prior", - "pkg": { - "0": { - "diffusers": "KandinskyPriorPipeline" - } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-2" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "Kandinsky3Img2ImgPipeline", - "Kandinsky3Pipeline", - "KandinskyCombinedPipeline", - "KandinskyImg2ImgCombinedPipeline", - "KandinskyImg2ImgPipeline", - "KandinskyInpaintCombinedPipeline", - "KandinskyInpaintPipeline", - "KandinskyPipeline", - "KandinskyV22CombinedPipeline", - "KandinskyV22Img2ImgCombinedPipeline", - "KandinskyV22Img2ImgPipeline", - "KandinskyV22InpaintCombinedPipeline", - "KandinskyV22InpaintPipeline", - "KandinskyV22Pipeline" - ] - } - }, - "info.unet.kolors": { - "diffusers": { - "repo": "Kwai-Kolors/Kolors-diffusers", - "pkg": { - "0": { - "diffusers": "KolorsPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "negative_prompt": "", - "guidance_scale": 5.0, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" - ], - "layer_b3": [ - "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" - ], - "layer_256": [ - "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" - ], - "identifiers": [ - ".DenseReluDense.wi.weight", - "encoder_hid_proj.weight" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ChatGLMModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kolors" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "KolorsImg2ImgPipeline", - "KolorsPAGPipeline", - "KolorsPipeline" - ] - } - }, - "info.dit.latte-1": { - "*": { - "repo": "maxin-cn/Latte-1", - "pkg": { - "0": { - "diffusers": "LattePipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "latte-1" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "LatteTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.ltx-video": { - "*": { - "repo": "Lightricks/LTX-Video", - "pkg": { - "0": { - "diffusers": "LTXImageToVideoPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.ltx-video-09": { - "*": { - "repo": "Lightricks/LTX-Video-0.9.5", - "pkg": { - "0": { - "diffusers": "LTXConditionPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video-09" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.lumina-next-sft": { - "diffusers": { - "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", - "pkg": { - "0": { - "diffusers": "LuminaPipeline", - "precision": " ops.precision.bfloat.B16" - } - }, - "identifiers": [ - "time_caption", - "feed_forward" - ], - "file_256": [ - "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" - ], - "layer_b3": [ - "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", - "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" - ], - "layer_256": [ - "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", - "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" - ], - "pipe_names": { - "transformer": [ - "LuminaNextDiT2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "GemmaPreTrainedModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "lumina-next-sft" - ] - }, - "tasks": [ - "Lumina2Pipeline", - "LuminaPipeline" - ] - } - }, - "info.dit.lumina-image-2": { - "*": { - "repo": "Alpha-VLLM/Lumina-Image-2.0", - "pkg": { - "0": { - "diffusers": "Lumina2Pipeline" - } - }, - "file_256": [ - "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", - "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" - ], - "layer_b3": [ - "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" - ], - "layer_256": [ - "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" - ], - "pipe_names": { - "transformer": [ - "Lumina2Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "Gemma2PreTrainedModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "lumina-image-2" - ] - }, - "tasks": [ - "Lumina2Pipeline" - ] - }, - "illustrious-lumina-v3": { - "repo": "OnomaAIResearch/Illustrious-Lumina-v0.03", - "file_256": [ - "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", - "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214" - ], - "layer_256": [ - "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", - "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828" - ], - "layer_b3": [ - "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", - "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c" - ] - } - }, - "info.dit.mochi-1": { - "*": { - "repo": "genmo/mochi-1-preview", - "pkg": { - "0": { - "diffusers": "MochiPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "mochi-1" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "mochi-1" - ], - "transformer": [ - "MochiTransformer3DModel" - ] - } - } - }, - "info.unet.musicldm": { - "*": { - "repo": "ucsd-reach/musicldm", - "pkg": { - "0": { - "diffusers": "MusicLDMPipeline", - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ClapTextModelWithProjection", - "ClapModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "musicldm" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "SpeechT5HifiGan" - ] - } - } - }, - "info.dit.pixart-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtAlphaPipeline" - } - }, - "identifiers": [ - "aspect_ratio", - "y_embedding", - "emb.resolution", - "caption_projection" - ], - "file_256": [ - "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" - ], - "layer_b3": [ - "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" - ], - "layer_256": [ - "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-xl-2-1024-ms" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - }, - "tasks": [ - "PixArtAlphaPipeline" - ] - } - }, - "info.dit.pixart-sigma-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtSigmaPipeline" - } - }, - "identifiers": [ - "adaln_single", - "scale_shift_table" - ], - "file_256": [ - "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", - "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" - ], - "layer_b3": [ - "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", - "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" - ], - "layer_256": [ - "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", - "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-sigma-xl-2-1024-ms" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - }, - "tasks": [ - "PixArtAlphaPipeline", - "PixArtSigmaPipeline" - ] - } - }, - "info.dit.qwen-image": { - "*": { - "repo": "Qwen/Qwen-Image", - "pkg": { - "0": { - "diffusers": "QwenImageInpaintPipeline" - } - }, - "file_256": [ - "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" - ], - "layer_b3": [ - "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" - ], - "layer_256": [ - "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image" - ], - "transformer": [ - "QwenImageTransformer2DModel" - ] - } - } - }, - "info.dit.qwen-image-edit": { - "*": { - "repo": "Qwen/Qwen-Image-Edit", - "pkg": { - "0": { - "diffusers": "QwenImageEditPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-edit" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "QwenImageTransformer2DModel" - ] - } - } - }, - "info.dit.sana-1024px-bf16": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", - "pkg": { - "0": { - "diffusers": "SanaPipeline", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 4.5, - "num_inference_steps": 20 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" - ], - "layer_b3": [ - "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" - ], - "layer_256": [ - "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-1024px-bf16" - ], - "text_encoder": [ - "Gemma2PreTrainedModel" - ], - "vae": [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "transformer": [ - "SanaTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - }, - "tasks": [ - "SanaPAGPipeline", - "SanaPipeline" - ] - } - }, - "info.controlnet.sana-1024px-controlnet": { - "diffusers": { - "repo": "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers", - "pkg": { - "0": { - "diffusers": "SanaControlNetPipeline" - } - } - } - }, - "info.dit.sana-sprint-1024px": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", - "pkg": { - "0": { - "diffusers": "SanaSprintPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-sprint-1024px" - ], - "text_encoder": [ - "Gemma2PreTrainedModel" - ], - "vae": [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "transformer": [ - "SanaTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - }, - "tasks": [ - "SanaPAGPipeline", - "SanaPipeline" - ] - } - }, - "info.unet.shap-e": { - "*": { - "repo": "openai/shap-e", - "pkg": { - "0": { - "diffusers": "ShapEPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 64, - "size": 256, - "guidance_scale": 15 - } - } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "shap-e" - ], - "scheduler": [ - "ops.scheduler.heun", - "discrete" - ], - "shap_e_renderer": [ - "ShapERenderer" - ] - } - } - }, - "info.dit.skyreels-v2-t2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2Pipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-t2v-720p" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-df-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-DF-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-df-720p" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-i2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-I2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2ImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-i2v-720p" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "image_processor": [ - "CLIPProcessor" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.stable-audio-open-1": { - "*": { - "repo": "stabilityai/stable-audio-open-1.0", - "pkg": { - "0": { - "diffusers": "StableAudioPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_end_in_s": 10, - "num_waveforms_per_prompt": 3 - } - } - }, - "pipe_names": { - "vae": [ - "info.vae.oobleck", - "stable-audio-open-1" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "projection_model": [ - "StableAudioProjectionModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-audio-open-1" - ], - "transformer": [ - "StableAudioDiTModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } - } - }, - "info.unet.stable-cascade": { - "prior": { - "repo": "stabilityai/stable-cascade-prior", - "pkg": { - "0": { - "diffusers": "StableCascadePriorPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "negative_prompt": "", - "num_images_per_prompt": 1, - "num_inference_steps": 20, - "guidance_scale": 4.0, - "width": 1024, - "height": 1024 - } - } - }, - "file_256": [ - "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", - "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", - "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", - "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", - "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", - "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" - ], - "layer_b3": [ - "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", - "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", - "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", - "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", - "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", - "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" - ], - "layer_256": [ - "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", - "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", - "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", - "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", - "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", - "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" - ], - "identifiers": [ - "down_blocks.0.2.kv_mapper", - "previewer", - "backbone" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "stable-cascade" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "prior": [ - "StableCascadeUNet" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ] - } - }, - "decoder": { - "repo": "stabilityai/stable-cascade", - "pkg": { - "0": { - "diffusers": "StableCascadeDecoderPipeline", - "generation": { - "negative_prompt": "", - "guidance_scale": 0.0, - "output_type": "pil", - "num_inference_steps": 10 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", - "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", - "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", - "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", - "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" - ], - "layer_b3": [ - "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", - "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", - "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", - "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", - "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" - ], - "layer_256": [ - "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", - "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", - "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", - "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", - "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" - ], - "identifiers": [ - "0.2.channelwise", - "clip_mapper.bias", - ".12.self_attn.k_proj.weight" - ], - "pipe_names": { - "decoder": [ - "StableCascadeUNet" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-cascade" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ], - "vqgan": [ - "PaellaVQModel" - ] - }, - "tasks": [ - "StableCascadeCombinedPipeline", - "StableCascadeDecoderPipeline" - ] - } - }, - "info.unet.stable-diffusion-v1-5": { - "*": { - "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", - "pkg": { - "0": { - "diffusers": "StableDiffusionPipeline" - } - }, - "identifiers": [ - "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" - ], - "file_256": [ - "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", - "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", - "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", - "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", - "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", - "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", - "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" - ], - "layer_b3": [ - "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", - "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", - "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", - "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" - ], - "layer_256": [ - "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", - "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", - "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-v1-5" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ] - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.unet.stable-unclip-2-1-l": { - "*": { - "repo": "fusing/stable-unclip-2-1-l", - "pkg": { - "0": { - "diffusers": "StableUnCLIPPipeline" - } - }, - "pipe_names": { - "prior_tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "prior_text_encoder": [ - "CLIPTextModelWithProjection" - ], - "prior": [ - "PriorTransformer" - ], - "prior_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_normalizer": [ - "StableUnCLIPImageNormalizer" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.unet.stable-diffusion-2-1-unclip": { - "*": { - "repo": "stabilityai/stable-diffusion-2-1-unclip-small", - "pkg": { - "0": { - "diffusers": "StableUnCLIPImg2ImgPipeline" - } - }, - "pipe_names": { - "feature_extractor": [ - "CLIPImageProcessor" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "image_normalizer": [ - "StableUnCLIPImageNormalizer" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-2-1-unclip" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.dit.stable-diffusion-3": { - "*": { - "repo": "stabilityai/stable-diffusion-3.5-medium", - "pkg": { - "0": { - "diffusers": "StableDiffusion3Pipeline", - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "model.diffusion_model.joint_blocks.", - "transformer_blocks.21.norm1_context.linear.weight", - "transformer_blocks.31.norm1_context.linear.weight", - "blocks.11.ff.net.2.weight" - ], - "file_256": [ - "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", - "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" - ], - "layer_b3": [ - "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", - "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" - ], - "layer_256": [ - "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", - "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" - ], - "pipe_names": { - "transformer": [ - "SD3Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.tae", - "stable-diffusion-3" - ], - "text_encoder": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "text_encoder_2": [ - "CLIPTextModelWithProjection" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "text_encoder_3": [ - "T5EncoderModel" - ], - "tokenizer_3": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "image_encoder": [ - "SiglipVisionModel" - ], - "feature_extractor": [ - "SiglipImageProcessor" - ] - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline" - ] - }, - "stable-diffusion-3-turbo": { - "repo": "tensorart/stable-diffusion-3.5-medium-turbo", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.5, - "height": 1024, - "width": 768 - } - } - }, - "file_256": [ - "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", - "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", - "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", - "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e" - ], - "layer_256": [ - "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ], - "layer_b3": [ - "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ] - } - }, - "info.unet.gligen-1-4-inpainting-text-box": { - "*": { - "repo": "masterful/gligen-1-4-inpainting-text-box", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENPipeline" - } - } - } - }, - "info.unet.gligen-inpainting-text-image": { - "*": { - "repo": "anhnct/Gligen_Inpainting_Text_Image", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENTextImagePipeline" - } - } - } - }, - "info.unet.ldm3d-4c": { - "*": { - "repo": "Intel/ldm3d-4c", - "pkg": { - "0": { - "diffusers": "StableDiffusionLDM3DPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ldm3d-4c" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.unet.stable-diffusion-xl-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "denoising_end": 0.8, - "num_inference_steps": 40, - "output_type": "latent", - "safety_checker": false, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", - "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", - "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", - "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" - ], - "layer_256": [ - "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", - "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", - "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" - ], - "layer_b3": [ - "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", - "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", - "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" - ], - "identifiers": [ - "logit_scale", - "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", - "add_embedding.linear_2.bias" - ], - "pipe_names": { - "vae": [ - "info.vae.eq", - "info.vae.ms-lc-eq", - "stable-diffusion-xl-1" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "text_encoder_2": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-1" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-1" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - }, - "pony-diffusion": { - "file_256": [ - "67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3" - ], - "layer_256": [ - "465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e" - ], - "layer_b3": [ - "bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071" - ] - }, - "pony-diffusion-turbo": { - "file_256": [ - "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", - "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2" - ], - "layer_256": [ - "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", - "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52" - ], - "layer_b3": [ - "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", - "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc" - ] - }, - "animagine-xl-4": { - "repo": "cagliostrolab/animagine-xl-4.0", - "file_256": [ - "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", - "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", - "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", - "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0" - ], - "layer_256": [ - "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", - "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", - "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", - "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65" - ], - "layer_b3": [ - "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", - "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", - "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", - "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447" - ] - }, - "illustrious-xl-v2": { - "repo": "OnomaAIResearch/Illustrious-XL-v2.0", - "file_256": [ - "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", - "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", - "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", - "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", - "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd" - ], - "layer_256": [ - "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", - "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", - "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", - "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", - "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10" - ], - "layer_b3": [ - "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", - "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", - "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", - "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", - "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c" - ] - }, - "playground-v2---aesthetic": { - "repo": "playgroundai/playground-v2.5-1024px-aesthetic", - "pkg": { - "0": { - "diffusers": "DiffusionPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 50, - "guidance_scale": 3 - } - } - }, - "file_256": [ - "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", - "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", - "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", - "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", - "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", - "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a" - ], - "layer_256": [ - "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", - "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", - "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", - "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", - "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c" - ], - "layer_b3": [ - "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", - "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", - "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", - "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", - "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", - "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" - ], - "pipe_names": {} - }, - "segmind-vega": { - "repo": "segmind/Segmind-Vega", - "file_256": [ - "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", - "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", - "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2" - ], - "layer_256": [ - "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", - "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", - "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741" - ], - "layer_b3": [ - "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", - "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", - "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1" - ] - }, - "ssd": { - "repo": "segmind/SSD-1B", - "file_256": [ - "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", - "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", - "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", - "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", - "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a" - ], - "layer_256": [ - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ], - "layer_b3": [ - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ] - } - }, - "info.unet.stable-diffusion-xl-refiner-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-refiner-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLImg2ImgPipeline" - }, - "1": { - "diffusers": "DiffusionPipeline", - "generation": { - "num_inference_steps": 40, - "denoising_end": 0.8 - } - } - }, - "identifiers": [ - "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" - ], - "file_256": [ - "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", - "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", - "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" - ], - "layer_b3": [ - "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", - "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", - "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" - ], - "layer_256": [ - "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", - "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", - "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "text_encoder_2": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.unet.sdxl-pix2pix-768": { - "*": { - "repo": "diffusers/sdxl-instructpix2pix-768", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLInstructPix2PixPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "text_encoder_2": [ - "CLIPTextModelWithProjection" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ] - } - }, - "info.unet.stable-video-diffusion-img2vid-xt": { - "*": { - "repo": "stabilityai/stable-video-diffusion-img2vid-xt", - "pkg": { - "0": { - "diffusers": "StableVideoDiffusionPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "image_encoder": [ - "CLIPVisionModelWithProjection" - ], - "unet": [ - "UNetSpatioTemporalConditionModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - } - } - }, - "info.dit.visualclozepipeline-384": { - "*": { - "repo": "VisualCloze/VisualClozePipeline-384", - "pkg": { - "0": { - "diffusers": "VisualClozeGenerationPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - } - } - }, - "info.dit.wan2-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", - "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", - "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", - "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", - "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", - "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", - "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", - "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" - ], - "layer_b3": [ - "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", - "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", - "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", - "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", - "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", - "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", - "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" - ], - "layer_256": [ - "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", - "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", - "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", - "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", - "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", - "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", - "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan2-t2v" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.wan2-i2v-480p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", - "pkg": { - "0": { - "diffusers": "WanImageToVideoPipeline" - } - }, - "file_256": [ - "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", - "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", - "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", - "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", - "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", - "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", - "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", - "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", - "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" - ], - "layer_b3": [ - "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", - "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", - "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", - "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", - "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" - ], - "layer_256": [ - "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", - "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", - "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", - "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", - "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan2-i2v-480p" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "vae": [ - "info.vae.wan", - "wan2-i2v-480p" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "image_processor": [ - "CLIPImageProcessor" - ], - "image_encoder": [ - "CLIPVisionModel" - ], - "transformer": [ - "WanTransformer3DModel" - ], - "transformer_2": [ - "WanTransformer3DModel" - ] - } - } - }, - "info.dit.wan21-vace": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-VACE-1.3B-diffusers", - "pkg": { - "0": { - "diffusers": "WanVACEPipeline" - } - }, - "file_256": [ - "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", - "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", - "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", - "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", - "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" - ], - "layer_b3": [ - "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", - "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", - "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", - "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" - ], - "layer_256": [ - "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", - "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", - "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", - "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-vace" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "transformer": [ - "WanVACETransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.wan21-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanVideoToVideoPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-t2v" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "transformer": [ - "WanTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.unet.wuerstchen": { - "prior": { - "repo": "warp-ai/wuerstchen-prior", - "pkg": { - "0": { - "diffusers": "WuerstchenPriorPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wuerstchen" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "prior": [ - "WuerstchenPrior" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ] - }, - "tasks": [ - "WuerstchenCombinedPipeline", - "WuerstchenDecoderPipeline" - ] - }, - "decoder": { - "repo": "warp-ai/wuerstchen", - "pkg": { - "0": { - "diffusers": "WuerstchenDecoderPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wuerstchen" - ], - "text_encoder": [ - "CLIPTextModel" - ], - "decoder": [ - "WuerstchenDiffNeXt" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ], - "vqgan": [ - "PaellaVQModel" - ] - }, - "tasks": [ - "WuerstchenCombinedPipeline", - "WuerstchenDecoderPipeline" - ] - } - }, - "info.encoder.tokenizer": { - "powermoe": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "persimmon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "wav2vec2-conformer-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "xclip-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "vilt-b32-mlm": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "grounding-dino": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "mpnet": { - "pkg": { - "0": { - "transformers": "transformers.models.mpnet.tokenization_mpnet.MPNetTokenizer" - }, - "1": { - "transformers": "transformers.models.mpnet.tokenization_mpnet_fast.MPNetTokenizerFast" - } - } - }, - "vit-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "starcoder2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "glm-4v-thinking": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "jamba-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "lilt-roberta-en": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" - }, - "1": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3_fast.LayoutLMv3TokenizerFast" - } - } - }, - "aria-chat": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "helium": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "mvp": { - "pkg": { - "0": { - "transformers": "transformers.models.mvp.tokenization_mvp.MvpTokenizer" - }, - "1": { - "transformers": "transformers.models.mvp.tokenization_mvp_fast.MvpTokenizerFast" - } - } - }, - "wmt19-en-ru": { - "pkg": { - "0": { - "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" - } - } - }, - "vip-llava-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "owlv2-patch16": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "falcon": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "llama-3-vision": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "hf-moshiko": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "layoutlmv2-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2.LayoutLMv2Tokenizer" - }, - "1": { - "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2_fast.LayoutLMv2TokenizerFast" - } - } - }, - "canine-s": { - "pkg": { - "0": { - "transformers": "transformers.models.canine.tokenization_canine.CanineTokenizer" - } - } - }, - "idefics3-llama3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "owlvit-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "phi-3-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "deberta": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta.tokenization_deberta.DebertaTokenizer" - }, - "1": { - "transformers": "transformers.models.deberta.tokenization_deberta_fast.DebertaTokenizerFast" - } - } - }, - "gpt2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_sw3.tokenization_gpt_sw3.GPTSw3Tokenizer" - } - } - }, - "xlm-mlm-en-2048": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm.tokenization_xlm.XLMTokenizer" - } - } - }, - "llava": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "udop": { - "pkg": { - "0": { - "transformers": "transformers.models.udop.tokenization_udop.UdopTokenizer" - }, - "1": { - "transformers": "transformers.models.udop.tokenization_udop_fast.UdopTokenizerFast" - } - } - }, - "moe-active-shared-experts": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "layoutlm-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlm.tokenization_layoutlm.LayoutLMTokenizer" - }, - "1": { - "transformers": "transformers.models.layoutlm.tokenization_layoutlm_fast.LayoutLMTokenizerFast" - } - } - }, - "align": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "retribert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.deprecated.retribert.tokenization_retribert.RetriBertTokenizer" - }, - "1": { - "transformers": "transformers.models.deprecated.retribert.tokenization_retribert_fast.RetriBertTokenizerFast" - } - } - }, - "ctrl": { - "pkg": { - "0": { - "transformers": "transformers.models.ctrl.tokenization_ctrl.CTRLTokenizer" - } - } - }, - "smollm3": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "layoutlmv3": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" - }, - "1": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3_fast.LayoutLMv3TokenizerFast" - } - } - }, - "openai-gpt": { - "pkg": { - "0": { - "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" - }, - "1": { - "transformers": "transformers.models.openai.tokenization_openai_fast.OpenAIGPTTokenizerFast" - } - } - }, - "blip-flan-t5": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "siglip-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.siglip.tokenization_siglip.SiglipTokenizer" - } - } - }, - "omdet-turbo-swin-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "funnel": { - "pkg": { - "0": { - "transformers": "transformers.models.funnel.tokenization_funnel.FunnelTokenizer" - }, - "1": { - "transformers": "transformers.models.funnel.tokenization_funnel_fast.FunnelTokenizerFast" - } - } - }, - "qwen2": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - }, - "1": { - "transformers": "transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast" - } - } - }, - "aimv2-patch14-224-lit": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "data2vec-text": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "efficient-mlm-m0-0": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "gemma2": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - }, - "1": { - "transformers": "transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast" - } - } - }, - "yoso-4096": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - }, - "1": { - "transformers": "transformers.models.albert.tokenization_albert_fast.AlbertTokenizerFast" - } - } - }, - "llama-4-scout-16e": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "olmo-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "plbart": { - "pkg": { - "0": { - "transformers": "transformers.models.plbart.tokenization_plbart.PLBartTokenizer" - } - } - }, - "mixtral-8x": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "bitnet-b18-4t": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "lxmert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.lxmert.tokenization_lxmert.LxmertTokenizer" - }, - "1": { - "transformers": "transformers.models.lxmert.tokenization_lxmert_fast.LxmertTokenizerFast" - } - } - }, - "chameleon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "albert-xx-v2": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - }, - "1": { - "transformers": "transformers.models.albert.tokenization_albert_fast.AlbertTokenizerFast" - } - } - }, - "ernie-3-zh": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "clvp-dev": { - "pkg": { - "0": { - "transformers": "transformers.models.clvp.tokenization_clvp.ClvpTokenizer" - } - } - }, - "esm": { - "pkg": { - "0": { - "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" - } - } - }, - "rembert": { - "pkg": { - "0": { - "transformers": "transformers.models.rembert.tokenization_rembert.RemBertTokenizer" - }, - "1": { - "transformers": "transformers.models.rembert.tokenization_rembert_fast.RemBertTokenizerFast" - } - } - }, - "c4ai-command-r-v01": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere_fast.CohereTokenizerFast" - } - } - }, - "rwkv-4-pile": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "umt5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - }, - "1": { - "transformers": "transformers.models.t5.tokenization_t5_fast.T5TokenizerFast" - } - } - }, - "gemma": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - }, - "1": { - "transformers": "transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast" - } - } - }, - "reformer-crime-and-punishment": { - "pkg": { - "0": { - "transformers": "transformers.models.reformer.tokenization_reformer.ReformerTokenizer" - }, - "1": { - "transformers": "transformers.models.reformer.tokenization_reformer_fast.ReformerTokenizerFast" - } - } - }, - "wav2vec2-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "nezha-cn": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "git": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "kosmos-2-patch14-224": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast" - } - } - }, - "olmoe-0924": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "phi-1": { - "pkg": { - "0": { - "transformers": "transformers.models.codegen.tokenization_codegen.CodeGenTokenizer" - }, - "1": { - "transformers": "transformers.models.codegen.tokenization_codegen_fast.CodeGenTokenizerFast" - } - } - }, - "codegen-mono": { - "pkg": { - "0": { - "transformers": "transformers.models.codegen.tokenization_codegen.CodeGenTokenizer" - }, - "1": { - "transformers": "transformers.models.codegen.tokenization_codegen_fast.CodeGenTokenizerFast" - } - } - }, - "data2vec-audio-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "musicgen": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - }, - "1": { - "transformers": "transformers.models.t5.tokenization_t5_fast.T5TokenizerFast" - } - } - }, - "olmo2-1124-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "splinter": { - "pkg": { - "0": { - "transformers": "transformers.models.splinter.tokenization_splinter.SplinterTokenizer" - }, - "1": { - "transformers": "transformers.models.splinter.tokenization_splinter_fast.SplinterTokenizerFast" - } - } - }, - "luke": { - "pkg": { - "0": { - "transformers": "transformers.models.luke.tokenization_luke.LukeTokenizer" - } - } - }, - "glm-4-chat": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "long-t5-local": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - }, - "1": { - "transformers": "transformers.models.t5.tokenization_t5_fast.T5TokenizerFast" - } - } - }, - "nemotron-3-hf": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "wav2vec2-bert-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "led-16384": { - "pkg": { - "0": { - "transformers": "transformers.models.led.tokenization_led.LEDTokenizer" - }, - "1": { - "transformers": "transformers.models.led.tokenization_led_fast.LEDTokenizerFast" - } - } - }, - "idefics2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "squeezebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.squeezebert.tokenization_squeezebert.SqueezeBertTokenizer" - }, - "1": { - "transformers": "transformers.models.squeezebert.tokenization_squeezebert_fast.SqueezeBertTokenizerFast" - } - } - }, - "mms-tts-eng": { - "pkg": { - "0": { - "transformers": "transformers.models.vits.tokenization_vits.VitsTokenizer" - } - } - }, - "mt5": { - "pkg": { - "0": { - "transformers": "transformers.models.mt5.tokenization_mt5.MT5Tokenizer" - }, - "1": { - "transformers": "transformers.models.mt5.tokenization_mt5_fast.MT5TokenizerFast" - } - } - }, - "paligemma": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "speecht5-asr": { - "pkg": { - "0": { - "transformers": "transformers.models.speecht5.tokenization_speecht5.SpeechT5Tokenizer" - } - } - }, - "conv-bert": { - "pkg": { - "0": { - "transformers": "transformers.models.convbert.tokenization_convbert.ConvBertTokenizer" - }, - "1": { - "transformers": "transformers.models.convbert.tokenization_convbert_fast.ConvBertTokenizerFast" - } - } - }, - "mamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "c4ai-command-r-12-2024": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere_fast.CohereTokenizerFast" - } - } - }, - "xmod": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast" - } - } - }, - "bart": { - "pkg": { - "0": { - "transformers": "transformers.models.bart.tokenization_bart.BartTokenizer" - }, - "1": { - "transformers": "transformers.models.bart.tokenization_bart_fast.BartTokenizerFast" - } - } - }, - "voxtral-2507": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "pixtral": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "whisper": { - "pkg": { - "0": { - "transformers": "transformers.models.whisper.tokenization_whisper.WhisperTokenizer" - }, - "1": { - "transformers": "transformers.models.whisper.tokenization_whisper_fast.WhisperTokenizerFast" - } - } - }, - "blip-vqa": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "flaubert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" - } - } - }, - "transfo-xl-wt103": { - "pkg": { - "0": { - "transformers": "transformers.models.deprecated.transfo_xl.tokenization_transfo_xl.TransfoXLTokenizer" - } - } - }, - "moonshine": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "tvp": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "biogpt": { - "pkg": { - "0": { - "transformers": "transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer" - } - } - }, - "opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "blip2-opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "gptsan-japanese": { - "pkg": { - "0": { - "transformers": "transformers.models.deprecated.gptsan_japanese.tokenization_gptsan_japanese.GPTSanJapaneseTokenizer" - } - } - }, - "dpr-question-encoder-single-nq": { - "pkg": { - "0": { - "transformers": "transformers.models.dpr.tokenization_dpr.DPRQuestionEncoderTokenizer" - }, - "1": { - "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" - } - } - }, - "mbart-cc25": { - "pkg": { - "0": { - "transformers": "transformers.models.mbart.tokenization_mbart.MBartTokenizer" - }, - "1": { - "transformers": "transformers.models.mbart.tokenization_mbart_fast.MBartTokenizerFast" - } - } - }, - "idefics": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "diffllama-handcut": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "deberta-v2-x": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2.DebertaV2Tokenizer" - }, - "1": { - "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2_fast.DebertaV2TokenizerFast" - } - } - }, - "granite": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "internvl3-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - }, - "1": { - "transformers": "transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast" - } - } - }, - "fnet": { - "pkg": { - "0": { - "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" - }, - "1": { - "transformers": "transformers.models.fnet.tokenization_fnet_fast.FNetTokenizerFast" - } - } - }, - "blenderbot": { - "pkg": { - "0": { - "transformers": "transformers.models.blenderbot_small.tokenization_blenderbot_small.BlenderbotSmallTokenizer" - } - } - }, - "clipseg-rd64": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "jetmoe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "mobilebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.mobilebert.tokenization_mobilebert.MobileBertTokenizer" - }, - "1": { - "transformers": "transformers.models.mobilebert.tokenization_mobilebert_fast.MobileBertTokenizerFast" - } - } - }, - "groupvit-gcc-yfcc": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - }, - "1": { - "transformers": "transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast" - } - } - }, - "ibert-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "nystromformer-512": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - }, - "1": { - "transformers": "transformers.models.albert.tokenization_albert_fast.AlbertTokenizerFast" - } - } - }, - "gpt-j": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "stablelm-4e1t": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "hubert-ls960": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "mpt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "xlstm": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast" - } - } - }, - "xglm": { - "pkg": { - "0": { - "transformers": "transformers.models.xglm.tokenization_xglm.XGLMTokenizer" - }, - "1": { - "transformers": "transformers.models.xglm.tokenization_xglm_fast.XGLMTokenizerFast" - } - } - }, - "afm": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "clap-htsat-fused": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "zamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "xlnet-cased": { - "pkg": { - "0": { - "transformers": "transformers.models.xlnet.tokenization_xlnet.XLNetTokenizer" - }, - "1": { - "transformers": "transformers.models.xlnet.tokenization_xlnet_fast.XLNetTokenizerFast" - } - } - }, - "nllb-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.nllb.tokenization_nllb.NllbTokenizer" - }, - "1": { - "transformers": "transformers.models.nllb.tokenization_nllb_fast.NllbTokenizerFast" - } - } - }, - "jukebox-lyrics": { - "pkg": { - "0": { - "transformers": "transformers.models.deprecated.jukebox.tokenization_jukebox.JukeboxTokenizer" - } - } - }, - "mistral-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "xlm-roberta-xl": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast" - } - } - }, - "t5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - }, - "1": { - "transformers": "transformers.models.t5.tokenization_t5_fast.T5TokenizerFast" - } - } - }, - "mgp-str": { - "pkg": { - "0": { - "transformers": "transformers.models.mgp_str.tokenization_mgp_str.MgpstrTokenizer" - } - } - }, - "opus-mt-en-de": { - "pkg": { - "0": { - "transformers": "transformers.models.marian.tokenization_marian.MarianTokenizer" - } - } - }, - "glm-4-0414": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "mega-wikitext": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "janus": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "roformer-chinese": { - "pkg": { - "0": { - "transformers": "transformers.models.roformer.tokenization_roformer.RoFormerTokenizer" - }, - "1": { - "transformers": "transformers.models.roformer.tokenization_roformer_fast.RoFormerTokenizerFast" - } - } - }, - "qwen3": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - }, - "1": { - "transformers": "transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast" - } - } - }, - "siglip2-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - }, - "1": { - "transformers": "transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast" - } - } - }, - "mra-512-4": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "tapas-finetuned-sqa": { - "pkg": { - "0": { - "transformers": "transformers.models.tapas.tokenization_tapas.TapasTokenizer" - } - } - }, - "zamba-v1": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "bark": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "electra-discriminator": { - "pkg": { - "0": { - "transformers": "transformers.models.electra.tokenization_electra.ElectraTokenizer" - }, - "1": { - "transformers": "transformers.models.electra.tokenization_electra_fast.ElectraTokenizerFast" - } - } - }, - "language-perceiver": { - "pkg": { - "0": { - "transformers": "transformers.models.perceiver.tokenization_perceiver.PerceiverTokenizer" - } - } - }, - "mm-grounding-dino-o365v1-goldg-v3det": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "camembert": { - "pkg": { - "0": { - "transformers": "transformers.models.camembert.tokenization_camembert.CamembertTokenizer" - }, - "1": { - "transformers": "transformers.models.camembert.tokenization_camembert_fast.CamembertTokenizerFast" - } - } - }, - "exaone-4": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "bloom": { - "pkg": { - "0": { - "transformers": "transformers.models.bloom.tokenization_bloom_fast.BloomTokenizerFast" - } - } - }, - "bros-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "megatron-bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - }, - "1": { - "transformers": "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast" - } - } - }, - "bert-for-seq-generation-l-24-bbc-encoder": { - "pkg": { - "0": { - "transformers": "transformers.models.bert_generation.tokenization_bert_generation.BertGenerationTokenizer" - } - } - }, - "modernbert": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_fast.PreTrainedTokenizerFast" - } - } - }, - "max-text-01-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - }, - "1": { - "transformers": "transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast" - } - } - }, - "bridgetower": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast" - } - } - }, - "phi-3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - }, - "1": { - "transformers": "transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast" - } - } - }, - "xlm-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - }, - "1": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast" - } - } - } - }, - "info.moe.powermoe": { - "*": { - "repo": "ibm-research/PowerMoE-3b", - "pkg": { - "0": { - "transformers": "GraniteMoeModel" - } - }, - "tasks": [ - "GraniteMoeForCausalLM", - "GraniteMoeModel", - "GraniteMoePreTrainedModel" - ] - } - }, - "info.aet.bert-uncased": { - "*": { - "repo": "google-bert/bert-base-uncased", - "pkg": { - "0": { - "transformers": "BertModel" - } - }, - "file_256": [ - "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" - ], - "layer_b3": [ - "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" - ], - "layer_256": [ - "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" - ], - "tasks": [ - "BertForMaskedLM", - "BertForMultipleChoice", - "BertForNextSentencePrediction", - "BertForPreTraining", - "BertForQuestionAnswering", - "BertForSequenceClassification", - "BertForTokenClassification", - "BertLayer", - "BertLMHeadModel", - "BertModel", - "BertPreTrainedModel" - ] - } - }, - "info.art.persimmon": { - "*": { - "repo": "adept/persimmon-8b-base", - "pkg": { - "0": { - "transformers": "PersimmonModel" - } - }, - "tasks": [ - "PersimmonForCausalLM", - "PersimmonModel", - "PersimmonPreTrainedModel", - "PersimmonForSequenceClassification", - "PersimmonForTokenClassification" - ] - } - }, - "info.aet.s2t-librispeech-asr": { - "*": { - "repo": "facebook/s2t-small-librispeech-asr", - "pkg": { - "0": { - "transformers": "Speech2TextModel" - } - }, - "tasks": [ - "Speech2TextForConditionalGeneration", - "Speech2TextModel", - "Speech2TextPreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-conformer-rel-pos": { - "*": { - "repo": "facebook/wav2vec2-conformer-rel-pos-large", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerModel" - } - }, - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.gan.univnet-dev": { - "*": { - "repo": "dg845/univnet-dev", - "pkg": { - "0": { - "transformers": "UnivNetModel" - } - }, - "tasks": [ - "UnivNetModel" - ] - } - }, - "info.vit.xclip-patch32": { - "*": { - "repo": "microsoft/xclip-base-patch32", - "pkg": { - "0": { - "transformers": "XCLIPModel" - } - }, - "tasks": [ - "XCLIPModel", - "XCLIPPreTrainedModel", - "XCLIPTextModel", - "XCLIPVisionModel" - ] - } - }, - "info.art.gemma3-text": { - "*": { - "repo": "google/gemma-3-12b-it", - "pkg": { - "0": { - "transformers": "Gemma3TextModel" - } - }, - "tasks": [ - "Gemma3PreTrainedModel", - "Gemma3TextModel", - "Gemma3ForCausalLM", - "Gemma3ForConditionalGeneration", - "Gemma3Model", - "Gemma3ForSequenceClassification" - ] - } - }, - "info.vit.vilt-b32-mlm": { - "*": { - "repo": "dandelin/vilt-b32-mlm", - "pkg": { - "0": { - "transformers": "ViltModel" - } - }, - "tasks": [ - "ViltForImageAndTextRetrieval", - "ViltForImagesAndTextClassification", - "ViltForTokenClassification", - "ViltForMaskedLM", - "ViltForQuestionAnswering", - "ViltLayer", - "ViltModel", - "ViltPreTrainedModel" - ] - } - }, - "info.stst.switch-8": { - "*": { - "repo": "google/switch-base-8", - "pkg": { - "0": { - "transformers": "SwitchTransformersModel" - } - }, - "tasks": [ - "SwitchTransformersEncoderModel", - "SwitchTransformersForConditionalGeneration", - "SwitchTransformersModel", - "SwitchTransformersPreTrainedModel", - "SwitchTransformersTop1Router", - "SwitchTransformersSparseMLP" - ] - } - }, - "info.detr.grounding-dino": { - "*": { - "repo": "IDEA-Research/grounding-dino-tiny", - "pkg": { - "0": { - "transformers": "GroundingDinoModel" - } - }, - "tasks": [ - "GroundingDinoForObjectDetection", - "GroundingDinoModel", - "GroundingDinoPreTrainedModel" - ] - } - }, - "info.art.mpnet": { - "*": { - "repo": "microsoft/mpnet-base", - "pkg": { - "0": { - "transformers": "MPNetModel" - } - }, - "tasks": [ - "MPNetForMaskedLM", - "MPNetForMultipleChoice", - "MPNetForQuestionAnswering", - "MPNetForSequenceClassification", - "MPNetForTokenClassification", - "MPNetLayer", - "MPNetModel", - "MPNetPreTrainedModel" - ] - } - }, - "info.vit.chinese-clip-vit-patch16": { - "*": { - "repo": "OFA-Sys/chinese-clip-vit-base-patch16", - "pkg": { - "0": { - "transformers": "ChineseCLIPModel" - } - }, - "tasks": [ - "ChineseCLIPModel", - "ChineseCLIPPreTrainedModel", - "ChineseCLIPTextModel", - "ChineseCLIPVisionModel" - ] - } - }, - "info.vit.hiera-224": { - "*": { - "repo": "facebook/hiera-base-224-hf", - "pkg": { - "0": { - "transformers": "HieraModel" - } - }, - "tasks": [ - "HieraForImageClassification", - "HieraForPreTraining", - "HieraBackbone", - "HieraModel", - "HieraPreTrainedModel" - ] - } - }, - "info.vit.vit-patch16-224": { - "*": { - "repo": "google/vit-base-patch16-224", - "pkg": { - "0": { - "transformers": "ViTModel" - } - }, - "tasks": [ - "ViTForImageClassification", - "ViTForMaskedImageModeling", - "ViTModel", - "ViTPreTrainedModel" - ] - } - }, - "info.vit.vivit16x2-kinetics400": { - "*": { - "repo": "google/vivit-b-16x2-kinetics400", - "pkg": { - "0": { - "transformers": "VivitModel" - } - }, - "tasks": [ - "VivitModel", - "VivitPreTrainedModel", - "VivitForVideoClassification" - ] - } - }, - "info.art.starcoder2": { - "*": { - "repo": "bigcode/starcoder2-7b", - "pkg": { - "0": { - "transformers": "Starcoder2Model" - } - }, - "tasks": [ - "Starcoder2ForCausalLM", - "Starcoder2Model", - "Starcoder2PreTrainedModel", - "Starcoder2ForSequenceClassification", - "Starcoder2ForTokenClassification" - ] - } - }, - "info.vit.glm-4v-thinking": { - "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", - "pkg": { - "0": { - "transformers": "Glm4vModel" - } - }, - "tasks": [ - "Glm4vForConditionalGeneration", - "Glm4vModel", - "Glm4vPreTrainedModel", - "Glm4vTextModel" - ] - } - }, - "info.ssm.jamba-v0": { - "*": { - "repo": "ai21labs/Jamba-v0.1", - "pkg": { - "0": { - "transformers": "JambaModel" - } - }, - "tasks": [ - "JambaForCausalLM", - "JambaForSequenceClassification", - "JambaModel", - "JambaPreTrainedModel" - ] - } - }, - "info.aet.lilt-roberta-en": { - "*": { - "repo": "SCUT-DLVCLab/lilt-roberta-en-base", - "pkg": { - "0": { - "transformers": "LiltModel" - } - }, - "tasks": [ - "LiltForQuestionAnswering", - "LiltForSequenceClassification", - "LiltForTokenClassification", - "LiltModel", - "LiltPreTrainedModel" - ] - } - }, - "info.vit.video-llava-hf": { - "*": { - "repo": "LanguageBind/Video-LLaVA-7B-hf", - "pkg": { - "0": { - "transformers": "VideoLlavaModel" - } - }, - "tasks": [ - "VideoLlavaPreTrainedModel", - "VideoLlavaModel", - "VideoLlavaForConditionalGeneration" - ] - } - }, - "info.vit.aria-chat": { - "*": { - "repo": "rhymes-ai/Aria-Chat", - "pkg": { - "0": { - "transformers": "AriaModel" - } - }, - "tasks": [ - "AriaForConditionalGeneration", - "AriaPreTrainedModel", - "AriaTextPreTrainedModel", - "AriaTextModel", - "AriaModel", - "AriaTextForCausalLM" - ] - } - }, - "info.art.open-llama-v1": { - "*": { - "repo": "openlm-research/open_llama_3b", - "pkg": { - "0": { - "transformers": "OpenLlamaModel" - } - }, - "tasks": [ - "OpenLlamaPreTrainedModel", - "OpenLlamaModel", - "OpenLlamaForCausalLM", - "OpenLlamaForSequenceClassification" - ] - } - }, - "info.art.helium": { - "*": { - "repo": "kyutai/helium-1-2b", - "pkg": { - "0": { - "transformers": "HeliumModel" - } - }, - "tasks": [ - "HeliumPreTrainedModel", - "HeliumModel", - "HeliumForCausalLM", - "HeliumForSequenceClassification", - "HeliumForTokenClassification" - ] - } - }, - "info.stst.autoformer-tourism-monthly": { - "*": { - "repo": "huggingface/autoformer-tourism-monthly", - "pkg": { - "0": { - "transformers": "AutoformerModel" - } - }, - "tasks": [ - "AutoformerForPrediction", - "AutoformerModel", - "AutoformerPreTrainedModel" - ] - } - }, - "info.stst.mvp": { - "*": { - "repo": "RUCAIBox/mvp", - "pkg": { - "0": { - "transformers": "MvpModel" - } - }, - "tasks": [ - "MvpForCausalLM", - "MvpForConditionalGeneration", - "MvpForQuestionAnswering", - "MvpForSequenceClassification", - "MvpModel", - "MvpPreTrainedModel" - ] - } - }, - "info.vit.focalnet": { - "*": { - "repo": "microsoft/focalnet-tiny", - "pkg": { - "0": { - "transformers": "FocalNetModel" - } - }, - "tasks": [ - "FocalNetForImageClassification", - "FocalNetForMaskedImageModeling", - "FocalNetBackbone", - "FocalNetModel", - "FocalNetPreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v1-1--224": { - "*": { - "repo": "google/mobilenet_v1_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV1Model" - } - }, - "tasks": [ - "MobileNetV1ForImageClassification", - "MobileNetV1Model", - "MobileNetV1PreTrainedModel" - ] - } - }, - "info.stst.wmt19-en-ru": { - "*": { - "repo": "facebook/wmt19-en-ru", - "pkg": { - "0": { - "transformers": "FSMTModel" - } - }, - "tasks": [ - "FSMTForConditionalGeneration", - "FSMTModel", - "PretrainedFSMTModel" - ] - } - }, - "info.vit.vip-llava-hf": { - "*": { - "repo": "ybelkada/vip-llava-7b-hf", - "pkg": { - "0": { - "transformers": "VipLlavaModel" - } - }, - "tasks": [ - "VipLlavaModel", - "VipLlavaForConditionalGeneration", - "VipLlavaPreTrainedModel" - ] - } - }, - "info.vit.owlv2-patch16": { - "*": { - "repo": "google/owlv2-base-patch16", - "pkg": { - "0": { - "transformers": "Owlv2Model" - } - }, - "tasks": [ - "Owlv2Model", - "Owlv2PreTrainedModel", - "Owlv2TextModel", - "Owlv2VisionModel", - "Owlv2ForObjectDetection" - ] - } - }, - "info.vit.dinov2-with-registers": { - "*": { - "repo": "facebook/dinov2-with-registers-base", - "pkg": { - "0": { - "transformers": "Dinov2WithRegistersModel" - } - }, - "tasks": [ - "Dinov2WithRegistersPreTrainedModel", - "Dinov2WithRegistersModel", - "Dinov2WithRegistersForImageClassification", - "Dinov2WithRegistersBackbone" - ] - } - }, - "info.detr.dpt": { - "*": { - "repo": "Intel/dpt-large", - "pkg": { - "0": { - "transformers": "DPTModel" - } - }, - "tasks": [ - "DPTForDepthEstimation", - "DPTForSemanticSegmentation", - "DPTModel", - "DPTPreTrainedModel" - ] - } - }, - "info.ssm.falcon": { - "*": { - "repo": "tiiuae/falcon-7b", - "pkg": { - "0": { - "transformers": "FalconModel" - } - }, - "tasks": [ - "FalconForCausalLM", - "FalconModel", - "FalconPreTrainedModel", - "FalconForSequenceClassification", - "FalconForTokenClassification", - "FalconForQuestionAnswering" - ] - } - }, - "info.vit.llama-3-vision": { - "*": { - "repo": "meta-llama/Llama-3.2-11B-Vision", - "pkg": { - "0": { - "transformers": "MllamaModel" - } - }, - "tasks": [ - "MllamaForConditionalGeneration", - "MllamaForCausalLM", - "MllamaTextModel", - "MllamaVisionModel", - "MllamaPreTrainedModel", - "MllamaModel" - ] - } - }, - "info.art.hf-moshiko": { - "*": { - "repo": "kmhf/hf-moshiko", - "pkg": { - "0": { - "transformers": "MoshiModel" - } - }, - "tasks": [ - "MoshiForCausalLM", - "MoshiForConditionalGeneration", - "MoshiModel", - "MoshiPreTrainedModel" - ] - } - }, - "info.art.layoutlmv2-uncased": { - "*": { - "repo": "microsoft/layoutlmv2-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMv2Model" - } - }, - "tasks": [ - "LayoutLMv2ForQuestionAnswering", - "LayoutLMv2ForSequenceClassification", - "LayoutLMv2ForTokenClassification", - "LayoutLMv2Layer", - "LayoutLMv2Model", - "LayoutLMv2PreTrainedModel" - ] - } - }, - "info.vit.sam-vit-huge": { - "*": { - "repo": "facebook/sam-vit-huge", - "pkg": { - "0": { - "transformers": "SamVisionModel" - } - }, - "tasks": [ - "SamVisionModel", - "SamModel", - "SamPreTrainedModel" - ] - } - }, - "info.art.trajectory-transformer-halfcheetah-v2": { - "*": { - "repo": "CarlCochet/trajectory-transformer-halfcheetah-medium-v2", - "pkg": { - "0": { - "transformers": "TrajectoryTransformerModel" - } - }, - "tasks": [ - "TrajectoryTransformerModel", - "TrajectoryTransformerPreTrainedModel" - ] - } - }, - "info.art.canine-s": { - "*": { - "repo": "google/canine-s", - "pkg": { - "0": { - "transformers": "CanineModel" - } - }, - "tasks": [ - "CanineForMultipleChoice", - "CanineForQuestionAnswering", - "CanineForSequenceClassification", - "CanineForTokenClassification", - "CanineLayer", - "CanineModel", - "CaninePreTrainedModel" - ] - } - }, - "info.gan.dac": { - "*": { - "repo": "descript/dac_16khz", - "pkg": { - "0": { - "transformers": "DacModel" - } - }, - "tasks": [ - "DacModel", - "DacPreTrainedModel" - ] - } - }, - "info.vit.ast-finetuned-audioset-10-10-0593": { - "*": { - "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", - "pkg": { - "0": { - "transformers": "ASTModel" - } - }, - "tasks": [ - "ASTForAudioClassification", - "ASTModel", - "ASTPreTrainedModel" - ] - } - }, - "info.vit.idefics3-llama3": { - "*": { - "repo": "HuggingFaceM4/Idefics3-8B-Llama3", - "pkg": { - "0": { - "transformers": "Idefics3Model" - } - }, - "tasks": [ - "Idefics3ForConditionalGeneration", - "Idefics3PreTrainedModel", - "Idefics3Model", - "Idefics3VisionTransformer" - ] - } - }, - "info.detr.detr-resnet-50": { - "*": { - "repo": "facebook/detr-resnet-50", - "pkg": { - "0": { - "transformers": "DetrModel" - } - }, - "tasks": [ - "DetrForObjectDetection", - "DetrForSegmentation", - "DetrModel", - "DetrPreTrainedModel" - ] - } - }, - "info.vit.owlvit-patch32": { - "*": { - "repo": "google/owlvit-base-patch32", - "pkg": { - "0": { - "transformers": "OwlViTModel" - } - }, - "tasks": [ - "OwlViTModel", - "OwlViTPreTrainedModel", - "OwlViTTextModel", - "OwlViTVisionModel", - "OwlViTForObjectDetection" - ] - } - }, - "info.moe.phi-3-moe": { - "*": { - "repo": "microsoft/Phi-3.5-MoE-instruct", - "pkg": { - "0": { - "transformers": "PhimoeModel" - } - }, - "tasks": [ - "PhimoePreTrainedModel", - "PhimoeModel", - "PhimoeForCausalLM", - "PhimoeForSequenceClassification" - ] - } - }, - "info.art.deberta": { - "*": { - "repo": "microsoft/deberta-base", - "pkg": { - "0": { - "transformers": "DebertaModel" - } - }, - "tasks": [ - "DebertaForMaskedLM", - "DebertaForQuestionAnswering", - "DebertaForSequenceClassification", - "DebertaForTokenClassification", - "DebertaModel", - "DebertaPreTrainedModel" - ] - } - }, - "info.art.gpt2": { - "*": { - "repo": "openai-community/gpt2", - "pkg": { - "0": { - "transformers": "GPT2Model" - } - }, - "tasks": [ - "GPT2DoubleHeadsModel", - "GPT2ForQuestionAnswering", - "GPT2ForSequenceClassification", - "GPT2ForTokenClassification", - "GPT2LMHeadModel", - "GPT2Model", - "GPT2PreTrainedModel" - ] - } - }, - "info.vit.sam-hq-vit-h": { - "*": { - "repo": "sushmanth/sam_hq_vit_h", - "pkg": { - "0": { - "transformers": "SamHQModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.gan.dinat-in-224": { - "*": { - "repo": "shi-labs/dinat-mini-in1k-224", - "pkg": { - "0": { - "transformers": "DinatModel" - } - }, - "tasks": [ - "DinatForImageClassification", - "DinatModel", - "DinatPreTrainedModel", - "DinatBackbone" - ] - } - }, - "info.vit.llava-v1-mistral-hf": { - "*": { - "repo": "llava-hf/llava-v1.6-mistral-7b-hf", - "pkg": { - "0": { - "transformers": "LlavaNextModel" - } - }, - "tasks": [ - "LlavaNextForConditionalGeneration", - "LlavaNextPreTrainedModel", - "LlavaNextModel" - ] - } - }, - "info.art.xlm-mlm-en-2048": { - "*": { - "repo": "FacebookAI/xlm-mlm-en-2048", - "pkg": { - "0": { - "transformers": "XLMModel" - } - }, - "tasks": [ - "XLMForMultipleChoice", - "XLMForQuestionAnswering", - "XLMForQuestionAnsweringSimple", - "XLMForSequenceClassification", - "XLMForTokenClassification", - "XLMModel", - "XLMPreTrainedModel", - "XLMWithLMHeadModel" - ] - } - }, - "info.vit.llava": { - "*": { - "repo": "llava-hf/llava-9b", - "pkg": { - "0": { - "transformers": "LlavaModel" - } - }, - "file_256": [ - "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" - ], - "layer_b3": [ - "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" - ], - "layer_256": [ - "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" - ], - "tasks": [ - "LlavaForConditionalGeneration", - "LlavaPreTrainedModel", - "LlavaModel" - ] - } - }, - "info.vit.udop": { - "*": { - "repo": "microsoft/udop-large", - "pkg": { - "0": { - "transformers": "UdopModel" - } - }, - "tasks": [ - "UdopForConditionalGeneration", - "UdopPreTrainedModel", - "UdopModel", - "UdopEncoderModel" - ] - } - }, - "info.detr.rtdetr-r50vd": { - "*": { - "repo": "PekingU/rtdetr_r50vd", - "pkg": { - "0": { - "transformers": "RTDetrModel" - } - }, - "tasks": [ - "RTDetrForObjectDetection", - "RTDetrModel", - "RTDetrPreTrainedModel" - ] - } - }, - "info.vit.qwen2-vl": { - "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen2_5_VLModel" - } - }, - "file_256": [ - "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", - "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", - "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", - "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" - ], - "layer_b3": [ - "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", - "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", - "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", - "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" - ], - "layer_256": [ - "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", - "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", - "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", - "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" - ], - "tasks": [ - "Qwen2_5_VLForConditionalGeneration", - "Qwen2_5_VLModel", - "Qwen2_5_VLPreTrainedModel", - "Qwen2_5_VLTextModel" - ] - } - }, - "info.moe.moe-active-shared-experts": { - "*": { - "repo": "ibm-research/moe-7b-1b-active-shared-experts", - "pkg": { - "0": { - "transformers": "GraniteMoeSharedModel" - } - }, - "tasks": [ - "GraniteMoeSharedForCausalLM", - "GraniteMoeSharedModel", - "GraniteMoeSharedPreTrainedModel" - ] - } - }, - "info.stst.granite-speech": { - "*": { - "repo": "ibm-granite/granite-speech-3.3-8b", - "pkg": { - "0": { - "transformers": "GraniteSpeechForConditionalGeneration" - } - }, - "tasks": [ - "GraniteSpeechCTCEncoder", - "GraniteSpeechForConditionalGeneration", - "GraniteSpeechPreTrainedModel" - ] - } - }, - "info.aet.layoutlm-uncased": { - "*": { - "repo": "microsoft/layoutlm-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMModel" - } - }, - "tasks": [ - "LayoutLMForMaskedLM", - "LayoutLMForSequenceClassification", - "LayoutLMForTokenClassification", - "LayoutLMForQuestionAnswering", - "LayoutLMModel", - "LayoutLMPreTrainedModel" - ] - } - }, - "info.vit.align": { - "*": { - "repo": "kakaobrain/align-base", - "pkg": { - "0": { - "transformers": "AlignModel" - } - }, - "tasks": [ - "AlignPreTrainedModel", - "AlignTextModel", - "AlignVisionModel", - "AlignModel" - ] - } - }, - "info.vit.aya-vision": { - "*": { - "repo": "CohereForAI/aya-vision-8b", - "pkg": { - "0": { - "transformers": "AyaVisionModel" - } - }, - "tasks": [ - "AyaVisionForConditionalGeneration", - "AyaVisionPreTrainedModel", - "AyaVisionModel" - ] - } - }, - "info.vit.altclip": { - "*": { - "repo": "BAAI/AltCLIP", - "pkg": { - "0": { - "transformers": "AltCLIPModel" - } - }, - "tasks": [ - "AltCLIPPreTrainedModel", - "AltCLIPVisionModel", - "AltCLIPTextModel", - "AltCLIPModel" - ] - } - }, - "info.ssm.falcon-mamba": { - "*": { - "repo": "tiiuae/falcon-mamba-7b", - "pkg": { - "0": { - "transformers": "FalconMambaModel" - } - }, - "tasks": [ - "FalconMambaForCausalLM", - "FalconMambaModel", - "FalconMambaPreTrainedModel", - "FalconMambaCache" - ] - } - }, - "info.vit.retribert-uncased": { - "*": { - "repo": "yjernite/retribert-base-uncased", - "pkg": { - "0": { - "transformers": "RetriBertModel" - } - }, - "tasks": [ - "RetriBertModel", - "RetriBertPreTrainedModel" - ] - } - }, - "info.art.ctrl": { - "*": { - "repo": "Salesforce/ctrl", - "pkg": { - "0": { - "transformers": "CTRLModel" - } - }, - "tasks": [ - "CTRLForSequenceClassification", - "CTRLLMHeadModel", - "CTRLModel", - "CTRLPreTrainedModel" - ] - } - }, - "info.art.evolla-hf": { - "*": { - "repo": "westlake-repl/Evolla-10B-hf", - "pkg": { - "0": { - "transformers": "EvollaModel" - } - }, - "tasks": [ - "EvollaForProteinText2Text", - "EvollaModel", - "EvollaPreTrainedModel" - ] - } - }, - "info.vit.cvt-13": { - "*": { - "repo": "microsoft/cvt-13", - "pkg": { - "0": { - "transformers": "CvtModel" - } - }, - "tasks": [ - "CvtForImageClassification", - "CvtModel", - "CvtPreTrainedModel" - ] - } - }, - "info.moe.dots-llm1": { - "*": { - "repo": "rednote-hilab/dots.llm1.base", - "pkg": { - "0": { - "transformers": "Dots1Model" - } - }, - "tasks": [ - "Dots1PreTrainedModel", - "Dots1Model", - "Dots1ForCausalLM" - ] - } - }, - "info.art.smollm3": { - "*": { - "repo": "HuggingFaceTB/SmolLM3-3B", - "pkg": { - "0": { - "transformers": "SmolLM3Model" - } - }, - "tasks": [ - "SmolLM3PreTrainedModel", - "SmolLM3Model", - "SmolLM3ForCausalLM", - "SmolLM3ForSequenceClassification", - "SmolLM3ForTokenClassification", - "SmolLM3ForQuestionAnswering" - ] - } - }, - "info.vit.vit-mae": { - "*": { - "repo": "facebook/vit-mae-base", - "pkg": { - "0": { - "transformers": "ViTMAEModel" - } - }, - "tasks": [ - "ViTMAEForPreTraining", - "ViTMAELayer", - "ViTMAEModel", - "ViTMAEPreTrainedModel" - ] - } - }, - "info.vit.mobilevit": { - "*": { - "repo": "apple/mobilevit-small", - "pkg": { - "0": { - "transformers": "MobileViTModel" - } - }, - "tasks": [ - "MobileViTForImageClassification", - "MobileViTForSemanticSegmentation", - "MobileViTModel", - "MobileViTPreTrainedModel" - ] - } - }, - "info.aet.roc-bert-zh": { - "*": { - "repo": "weiweishi/roc-bert-base-zh", - "pkg": { - "0": { - "transformers": "RoCBertModel" - } - }, - "tasks": [ - "RoCBertForCausalLM", - "RoCBertForMaskedLM", - "RoCBertForMultipleChoice", - "RoCBertForPreTraining", - "RoCBertForQuestionAnswering", - "RoCBertForSequenceClassification", - "RoCBertForTokenClassification", - "RoCBertLayer", - "RoCBertModel", - "RoCBertPreTrainedModel" - ] - } - }, - "info.vit.layoutlmv3": { - "*": { - "repo": "microsoft/layoutlmv3-base", - "pkg": { - "0": { - "transformers": "LayoutLMv3Model" - } - }, - "tasks": [ - "LayoutLMv3ForQuestionAnswering", - "LayoutLMv3ForSequenceClassification", - "LayoutLMv3ForTokenClassification", - "LayoutLMv3Model", - "LayoutLMv3PreTrainedModel" - ] - } - }, - "info.gan.nat-in-224": { - "*": { - "repo": "shi-labs/nat-mini-in1k-224", - "pkg": { - "0": { - "transformers": "NatModel" - } - }, - "tasks": [ - "NatForImageClassification", - "NatModel", - "NatPreTrainedModel", - "NatBackbone" - ] - } - }, - "info.vit.mobilevitv2-1": { - "*": { - "repo": "apple/mobilevitv2-1.0-imagenet1k-256", - "pkg": { - "0": { - "transformers": "MobileViTV2Model" - } - }, - "tasks": [ - "MobileViTV2ForImageClassification", - "MobileViTV2ForSemanticSegmentation", - "MobileViTV2Model", - "MobileViTV2PreTrainedModel" - ] - } - }, - "info.art.openai-gpt": { - "*": { - "repo": "openai-community/openai-gpt", - "pkg": { - "0": { - "transformers": "OpenAIGPTModel" - } - }, - "tasks": [ - "OpenAIGPTDoubleHeadsModel", - "OpenAIGPTForSequenceClassification", - "OpenAIGPTLMHeadModel", - "OpenAIGPTModel", - "OpenAIGPTPreTrainedModel" - ] - } - }, - "info.vit.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine_x_coco", - "pkg": { - "0": { - "transformers": "HGNetV2Backbone" - } - }, - "tasks": [ - "HGNetV2Backbone", - "HGNetV2PreTrainedModel", - "HGNetV2ForImageClassification" - ] - } - }, - "info.art.m-ctc-t": { - "*": { - "repo": "speechbrain/m-ctc-t-large", - "pkg": { - "0": { - "transformers": "MCTCTModel" - } - }, - "tasks": [ - "MCTCTForCTC", - "MCTCTModel", - "MCTCTPreTrainedModel" - ] - } - }, - "info.aet.unispeech-1500h-cv": { - "*": { - "repo": "microsoft/unispeech-large-1500h-cv", - "pkg": { - "0": { - "transformers": "UniSpeechModel" - } - }, - "tasks": [ - "UniSpeechForCTC", - "UniSpeechForPreTraining", - "UniSpeechForSequenceClassification", - "UniSpeechModel", - "UniSpeechPreTrainedModel" - ] - } - }, - "info.vit.blip-flan-t5": { - "*": { - "repo": "Salesforce/instructblip-flan-t5-xl", - "pkg": { - "0": { - "transformers": "InstructBlipModel" - } - }, - "tasks": [ - "InstructBlipQFormerModel", - "InstructBlipPreTrainedModel", - "InstructBlipModel", - "InstructBlipForConditionalGeneration", - "InstructBlipVisionModel" - ] - } - }, - "info.vit.siglip-patch16-224": { - "*": { - "repo": "google/siglip-base-patch16-224", - "pkg": { - "0": { - "transformers": "SiglipModel" - } - }, - "tasks": [ - "SiglipModel", - "SiglipPreTrainedModel", - "SiglipTextModel", - "SiglipVisionModel", - "SiglipForImageClassification" - ] - } - }, - "info.detr.omdet-turbo-swin-hf": { - "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", - "pkg": { - "0": { - "transformers": "OmDetTurboForObjectDetection" - } - }, - "tasks": [ - "OmDetTurboForObjectDetection", - "OmDetTurboPreTrainedModel" - ] - } - }, - "info.art.musicgen-melody": { - "*": { - "repo": "facebook/musicgen-melody", - "pkg": { - "0": { - "transformers": "MusicgenMelodyModel" - } - }, - "tasks": [ - "MusicgenMelodyForConditionalGeneration", - "MusicgenMelodyForCausalLM", - "MusicgenMelodyModel", - "MusicgenMelodyPreTrainedModel" - ] - } - }, - "info.aet.funnel": { - "*": { - "repo": "funnel-transformer/small", - "pkg": { - "0": { - "transformers": "FunnelModel" - } - }, - "tasks": [ - "FunnelBaseModel", - "FunnelForMaskedLM", - "FunnelForMultipleChoice", - "FunnelForPreTraining", - "FunnelForQuestionAnswering", - "FunnelForSequenceClassification", - "FunnelForTokenClassification", - "FunnelModel", - "FunnelPreTrainedModel" - ] - } - }, - "info.vit.convnextv2-224": { - "*": { - "repo": "facebook/convnextv2-tiny-1k-224", - "pkg": { - "0": { - "transformers": "ConvNextV2Model" - } - }, - "tasks": [ - "ConvNextV2ForImageClassification", - "ConvNextV2Model", - "ConvNextV2PreTrainedModel", - "ConvNextV2Backbone" - ] - } - }, - "info.moe.glm-4-a": { - "*": { - "repo": "zai-org/GLM-4.5-Air", - "pkg": { - "0": { - "transformers": "Glm4MoeModel" - } - }, - "tasks": [ - "Glm4MoePreTrainedModel", - "Glm4MoeModel", - "Glm4MoeForCausalLM" - ] - } - }, - "info.detr.vit--384": { - "*": { - "repo": "google/vit-hybrid-base-bit-384", - "pkg": { - "0": { - "transformers": "ViTHybridModel" - } - }, - "tasks": [ - "ViTHybridForImageClassification", - "ViTHybridModel", - "ViTHybridPreTrainedModel" - ] - } - }, - "info.art.qwen2": { - "*": { - "repo": "Qwen/Qwen2-7B", - "pkg": { - "0": { - "transformers": "Qwen2Model" - } - }, - "tasks": [ - "Qwen2PreTrainedModel", - "Qwen2Model", - "Qwen2ForCausalLM", - "Qwen2ForSequenceClassification", - "Qwen2ForTokenClassification", - "Qwen2ForQuestionAnswering" - ] - }, - "bagel-mot": { - "repo": "ByteDance-Seed/BAGEL-7B-MoT", - "pkg": { - "0": { - "Bagel": "app" - } - } - } - }, - "info.vit.aimv2-patch14-224-lit": { - "*": { - "repo": "apple/aimv2-large-patch14-224-lit", - "pkg": { - "0": { - "transformers": "Aimv2Model" - } - }, - "tasks": [ - "Aimv2VisionModel", - "Aimv2Model", - "Aimv2PreTrainedModel", - "Aimv2TextModel" - ] - } - }, - "info.aet.data2vec-text": { - "*": { - "repo": "facebook/data2vec-text-base", - "pkg": { - "0": { - "transformers": "Data2VecTextModel" - } - }, - "tasks": [ - "Data2VecTextForCausalLM", - "Data2VecTextForMaskedLM", - "Data2VecTextForMultipleChoice", - "Data2VecTextForQuestionAnswering", - "Data2VecTextForSequenceClassification", - "Data2VecTextForTokenClassification", - "Data2VecTextModel", - "Data2VecTextPreTrainedModel" - ] - } - }, - "info.detr.conditional-detr-resnet-50": { - "*": { - "repo": "microsoft/conditional-detr-resnet-50", - "pkg": { - "0": { - "transformers": "ConditionalDetrModel" - } - }, - "tasks": [ - "ConditionalDetrForObjectDetection", - "ConditionalDetrForSegmentation", - "ConditionalDetrModel", - "ConditionalDetrPreTrainedModel" - ] - } - }, - "info.aet.efficient-mlm-m0-0": { - "*": { - "repo": "andreasmadsen/efficient_mlm_m0.40", - "pkg": { - "0": { - "transformers": "RobertaPreLayerNormModel" - } - }, - "tasks": [ - "RobertaPreLayerNormForCausalLM", - "RobertaPreLayerNormForMaskedLM", - "RobertaPreLayerNormForMultipleChoice", - "RobertaPreLayerNormForQuestionAnswering", - "RobertaPreLayerNormForSequenceClassification", - "RobertaPreLayerNormForTokenClassification", - "RobertaPreLayerNormModel", - "RobertaPreLayerNormPreTrainedModel" - ] - } - }, - "info.art.gemma2": { - "*": { - "repo": "google/gemma-2-9b", - "pkg": { - "0": { - "transformers": "Gemma2Model" - } - }, - "file_256": [ - "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", - "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" - ], - "layer_b3": [ - "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", - "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" - ], - "layer_256": [ - "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", - "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" - ], - "tasks": [ - "Gemma2ForCausalLM", - "Gemma2Model", - "Gemma2PreTrainedModel", - "Gemma2ForSequenceClassification", - "Gemma2ForTokenClassification" - ] - } - }, - "info.aet.yoso-4096": { - "*": { - "repo": "uw-madison/yoso-4096", - "pkg": { - "0": { - "transformers": "YosoModel" - } - }, - "tasks": [ - "YosoForMaskedLM", - "YosoForMultipleChoice", - "YosoForQuestionAnswering", - "YosoForSequenceClassification", - "YosoForTokenClassification", - "YosoLayer", - "YosoModel", - "YosoPreTrainedModel" - ] - } - }, - "info.aet.unispeech-sat-100h-libri-ft": { - "*": { - "repo": "microsoft/unispeech-sat-base-100h-libri-ft", - "pkg": { - "0": { - "transformers": "UniSpeechSatModel" - } - }, - "tasks": [ - "UniSpeechSatForAudioFrameClassification", - "UniSpeechSatForCTC", - "UniSpeechSatForPreTraining", - "UniSpeechSatForSequenceClassification", - "UniSpeechSatForXVector", - "UniSpeechSatModel", - "UniSpeechSatPreTrainedModel" - ] - } - }, - "info.vit.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4ForConditionalGeneration" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.art.olmo-hf": { - "*": { - "repo": "allenai/OLMo-7B-hf", - "pkg": { - "0": { - "transformers": "OlmoModel" - } - }, - "tasks": [ - "OlmoForCausalLM", - "OlmoModel", - "OlmoPreTrainedModel" - ] - } - }, - "info.aet.sew": { - "*": { - "repo": "asapp/sew-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWModel" - } - }, - "tasks": [ - "SEWForCTC", - "SEWForSequenceClassification", - "SEWModel", - "SEWPreTrainedModel" - ] - } - }, - "info.stst.plbart": { - "*": { - "repo": "uclanlp/plbart-base", - "pkg": { - "0": { - "transformers": "PLBartModel" - } - }, - "tasks": [ - "PLBartForCausalLM", - "PLBartForConditionalGeneration", - "PLBartForSequenceClassification", - "PLBartModel", - "PLBartPreTrainedModel" - ] - } - }, - "info.detr.deformable-detr": { - "*": { - "repo": "SenseTime/deformable-detr", - "pkg": { - "0": { - "transformers": "DetaModel" - } - }, - "tasks": [ - "DetaForObjectDetection", - "DetaModel", - "DetaPreTrainedModel" - ] - } - }, - "info.moe.mixtral-8x": { - "*": { - "repo": "mistralai/Mixtral-8x7B-v0.1", - "pkg": { - "0": { - "transformers": "MixtralModel" - } - }, - "tasks": [ - "MixtralForCausalLM", - "MixtralForQuestionAnswering", - "MixtralModel", - "MixtralPreTrainedModel", - "MixtralForSequenceClassification", - "MixtralForTokenClassification" - ] - } - }, - "info.gan.mimi": { - "*": { - "repo": "kyutai/mimi", - "pkg": { - "0": { - "transformers": "MimiModel" - } - }, - "tasks": [ - "MimiModel", - "MimiPreTrainedModel" - ] - } - }, - "info.art.bitnet-b18-4t": { - "*": { - "repo": "microsoft/bitnet-b1.58-2B-4T", - "pkg": { - "0": { - "transformers": "BitNetModel" - } - }, - "tasks": [ - "BitNetForCausalLM", - "BitNetModel", - "BitNetPreTrainedModel" - ] - } - }, - "info.art.bigbird-roberta": { - "*": { - "repo": "google/bigbird-roberta-base", - "pkg": { - "0": { - "transformers": "BigBirdModel" - } - }, - "tasks": [ - "BigBirdForCausalLM", - "BigBirdForMaskedLM", - "BigBirdForMultipleChoice", - "BigBirdForPreTraining", - "BigBirdForQuestionAnswering", - "BigBirdForSequenceClassification", - "BigBirdForTokenClassification", - "BigBirdLayer", - "BigBirdModel", - "BigBirdPreTrainedModel" - ] - } - }, - "info.art.lxmert-uncased": { - "*": { - "repo": "unc-nlp/lxmert-base-uncased", - "pkg": { - "0": { - "transformers": "LxmertModel" - } - }, - "tasks": [ - "LxmertEncoder", - "LxmertForPreTraining", - "LxmertForQuestionAnswering", - "LxmertModel", - "LxmertPreTrainedModel", - "LxmertVisualFeatureEncoder", - "LxmertXLayer" - ] - } - }, - "info.art.gpt-neox-japanese": { - "*": { - "repo": "abeja/gpt-neox-japanese-2.7b", - "pkg": { - "0": { - "transformers": "GPTNeoXJapaneseModel" - } - }, - "tasks": [ - "GPTNeoXJapaneseForCausalLM", - "GPTNeoXJapaneseLayer", - "GPTNeoXJapaneseModel", - "GPTNeoXJapanesePreTrainedModel" - ] - } - }, - "info.stst.m": { - "*": { - "repo": "facebook/m2m100_418M", - "pkg": { - "0": { - "transformers": "M2M100Model" - } - }, - "tasks": [ - "M2M100ForConditionalGeneration", - "M2M100Model", - "M2M100PreTrainedModel" - ] - } - }, - "info.art.chameleon": { - "*": { - "repo": "meta/chameleon-7B", - "pkg": { - "0": { - "transformers": "ChameleonModel" - } - }, - "tasks": [ - "ChameleonForConditionalGeneration", - "ChameleonModel", - "ChameleonPreTrainedModel", - "ChameleonVQVAE" - ] - }, - "lumina-mgpt-1024": { - "repo": "Alpha-VLLM/Lumina-mGPT-7B-1024", - "pkg": { - "0": { - "inference_solver": { - "FlexARInferenceSolver": { - "precision": "bf16", - "target_size": 768 - } - }, - "generation": { - "images": [], - "qas": [ - [ - "q1", - null - ] - ], - "max_gen_len": 8192, - "temperature": 1.0 - } - }, - "1": { - "inference_solver": "ChameleonXLLMXForConditionalGeneration" - } - }, - "file_256": [ - "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", - "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", - "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", - "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b" - ], - "layer_256": [ - "eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25" - ], - "layer_b3": [ - "6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656" - ] - } - }, - "info.aet.albert-xx-v2": { - "*": { - "repo": "albert/albert-xxlarge-v2", - "pkg": { - "0": { - "transformers": "AlbertModel" - } - }, - "tasks": [ - "AlbertPreTrainedModel", - "AlbertModel", - "AlbertForPreTraining", - "AlbertForMaskedLM", - "AlbertForSequenceClassification", - "AlbertForTokenClassification", - "AlbertForQuestionAnswering", - "AlbertForMultipleChoice" - ] - } - }, - "info.stst.pegasus": { - "*": { - "repo": "google/pegasus-large", - "pkg": { - "0": { - "transformers": "PegasusModel" - } - }, - "tasks": [ - "PegasusForCausalLM", - "PegasusForConditionalGeneration", - "PegasusModel", - "PegasusPreTrainedModel" - ] - } - }, - "info.aet.ernie-3-zh": { - "*": { - "repo": "nghuyong/ernie-3.0-base-zh", - "pkg": { - "0": { - "transformers": "ErnieModel" - } - }, - "tasks": [ - "ErnieForCausalLM", - "ErnieForMaskedLM", - "ErnieForMultipleChoice", - "ErnieForNextSentencePrediction", - "ErnieForPreTraining", - "ErnieForQuestionAnswering", - "ErnieForSequenceClassification", - "ErnieForTokenClassification", - "ErnieModel", - "ErniePreTrainedModel" - ] - } - }, - "info.vit.clvp-dev": { - "*": { - "repo": "susnato/clvp_dev", - "pkg": { - "0": { - "transformers": "ClvpModelForConditionalGeneration" - } - }, - "tasks": [ - "ClvpModelForConditionalGeneration", - "ClvpForCausalLM", - "ClvpModel", - "ClvpPreTrainedModel", - "ClvpEncoder", - "ClvpDecoder" - ] - } - }, - "info.vit.smolvlm": { - "*": { - "repo": "HuggingFaceTB/SmolVLM2-2.2B-Instruct", - "pkg": { - "0": { - "transformers": "SmolVLMModel" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.aet.esm": { - "*": { - "repo": "facebook/esm-1b", - "pkg": { - "0": { - "transformers": "EsmModel" - } - }, - "tasks": [ - "EsmForMaskedLM", - "EsmForSequenceClassification", - "EsmForTokenClassification", - "EsmModel", - "EsmPreTrainedModel" - ] - } - }, - "info.vit.tvlt": { - "*": { - "repo": "ZinengTang/tvlt-base", - "pkg": { - "0": { - "transformers": "TvltModel" - } - }, - "tasks": [ - "TvltModel", - "TvltForPreTraining", - "TvltForAudioVisualClassification", - "TvltPreTrainedModel" - ] - } - }, - "info.moe.gpt-oss": { - "*": { - "repo": "openai/gpt-oss-120b", - "pkg": { - "0": { - "transformers": "GptOssModel" - } - }, - "file_256": [ - "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", - "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" - ], - "layer_b3": [ - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", - "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" - ], - "layer_256": [ - "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", - "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" - ], - "tasks": [ - "GptOssForCausalLM", - "GptOssModel", - "GptOssPreTrainedModel" - ] - } - }, - "info.art.rembert": { - "*": { - "repo": "google/rembert", - "pkg": { - "0": { - "transformers": "RemBertModel" - } - }, - "tasks": [ - "RemBertForCausalLM", - "RemBertForMaskedLM", - "RemBertForMultipleChoice", - "RemBertForQuestionAnswering", - "RemBertForSequenceClassification", - "RemBertForTokenClassification", - "RemBertLayer", - "RemBertModel", - "RemBertPreTrainedModel" - ] - } - }, - "info.art.c4ai-command-r-v01": { - "*": { - "repo": "CohereForAI/c4ai-command-r-v01", - "pkg": { - "0": { - "transformers": "CohereModel" - } - }, - "tasks": [ - "CohereForCausalLM", - "CohereModel", - "CoherePreTrainedModel" - ] - } - }, - "info.rnn.rwkv-4-pile": { - "*": { - "repo": "RWKV/rwkv-4-169m-pile", - "pkg": { - "0": { - "transformers": "RwkvModel" - } - }, - "tasks": [ - "RwkvForCausalLM", - "RwkvModel", - "RwkvPreTrainedModel" - ] - } - }, - "info.stst.umt5": { - "*": { - "repo": "google/umt5-small", - "pkg": { - "0": { - "transformers": "UMT5Model" - } - }, - "identifiers": [ - "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" - ], - "file_256": [ - "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", - "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", - "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", - "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", - "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", - "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", - "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", - "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", - "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", - "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", - "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", - "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", - "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", - "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", - "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", - "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" - ], - "layer_b3": [ - "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", - "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", - "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", - "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", - "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", - "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", - "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", - "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", - "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", - "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", - "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", - "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", - "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", - "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", - "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", - "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", - "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", - "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" - ], - "layer_256": [ - "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", - "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", - "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", - "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", - "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", - "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", - "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", - "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", - "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", - "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", - "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", - "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", - "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", - "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", - "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", - "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", - "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", - "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" - ], - "tasks": [ - "UMT5EncoderModel", - "UMT5ForConditionalGeneration", - "UMT5ForQuestionAnswering", - "UMT5ForSequenceClassification", - "UMT5ForTokenClassification", - "UMT5Model", - "UMT5PreTrainedModel" - ] - } - }, - "info.art.gemma": { - "*": { - "repo": "google/gemma-7b", - "pkg": { - "0": { - "transformers": "GemmaModel" - } - }, - "file_256": [ - "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" - ], - "layer_b3": [ - "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", - "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" - ], - "layer_256": [ - "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", - "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" - ], - "tasks": [ - "GemmaModel", - "GemmaForCausalLM", - "GemmaForSequenceClassification", - "GemmaForTokenClassification", - "GemmaPreTrainedModel" - ] - } - }, - "info.vit.pvt-v2-b0": { - "*": { - "repo": "OpenGVLab/pvt_v2_b0", - "pkg": { - "0": { - "transformers": "PvtV2Model" - } - }, - "tasks": [ - "PvtV2ForImageClassification", - "PvtV2Model", - "PvtV2PreTrainedModel", - "PvtV2Backbone" - ] - } - }, - "info.aet.test-dec": { - "*": { - "repo": "blab-jhu/test-32m-dec", - "pkg": { - "0": { - "transformers": "ModernBertDecoderModel" - } - }, - "tasks": [ - "ModernBertDecoderModel", - "ModernBertDecoderPreTrainedModel", - "ModernBertDecoderForCausalLM", - "ModernBertDecoderForSequenceClassification" - ] - } - }, - "info.vit.deepseek-vl-chat": { - "*": { - "repo": "deepseek-community/deepseek-vl-1.3b-chat", - "pkg": { - "0": { - "transformers": "DeepseekVLModel" - } - }, - "tasks": [ - "DeepseekVLPreTrainedModel", - "DeepseekVLModel", - "DeepseekVLForConditionalGeneration" - ] - } - }, - "info.aet.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralEncoder" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.vit.command-a-vision-07-2025": { - "*": { - "repo": "CohereLabs/command-a-vision-07-2025", - "pkg": { - "0": { - "transformers": "Cohere2VisionModel" - } - }, - "tasks": [ - "Cohere2VisionForConditionalGeneration", - "Cohere2VisionPreTrainedModel", - "Cohere2VisionModel" - ] - } - }, - "info.art.reformer-crime-and-punishment": { - "*": { - "repo": "google/reformer-crime-and-punishment", - "pkg": { - "0": { - "transformers": "ReformerModel" - } - }, - "tasks": [ - "ReformerAttention", - "ReformerForMaskedLM", - "ReformerForQuestionAnswering", - "ReformerForSequenceClassification", - "ReformerLayer", - "ReformerModel", - "ReformerModelWithLMHead", - "ReformerPreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-960h": { - "*": { - "repo": "facebook/wav2vec2-base-960h", - "pkg": { - "0": { - "transformers": "Wav2Vec2Model" - } - }, - "tasks": [ - "Wav2Vec2ForAudioFrameClassification", - "Wav2Vec2ForCTC", - "Wav2Vec2ForMaskedLM", - "Wav2Vec2ForPreTraining", - "Wav2Vec2ForSequenceClassification", - "Wav2Vec2ForXVector", - "Wav2Vec2Model", - "Wav2Vec2PreTrainedModel" - ] - } - }, - "info.detr.resnet18-a1-in": { - "*": { - "repo": "timm/resnet18.a1_in1k", - "pkg": { - "0": { - "transformers": "TimmWrapperModel" - } - }, - "tasks": [ - "TimmWrapperPreTrainedModel", - "TimmWrapperModel", - "TimmWrapperForImageClassification" - ] - } - }, - "info.vit.videomae": { - "*": { - "repo": "MCG-NJU/videomae-base", - "pkg": { - "0": { - "transformers": "VideoMAEModel" - } - }, - "tasks": [ - "VideoMAEForPreTraining", - "VideoMAEModel", - "VideoMAEPreTrainedModel", - "VideoMAEForVideoClassification" - ] - } - }, - "info.art.nezha-cn": { - "*": { - "repo": "sijunhe/nezha-cn-base", - "pkg": { - "0": { - "transformers": "NezhaModel" - } - }, - "tasks": [ - "NezhaForNextSentencePrediction", - "NezhaForMaskedLM", - "NezhaForPreTraining", - "NezhaForMultipleChoice", - "NezhaForQuestionAnswering", - "NezhaForSequenceClassification", - "NezhaForTokenClassification", - "NezhaModel", - "NezhaPreTrainedModel" - ] - } - }, - "info.vit.git": { - "*": { - "repo": "microsoft/git-base", - "pkg": { - "0": { - "transformers": "GitModel" - } - }, - "tasks": [ - "GitForCausalLM", - "GitModel", - "GitPreTrainedModel", - "GitVisionModel" - ] - } - }, - "info.vit.kosmos-2-patch14-224": { - "*": { - "repo": "microsoft/kosmos-2-patch14-224", - "pkg": { - "0": { - "transformers": "Kosmos2Model" - } - }, - "tasks": [ - "Kosmos2ForConditionalGeneration", - "Kosmos2Model", - "Kosmos2PreTrainedModel" - ] - } - }, - "info.art.stt-en-trfs": { - "*": { - "repo": "kyutai/stt-2.6b-en-trfs", - "pkg": { - "0": { - "transformers": "KyutaiSpeechToTextModel" - } - }, - "tasks": [ - "KyutaiSpeechToTextPreTrainedModel", - "KyutaiSpeechToTextModel", - "KyutaiSpeechToTextForConditionalGeneration" - ] - } - }, - "info.art.csm": { - "*": { - "repo": "sesame/csm-1b", - "pkg": { - "0": { - "transformers": "CsmForConditionalGeneration" - } - }, - "tasks": [ - "CsmPreTrainedModel", - "CsmBackboneModel", - "CsmDepthDecoderModel", - "CsmDepthDecoderForCausalLM", - "CsmForConditionalGeneration" - ] - } - }, - "info.detr.dab-detr": { - "*": { - "repo": "IDEA-Research/dab-detr-resnet-50", - "pkg": { - "0": { - "transformers": "DabDetrModel" - } - }, - "tasks": [ - "DabDetrForObjectDetection", - "DabDetrModel", - "DabDetrPreTrainedModel" - ] - } - }, - "info.vit.timesformer-finetuned-k600": { - "*": { - "repo": "facebook/timesformer-base-finetuned-k600", - "pkg": { - "0": { - "transformers": "TimesformerModel" - } - }, - "tasks": [ - "TimesformerModel", - "TimesformerForVideoClassification", - "TimesformerPreTrainedModel" - ] - } - }, - "info.ssm.falconh1-t-hf": { - "*": { - "repo": "tiiuae/Falcon-H1-34B-Instruct", - "pkg": { - "0": { - "transformers": "FalconH1Model" - } - }, - "tasks": [ - "FalconH1Model", - "FalconH1ForCausalLM", - "FalconH1PreTrainedModel" - ] - } - }, - "info.moe.olmoe-0924": { - "*": { - "repo": "allenai/OLMoE-1B-7B-0924", - "pkg": { - "0": { - "transformers": "OlmoeModel" - } - }, - "tasks": [ - "OlmoeForCausalLM", - "OlmoeModel", - "OlmoePreTrainedModel" - ] - } - }, - "info.moe.deepseek-v2-lite": { - "*": { - "repo": "deepseek-ai/DeepSeek-V2-Lite", - "pkg": { - "0": { - "transformers": "DeepseekV2Model" - } - }, - "tasks": [ - "DeepseekV2PreTrainedModel", - "DeepseekV2Model", - "DeepseekV2ForCausalLM", - "DeepseekV2ForSequenceClassification" - ] - } - }, - "info.art.phi-1": { - "*": { - "repo": "microsoft/phi-1", - "pkg": { - "0": { - "transformers": "PhiModel" - } - }, - "tasks": [ - "PhiPreTrainedModel", - "PhiModel", - "PhiForCausalLM", - "PhiForSequenceClassification", - "PhiForTokenClassification" - ] - } - }, - "info.vit.swin-patch4-window7-224": { - "*": { - "repo": "microsoft/swin-tiny-patch4-window7-224", - "pkg": { - "0": { - "transformers": "MaskFormerSwinModel" - } - }, - "tasks": [ - "MaskFormerSwinBackbone", - "MaskFormerSwinModel", - "MaskFormerSwinPreTrainedModel" - ] - } - }, - "info.art.codegen-mono": { - "*": { - "repo": "Salesforce/codegen-2B-mono", - "pkg": { - "0": { - "transformers": "CodeGenModel" - } - }, - "tasks": [ - "CodeGenForCausalLM", - "CodeGenModel", - "CodeGenPreTrainedModel" - ] - } - }, - "info.aet.data2vec-audio-960h": { - "*": { - "repo": "facebook/data2vec-audio-base-960h", - "pkg": { - "0": { - "transformers": "Data2VecAudioModel" - } - }, - "tasks": [ - "Data2VecAudioForAudioFrameClassification", - "Data2VecAudioForCTC", - "Data2VecAudioForSequenceClassification", - "Data2VecAudioForXVector", - "Data2VecAudioModel", - "Data2VecAudioPreTrainedModel" - ] - } - }, - "info.detr.upernet-convnext": { - "*": { - "repo": "openmmlab/upernet-convnext-tiny", - "pkg": { - "0": { - "transformers": "UperNetForSemanticSegmentation" - } - }, - "tasks": [ - "UperNetForSemanticSegmentation", - "UperNetPreTrainedModel" - ] - } - }, - "info.art.musicgen": { - "*": { - "repo": "facebook/musicgen-small", - "pkg": { - "0": { - "transformers": "MusicgenModel" - } - }, - "tasks": [ - "MusicgenForConditionalGeneration", - "MusicgenForCausalLM", - "MusicgenModel", - "MusicgenPreTrainedModel" - ] - } - }, - "info.art.olmo2-1124-hf": { - "*": { - "repo": "allenai/Olmo-2-1124-7B", - "pkg": { - "0": { - "transformers": "Olmo2Model" - } - }, - "tasks": [ - "Olmo2ForCausalLM", - "Olmo2Model", - "Olmo2PreTrainedModel" - ] - } - }, - "info.art.splinter": { - "*": { - "repo": "tau/splinter-base", - "pkg": { - "0": { - "transformers": "SplinterModel" - } - }, - "tasks": [ - "SplinterForQuestionAnswering", - "SplinterForPreTraining", - "SplinterLayer", - "SplinterModel", - "SplinterPreTrainedModel" - ] - } - }, - "info.art.luke": { - "*": { - "repo": "studio-ousia/luke-base", - "pkg": { - "0": { - "transformers": "LukeModel" - } - }, - "tasks": [ - "LukeForEntityClassification", - "LukeForEntityPairClassification", - "LukeForEntitySpanClassification", - "LukeForMultipleChoice", - "LukeForQuestionAnswering", - "LukeForSequenceClassification", - "LukeForTokenClassification", - "LukeForMaskedLM", - "LukeModel", - "LukePreTrainedModel" - ] - } - }, - "info.art.glm-4-chat": { - "*": { - "repo": "zai-org/glm-4-9b-chat", - "pkg": { - "0": { - "transformers": "GlmModel" - } - }, - "tasks": [ - "GlmPreTrainedModel", - "GlmModel", - "GlmForCausalLM", - "GlmForSequenceClassification", - "GlmForTokenClassification" - ] - } - }, - "info.vit.vit-msn": { - "*": { - "repo": "facebook/vit-msn-base", - "pkg": { - "0": { - "transformers": "ViTMSNModel" - } - }, - "tasks": [ - "ViTMSNModel", - "ViTMSNForImageClassification", - "ViTMSNPreTrainedModel" - ] - } - }, - "info.cnn.yolos": { - "*": { - "repo": "hustvl/yolos-base", - "pkg": { - "0": { - "transformers": "YolosModel" - } - }, - "tasks": [ - "YolosForObjectDetection", - "YolosModel", - "YolosPreTrainedModel" - ] - } - }, - "info.vit.vitpose-simple": { - "*": { - "repo": "usyd-community/vitpose-base-simple", - "pkg": { - "0": { - "transformers": "VitPoseBackbone" - } - }, - "tasks": [ - "VitPoseBackbonePreTrainedModel", - "VitPoseBackbone" - ] - } - }, - "info.aet.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2QFormerModel" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.stst.long-t5-local": { - "*": { - "repo": "google/long-t5-local-base", - "pkg": { - "0": { - "transformers": "LongT5Model" - } - }, - "tasks": [ - "LongT5EncoderModel", - "LongT5ForConditionalGeneration", - "LongT5Model", - "LongT5PreTrainedModel" - ] - } - }, - "info.art.nemotron-3-hf": { - "*": { - "repo": "mgoin/nemotron-3-8b-chat-4k-sft-hf", - "pkg": { - "0": { - "transformers": "NemotronModel" - } - }, - "tasks": [ - "NemotronForQuestionAnswering", - "NemotronForCausalLM", - "NemotronModel", - "NemotronPreTrainedModel", - "NemotronForSequenceClassification", - "NemotronForTokenClassification" - ] - } - }, - "info.aet.wav2vec2-bert-rel-pos": { - "*": { - "repo": "facebook/w2v-bert-2.0", - "pkg": { - "0": { - "transformers": "Wav2Vec2BertModel" - } - }, - "tasks": [ - "Wav2Vec2BertForAudioFrameClassification", - "Wav2Vec2BertForCTC", - "Wav2Vec2BertForSequenceClassification", - "Wav2Vec2BertForXVector", - "Wav2Vec2BertModel", - "Wav2Vec2BertPreTrainedModel" - ] - } - }, - "info.art.trocr-handwritten": { - "*": { - "repo": "microsoft/trocr-base-handwritten", - "pkg": { - "0": { - "transformers": "TrOCRForCausalLM" - } - }, - "tasks": [ - "TrOCRForCausalLM", - "TrOCRPreTrainedModel" - ] - } - }, - "info.art.llama-2-hf": { - "*": { - "repo": "meta-llama/Llama-2-7b-hf", - "pkg": { - "0": { - "transformers": "LlamaModel" - } - }, - "tasks": [ - "LlamaForCausalLM", - "LlamaModel", - "LlamaPreTrainedModel", - "LlamaForSequenceClassification", - "LlamaForQuestionAnswering", - "LlamaForTokenClassification" - ] - } - }, - "info.rnn.recurrentgemma": { - "*": { - "repo": "google/recurrentgemma-2b", - "pkg": { - "0": { - "transformers": "RecurrentGemmaModel" - } - }, - "tasks": [ - "RecurrentGemmaForCausalLM", - "RecurrentGemmaModel", - "RecurrentGemmaPreTrainedModel" - ] - } - }, - "info.stst.led-16384": { - "*": { - "repo": "allenai/led-base-16384", - "pkg": { - "0": { - "transformers": "LEDModel" - } - }, - "tasks": [ - "LEDForConditionalGeneration", - "LEDForQuestionAnswering", - "LEDForSequenceClassification", - "LEDModel", - "LEDPreTrainedModel" - ] - } - }, - "info.detr.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine-xlarge-coco", - "pkg": { - "0": { - "transformers": "DFineModel" - } - }, - "tasks": [ - "DFineModel", - "DFinePreTrainedModel", - "DFineForObjectDetection" - ] - } - }, - "info.vit.vjepa2-vitl-fpc64-256": { - "*": { - "repo": "facebook/vjepa2-vitl-fpc64-256", - "pkg": { - "0": { - "transformers": "VJEPA2Model" - } - }, - "tasks": [ - "VJEPA2Model", - "VJEPA2PreTrainedModel", - "VJEPA2ForVideoClassification" - ] - } - }, - "info.aet.lightglue-superpoint": { - "*": { - "repo": "ETH-CVG/lightglue_superpoint", - "pkg": { - "0": { - "transformers": "LightGlueForKeypointMatching" - } - }, - "tasks": [ - "LightGluePreTrainedModel", - "LightGlueForKeypointMatching" - ] - } - }, - "info.ssm.mamba": { - "*": { - "repo": "state-spaces/mamba-2.8b", - "pkg": { - "0": { - "transformers": "MambaModel" - } - }, - "tasks": [ - "MambaForCausalLM", - "MambaModel", - "MambaPreTrainedModel", - "MambaCache" - ] - } - }, - "info.vit.idefics2": { - "*": { - "repo": "HuggingFaceM4/idefics2-8b", - "pkg": { - "0": { - "transformers": "Idefics2Model" - } - }, - "tasks": [ - "Idefics2ForConditionalGeneration", - "Idefics2PreTrainedModel", - "Idefics2Model" - ] - } - }, - "info.art.squeezebert-uncased": { - "*": { - "repo": "squeezebert/squeezebert-uncased", - "pkg": { - "0": { - "transformers": "SqueezeBertModel" - } - }, - "tasks": [ - "SqueezeBertForMaskedLM", - "SqueezeBertForMultipleChoice", - "SqueezeBertForQuestionAnswering", - "SqueezeBertForSequenceClassification", - "SqueezeBertForTokenClassification", - "SqueezeBertModel", - "SqueezeBertModule", - "SqueezeBertPreTrainedModel" - ] - } - }, - "info.art.mms-tts-eng": { - "*": { - "repo": "facebook/mms-tts-eng", - "pkg": { - "0": { - "transformers": "VitsModel" - } - }, - "tasks": [ - "VitsModel", - "VitsPreTrainedModel" - ] - } - }, - "info.aet.fastspeech2-conformer": { - "*": { - "repo": "espnet/fastspeech2_conformer", - "pkg": { - "0": { - "transformers": "FastSpeech2ConformerModel" - } - }, - "tasks": [ - "FastSpeech2ConformerWithHifiGan", - "FastSpeech2ConformerHifiGan", - "FastSpeech2ConformerModel", - "FastSpeech2ConformerPreTrainedModel" - ] - } - }, - "info.vit.textnet": { - "*": { - "repo": "czczup/textnet-base", - "pkg": { - "0": { - "transformers": "TextNetModel" - } - }, - "tasks": [ - "TextNetBackbone", - "TextNetModel", - "TextNetPreTrainedModel", - "TextNetForImageClassification" - ] - } - }, - "info.vit.depth": { - "*": { - "repo": "apple/DepthPro", - "pkg": { - "0": { - "transformers": "DepthProModel" - } - }, - "tasks": [ - "DepthProPreTrainedModel", - "DepthProModel", - "DepthProForDepthEstimation" - ] - } - }, - "info.stst.bigbird-pegasus-arxiv": { - "*": { - "repo": "google/bigbird-pegasus-large-arxiv", - "pkg": { - "0": { - "transformers": "BigBirdPegasusModel" - } - }, - "tasks": [ - "BigBirdPegasusForCausalLM", - "BigBirdPegasusForConditionalGeneration", - "BigBirdPegasusForQuestionAnswering", - "BigBirdPegasusForSequenceClassification", - "BigBirdPegasusModel", - "BigBirdPegasusPreTrainedModel" - ] - } - }, - "info.stst.mt5": { - "*": { - "repo": "google/mt5-small", - "pkg": { - "0": { - "transformers": "MT5Model" - } - }, - "identifiers": [ - [ - 250112, - 2048 - ], - "text_encoders.mt5xl.transformer.shared.weight" - ], - "file_256": [ - "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", - "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" - ], - "layer_b3": [ - "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51" - ], - "layer_256": [ - "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", - "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" - ], - "tasks": [ - "MT5EncoderModel", - "MT5ForConditionalGeneration", - "MT5ForQuestionAnswering", - "MT5ForSequenceClassification", - "MT5ForTokenClassification", - "MT5Model", - "MT5PreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v2-1--224": { - "*": { - "repo": "google/mobilenet_v2_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV2Model" - } - }, - "tasks": [ - "MobileNetV2ForImageClassification", - "MobileNetV2ForSemanticSegmentation", - "MobileNetV2Model", - "MobileNetV2PreTrainedModel" - ] - } - }, - "info.vit.paligemma": { - "*": { - "repo": "google/paligemma2-3b-mix-224", - "pkg": { - "0": { - "transformers": "PaliGemmaModel" - } - }, - "tasks": [ - "PaliGemmaForConditionalGeneration", - "PaliGemmaPreTrainedModel", - "PaliGemmaModel" - ] - } - }, - "info.stst.speecht5-asr": { - "*": { - "repo": "microsoft/speecht5_asr", - "pkg": { - "0": { - "transformers": "SpeechT5Model" - } - }, - "tasks": [ - "SpeechT5ForSpeechToText", - "SpeechT5ForSpeechToSpeech", - "SpeechT5ForTextToSpeech", - "SpeechT5Model", - "SpeechT5PreTrainedModel", - "SpeechT5HifiGan" - ] - } - }, - "info.art.conv-bert": { - "*": { - "repo": "YituTech/conv-bert-base", - "pkg": { - "0": { - "transformers": "ConvBertModel" - } - }, - "tasks": [ - "ConvBertForMaskedLM", - "ConvBertForMultipleChoice", - "ConvBertForQuestionAnswering", - "ConvBertForSequenceClassification", - "ConvBertForTokenClassification", - "ConvBertLayer", - "ConvBertModel", - "ConvBertPreTrainedModel" - ] - } - }, - "info.ssm.mamba2": { - "*": { - "repo": "AntonV/mamba2-2.7b-hf", - "pkg": { - "0": { - "transformers": "Mamba2Model" - } - }, - "tasks": [ - "Mamba2ForCausalLM", - "Mamba2Model", - "Mamba2PreTrainedModel" - ] - } - }, - "info.art.c4ai-command-r-12-2024": { - "*": { - "repo": "CohereLabs/c4ai-command-r7b-12-2024", - "pkg": { - "0": { - "transformers": "Cohere2Model" - } - }, - "tasks": [ - "Cohere2ForCausalLM", - "Cohere2Model", - "Cohere2PreTrainedModel" - ] - } - }, - "info.vit.regnet-y-040": { - "*": { - "repo": "facebook/regnet-y-040", - "pkg": { - "0": { - "transformers": "RegNetModel" - } - }, - "tasks": [ - "RegNetForImageClassification", - "RegNetModel", - "RegNetPreTrainedModel" - ] - } - }, - "info.aet.xmod": { - "*": { - "repo": "facebook/xmod-base", - "pkg": { - "0": { - "transformers": "XmodModel" - } - }, - "tasks": [ - "XmodForCausalLM", - "XmodForMaskedLM", - "XmodForMultipleChoice", - "XmodForQuestionAnswering", - "XmodForSequenceClassification", - "XmodForTokenClassification", - "XmodModel", - "XmodPreTrainedModel" - ] - } - }, - "info.stst.bart": { - "*": { - "repo": "facebook/bart-large", - "pkg": { - "0": { - "transformers": "BartModel" - } - }, - "tasks": [ - "BartForCausalLM", - "BartForConditionalGeneration", - "BartForQuestionAnswering", - "BartForSequenceClassification", - "BartModel", - "BartPreTrainedModel", - "BartPretrainedModel", - "PretrainedBartModel" - ] - } - }, - "info.detr.table-transformer-detection": { - "*": { - "repo": "microsoft/table-transformer-detection", - "pkg": { - "0": { - "transformers": "TableTransformerModel" - } - }, - "tasks": [ - "TableTransformerForObjectDetection", - "TableTransformerModel", - "TableTransformerPreTrainedModel" - ] - } - }, - "info.vit.resnet-50": { - "*": { - "repo": "microsoft/resnet-50", - "pkg": { - "0": { - "transformers": "ResNetModel" - } - }, - "tasks": [ - "ResNetForImageClassification", - "ResNetModel", - "ResNetPreTrainedModel", - "ResNetBackbone" - ] - } - }, - "info.art.bert-uncased": { - "*": { - "repo": "google-bert/bert-base-uncased", - "pkg": { - "0": { - "transformers": "QDQBertModel" - } - }, - "tasks": [ - "QDQBertForMaskedLM", - "QDQBertForMultipleChoice", - "QDQBertForNextSentencePrediction", - "QDQBertForQuestionAnswering", - "QDQBertForSequenceClassification", - "QDQBertForTokenClassification", - "QDQBertLayer", - "QDQBertLMHeadModel", - "QDQBertModel", - "QDQBertPreTrainedModel" - ] - } - }, - "info.stst.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralForConditionalGeneration" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.vit.pixtral": { - "*": { - "repo": "mistralai/Pixtral-12B-Base-2409", - "pkg": { - "0": { - "transformers": "PixtralVisionModel" - } - }, - "tasks": [ - "PixtralVisionModel", - "PixtralPreTrainedModel" - ] - } - }, - "info.aet.whisper": { - "*": { - "repo": "openai/whisper-tiny", - "pkg": { - "0": { - "transformers": "WhisperModel" - } - }, - "tasks": [ - "WhisperForCausalLM", - "WhisperForConditionalGeneration", - "WhisperModel", - "WhisperPreTrainedModel", - "WhisperForAudioClassification" - ] - } - }, - "info.detr.rtdetr-r18vd": { - "*": { - "repo": "PekingU/rtdetr_r18vd", - "pkg": { - "0": { - "transformers": "RTDetrV2Model" - } - }, - "tasks": [ - "RTDetrV2Model", - "RTDetrV2PreTrainedModel", - "RTDetrV2ForObjectDetection" - ] - } - }, - "info.aet.wavlm": { - "*": { - "repo": "microsoft/wavlm-base", - "pkg": { - "0": { - "transformers": "WavLMModel" - } - }, - "tasks": [ - "WavLMForAudioFrameClassification", - "WavLMForCTC", - "WavLMForSequenceClassification", - "WavLMForXVector", - "WavLMModel", - "WavLMPreTrainedModel" - ] - } - }, - "info.vit.beit-patch16-224-pt": { - "*": { - "repo": "microsoft/beit-base-patch16-224-pt22k", - "pkg": { - "0": { - "transformers": "BeitModel" - } - }, - "tasks": [ - "BeitForImageClassification", - "BeitForMaskedImageModeling", - "BeitForSemanticSegmentation", - "BeitModel", - "BeitPreTrainedModel", - "BeitBackbone" - ] - } - }, - "info.vit.blip-vqa": { - "*": { - "repo": "Salesforce/blip-vqa-base", - "pkg": { - "0": { - "transformers": "BlipModel" - } - }, - "tasks": [ - "BlipModel", - "BlipPreTrainedModel", - "BlipForConditionalGeneration", - "BlipForQuestionAnswering", - "BlipVisionModel", - "BlipTextModel", - "BlipForImageTextRetrieval" - ] - } - }, - "info.art.flaubert-uncased": { - "*": { - "repo": "flaubert/flaubert_base_uncased", - "pkg": { - "0": { - "transformers": "FlaubertModel" - } - }, - "tasks": [ - "FlaubertForMultipleChoice", - "FlaubertForQuestionAnswering", - "FlaubertForQuestionAnsweringSimple", - "FlaubertForSequenceClassification", - "FlaubertForTokenClassification", - "FlaubertModel", - "FlaubertWithLMHeadModel", - "FlaubertPreTrainedModel" - ] - } - }, - "info.art.transfo-xl-wt103": { - "*": { - "repo": "transfo-xl/transfo-xl-wt103", - "pkg": { - "0": { - "transformers": "TransfoXLModel" - } - }, - "tasks": [ - "AdaptiveEmbedding", - "TransfoXLForSequenceClassification", - "TransfoXLLMHeadModel", - "TransfoXLModel", - "TransfoXLPreTrainedModel" - ] - } - }, - "info.art.ernie-45-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-0.3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5Model" - } - }, - "tasks": [ - "Ernie4_5ForCausalLM", - "Ernie4_5Model", - "Ernie4_5PreTrainedModel" - ] - } - }, - "info.stst.moonshine": { - "*": { - "repo": "UsefulSensors/moonshine-tiny", - "pkg": { - "0": { - "transformers": "MoonshineModel" - } - }, - "tasks": [ - "MoonshineModel", - "MoonshinePreTrainedModel", - "MoonshineForConditionalGeneration" - ] - } - }, - "info.detr.tvp": { - "*": { - "repo": "Intel/tvp-base", - "pkg": { - "0": { - "transformers": "TvpModel" - } - }, - "tasks": [ - "TvpModel", - "TvpPreTrainedModel", - "TvpForVideoGrounding" - ] - } - }, - "info.art.biogpt": { - "*": { - "repo": "microsoft/biogpt", - "pkg": { - "0": { - "transformers": "BioGptModel" - } - }, - "tasks": [ - "BioGptForCausalLM", - "BioGptForTokenClassification", - "BioGptForSequenceClassification", - "BioGptModel", - "BioGptPreTrainedModel" - ] - } - }, - "info.art.opt": { - "*": { - "repo": "facebook/opt-350m", - "pkg": { - "0": { - "transformers": "OPTModel" - } - }, - "tasks": [ - "OPTForCausalLM", - "OPTModel", - "OPTPreTrainedModel", - "OPTForSequenceClassification", - "OPTForQuestionAnswering" - ] - } - }, - "info.vit.ijepa-vith14": { - "*": { - "repo": "facebook/ijepa_vith14_1k", - "pkg": { - "0": { - "transformers": "IJepaModel" - } - }, - "tasks": [ - "IJepaPreTrainedModel", - "IJepaModel", - "IJepaForImageClassification" - ] - } - }, - "info.vit.van": { - "*": { - "repo": "Visual-Attention-Network/van-base", - "pkg": { - "0": { - "transformers": "VanModel" - } - }, - "tasks": [ - "VanForImageClassification", - "VanModel", - "VanPreTrainedModel" - ] - } - }, - "info.vit.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2Model" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.vit.poolformer-s12": { - "*": { - "repo": "sail/poolformer_s12", - "pkg": { - "0": { - "transformers": "PoolFormerModel" - } - }, - "tasks": [ - "PoolFormerForImageClassification", - "PoolFormerModel", - "PoolFormerPreTrainedModel" - ] - } - }, - "info.stst.gptsan-japanese": { - "*": { - "repo": "Tanrei/GPTSAN-japanese", - "pkg": { - "0": { - "transformers": "GPTSanJapaneseForConditionalGeneration" - } - }, - "tasks": [ - "GPTSanJapaneseForConditionalGeneration", - "GPTSanJapaneseModel", - "GPTSanJapanesePreTrainedModel" - ] - } - }, - "info.art.ernie-4-a-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-21B-A3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5_MoeModel" - } - }, - "tasks": [ - "Ernie4_5_MoeForCausalLM", - "Ernie4_5_MoeModel", - "Ernie4_5_MoePreTrainedModel" - ] - } - }, - "info.vit.swiftformer-xs": { - "*": { - "repo": "MBZUAI/swiftformer-xs", - "pkg": { - "0": { - "transformers": "SwiftFormerModel" - } - }, - "tasks": [ - "SwiftFormerForImageClassification", - "SwiftFormerModel", - "SwiftFormerPreTrainedModel" - ] - } - }, - "info.aet.dpr-question-encoder-single-nq": { - "*": { - "repo": "facebook/dpr-question_encoder-single-nq-base", - "pkg": { - "0": { - "transformers": "DPRQuestionEncoder" - } - }, - "tasks": [ - "DPRContextEncoder", - "DPRPretrainedContextEncoder", - "DPRPreTrainedModel", - "DPRPretrainedQuestionEncoder", - "DPRPretrainedReader", - "DPRQuestionEncoder", - "DPRReader" - ] - } - }, - "info.stst.mbart-cc25": { - "*": { - "repo": "facebook/mbart-large-cc25", - "pkg": { - "0": { - "transformers": "MBartModel" - } - }, - "tasks": [ - "MBartForCausalLM", - "MBartForConditionalGeneration", - "MBartForQuestionAnswering", - "MBartForSequenceClassification", - "MBartModel", - "MBartPreTrainedModel" - ] - } - }, - "info.vit.idefics": { - "*": { - "repo": "HuggingFaceM4/idefics-9b", - "pkg": { - "0": { - "transformers": "IdeficsModel" - } - }, - "tasks": [ - "IdeficsForVisionText2Text", - "IdeficsModel", - "IdeficsPreTrainedModel" - ] - } - }, - "info.art.diffllama-handcut": { - "*": { - "repo": "kajuma/DiffLlama-0.3B-handcut", - "pkg": { - "0": { - "transformers": "DiffLlamaModel" - } - }, - "tasks": [ - "DiffLlamaPreTrainedModel", - "DiffLlamaModel", - "DiffLlamaForCausalLM", - "DiffLlamaForSequenceClassification", - "DiffLlamaForQuestionAnswering", - "DiffLlamaForTokenClassification" - ] - } - }, - "info.moe.doge": { - "*": { - "repo": "SmallDoge/Doge-320M", - "pkg": { - "0": { - "transformers": "DogeModel" - } - }, - "tasks": [ - "DogeForCausalLM", - "DogeModel", - "DogePreTrainedModel", - "DogeForSequenceClassification" - ] - } - }, - "info.vit.siglip-so-patch14-384": { - "*": { - "repo": "google/siglip-so400m-patch14-384", - "pkg": { - "0": { - "transformers": "SmolVLMVisionTransformer" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.moe.qwen3-a": { - "*": { - "repo": "Qwen/Qwen3-30B-A3B", - "pkg": { - "0": { - "transformers": "Qwen3MoeModel" - } - }, - "file_256": [ - "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" - ], - "layer_b3": [ - "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" - ], - "layer_256": [ - "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" - ], - "tasks": [ - "Qwen3MoeForCausalLM", - "Qwen3MoeForQuestionAnswering", - "Qwen3MoeModel", - "Qwen3MoePreTrainedModel", - "Qwen3MoeForSequenceClassification", - "Qwen3MoeForTokenClassification" - ] - } - }, - "info.vit.clip-vit-patch32": { - "*": { - "repo": "openai/clip-vit-base-patch32", - "pkg": { - "0": { - "transformers": "CLIPTextModel" - } - }, - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.data2vec-vision": { - "*": { - "repo": "facebook/data2vec-vision-base", - "pkg": { - "0": { - "transformers": "Data2VecVisionModel" - } - }, - "tasks": [ - "Data2VecVisionForImageClassification", - "Data2VecVisionForSemanticSegmentation", - "Data2VecVisionModel", - "Data2VecVisionPreTrainedModel" - ] - } - }, - "info.art.deberta-v2-x": { - "*": { - "repo": "microsoft/deberta-v2-xlarge", - "pkg": { - "0": { - "transformers": "DebertaV2Model" - } - }, - "tasks": [ - "DebertaV2ForMaskedLM", - "DebertaV2ForMultipleChoice", - "DebertaV2ForQuestionAnswering", - "DebertaV2ForSequenceClassification", - "DebertaV2ForTokenClassification", - "DebertaV2Model", - "DebertaV2PreTrainedModel" - ] - } - }, - "info.art.granite": { - "*": { - "repo": "ibm-granite/granite-3.3-2b-base", - "pkg": { - "0": { - "transformers": "GraniteModel" - } - }, - "tasks": [ - "GraniteForCausalLM", - "GraniteModel", - "GranitePreTrainedModel" - ] - } - }, - "info.art.aria": { - "*": { - "repo": "rhymes-ai/Aria", - "pkg": { - "0": { - "transformers": "AriaTextModel" - } - }, - "tasks": [ - "AriaForConditionalGeneration", - "AriaPreTrainedModel", - "AriaTextPreTrainedModel", - "AriaTextModel", - "AriaModel", - "AriaTextForCausalLM" - ] - } - }, - "info.vit.fuyu": { - "*": { - "repo": "adept/fuyu-8b", - "pkg": { - "0": { - "transformers": "FuyuModel" - } - }, - "tasks": [ - "FuyuForCausalLM", - "FuyuPreTrainedModel", - "FuyuModel" - ] - } - }, - "info.vit.donut": { - "*": { - "repo": "naver-clova-ix/donut-base", - "pkg": { - "0": { - "transformers": "DonutSwinModel" - } - }, - "tasks": [ - "DonutSwinModel", - "DonutSwinPreTrainedModel", - "DonutSwinForImageClassification" - ] - } - }, - "info.vit.internvl3-hf": { - "*": { - "repo": "OpenGVLab/InternVL3-1B-hf", - "pkg": { - "0": { - "transformers": "InternVLModel" - } - }, - "tasks": [ - "InternVLVisionPreTrainedModel", - "InternVLVisionModel", - "InternVLPreTrainedModel", - "InternVLModel", - "InternVLForConditionalGeneration" - ] - } - }, - "info.vit.bit-50": { - "*": { - "repo": "google/bit-50", - "pkg": { - "0": { - "transformers": "BitModel" - } - }, - "tasks": [ - "BitForImageClassification", - "BitModel", - "BitPreTrainedModel", - "BitBackbone" - ] - } - }, - "info.vit.convnext-224": { - "*": { - "repo": "facebook/convnext-tiny-224", - "pkg": { - "0": { - "transformers": "ConvNextModel" - } - }, - "tasks": [ - "ConvNextForImageClassification", - "ConvNextModel", - "ConvNextPreTrainedModel", - "ConvNextBackbone" - ] - } - }, - "info.art.fnet": { - "*": { - "repo": "google/fnet-base", - "pkg": { - "0": { - "transformers": "FNetModel" - } - }, - "tasks": [ - "FNetForMaskedLM", - "FNetForMultipleChoice", - "FNetForNextSentencePrediction", - "FNetForPreTraining", - "FNetForQuestionAnswering", - "FNetForSequenceClassification", - "FNetForTokenClassification", - "FNetLayer", - "FNetModel", - "FNetPreTrainedModel" - ] - } - }, - "info.vit.llava-onevision-qwen2-ov-hf": { - "*": { - "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", - "pkg": { - "0": { - "transformers": "LlavaOnevisionModel" - } - }, - "tasks": [ - "LlavaOnevisionModel", - "LlavaOnevisionForConditionalGeneration", - "LlavaOnevisionPreTrainedModel" - ] - } - }, - "info.stst.pegasus-x": { - "*": { - "repo": "google/pegasus-x-large", - "pkg": { - "0": { - "transformers": "PegasusXModel" - } - }, - "tasks": [ - "PegasusXForConditionalGeneration", - "PegasusXModel", - "PegasusXPreTrainedModel" - ] - } - }, - "info.vit.swin2sr-classicalsr-x2-64": { - "*": { - "repo": "caidas/swin2sr-classicalsr-x2-64", - "pkg": { - "0": { - "transformers": "Swin2SRModel" - } - }, - "tasks": [ - "Swin2SRForImageSuperResolution", - "Swin2SRModel", - "Swin2SRPreTrainedModel" - ] - } - }, - "info.stst.blenderbot": { - "*": { - "repo": "facebook/blenderbot-3B", - "pkg": { - "0": { - "transformers": "BlenderbotModel" - } - }, - "tasks": [ - "BlenderbotForCausalLM", - "BlenderbotForConditionalGeneration", - "BlenderbotModel", - "BlenderbotPreTrainedModel" - ] - } - }, - "info.vit.clipseg-rd64": { - "*": { - "repo": "CIDAS/clipseg-rd64", - "pkg": { - "0": { - "transformers": "CLIPSegModel" - } - }, - "tasks": [ - "CLIPSegModel", - "CLIPSegPreTrainedModel", - "CLIPSegTextModel", - "CLIPSegVisionModel", - "CLIPSegForImageSegmentation" - ] - } - }, - "info.moe.jetmoe": { - "*": { - "repo": "jetmoe/jetmoe-8b", - "pkg": { - "0": { - "transformers": "JetMoeModel" - } - }, - "tasks": [ - "JetMoeForCausalLM", - "JetMoeModel", - "JetMoePreTrainedModel", - "JetMoeForSequenceClassification" - ] - } - }, - "info.art.mobilebert-uncased": { - "*": { - "repo": "google/mobilebert-uncased", - "pkg": { - "0": { - "transformers": "MobileBertModel" - } - }, - "tasks": [ - "MobileBertForMaskedLM", - "MobileBertForMultipleChoice", - "MobileBertForNextSentencePrediction", - "MobileBertForPreTraining", - "MobileBertForQuestionAnswering", - "MobileBertForSequenceClassification", - "MobileBertForTokenClassification", - "MobileBertLayer", - "MobileBertModel", - "MobileBertPreTrainedModel" - ] - } - }, - "info.vit.groupvit-gcc-yfcc": { - "*": { - "repo": "nvidia/groupvit-gcc-yfcc", - "pkg": { - "0": { - "transformers": "GroupViTModel" - } - }, - "tasks": [ - "GroupViTModel", - "GroupViTPreTrainedModel", - "GroupViTTextModel", - "GroupViTVisionModel" - ] - } - }, - "info.aet.ibert-roberta": { - "*": { - "repo": "kssteven/ibert-roberta-base", - "pkg": { - "0": { - "transformers": "IBertModel" - } - }, - "tasks": [ - "IBertForMaskedLM", - "IBertForMultipleChoice", - "IBertForQuestionAnswering", - "IBertForSequenceClassification", - "IBertForTokenClassification", - "IBertModel", - "IBertPreTrainedModel" - ] - } - }, - "info.stst.pop2piano": { - "*": { - "repo": "sweetcocoa/pop2piano", - "pkg": { - "0": { - "transformers": "Pop2PianoForConditionalGeneration" - } - }, - "tasks": [ - "Pop2PianoForConditionalGeneration", - "Pop2PianoPreTrainedModel" - ] - } - }, - "info.moe.deepseek-v3": { - "*": { - "repo": "bzantium/tiny-deepseek-v3", - "pkg": { - "0": { - "transformers": "DeepseekV3Model" - } - }, - "tasks": [ - "DeepseekV3PreTrainedModel", - "DeepseekV3Model", - "DeepseekV3ForCausalLM" - ] - } - }, - "info.art.nystromformer-512": { - "*": { - "repo": "uw-madison/nystromformer-512", - "pkg": { - "0": { - "transformers": "NystromformerModel" - } - }, - "tasks": [ - "NystromformerForMaskedLM", - "NystromformerForMultipleChoice", - "NystromformerForQuestionAnswering", - "NystromformerForSequenceClassification", - "NystromformerForTokenClassification", - "NystromformerLayer", - "NystromformerModel", - "NystromformerPreTrainedModel" - ] - } - }, - "info.vit.sam-hq-vit-huge": { - "*": { - "repo": "syscv-community/sam-hq-vit-huge", - "pkg": { - "0": { - "transformers": "SamHQVisionModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.aet.qwen2-audio": { - "*": { - "repo": "Qwen/Qwen2-Audio-7B", - "pkg": { - "0": { - "transformers": "Qwen2AudioEncoder" - } - }, - "tasks": [ - "Qwen2AudioForConditionalGeneration", - "Qwen2AudioPreTrainedModel", - "Qwen2AudioEncoder" - ] - } - }, - "info.aet.ernie-m--pytorch": { - "*": { - "repo": "susnato/ernie-m-base_pytorch", - "pkg": { - "0": { - "transformers": "ErnieMModel" - } - }, - "tasks": [ - "ErnieMForMultipleChoice", - "ErnieMForQuestionAnswering", - "ErnieMForSequenceClassification", - "ErnieMForTokenClassification", - "ErnieMModel", - "ErnieMPreTrainedModel", - "ErnieMForInformationExtraction" - ] - } - }, - "info.art.imagegpt": { - "*": { - "repo": "openai/imagegpt-small", - "pkg": { - "0": { - "transformers": "ImageGPTModel" - } - }, - "tasks": [ - "ImageGPTForCausalImageModeling", - "ImageGPTForImageClassification", - "ImageGPTModel", - "ImageGPTPreTrainedModel" - ] - } - }, - "info.vit.got-ocr-2-hf": { - "*": { - "repo": "stepfun-ai/GOT-OCR-2.0-hf", - "pkg": { - "0": { - "transformers": "GotOcr2Model" - } - }, - "tasks": [ - "GotOcr2PreTrainedModel", - "GotOcr2Model", - "GotOcr2ForConditionalGeneration" - ] - } - }, - "info.art.gpt-j": { - "*": { - "repo": "EleutherAI/gpt-j-6B", - "pkg": { - "0": { - "transformers": "GPTJModel" - } - }, - "tasks": [ - "GPTJForCausalLM", - "GPTJForQuestionAnswering", - "GPTJForSequenceClassification", - "GPTJModel", - "GPTJPreTrainedModel" - ] - } - }, - "info.art.stablelm-4e1t": { - "*": { - "repo": "stabilityai/stablelm-3b-4e1t", - "pkg": { - "0": { - "transformers": "StableLmModel" - } - }, - "tasks": [ - "StableLmForCausalLM", - "StableLmModel", - "StableLmPreTrainedModel", - "StableLmForSequenceClassification", - "StableLmForTokenClassification" - ] - } - }, - "info.aet.hubert-ls960": { - "*": { - "repo": "facebook/hubert-base-ls960", - "pkg": { - "0": { - "transformers": "HubertModel" - } - }, - "tasks": [ - "HubertForCTC", - "HubertForSequenceClassification", - "HubertModel", - "HubertPreTrainedModel" - ] - } - }, - "info.art.mpt": { - "*": { - "repo": "mosaicml/mpt-7b", - "pkg": { - "0": { - "transformers": "MptModel" - } - }, - "tasks": [ - "MptForCausalLM", - "MptModel", - "MptPreTrainedModel", - "MptForSequenceClassification", - "MptForTokenClassification", - "MptForQuestionAnswering" - ] - } - }, - "info.lstm.xlstm": { - "*": { - "repo": "NX-AI/xLSTM-7b", - "pkg": { - "0": { - "transformers": "xLSTMModel" - } - }, - "tasks": [ - "xLSTMForCausalLM", - "xLSTMModel", - "xLSTMPreTrainedModel" - ] - } - }, - "info.art.xglm": { - "*": { - "repo": "facebook/xglm-564M", - "pkg": { - "0": { - "transformers": "XGLMModel" - } - }, - "tasks": [ - "XGLMForCausalLM", - "XGLMModel", - "XGLMPreTrainedModel" - ] - } - }, - "info.art.afm": { - "*": { - "repo": "arcee-ai/AFM-4.5B", - "pkg": { - "0": { - "transformers": "ArceeModel" - } - }, - "tasks": [ - "ArceeForCausalLM", - "ArceeForQuestionAnswering", - "ArceeForSequenceClassification", - "ArceeForTokenClassification", - "ArceeModel", - "ArceePreTrainedModel" - ] - } - }, - "info.vit.clap-htsat-fused": { - "*": { - "repo": "laion/clap-htsat-fused", - "pkg": { - "0": { - "transformers": "ClapModel" - } - }, - "file_256": [ - "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", - "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" - ], - "layer_b3": [ - "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", - "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" - ], - "layer_256": [ - "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", - "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" - ], - "tasks": [ - "ClapModel", - "ClapPreTrainedModel", - "ClapTextModel", - "ClapTextModelWithProjection", - "ClapAudioModel", - "ClapAudioModelWithProjection" - ] - } - }, - "info.ssm.zamba2": { - "*": { - "repo": "Zyphra/Zamba2-2.7B", - "pkg": { - "0": { - "transformers": "Zamba2Model" - } - }, - "tasks": [ - "Zamba2ForCausalLM", - "Zamba2ForSequenceClassification", - "Zamba2Model", - "Zamba2PreTrainedModel" - ] - } - }, - "info.vit.perception-lm": { - "*": { - "repo": "facebook/Perception-LM-1B", - "pkg": { - "0": { - "transformers": "PerceptionLMModel" - } - }, - "tasks": [ - "PerceptionLMForConditionalGeneration", - "PerceptionLMPreTrainedModel", - "PerceptionLMModel" - ] - } - }, - "info.art.xlnet-cased": { - "*": { - "repo": "xlnet/xlnet-large-cased", - "pkg": { - "0": { - "transformers": "XLNetModel" - } - }, - "tasks": [ - "XLNetForMultipleChoice", - "XLNetForQuestionAnswering", - "XLNetForQuestionAnsweringSimple", - "XLNetForSequenceClassification", - "XLNetForTokenClassification", - "XLNetLMHeadModel", - "XLNetModel", - "XLNetPreTrainedModel" - ] - } - }, - "info.stst.nllb-moe": { - "*": { - "repo": "facebook/nllb-moe-54b", - "pkg": { - "0": { - "transformers": "NllbMoeModel" - } - }, - "tasks": [ - "NllbMoeForConditionalGeneration", - "NllbMoeModel", - "NllbMoePreTrainedModel", - "NllbMoeTop2Router", - "NllbMoeSparseMLP" - ] - } - }, - "info.art.jukebox-lyrics": { - "*": { - "repo": "openai/jukebox-1b-lyrics", - "pkg": { - "0": { - "transformers": "JukeboxModel" - } - }, - "tasks": [ - "JukeboxModel", - "JukeboxPreTrainedModel", - "JukeboxVQVAE", - "JukeboxPrior" - ] - } - }, - "info.art.mistral-v0": { - "*": { - "repo": "mistralai/Mistral-7B-v0.1", - "pkg": { - "0": { - "transformers": "MistralModel" - } - }, - "tasks": [ - "MistralForCausalLM", - "MistralForQuestionAnswering", - "MistralModel", - "MistralPreTrainedModel", - "MistralForSequenceClassification", - "MistralForTokenClassification" - ] - } - }, - "info.vit.colpali-v1": { - "*": { - "repo": "vidore/colpali-v1.2", - "pkg": { - "0": { - "transformers": "ColPaliForRetrieval" - } - }, - "tasks": [ - "ColPaliForRetrieval", - "ColPaliPreTrainedModel" - ] - } - }, - "info.aet.xlm-roberta-xl": { - "*": { - "repo": "facebook/xlm-roberta-xl", - "pkg": { - "0": { - "transformers": "XLMRobertaXLModel" - } - }, - "tasks": [ - "XLMRobertaXLForCausalLM", - "XLMRobertaXLForMaskedLM", - "XLMRobertaXLForMultipleChoice", - "XLMRobertaXLForQuestionAnswering", - "XLMRobertaXLForSequenceClassification", - "XLMRobertaXLForTokenClassification", - "XLMRobertaXLModel", - "XLMRobertaXLPreTrainedModel" - ] - } - }, - "info.stst.t5": { - "*": { - "repo": "google-t5/t5-small", - "pkg": { - "0": { - "transformers": "T5Model" - } - }, - "identifiers": [ - [ - 4096 - ], - "encoder.embed_tokens.weight", - "text_encoders.t5xxl.transformer.shared.weight", - "t5xxl", - "encoder.block.0.layer.1.DenseReluDense.wi.weight" - ], - "file_256": [ - "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", - "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", - "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", - "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", - "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", - "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", - "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", - "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", - "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", - "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", - "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", - "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", - "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", - "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", - "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", - "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", - "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", - "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", - "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", - "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", - "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", - "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", - "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", - "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", - "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", - "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", - "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" - ], - "layer_b3": [ - "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", - "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", - "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", - "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", - "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", - "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", - "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", - "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", - "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", - "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", - "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", - "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", - "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", - "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", - "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", - "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", - "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", - "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", - "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", - "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", - "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", - "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", - "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", - "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", - "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", - "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", - "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", - "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", - "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", - "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" - ], - "layer_256": [ - "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", - "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", - "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", - "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", - "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", - "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", - "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", - "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", - "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", - "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", - "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", - "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", - "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", - "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", - "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", - "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", - "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", - "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", - "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", - "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", - "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", - "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", - "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", - "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", - "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", - "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", - "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", - "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" - ], - "tasks": [ - "T5EncoderModel", - "T5ForConditionalGeneration", - "T5Model", - "T5PreTrainedModel", - "T5ForQuestionAnswering", - "T5ForSequenceClassification", - "T5ForTokenClassification" - ] - } - }, - "info.vit.mgp-str": { - "*": { - "repo": "alibaba-damo/mgp-str-base", - "pkg": { - "0": { - "transformers": "MgpstrForSceneTextRecognition" - } - }, - "tasks": [ - "MgpstrModel", - "MgpstrPreTrainedModel", - "MgpstrForSceneTextRecognition" - ] - } - }, - "info.art.visualbert-vqa-coco-pre": { - "*": { - "repo": "uclanlp/visualbert-vqa-coco-pre", - "pkg": { - "0": { - "transformers": "VisualBertModel" - } - }, - "tasks": [ - "VisualBertForMultipleChoice", - "VisualBertForPreTraining", - "VisualBertForQuestionAnswering", - "VisualBertForRegionToPhraseAlignment", - "VisualBertForVisualReasoning", - "VisualBertLayer", - "VisualBertModel", - "VisualBertPreTrainedModel" - ] - } - }, - "info.moe.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4TextModel" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.stst.opus-mt-en-de": { - "*": { - "repo": "Helsinki-NLP/opus-mt-en-de", - "pkg": { - "0": { - "transformers": "MarianModel" - } - }, - "tasks": [ - "MarianForCausalLM", - "MarianModel", - "MarianMTModel", - "MarianPreTrainedModel" - ] - } - }, - "info.art.glm-4-0414": { - "*": { - "repo": "zai-org/GLM-4-9B-0414", - "pkg": { - "0": { - "transformers": "Glm4Model" - } - }, - "tasks": [ - "Glm4PreTrainedModel", - "Glm4Model", - "Glm4ForCausalLM", - "Glm4ForSequenceClassification", - "Glm4ForTokenClassification" - ] - } - }, - "info.art.mega-wikitext": { - "*": { - "repo": "mnaylor/mega-base-wikitext", - "pkg": { - "0": { - "transformers": "MegaModel" - } - }, - "tasks": [ - "MegaForCausalLM", - "MegaForMaskedLM", - "MegaForMultipleChoice", - "MegaForQuestionAnswering", - "MegaForSequenceClassification", - "MegaForTokenClassification", - "MegaModel", - "MegaPreTrainedModel" - ] - } - }, - "info.vit.janus": { - "*": { - "repo": "deepseek-community/Janus-Pro-1B", - "pkg": { - "0": { - "transformers": "JanusModel" - } - }, - "tasks": [ - "JanusPreTrainedModel", - "JanusForConditionalGeneration", - "JanusModel", - "JanusVQVAE", - "JanusVisionModel" - ] - } - }, - "info.art.roformer-chinese": { - "*": { - "repo": "junnyu/roformer_chinese_base", - "pkg": { - "0": { - "transformers": "RoFormerModel" - } - }, - "tasks": [ - "RoFormerForCausalLM", - "RoFormerForMaskedLM", - "RoFormerForMultipleChoice", - "RoFormerForQuestionAnswering", - "RoFormerForSequenceClassification", - "RoFormerForTokenClassification", - "RoFormerLayer", - "RoFormerModel", - "RoFormerPreTrainedModel" - ] - } - }, - "info.moe.qwen15-moe-a": { - "*": { - "repo": "Qwen/Qwen1.5-MoE-A2.7B", - "pkg": { - "0": { - "transformers": "Qwen2MoeModel" - } - }, - "tasks": [ - "Qwen2MoeForCausalLM", - "Qwen2MoeForQuestionAnswering", - "Qwen2MoeModel", - "Qwen2MoePreTrainedModel", - "Qwen2MoeForSequenceClassification", - "Qwen2MoeForTokenClassification" - ] - } - }, - "info.vit.gemma-3": { - "*": { - "repo": "google/gemma-3-4b-it", - "pkg": { - "0": { - "transformers": "ShieldGemma2ForImageClassification" - } - }, - "tasks": [ - "ShieldGemma2ForImageClassification" - ] - } - }, - "info.art.qwen3": { - "*": { - "repo": "Qwen/Qwen3-8B", - "pkg": { - "0": { - "transformers": "Qwen3Model" - } - }, - "tasks": [ - "Qwen3ForCausalLM", - "Qwen3ForQuestionAnswering", - "Qwen3PreTrainedModel", - "Qwen3Model", - "Qwen3ForSequenceClassification", - "Qwen3ForTokenClassification" - ] - } - }, - "info.stst.qwen2-audio": { - "*": { - "repo": "Qwen/Qwen2-Audio-7B", - "pkg": { - "0": { - "transformers": "Qwen2AudioForConditionalGeneration" - } - }, - "tasks": [ - "Qwen2AudioForConditionalGeneration", - "Qwen2AudioPreTrainedModel", - "Qwen2AudioEncoder" - ] - } - }, - "info.vit.siglip2-patch16-224": { - "*": { - "repo": "google/siglip2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Siglip2Model" - } - }, - "tasks": [ - "Siglip2Model", - "Siglip2PreTrainedModel", - "Siglip2TextModel", - "Siglip2VisionModel", - "Siglip2ForImageClassification" - ] - } - }, - "info.vit.mlcd-vit-bigg-patch14-336": { - "*": { - "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", - "pkg": { - "0": { - "transformers": "MLCDVisionModel" - } - }, - "tasks": [ - "MLCDPreTrainedModel", - "MLCDVisionModel" - ] - } - }, - "info.aet.mra-512-4": { - "*": { - "repo": "uw-madison/mra-base-512-4", - "pkg": { - "0": { - "transformers": "MraModel" - } - }, - "tasks": [ - "MraForMaskedLM", - "MraForMultipleChoice", - "MraForQuestionAnswering", - "MraForSequenceClassification", - "MraForTokenClassification", - "MraLayer", - "MraModel", - "MraPreTrainedModel" - ] - } - }, - "info.ssm.powermoe": { - "*": { - "repo": "ibm-research/PowerMoE-3b", - "pkg": { - "0": { - "transformers": "GraniteMoeHybridModel" - } - }, - "tasks": [ - "GraniteMoeHybridForCausalLM", - "GraniteMoeHybridModel", - "GraniteMoeHybridPreTrainedModel" - ] - } - }, - "info.vit.swinv2-patch4-window8-256": { - "*": { - "repo": "microsoft/swinv2-tiny-patch4-window8-256", - "pkg": { - "0": { - "transformers": "Swinv2Model" - } - }, - "tasks": [ - "Swinv2ForImageClassification", - "Swinv2ForMaskedImageModeling", - "Swinv2Model", - "Swinv2PreTrainedModel", - "Swinv2Backbone" - ] - } - }, - "info.art.tapas-finetuned-sqa": { - "*": { - "repo": "google/tapas-base-finetuned-sqa", - "pkg": { - "0": { - "transformers": "TapasModel" - } - }, - "tasks": [ - "TapasForMaskedLM", - "TapasForQuestionAnswering", - "TapasForSequenceClassification", - "TapasModel", - "TapasPreTrainedModel" - ] - } - }, - "info.vit.vitdet-patch16-224": { - "*": { - "repo": "google/vitdet-base-patch16-224", - "pkg": { - "0": { - "transformers": "VitDetModel" - } - }, - "tasks": [ - "VitDetModel", - "VitDetPreTrainedModel", - "VitDetBackbone" - ] - } - }, - "info.art.gpt-neox": { - "*": { - "repo": "EleutherAI/gpt-neox-20b", - "pkg": { - "0": { - "transformers": "GPTNeoXModel" - } - }, - "tasks": [ - "GPTNeoXForCausalLM", - "GPTNeoXForQuestionAnswering", - "GPTNeoXForSequenceClassification", - "GPTNeoXForTokenClassification", - "GPTNeoXLayer", - "GPTNeoXModel", - "GPTNeoXPreTrainedModel" - ] - } - }, - "info.ssm.zamba-v1": { - "*": { - "repo": "Zyphra/Zamba-7B-v1", - "pkg": { - "0": { - "transformers": "ZambaModel" - } - }, - "tasks": [ - "ZambaForCausalLM", - "ZambaForSequenceClassification", - "ZambaModel", - "ZambaPreTrainedModel" - ] - } - }, - "info.aet.markuplm": { - "*": { - "repo": "microsoft/markuplm-base", - "pkg": { - "0": { - "transformers": "MarkupLMModel" - } - }, - "tasks": [ - "MarkupLMForQuestionAnswering", - "MarkupLMForSequenceClassification", - "MarkupLMForTokenClassification", - "MarkupLMModel", - "MarkupLMPreTrainedModel" - ] - } - }, - "info.art.bark": { - "*": { - "repo": "suno/bark", - "pkg": { - "0": { - "transformers": "BarkModel" - } - }, - "tasks": [ - "BarkFineModel", - "BarkSemanticModel", - "BarkCoarseModel", - "BarkModel", - "BarkPreTrainedModel", - "BarkCausalModel" - ] - } - }, - "info.aet.roberta": { - "*": { - "repo": "FacebookAI/roberta-base", - "pkg": { - "0": { - "transformers": "RobertaModel" - } - }, - "tasks": [ - "RobertaForCausalLM", - "RobertaForMaskedLM", - "RobertaForMultipleChoice", - "RobertaForQuestionAnswering", - "RobertaForSequenceClassification", - "RobertaForTokenClassification", - "RobertaModel", - "RobertaPreTrainedModel" - ] - } - }, - "info.aet.sew-d": { - "*": { - "repo": "asapp/sew-d-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWDModel" - } - }, - "tasks": [ - "SEWDForCTC", - "SEWDForSequenceClassification", - "SEWDModel", - "SEWDPreTrainedModel" - ] - } - }, - "info.vit.dinov2-patch16-224": { - "*": { - "repo": "google/dinov2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Dinov2Model" - } - }, - "tasks": [ - "Dinov2ForImageClassification", - "Dinov2Model", - "Dinov2PreTrainedModel", - "Dinov2Backbone" - ] - } - }, - "info.aet.electra-discriminator": { - "*": { - "repo": "google/electra-small-discriminator", - "pkg": { - "0": { - "transformers": "ElectraModel" - } - }, - "tasks": [ - "ElectraForCausalLM", - "ElectraForMaskedLM", - "ElectraForMultipleChoice", - "ElectraForPreTraining", - "ElectraForQuestionAnswering", - "ElectraForSequenceClassification", - "ElectraForTokenClassification", - "ElectraModel", - "ElectraPreTrainedModel" - ] - } - }, - "info.vit.language-perceiver": { - "*": { - "repo": "deepmind/language-perceiver", - "pkg": { - "0": { - "transformers": "PerceiverModel" - } - }, - "tasks": [ - "PerceiverForImageClassificationConvProcessing", - "PerceiverForImageClassificationFourier", - "PerceiverForImageClassificationLearned", - "PerceiverForMaskedLM", - "PerceiverForMultimodalAutoencoding", - "PerceiverForOpticalFlow", - "PerceiverForSequenceClassification", - "PerceiverLayer", - "PerceiverModel", - "PerceiverPreTrainedModel" - ] - } - }, - "info.vit.glpn-kitti": { - "*": { - "repo": "vinvino02/glpn-kitti", - "pkg": { - "0": { - "transformers": "GLPNModel" - } - }, - "tasks": [ - "GLPNForDepthEstimation", - "GLPNLayer", - "GLPNModel", - "GLPNPreTrainedModel" - ] - } - }, - "info.vit.segformer-b0-finetuned-ade-512-512": { - "*": { - "repo": "nvidia/segformer-b0-finetuned-ade-512-512", - "pkg": { - "0": { - "transformers": "SegformerModel" - } - }, - "tasks": [ - "SegformerDecodeHead", - "SegformerForImageClassification", - "SegformerForSemanticSegmentation", - "SegformerLayer", - "SegformerModel", - "SegformerPreTrainedModel" - ] - } - }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { - "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", - "pkg": { - "0": { - "transformers": "MMGroundingDinoModel" - } - }, - "tasks": [ - "MMGroundingDinoForObjectDetection", - "MMGroundingDinoModel", - "MMGroundingDinoPreTrainedModel" - ] - } - }, - "info.vit.llava-next-video-hf": { - "*": { - "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", - "pkg": { - "0": { - "transformers": "LlavaNextVideoModel" - } - }, - "tasks": [ - "LlavaNextVideoForConditionalGeneration", - "LlavaNextVideoModel", - "LlavaNextVideoPreTrainedModel" - ] - } - }, - "info.gan.encodec": { - "*": { - "repo": "facebook/encodec_24khz", - "pkg": { - "0": { - "transformers": "EncodecModel" - } - }, - "tasks": [ - "EncodecModel", - "EncodecPreTrainedModel" - ] - } - }, - "info.aet.camembert": { - "*": { - "repo": "almanach/camembert-base", - "pkg": { - "0": { - "transformers": "CamembertModel" - } - }, - "tasks": [ - "CamembertForCausalLM", - "CamembertForMaskedLM", - "CamembertForMultipleChoice", - "CamembertForQuestionAnswering", - "CamembertForSequenceClassification", - "CamembertForTokenClassification", - "CamembertModel", - "CamembertPreTrainedModel" - ] - } - }, - "info.art.exaone-4": { - "*": { - "repo": "LGAI-EXAONE/EXAONE-4.0-32B", - "pkg": { - "0": { - "transformers": "Exaone4Model" - } - }, - "tasks": [ - "Exaone4PreTrainedModel", - "Exaone4Model", - "Exaone4ForCausalLM", - "Exaone4ForSequenceClassification", - "Exaone4ForTokenClassification", - "Exaone4ForQuestionAnswering" - ] - } - }, - "info.art.bloom": { - "*": { - "repo": "bigscience/bloom", - "pkg": { - "0": { - "transformers": "BloomModel" - } - }, - "tasks": [ - "BloomForCausalLM", - "BloomModel", - "BloomPreTrainedModel", - "BloomForSequenceClassification", - "BloomForTokenClassification", - "BloomForQuestionAnswering" - ] - } - }, - "info.ssm.bamba-t-hf": { - "*": { - "repo": "ibm-fms/Bamba-9.8b-2.2T-hf", - "pkg": { - "0": { - "transformers": "BambaModel" - } - }, - "tasks": [ - "BambaModel", - "BambaForCausalLM", - "BambaPreTrainedModel" - ] - } - }, - "info.vit.seggpt-vit": { - "*": { - "repo": "BAAI/seggpt-vit-large", - "pkg": { - "0": { - "transformers": "SegGptModel" - } - }, - "tasks": [ - "SegGptModel", - "SegGptPreTrainedModel", - "SegGptForImageSegmentation" - ] - } - }, - "info.art.bros-uncased": { - "*": { - "repo": "jinho8345/bros-base-uncased", - "pkg": { - "0": { - "transformers": "BrosModel" - } - }, - "tasks": [ - "BrosPreTrainedModel", - "BrosModel", - "BrosForTokenClassification", - "BrosSpadeEEForTokenClassification", - "BrosSpadeELForTokenClassification" - ] - } - }, - "info.vit.mistral-3-2503": { - "*": { - "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", - "pkg": { - "0": { - "transformers": "Mistral3Model" - } - }, - "tasks": [ - "Mistral3Model", - "Mistral3PreTrainedModel", - "Mistral3ForConditionalGeneration" - ] - } - }, - "info.vit.phi-4": { - "*": { - "repo": "microsoft/Phi-4-multimodal-instruct", - "pkg": { - "0": { - "transformers": "Phi4MultimodalModel" - } - }, - "file_256": [ - "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" - ], - "layer_b3": [ - "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" - ], - "layer_256": [ - "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" - ], - "tasks": [ - "Phi4MultimodalAudioPreTrainedModel", - "Phi4MultimodalAudioModel", - "Phi4MultimodalVisionPreTrainedModel", - "Phi4MultimodalVisionModel", - "Phi4MultimodalPreTrainedModel", - "Phi4MultimodalModel", - "Phi4MultimodalForCausalLM" - ] - } - }, - "info.aet.megatron-bert-uncased": { - "*": { - "repo": "nvidia/megatron-bert-uncased-345m", - "pkg": { - "0": { - "transformers": "MegatronBertModel" - } - }, - "tasks": [ - "MegatronBertForCausalLM", - "MegatronBertForMaskedLM", - "MegatronBertForMultipleChoice", - "MegatronBertForNextSentencePrediction", - "MegatronBertForPreTraining", - "MegatronBertForQuestionAnswering", - "MegatronBertForSequenceClassification", - "MegatronBertForTokenClassification", - "MegatronBertModel", - "MegatronBertPreTrainedModel" - ] - } - }, - "info.gan.levit-128s": { - "*": { - "repo": "facebook/levit-128S", - "pkg": { - "0": { - "transformers": "LevitModel" - } - }, - "tasks": [ - "LevitForImageClassification", - "LevitForImageClassificationWithTeacher", - "LevitModel", - "LevitPreTrainedModel" - ] - } - }, - "info.art.gpt-neo": { - "*": { - "repo": "EleutherAI/gpt-neo-1.3B", - "pkg": { - "0": { - "transformers": "GPTNeoModel" - } - }, - "tasks": [ - "GPTNeoForCausalLM", - "GPTNeoForQuestionAnswering", - "GPTNeoForSequenceClassification", - "GPTNeoForTokenClassification", - "GPTNeoModel", - "GPTNeoPreTrainedModel" - ] - } - }, - "info.aet.bert-for-seq-generation-l-24-bbc-encoder": { - "*": { - "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", - "pkg": { - "0": { - "transformers": "BertGenerationEncoder" - } - }, - "tasks": [ - "BertGenerationDecoder", - "BertGenerationEncoder", - "BertGenerationPreTrainedModel" - ] - } - }, - "info.aet.modernbert": { - "*": { - "repo": "answerdotai/ModernBERT-base", - "pkg": { - "0": { - "transformers": "ModernBertModel" - } - }, - "tasks": [ - "ModernBertModel", - "ModernBertPreTrainedModel", - "ModernBertForMaskedLM", - "ModernBertForSequenceClassification", - "ModernBertForTokenClassification", - "ModernBertForQuestionAnswering", - "ModernBertForMultipleChoice" - ] - } - }, - "info.moe.max-text-01-hf": { - "*": { - "repo": "MiniMaxAI/MiniMax-Text-01-hf", - "pkg": { - "0": { - "transformers": "MiniMaxModel" - } - }, - "tasks": [ - "MiniMaxPreTrainedModel", - "MiniMaxModel", - "MiniMaxForCausalLM", - "MiniMaxForSequenceClassification", - "MiniMaxForTokenClassification", - "MiniMaxForQuestionAnswering" - ] - } - }, - "info.vit.bridgetower": { - "*": { - "repo": "BridgeTower/bridgetower-base", - "pkg": { - "0": { - "transformers": "BridgeTowerModel" - } - }, - "tasks": [ - "BridgeTowerForContrastiveLearning", - "BridgeTowerForImageAndTextRetrieval", - "BridgeTowerForMaskedLM", - "BridgeTowerModel", - "BridgeTowerPreTrainedModel" - ] - } - }, - "info.vit.deit-distilled-patch16-224": { - "*": { - "repo": "facebook/deit-base-distilled-patch16-224", - "pkg": { - "0": { - "transformers": "DeiTModel" - } - }, - "tasks": [ - "DeiTForImageClassification", - "DeiTForImageClassificationWithTeacher", - "DeiTForMaskedImageModeling", - "DeiTModel", - "DeiTPreTrainedModel" - ] - } - }, - "info.art.phi-3": { - "*": { - "repo": "microsoft/Phi-3-mini-4k-instruct", - "pkg": { - "0": { - "transformers": "Phi3Model" - } - }, - "tasks": [ - "Phi3PreTrainedModel", - "Phi3Model", - "Phi3ForCausalLM", - "Phi3ForSequenceClassification", - "Phi3ForTokenClassification" - ] - } - }, - "info.vit.colqwen2-v1-hf": { - "*": { - "repo": "vidore/colqwen2-v1.0-hf", - "pkg": { - "0": { - "transformers": "ColQwen2ForRetrieval" - } - }, - "tasks": [ - "ColQwen2ForRetrieval", - "ColQwen2PreTrainedModel" - ] - } - }, - "info.aet.xlm-roberta": { - "*": { - "repo": "FacebookAI/xlm-roberta-base", - "pkg": { - "0": { - "transformers": "XLMRobertaModel" - } - }, - "tasks": [ - "XLMRobertaForCausalLM", - "XLMRobertaForMaskedLM", - "XLMRobertaForMultipleChoice", - "XLMRobertaForQuestionAnswering", - "XLMRobertaForSequenceClassification", - "XLMRobertaForTokenClassification", - "XLMRobertaModel", - "XLMRobertaPreTrainedModel" - ] - } - }, - "ops.precision.uint": { - "U8": { - "pkg": { - "0": { - "torch": { - "uint8": { - "variant": "uint8" - } - } - } - } - }, - "U16": { - "pkg": { - "0": { - "torch": { - "uint16": { - "variant": "uint16" - } - } - } - } - }, - "U32": { - "pkg": { - "0": { - "torch": { - "uint32": { - "variant": "uint32" - } - } - } - } - }, - "U64": { - "pkg": { - "0": { - "torch": { - "uint64": { - "variant": "uint64" - } - } - } - } - }, - "U1": { - "pkg": { - "0": { - "torch": { - "uint1": { - "variant": "uint1" - } - } - } - } - }, - "U2": { - "pkg": { - "0": { - "torch": { - "uint2": { - "variant": "uint2" - } - } - } - } - }, - "U3": { - "pkg": { - "0": { - "torch": { - "uint3": { - "variant": "uint3" - } - } - } - } - }, - "U4": { - "pkg": { - "0": { - "torch": { - "uint4": { - "variant": "uint4" - } - } - } - } - }, - "U5": { - "pkg": { - "0": { - "torch": { - "uint5": { - "variant": "uint5" - } - } - } - } - }, - "U6": { - "pkg": { - "0": { - "torch": { - "uint6": { - "variant": "uint6" - } - } - } - } - }, - "U7": { - "pkg": { - "0": { - "torch": { - "uint7": { - "variant": "uint7" - } - } - } - } - } - }, - "ops.precision.int": { - "I8": { - "pkg": { - "0": { - "torch": { - "int8": { - "variant": "int8" - } - } - } - } - }, - "I16": { - "pkg": { - "0": { - "torch": { - "int16": { - "variant": "int16" - } - } - } - } - }, - "I32": { - "pkg": { - "0": { - "torch": { - "int32": { - "variant": "int32" - } - } - } - } - }, - "I64": { - "pkg": { - "0": { - "torch": { - "int64": { - "variant": "int64" - } - } - } - } - }, - "Q8": { - "pkg": { - "0": { - "torch": { - "qint8": { - "variant": "qint8" - } - } - } - } - }, - "Q32": { - "pkg": { - "0": { - "torch": { - "qint32": { - "variant": "qint32" - } - } - } - } - }, - "I1": { - "pkg": { - "0": { - "torch": { - "int1": { - "variant": "int1" - } - } - } - } - }, - "I2": { - "pkg": { - "0": { - "torch": { - "int2": { - "variant": "int2" - } - } - } - } - }, - "I3": { - "pkg": { - "0": { - "torch": { - "int3": { - "variant": "int3" - } - } - } - } - }, - "I4": { - "pkg": { - "0": { - "torch": { - "int4": { - "variant": "int4" - } - } - } - } - }, - "I5": { - "pkg": { - "0": { - "torch": { - "int5": { - "variant": "int5" - } - } - } - } - }, - "I6": { - "pkg": { - "0": { - "torch": { - "int6": { - "variant": "int6" - } - } - } - } - }, - "I7": { - "pkg": { - "0": { - "torch": { - "int7": { - "variant": "int7" - } - } - } - } - } - }, - "ops.precision.float": { - "F16": { - "pkg": { - "0": { - "torch": { - "float16": { - "variant": "fp16" - } - } - } - } - }, - "F32": { - "pkg": { - "0": { - "torch": { - "float32": { - "variant": "fp32" - } - } - } - } - }, - "F64": { - "pkg": { - "0": { - "torch": { - "float64": { - "variant": "fp64" - } - } - } - } - }, - "F8_E5M2": { - "pkg": { - "0": { - "torch": { - "float8_e5m2": { - "variant": "fp8_e5m2" - } - } - } - } - }, - "F8_E4M3": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fn": { - "variant": "fp8_e4m3fn" - } - } - } - } - }, - "F8_E5M2FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e5m2fnuz": { - "variant": "fp8_e5m2fnuz" - } - } - } - } - }, - "F8_E4M3FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fnuz": { - "variant": "fp8_e4m3fnuz" - } - } - } - } - }, - "F8_E8M0FNU": { - "pkg": { - "0": { - "torch": { - "float8_e8m0fnu": { - "variant": "fp8_e8m0fnu" - } - } - } - } - }, - "F8_E2M1": { - "pkg": { - "0": { - "torch": { - "float4_e2m1fn_x2": { - "variant": "fp4_e2m1fn_x2" - } - } - } - } - } - }, - "ops.precision.complex": { - "C32": { - "pkg": { - "0": { - "torch": { - "complex32": { - "variant": "complex32" - } - } - } - } - }, - "C64": { - "pkg": { - "0": { - "torch": { - "complex64": { - "variant": "complex64" - } - } - } - } - }, - "C128": { - "pkg": { - "0": { - "torch": { - "complex128": { - "variant": "complex128" - } - } - } - } - } - }, - "ops.precision.bool": { - "Bbool": { - "pkg": { - "0": { - "torch": { - "bool": { - "variant": "bool" - } - } - } - } - } - }, - "ops.precision.quint": { - "Q8": { - "pkg": { - "0": { - "torch": { - "quint8": { - "variant": "quint8" - } - } - } - } - }, - "Q4x2": { - "pkg": { - "0": { - "torch": { - "quint4x2": { - "variant": "quint4x2" - } - } - } - } - }, - "Q2x4": { - "pkg": { - "0": { - "torch": { - "quint2x4": { - "variant": "quint2x4" - } - } - } - } - } - }, - "ops.precision.bfloat": { - "B16": { - "pkg": { - "0": { - "torch": { - "bfloat16": { - "variant": "bf16" - } - } - } - } - } - }, - "ops.precision.bits": { - "B1x8": { - "pkg": { - "0": { - "torch": { - "bits1x8": { - "variant": "bits1x8" - } - } - } - } - }, - "B2x4": { - "pkg": { - "0": { - "torch": { - "bits2x4": { - "variant": "bits2x4" - } - } - } - } - }, - "B4x2": { - "pkg": { - "0": { - "torch": { - "bits4x2": { - "variant": "bits4x2" - } - } - } - } - }, - "B8": { - "pkg": { - "0": { - "torch": { - "bits8": { - "variant": "bits8" - } - } - } - } - }, - "B16": { - "pkg": { - "0": { - "torch": { - "bits16": { - "variant": "bits16" - } - } - } - } - } - }, - "ops.scheduler.amused": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "AmusedScheduler", - "module_path": "diffusers.schedulers.scheduling_amused" - } - } - } - }, - "ops.scheduler.cmstochasticiterative": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CMStochasticIterativeScheduler", - "module_path": "diffusers.schedulers.scheduling_consistency_models" - } - } - } - }, - "ops.scheduler.cogvideoxddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_cogvideox" - } - } - } - }, - "ops.scheduler.cogvideoxdpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_dpm_cogvideox" - } - } - } - }, - "ops.scheduler.ddiminverse": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_inverse" - } - } - } - }, - "ops.scheduler.ddimparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_parallel" - } - } - } - }, - "ops.scheduler.ddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim" - } - } - } - }, - "ops.scheduler.ddpmparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_parallel" - } - } - } - }, - "ops.scheduler.ddpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm" - } - } - } - }, - "ops.scheduler.ddpmwuerstchen": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMWuerstchenScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_wuerstchen" - } - } - } - }, - "ops.scheduler.deis": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DEISMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_deis_multistep" - } - } - } - }, - "ops.scheduler.dpminverse": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep_inverse" - } - } - } - }, - "ops.scheduler.dpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.dpmsinglestep": { - "solver": { - "pkg": { - "0": { - "diffusers": "DPMSolverSinglestepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_singlestep" - } - } - } - }, - "ops.scheduler.edmdpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "EDMDPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.edmeuler": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "EDMEulerScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_euler" - } - } - } - }, - "ops.scheduler.eulerancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerAncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_ancestral_discrete" - } - } - } - }, - "ops.scheduler.euler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatcheuler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchEulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatchheun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchHeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_heun_discrete" - } - } - } - }, - "ops.scheduler.flowmatchlcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "FlowMatchLCMScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_lcm" - } - } - } - }, - "ops.scheduler.heun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "HeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_heun_discrete" - } - } - } - }, - "ops.scheduler.ipndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "IPNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_ipndm" - } - } - } - }, - "ops.scheduler.karrasve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "KarrasVeScheduler", - "module_path": "diffusers.schedulers.deprecated.scheduling_karras_ve" - } - } - } - }, - "ops.scheduler.kdpm2ancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2AncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete" - } - } - } - }, - "ops.scheduler.kdpm2": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2DiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_discrete" - } - } - } - }, - "ops.scheduler.lcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "LCMScheduler", - "module_path": "diffusers.schedulers.scheduling_lcm" - } - } - } - }, - "ops.scheduler.pndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "PNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_pndm" - } - } - } - }, - "ops.scheduler.repaint": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "RePaintScheduler", - "module_path": "diffusers.schedulers.scheduling_repaint" - } - } - } - }, - "ops.scheduler.sa": { - "solver": { - "pkg": { - "0": { - "diffusers": "SASolverScheduler", - "module_path": "diffusers.schedulers.scheduling_sasolver" - } - } - } - }, - "ops.scheduler.scm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "SCMScheduler", - "module_path": "diffusers.schedulers.scheduling_scm" - } - } - } - }, - "ops.scheduler.scoresdeve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "ScoreSdeVeScheduler", - "module_path": "diffusers.schedulers.scheduling_sde_ve" - } - } - } - }, - "ops.scheduler.tcd": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "TCDScheduler", - "module_path": "diffusers.schedulers.scheduling_tcd" - } - } - } - }, - "ops.scheduler.unclip": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "UnCLIPScheduler", - "module_path": "diffusers.schedulers.scheduling_unclip" - } - } - } - }, - "ops.scheduler.unipc": { - "multistep": { - "pkg": { - "0": { - "diffusers": "UniPCMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_unipc_multistep" - } - } - } - }, - "ops.scheduler.vqdiffusion": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "VQDiffusionScheduler", - "module_path": "diffusers.schedulers.scheduling_vq_diffusion" - } - } - } - }, - "ops.scheduler.lms": { - "discrete": { - "pkg": { - "0": { - "diffusers": "LMSDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_lms_discrete" - } - } - } - }, - "ops.scheduler.cosinedpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "CosineDPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_cosine_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.dpmsde": { - "solver": { - "pkg": { - "0": { - "diffusers": "DPMSolverSDEScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_sde" - } - } - } - }, - "ops.scheduler.karrasdiffusion": { - "schedulers": { - "pkg": { - "0": { - "diffusers": "KarrasDiffusionSchedulers", - "module_path": "diffusers.schedulers.scheduling_utils" - } - } - } - }, - "info.lora.dmd": { - "stable-diffusion-xl-1": { - "repo": "tianweiy/DMD2", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "timesteps": [ - 999, - 749, - 499, - 249 - ] - }, - "scheduler": { - "ops.scheduler.lcm": "" - } - } - }, - "file_256": [ - "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", - "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb" - ] - } - }, - "info.lora.dpo": { - "stable-diffusion-xl-1": { - "repo": "radames/sdxl-DPO-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5, - "num_inference_steps": 4 - }, - "scheduler": { - "ops.scheduler.dpm": { - "algorithm_type": "sde-dpmsolver++", - "use_karras_sigmas": true, - "order": 2 - } - } - } - }, - "file_256": [ - "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", - "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad" - ] - } - }, - "info.lora.flash": { - "stable-diffusion-xl-1": { - "repo": "jasperai/flash-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": "ops.scheduler.lcm" - } - }, - "file_256": [ - "afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7" - ] - }, - "pixart-alpha": { - "repo": "jasperai/flash-pixart", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b" - ] - }, - "stable-diffusion-3": { - "repo": "jasperai/flash-sd3", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15" - ] - }, - "stable-diffusion-v1-5": { - "repo": "jasperai/flash-sd", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - }, - "file_256": [ - "99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f" - ] - } - }, - "info.lora.hyper": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - } - } - }, - "file_256": { - "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": { - "num_inference_steps": 12 - }, - "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": { - "num_inference_steps": 8 - }, - "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "flux1-dev": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": { - "num_inference_steps": 16 - }, - "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": { - "num_inference_steps": 4 - }, - "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": { - "num_inference_steps": 8 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": { - "num_inference_steps": 12 - }, - "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": { - "num_inference_steps": 8 - }, - "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - } - }, - "info.lora.lcm": { - "stable-diffusion-xl-1": { - "repo": "latent-consistency/lcm-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141" - ] - }, - "ssd": { - "repo": "latent-consistency/lcm-lora-ssd-1b", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b" - ] - }, - "segmind-vega": { - "repo": "segmind/Segmind-VegaRT", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "gen_kwargs": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb" - ] - }, - "stable-diffusion-v1-5": { - "repo": "latent-consistency/lcm-lora-sdv1-5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4" - ] - } - }, - "info.lora.lightning": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/SDXL-Lightning", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - } - } - }, - "info.lora.pcm": { - "stable-diffusion-xl-1": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": { - "num_inference_steps": 16 - }, - "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": { - "num_inference_steps": 16 - }, - "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": { - "num_inference_steps": 4 - }, - "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": { - "num_inference_steps": 4 - }, - "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": { - "num_inference_steps": 8 - }, - "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": { - "num_inference_steps": 8 - }, - "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - }, - "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": { - "num_inference_steps": 16 - }, - "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": { - "num_inference_steps": 4 - }, - "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": { - "num_inference_steps": 8 - }, - "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": { - "num_inference_steps": 2, - "guidance_scale": 1.2 - }, - "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - } - } - } - }, - "info.lora.slam": { - "stable-diffusion-xl-1": { - "repo": "alimama-creative/slam-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 1 - } - } - }, - "file_256": [ - "22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91" - ] - }, - "stable-diffusion-v1-5": { - "repo": "alimama-creative/slam-sd1.5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - } - } - }, - "info.lora.spo": { - "stable-diffusion-xl-1": { - "repo": "SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df" - ] - }, - "stable-diffusion-v1-5": { - "repo": "SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5 - } - } - }, - "file_256": [ - "1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4" - ] - } - }, - "info.lora.tcd": { - "stable-diffusion-xl-1": { - "repo": "h1t/TCD-SDXL-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "eta": 0.3 - }, - "scheduler": { - "ops.scheduler.tcd": {} - } - } - }, - "file_256": [ - "2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba" - ] - }, - "stable-diffusion-v1-5": { - "repo": "h1t/TCD-SD15-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232" - ], - "layer_256": [ - "e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75" - ], - "layer_b3": [ - "90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b" - ] - } - }, - "info.lora.turbo": { - "stable-diffusion-xl-1": { - "file_256": [ - "a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69" - ] - }, - "flux1-dev": { - "repo": "alimama-creative/FLUX.1-Turbo-Alpha", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - }, - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 8, - "max_sequence_length": 512 - } - } - }, - "file_256": [ - "77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff" - ] - }, - "stable-diffusion-3": { - "repo": "tensorart/stable-diffusion-3.5-large-TurboX", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.flow-match": { - "shift": 5 - } - } - } - }, - "file_256": { - "fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": { - "num_inference_steps": "8" - } - } - } - }, - "info.art.audiogen": { - "*": { - "repo": "facebook/audiogen-medium", - "pkg": { - "0": { - "audiocraft": "models.AudioGen", - "generation": { - "duration": 5 - }, - "stage_2": { - "audiocraft": ".data.audioaudio_write", - "generation": { - "strategy": "loudness", - "loudness_compressor": true - } - } - } - } - } - }, - "info.art.parler-tts-v1": { - "*": { - "repo": "parler-tts/parler-tts-large-v1", - "pkg": { - "0": { - "parler_tts": "ParlerTTSForConditionalGeneration", - "generation": { - "return_tensors": "pt" - } - } - } - } - }, - "info.gan.snac-st": { - "*": { - "repo": "Zuellni/snac-24khz-ST", - "pkg": { - "0": { - "snac": "SNAC" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio" - } - }, - "file_256": [ - "e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", - "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d" - ], - "layer_256": [ - "35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", - "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841" - ], - "layer_b3": [ - "18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", - "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119" - ] - } - }, - "info.gan.kokoro": { - "*": { - "repo": "hexgrad/Kokoro-82M", - "pkg": { - "0": { - "kokoro": "KPipeline" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", - "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4" - ], - "layer_256": [ - "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", - "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b" - ], - "layer_b3": [ - "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", - "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", - "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e932dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92" - ] - } - }, - "info.stst.silero-vad": { - "*": { - "repo": "freddyaboulton/silero-vad", - "pkg": { - "0": { - "onnx": "onnx" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9" - ], - "layer_256": [ - "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd" - ], - "layer_b3": [ - "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", - "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", - "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", - "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e" - ] - } - }, - "info.stst.wav2vec2-conformer-rope-960h-ft": { - "*": { - "repo": "facebook/wav2vec2-conformer-rope-large-960h-ft", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerForCTC" - } - }, - "file_256": [ - "97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d" - ], - "layer_256": [ - "1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d" - ], - "layer_b3": [ - "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" - ], - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.art.orpheus-0-ft": { - "*": { - "repo": "canopylabs/orpheus-3b-0.1-ft", - "pkg": { - "0": { - "orpheus_tts": "OrpheusModel", - "generation": { - "max_model_len": 2048 - } - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.art.outetts-0": { - "*": { - "repo": "OuteAI/OuteTTS-0.3-1B", - "pkg": { - "0": { - "outetts": "InterfaceHF" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.gan.speecht5-hifigan": { - "*": { - "file_256": [ - "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c" - ], - "layer_256": [ - "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770" - ], - "layer_b3": [ - "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956" - ] - } - }, - "info.dit.wan2-flf2v-720p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", - "file_256": [ - "", - "" - ], - "layer_256": [ - "" - ], - "layer_b3": [ - "" - ] - } - }, - "ops.patch.hidiffusion": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "hidiffusion": { - "apply_hidiffusion": { - "timesteps": "StableDiffusionXLTimesteps" - } - }, - "generation": { - "height": 2048, - "width": 2048, - "eta": 1.0, - "guidance_scale": 7.5, - "num_inference_steps": 10 - } - } - } - } - }, - "ops.scheduler.align-your-steps": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "diffusers": "schedulers.scheduling_utils.AysSchedules", - "generation": { - "timesteps": "StableDiffusionXLTimesteps", - "num_inference_steps": 10 - } - } - } - } - }, - "info.vit.clip-vit-patch14": { - "*": { - "repo": "openai/clip-vit-large-patch14", - "pkg": { - "0": { - "transformers": "CLIPTextModel" - } - }, - "file_256": [ - "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", - "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", - "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", - "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", - "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", - "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", - "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", - "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", - "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", - "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", - "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", - "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", - "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", - "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", - "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", - "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", - "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1" - ], - "layer_256": [ - "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", - "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", - "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", - "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", - "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", - "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", - "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", - "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", - "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", - "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", - "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", - "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", - "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3" - ], - "layer_b3": [ - "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", - "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", - "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", - "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", - "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", - "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", - "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", - "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", - "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", - "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", - "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", - "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", - "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", - "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", - "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", - "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-g-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-g-14-laion2B-s12B-b42K", - "pkg": { - "0": { - "transformers": "CLIPTextModelWithProjection" - } - }, - "file_256": [ - "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", - "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", - "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", - "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", - "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", - "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", - "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", - "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", - "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", - "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b" - ], - "layer_256": [ - "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", - "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", - "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", - "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", - "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", - "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", - "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46" - ], - "layer_b3": [ - "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", - "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", - "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", - "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", - "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", - "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", - "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-h-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K", - "pkg": { - "0": { - "transformers": "CLIPModel" - } - }, - "file_256": [ - "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", - "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", - "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161" - ], - "layer_256": [ - "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", - "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", - "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c" - ], - "layer_b3": [ - "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", - "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", - "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.aet.chatglm3": { - "*": { - "repo": "zai-org/chatglm3-6b", - "pkg": { - "0": { - "transformers": "AutoModel" - } - }, - "file_256": [ - "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", - "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d" - ], - "layer_256": [ - "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44" - ], - "layer_b3": [ - "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481" - ] - } - }, - "info.vae.tae": { - "stable-diffusion-3": { - "repo": "madebyollin/taesd3", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399" - ] - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/taesdxl", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f" - ] - }, - "stable-diffusion-v1-5": { - "repo": "madebyollin/taesd", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549" - ] - }, - "flux1-dev": { - "repo": "madebyollin/taef1", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449" - ] - } - }, - "info.vae.kl": { - "qwen-image": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLQwenImage" - } - }, - "file_256": [ - "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344" - ], - "layer_256": [ - "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc" - ], - "layer_b3": [ - "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b" - ] - }, - "ltx-video": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLLTXVideo" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "allegro": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLAllegro" - } - }, - "file_256": [ - "47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a" - ], - "layer_256": [ - "bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f" - ], - "layer_b3": [ - "93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0" - ] - }, - "cosmos-1-diffusion-video2world": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCosmos" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "easyanimatev5-zh": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMagvit" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "hunyuanvideo-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLHunyuanVideo" - } - }, - "file_256": [ - "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", - "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", - "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", - "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0" - ] - }, - "mochi-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMochi" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "audioldm-s-v2": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5" - ], - "layer_256": [ - "54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6" - ], - "layer_b3": [ - "00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de" - ] - }, - "stable-video-diffusion-img2vid-xt": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLTemporalDecoder" - } - } - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/sdxl-vae-fp16-fix", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", - "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", - "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", - "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", - "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", - "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", - "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", - "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0" - ] - }, - "stable-diffusion-xl-1*": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", - "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", - "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74" - ] - }, - "shuttle-jaguar": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904" - ], - "layer_256": [ - "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b" - ], - "layer_b3": [ - "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", - "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0" - ] - }, - "flux1-dev": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", - "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", - "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", - "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc" - ], - "layer_256": [ - "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", - "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", - "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", - "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80" - ], - "layer_b3": [ - "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", - "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903" - ] - }, - "musicldm": { - "file_256": [ - "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4" - ], - "layer_256": [ - "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f" - ], - "layer_b3": [ - "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0" - ] - }, - "stable-diffusion-v1-5": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", - "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", - "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", - "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", - "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", - "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", - "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", - "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c" - ], - "layer_256": [ - "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", - "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3" - ], - "layer_b3": [ - "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", - "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833" - ] - } - }, - "info.vae.wan": { - "wan2-i2v-480p": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLWan", - "precision": "ops.precision.float.F32" - } - }, - "file_256": [ - "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", - "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b" - ], - "layer_256": [ - "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", - "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e" - ], - "layer_b3": [ - "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", - "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433" - ] - }, - "skyreels-v2-t2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "skyreels-v2-i2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.cogvideox": { - "cogvideox-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCogVideoX" - } - }, - "file_256": [ - "a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e" - ], - "layer_256": [ - "43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e" - ], - "layer_b3": [ - "246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb" - ] - }, - "cogvideox-fun-v-pose": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "consisid": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.dc": { - "sana-1024px-bf16": { - "pkg": { - "0": { - "diffusers": "AutoencoderDC" - } - }, - "file_256": [ - "15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f" - ], - "layer_256": [ - "abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde" - ], - "layer_b3": [ - "cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0" - ] - } - }, - "info.vae.oobleck": { - "stable-audio-open-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderOobleck" - } - } - } - }, - "info.vae.eq": { - "stable-diffusion-xl-1": { - "repo": "KBlueLeaf/EQ-SDXL-VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - }, - "info.vae.ms-lc-eq": { - "stable-diffusion-xl-1": { - "repo": "Anzhc/MS-LC-EQ-D-VR_VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - } + "expected": "data" } \ No newline at end of file From c94c716f5657e372c13be6ba019a1ad67393db77 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sun, 11 Jan 2026 01:25:08 -0500 Subject: [PATCH 02/16] ~huge refactoring --- LICENSE | 4 +- MIR.egg-info/PKG-INFO | 5 +- MIR.egg-info/SOURCES.txt | 3 + MIR.egg-info/requires.txt | 2 + README.md | 6 +- mir.json | 7819 +++++++++++++++++++++++ mir/automata.py | 230 +- mir/config/constants.py | 127 +- mir/config/conversion.py | 143 +- mir/doc_parser.py | 14 +- mir/indexers.py | 276 +- mir/inspect/classes.py | 30 - mir/inspect/metadata.py | 205 +- mir/inspect/pipes.py | 17 +- mir/inspect/tasks.py | 67 +- mir/maid.py | 17 +- mir/mir.json | 5026 ++++++++++++++- mir/spec/{mir.py => __init__.py} | 0 mir/spec/docstring_patterns.json | 41 + mir/spec/missing_params.json | 62 + mir/spec/repo_migrations.json | 29 + mir/spec/template.json | 17 +- mir/tag.py | 64 +- pyproject.toml | 2 + tests/test_find_docstring_run.py | 5 + tests/test_gather_diffusers_metadata.py | 10 +- tests/test_mir_db_create_restore.py | 2 +- tests/test_mir_tagging.py | 16 +- tests/test_regex_constants.py | 4 +- uv.lock | 538 +- 30 files changed, 13907 insertions(+), 874 deletions(-) create mode 100644 mir.json rename mir/spec/{mir.py => __init__.py} (100%) create mode 100644 mir/spec/docstring_patterns.json create mode 100644 mir/spec/missing_params.json create mode 100644 mir/spec/repo_migrations.json create mode 100644 tests/test_find_docstring_run.py diff --git a/LICENSE b/LICENSE index 1fe559b..eab9da3 100644 --- a/LICENSE +++ b/LICENSE @@ -6,10 +6,10 @@ Without limiting other conditions in the License, the grant of rights under the For purposes of the foregoing, “Sell” means practicing any or all of the rights granted to you under the License to provide to third parties, for a fee or other consideration (including without limitation fees for hosting or consulting/ support services related to the Software), a product or service whose value derives, entirely or substantially, from the functionality of the Software. Any license notice or attribution required by the License must also include this Commons Clause License Condition notice. -Software: zodiac +Software: mir License : Mozilla Public License v. 2.0 Licensor: darkshapes github.com/darkshapes -This Source Code Form is subject to the terms of the Mozilla Public License, v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain one at https://mozilla.org/MPL/2.0/. \ No newline at end of file +This Source Code Form is subject to the terms of the Mozilla Public License, v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain one at https://mozilla.org/MPL/2.0/. diff --git a/MIR.egg-info/PKG-INFO b/MIR.egg-info/PKG-INFO index 678b0bd..d98b3d3 100644 --- a/MIR.egg-info/PKG-INFO +++ b/MIR.egg-info/PKG-INFO @@ -11,13 +11,14 @@ License: “Commons Clause” License Condition v1.0 For purposes of the foregoing, “Sell” means practicing any or all of the rights granted to you under the License to provide to third parties, for a fee or other consideration (including without limitation fees for hosting or consulting/ support services related to the Software), a product or service whose value derives, entirely or substantially, from the functionality of the Software. Any license notice or attribution required by the License must also include this Commons Clause License Condition notice. - Software: zodiac + Software: mir License : Mozilla Public License v. 2.0 Licensor: darkshapes github.com/darkshapes This Source Code Form is subject to the terms of the Mozilla Public License, v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain one at https://mozilla.org/MPL/2.0/. + Project-URL: Homepage, https://github.com/darkshapes/MIR Project-URL: Documentation, https://github.com/darkshapes/sdbx/wiki Keywords: ML,AI,URI,schema,diffusion,LLM,identification @@ -33,8 +34,10 @@ Requires-Python: >=3.11 Description-Content-Type: text/markdown License-File: LICENSE Requires-Dist: diffusers>=0.35.2 +Requires-Dist: ftfy>=6.3.1 Requires-Dist: huggingface-hub[hf-xet]>=1.1.7 Requires-Dist: pydantic>=2.12.5 +Requires-Dist: sentencepiece>=0.2.1 Requires-Dist: tokenizers>=0.22.1 Requires-Dist: torch>=2.9.1 Requires-Dist: torchvision>=0.24.1 diff --git a/MIR.egg-info/SOURCES.txt b/MIR.egg-info/SOURCES.txt index 23176a9..dea9843 100644 --- a/MIR.egg-info/SOURCES.txt +++ b/MIR.egg-info/SOURCES.txt @@ -1,3 +1,4 @@ +.env .gitignore CODE_OF_CONDUCT.md LICENSE @@ -30,6 +31,7 @@ mir/inspect/metadata.py mir/inspect/parenting.py mir/inspect/pipes.py mir/inspect/tasks.py +mir/spec/docstring_patterns.json mir/spec/mir.py mir/spec/modes.json mir/spec/template.json @@ -37,6 +39,7 @@ mir/spec/versions.json tests/test_class_parent.py tests/test_deconstructors_root.py tests/test_doc_parser.py +tests/test_find_docstring_run.py tests/test_gather_diffusers_metadata.py tests/test_json_io.py tests/test_mir_db_create_restore.py diff --git a/MIR.egg-info/requires.txt b/MIR.egg-info/requires.txt index d9c4e5b..089ac9c 100644 --- a/MIR.egg-info/requires.txt +++ b/MIR.egg-info/requires.txt @@ -1,6 +1,8 @@ diffusers>=0.35.2 +ftfy>=6.3.1 huggingface-hub[hf-xet]>=1.1.7 pydantic>=2.12.5 +sentencepiece>=0.2.1 tokenizers>=0.22.1 torch>=2.9.1 torchvision>=0.24.1 diff --git a/README.md b/README.md index e9c5b1b..d993ad2 100644 --- a/README.md +++ b/README.md @@ -93,14 +93,14 @@ Meant to be created by standards community, derived from code and file analysis |
ART
| Autoregressive Transformer | |
BRNN
| Bi-directional Recurrent Neural Network | |
CNN
| Convolutional Neural Network | -|
CONTROLNET
| Controlnet | +|
CONTROLNET
| ControlNet | |
DETR
| Detection Transformer | |
GAN
| Generative Adversarial Model | -|
GRU
| Gated recurrent unit | +|
GRU
| Gated Recurrent Unit | |
LORA
| Low-Rank Adaptation | |
LSTM
| Long Short-Term Memory | |
MOE
| Mixture of Experts | -|
RBM
| Restricted Boltzmann machine | +|
RBM
| Restricted Boltzmann Machine | |
RCNN
| Region-based Convolutional Neural Network | |
RESNET
| Residual Network | |
RNN
| Recurrent Neural Network | diff --git a/mir.json b/mir.json new file mode 100644 index 0000000..c73a611 --- /dev/null +++ b/mir.json @@ -0,0 +1,7819 @@ +{ + "info.controlnet.sd-controlnet-canny": { + "*": { + "repo": "lllyasviel/sd-controlnet-canny", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.blipdiffusion-controlnet": { + "*": { + "repo": "Salesforce/blipdiffusion-controlnet", + "pkg": { + "0": { + "diffusers": "BlipDiffusionControlNetPipeline" + } + } + } + }, + "info.controlnet.control-v11p-sd15-inpaint": { + "*": { + "repo": "lllyasviel/control_v11p_sd15_inpaint", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-canny-sdxl-1": { + "*": { + "repo": "diffusers/controlnet-canny-sdxl-1.0", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-depth-sdxl-1": { + "*": { + "repo": "diffusers/controlnet-depth-sdxl-1.0-small", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-union-sdxl-1": { + "*": { + "repo": "xinsir/controlnet-union-sdxl-1.0", + "pkg": { + "0": { + "diffusers": "ControlNetUnionModel" + } + } + } + }, + "info.controlnet.sd3-controlnet-canny": { + "*": { + "repo": "InstantX/SD3-Controlnet-Canny", + "pkg": { + "0": { + "diffusers": "SD3ControlNetModel" + } + } + } + }, + "info.controlnet.sd3-controlnet-inpainting": { + "*": { + "repo": "alimama-creative/SD3-Controlnet-Inpainting", + "pkg": { + "0": { + "diffusers": "SD3ControlNetModel" + } + } + } + }, + "info.controlnet.testing-conrolnetxs-sd2-canny": { + "*": { + "repo": "UmerHA/Testing-ConrolNetXS-SD2.1-canny", + "pkg": { + "0": { + "diffusers": "ControlNetXSAdapter" + } + } + } + }, + "info.controlnet.testing-conrolnetxs-sdxl-canny": { + "*": { + "repo": "UmerHA/Testing-ConrolNetXS-SDXL-canny", + "pkg": { + "0": { + "diffusers": "ControlNetXSAdapter" + } + } + } + }, + "info.unet.stable-diffusion-v1-5": { + "*": { + "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", + "pkg": { + "0": { + "diffusers": "StableDiffusionPipeline" + } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-v1-5" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "safety_checker": [ + "StableDiffusionSafetyChecker" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ] + } + } + }, + "info.unet.stable-unclip-2-1-l": { + "*": { + "repo": "fusing/stable-unclip-2-1-l", + "pkg": { + "0": { + "diffusers": "StableUnCLIPPipeline" + } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "prior_tokenizer": [ + "info.encoder.tokenizer", + "stable-unclip-2-1-l" + ], + "prior_text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "prior": [ + "PriorTransformer" + ], + "prior_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_normalizer": [ + "StableUnCLIPImageNormalizer" + ], + "image_noising_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-unclip-2-1-l" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vae": [ + "AutoencoderKL" + ] + } + } + }, + "info.unet.stable-diffusion-2-1-unclip": { + "*": { + "repo": "stabilityai/stable-diffusion-2-1-unclip-small", + "pkg": { + "0": { + "diffusers": "StableUnCLIPImg2ImgPipeline" + } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "feature_extractor": [ + "CLIPImageProcessor" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "image_normalizer": [ + "StableUnCLIPImageNormalizer" + ], + "image_noising_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-2-1-unclip" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vae": [ + "AutoencoderKL" + ] + } + } + }, + "info.unet.stable-diffusion-xl-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-base-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLPipeline" + } + }, + "tasks": [ + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "info.vae.eq", + "info.vae.ms-lc-eq", + "stable-diffusion-xl-1" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-1" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-1" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + }, + "pony-diffusion": { + "file_256": [ + "67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3" + ], + "layer_256": [ + "465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e" + ], + "layer_b3": [ + "bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071" + ] + }, + "pony-diffusion-turbo": { + "file_256": [ + "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", + "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2" + ], + "layer_256": [ + "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", + "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52" + ], + "layer_b3": [ + "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", + "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc" + ] + }, + "animagine-xl-4": { + "repo": "cagliostrolab/animagine-xl-4.0", + "file_256": [ + "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", + "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", + "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", + "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0" + ], + "layer_256": [ + "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", + "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", + "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", + "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65" + ], + "layer_b3": [ + "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", + "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", + "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", + "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447" + ] + }, + "illustrious-xl-v2": { + "repo": "OnomaAIResearch/Illustrious-XL-v2.0", + "file_256": [ + "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", + "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", + "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", + "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", + "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd" + ], + "layer_256": [ + "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", + "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", + "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", + "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", + "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10" + ], + "layer_b3": [ + "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", + "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", + "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", + "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", + "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c" + ] + }, + "playground-v2---aesthetic": { + "repo": "playgroundai/playground-v2.5-1024px-aesthetic", + "pkg": { + "0": { + "diffusers": "DiffusionPipeline", + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 50, + "guidance_scale": 3 + } + } + }, + "file_256": [ + "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", + "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", + "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", + "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", + "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", + "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a" + ], + "layer_256": [ + "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", + "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", + "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", + "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", + "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c" + ], + "layer_b3": [ + "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", + "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", + "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", + "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", + "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", + "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" + ], + "pipe_names": {} + }, + "segmind-vega": { + "repo": "segmind/Segmind-Vega", + "file_256": [ + "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", + "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", + "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2" + ], + "layer_256": [ + "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", + "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", + "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741" + ], + "layer_b3": [ + "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", + "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", + "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1" + ] + }, + "ssd": { + "repo": "segmind/SSD-1B", + "file_256": [ + "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", + "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", + "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", + "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", + "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a" + ], + "layer_256": [ + "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", + "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", + "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", + "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", + "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" + ], + "layer_b3": [ + "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", + "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", + "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", + "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", + "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" + ] + } + }, + "info.unet.stable-diffusion-xl-refiner-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-refiner-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLImg2ImgPipeline" + } + }, + "tasks": [ + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-refiner-1" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-refiner-1" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.unet.sdxl-pix2pix-768": { + "*": { + "repo": "diffusers/sdxl-instructpix2pix-768", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLInstructPix2PixPipeline" + } + }, + "tasks": [ + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "sdxl-pix2pix-768" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "sdxl-pix2pix-768" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + } + } + }, + "info.dit.allegro": { + "*": { + "repo": "rhymes-ai/Allegro", + "pkg": { + "0": { + "diffusers": "AllegroPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "allegro" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "info.vae.kl", + "allegro" + ], + "transformer": [ + "AllegroTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + } + } + }, + "info.dit.amused-512": { + "*": { + "repo": "amused/amused-512", + "pkg": { + "0": { + "diffusers": "AmusedInpaintPipeline" + } + }, + "pipe_names": { + "vqvae": [ + "VQModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "amused-512" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "transformer": [ + "UVit2DModel" + ], + "scheduler": [ + "ops.scheduler.amused", + "scheduler" + ] + } + } + }, + "info.lora.animatediff-motion-adapter-v1-5-2": { + "*": { + "repo": "guoyww/animatediff-motion-adapter-v1-5-2", + "pkg": { + "0": { + "diffusers": "AnimateDiffVideoToVideoPipeline" + } + } + } + }, + "info.lora.animatediff-motion-adapter-sdxl": { + "*": { + "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", + "pkg": { + "0": { + "diffusers": "AnimateDiffSDXLPipeline" + } + } + } + }, + "info.controlnet.animatediff-sparsectrl-scribble": { + "*": { + "repo": "guoyww/animatediff-sparsectrl-scribble", + "pkg": { + "0": { + "diffusers": "SparseControlNetModel" + } + } + } + }, + "info.controlnet.animatelcm": { + "*": { + "repo": "wangfuyun/AnimateLCM", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.dit.bria-3": { + "*": { + "repo": "briaai/BRIA-3.2", + "pkg": { + "0": { + "diffusers": "BriaPipeline" + } + }, + "pipe_names": { + "transformer": [ + "BriaTransformer2DModel" + ], + "scheduler": [ + [ + "ops.scheduler.euler", + "discrete" + ], + [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "bria-3" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.flux2-dev": { + "*": { + "repo": "black-forest-labs/FLUX.2-dev", + "pkg": { + "0": { + "diffusers": "Flux2Pipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "Mistral3ForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux2-dev" + ], + "transformer": [ + "Flux2Transformer2DModel" + ] + } + } + }, + "info.dit.flux1-schnell": { + "*": { + "repo": "black-forest-labs/FLUX.1-schnell", + "pkg": { + "0": { + "diffusers": "FluxInpaintPipeline" + } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-schnell" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-schnell" + ], + "transformer": [ + "FluxTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + }, + "shuttle-3-aesthetic": { + "repo": "shuttleai/shuttle-3.1-aesthetic", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", + "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" + ], + "layer_256": [ + "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", + "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a" + ], + "layer_b3": [ + "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", + "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c" + ] + }, + "shuttle-3-diffusion": { + "repo": "shuttleai/shuttle-3-diffusion", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", + "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", + "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", + "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8" + ], + "layer_256": [ + "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", + "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", + "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c" + ], + "layer_b3": [ + "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", + "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", + "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd" + ] + }, + "shuttle-jaguar": { + "repo": "shuttleai/shuttle-jaguar", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", + "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f" + ], + "layer_b3": [ + "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", + "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672" + ] + } + }, + "info.controlnet.flux1-canny-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Canny-dev", + "pkg": { + "0": { + "diffusers": "FluxControlPipeline" + } + } + } + }, + "info.controlnet.flux1-dev-controlnet-canny": { + "*": { + "repo": "InstantX/FLUX.1-dev-controlnet-canny", + "pkg": { + "0": { + "diffusers": "FluxControlNetModel" + } + } + } + }, + "info.controlnet.flux1-dev-controlnet-canny-alpha": { + "*": { + "repo": "InstantX/FLUX.1-dev-Controlnet-Canny-alpha", + "pkg": { + "0": { + "diffusers": "FluxControlNetModel" + } + } + } + }, + "info.dit.flux1-fill-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Fill-dev", + "pkg": { + "0": { + "diffusers": "FluxFillPipeline" + } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-fill-dev" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-fill-dev" + ], + "transformer": [ + "FluxTransformer2DModel" + ] + } + } + }, + "info.dit.flux1-kontext-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Kontext-dev", + "pkg": { + "0": { + "diffusers": "FluxKontextInpaintPipeline" + } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-kontext-dev" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-kontext-dev" + ], + "transformer": [ + "FluxTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.flux1-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-dev", + "pkg": { + "0": { + "diffusers": "FluxPipeline" + } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-dev" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-dev" + ], + "transformer": [ + "FluxTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + }, + "mystic": { + "repo": "enhanceaiteam/Mystic", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 16, + "guidance_scale": 7.5, + "width": 768, + "height": 1024 + } + } + }, + "file_256": [ + "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", + "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" + ], + "layer_256": [ + "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" + ], + "layer_b3": [ + "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" + ] + }, + "flux1-lite": { + "repo": "freepik/flux.1-lite-8b", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 28 + } + } + }, + "file_256": [ + "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", + "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" + ], + "layer_256": [ + "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" + ], + "layer_b3": [ + "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" + ] + }, + "f-lite": { + "repo": "freepik/f-lite", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "f-lite-texture": { + "repo": "freepik/f-lite-texture", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "flux": { + "repo": "TencentARC/flux-mini", + "file_256": [ + "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" + ], + "layer_256": [ + "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" + ], + "layer_b3": [ + "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" + ] + }, + "flex2": { + "repo": "ostris/Flex.2-preview", + "file_256": [ + "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", + "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" + ], + "layer_256": [ + "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" + ], + "layer_b3": [ + "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" + ] + }, + "flex1-alpha": { + "repo": "ostris/Flex.1-alpha", + "file_256": [ + "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", + "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" + ], + "layer_256": [ + "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" + ], + "layer_b3": [ + "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" + ] + } + }, + "info.dit.prx-512-t2i-sft": { + "*": { + "repo": "Photoroom/prx-512-t2i-sft", + "pkg": { + "0": { + "diffusers": "PRXPipeline" + } + }, + "pipe_names": { + "transformer": [ + "PRXTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder": [ + "T5GemmaEncoder" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "prx-512-t2i-sft" + ], + "vae": [ + "AutoencoderKL", + [ + "info.vae.dc", + "sana-1024px-bf16" + ], + "NoneType" + ] + } + } + }, + "info.unet.audioldm-s-v2": { + "*": { + "repo": "cvssp/audioldm-s-full-v2", + "pkg": { + "0": { + "diffusers": "AudioLDMPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "ClapTextModelWithProjection" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vocoder": [ + "SpeechT5HifiGan" + ] + } + } + }, + "info.unet.audioldm2": { + "*": { + "repo": "cvssp/audioldm2", + "pkg": { + "0": { + "diffusers": "AudioLDM2Pipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "ClapModel" + ], + "text_encoder_2": [ + "T5EncoderModel", + "VitsModel" + ], + "projection_model": [ + "AudioLDM2ProjectionModel" + ], + "language_model": [ + "info.art.gpt2", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "audioldm2" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "audioldm2" + ], + "feature_extractor": [ + "ClapFeatureExtractor" + ], + "unet": [ + "AudioLDM2UNet2DConditionModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vocoder": [ + "SpeechT5HifiGan" + ] + } + } + }, + "info.unet.blipdiffusion": { + "*": { + "repo": "Salesforce/blipdiffusion", + "pkg": { + "0": { + "diffusers": "BlipDiffusionPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "blipdiffusion" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + "ops.scheduler.pndm", + "scheduler" + ], + "qformer": [ + "info.vit.blip2-opt", + "*" + ], + "image_processor": [ + "BlipImageProcessor" + ] + } + } + }, + "info.dit.chroma": { + "*": { + "repo": "lodestones/Chroma", + "pkg": { + "0": { + "diffusers": "ChromaPipeline" + } + }, + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + }, + "chroma1-hd": { + "repo": "lodestones/Chroma1-HD", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 40 + } + } + }, + "file_256": [ + "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", + "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", + "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc" + ] + }, + "chroma1-flash": { + "repo": "lodestones/Chroma1-Flash", + "pkg": { + "0": { + "diffusers": "ChromaPipeline", + "generation": { + "num_inference_steps": 8, + "guidance_scale": 1.0, + "num_images_per_prompt": 1 + } + } + }, + "file_256": [ + "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", + "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", + "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" + ], + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.chroma1-hd": { + "*": { + "repo": "lodestones/Chroma1-HD", + "pkg": { + "0": { + "diffusers": "ChromaImg2ImgPipeline" + } + }, + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma1-hd" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.cogvideox": { + "*": { + "repo": "zai-org/CogVideoX-2b", + "pkg": { + "0": { + "diffusers": "CogVideoXPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogvideox" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "transformer": [ + "CogVideoXTransformer3DModel" + ], + "scheduler": [ + [ + "ops.scheduler.cogvideoxddim", + "scheduler" + ], + [ + "ops.scheduler.cogvideoxdpm", + "scheduler" + ] + ] + } + } + }, + "info.controlnet.cogvideox-fun-v-pose": { + "*": { + "repo": "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", + "pkg": { + "0": { + "diffusers": "CogVideoXFunControlPipeline" + } + } + } + }, + "info.dit.cogvideox-i2v": { + "*": { + "repo": "zai-org/CogVideoX-5b-I2V", + "pkg": { + "0": { + "diffusers": "CogVideoXImageToVideoPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogvideox-i2v" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "info.vae.cogvideox", + "cogvideox-i2v" + ], + "transformer": [ + "CogVideoXTransformer3DModel" + ], + "scheduler": [ + [ + "ops.scheduler.cogvideoxddim", + "scheduler" + ], + [ + "ops.scheduler.cogvideoxdpm", + "scheduler" + ] + ] + } + } + }, + "info.dit.cogview3": { + "*": { + "repo": "zai-org/CogView3-Plus-3B", + "pkg": { + "0": { + "diffusers": "CogView3PlusPipeline" + } + }, + "tasks": [ + "CogView3PlusPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogview3" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "CogView3PlusTransformer2DModel" + ], + "scheduler": [ + [ + "ops.scheduler.cogvideoxddim", + "scheduler" + ], + [ + "ops.scheduler.cogvideoxdpm", + "scheduler" + ] + ] + } + } + }, + "info.dit.cogview4": { + "*": { + "repo": "zai-org/CogView4-6B", + "pkg": { + "0": { + "diffusers": "CogView4Pipeline" + } + }, + "tasks": [ + "CogView4ControlPipeline", + "CogView4Pipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogview4" + ], + "text_encoder": [ + "GlmModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "CogView4Transformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.controlnet.cogview4-control": { + "*": { + "repo": "zai-org/CogView4-6B-Control", + "pkg": { + "0": { + "diffusers": "CogView4ControlPipeline" + } + } + } + }, + "info.dit.pre-trianed": { + "*": { + "repo": "model_id, revision=\"diffusers/base/pre-trianed", + "pkg": { + "0": { + "diffusers": "Cosmos2_5_PredictBasePipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "pre-trianed" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] + } + } + }, + "info.dit.cosmos-predict2-text2image": { + "*": { + "repo": "nvidia/Cosmos-Predict2-2B-Text2Image", + "pkg": { + "0": { + "diffusers": "Cosmos2TextToImagePipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-predict2-text2image" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] + } + } + }, + "info.dit.cosmos-predict2-video2world": { + "*": { + "repo": "nvidia/Cosmos-Predict2-2B-Video2World", + "pkg": { + "0": { + "diffusers": "Cosmos2VideoToWorldPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-predict2-video2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] + } + } + }, + "info.dit.cosmos-1-diffusion-text2world": { + "*": { + "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Text2World", + "pkg": { + "0": { + "diffusers": "CosmosTextToWorldPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-1-diffusion-text2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "cosmos-1-diffusion-video2world" + ], + "scheduler": [ + "ops.scheduler.edmeuler", + "scheduler" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] + } + } + }, + "info.dit.cosmos-1-diffusion-video2world": { + "*": { + "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Video2World", + "pkg": { + "0": { + "diffusers": "CosmosVideoToWorldPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-1-diffusion-video2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "cosmos-1-diffusion-video2world" + ], + "scheduler": [ + "ops.scheduler.edmeuler", + "scheduler" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] + } + } + }, + "info.unet.if-i-xl-v1": { + "*": { + "repo": "DeepFloyd/IF-I-XL-v1.0", + "pkg": { + "0": { + "diffusers": "IFPipeline" + } + }, + "tasks": [ + "IFImg2ImgPipeline", + "IFInpaintingPipeline", + "IFPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "if-i-xl-v1" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "scheduler": [ + "ops.scheduler.ddpm", + "scheduler" + ] + } + } + }, + "info.dit.easyanimatev5-zh": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimatePipeline" + } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "easyanimatev5-zh" + ], + "text_encoder": [ + "Qwen2VLForConditionalGeneration", + "BertModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "easyanimatev5-zh" + ], + "transformer": [ + "EasyAnimateTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.controlnet.easyanimatev5-zh-control": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-Control-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimateControlPipeline" + } + } + } + }, + "info.dit.easyanimatev5-zh-inp": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-InP-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimateInpaintPipeline" + } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "easyanimatev5-zh" + ], + "text_encoder": [ + "Qwen2VLForConditionalGeneration", + "BertModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "easyanimatev5-zh-inp" + ], + "transformer": [ + "EasyAnimateTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.hidream-i1": { + "*": { + "repo": "HiDream-ai/HiDream-I1-Full", + "pkg": { + "0": { + "diffusers": "HiDreamImagePipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_3": [ + "T5EncoderModel" + ], + "tokenizer_3": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_4": [ + "LlamaForCausalLM" + ], + "tokenizer_4": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "transformer": [ + "HiDreamImageTransformer2DModel" + ] + } + } + }, + "info.dit.hunyuandit-v1": { + "diffusers": { + "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanDiTPipeline" + } + }, + "tasks": [ + "HunyuanDiTPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "BertModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuandit-v1" + ], + "transformer": [ + "HunyuanDiT2DModel" + ], + "scheduler": [ + "ops.scheduler.ddpm", + "scheduler" + ], + "safety_checker": [ + "StableDiffusionSafetyChecker" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuandit-v1" + ] + } + } + }, + "info.dit.hunyuanvideo": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo", + "pkg": { + "0": { + "diffusers": "HunyuanVideoPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "LlamaModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo" + ], + "transformer": [ + "HunyuanVideoTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo" + ] + } + } + }, + "info.dit.hunyuanvideo-i2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-I2V", + "pkg": { + "0": { + "diffusers": "HunyuanVideoImageToVideoPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "LlavaForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-i2v" + ], + "transformer": [ + "HunyuanVideoTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-i2v" + ], + "image_processor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.hunyuanvideo-1-480p-t2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_t2v", + "pkg": { + "0": { + "diffusers": "HunyuanVideo15Pipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "Qwen2_5_VLTextModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-t2v" + ], + "transformer": [ + "HunyuanVideo15Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-t2v" + ], + "guider": [ + "ClassifierFreeGuidance" + ] + } + } + }, + "info.dit.hunyuanvideo-1-480p-i2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_i2v", + "pkg": { + "0": { + "diffusers": "HunyuanVideo15ImageToVideoPipeline" + } + }, + "pipe_names": { + "text_encoder": [ + "Qwen2_5_VLTextModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-i2v" + ], + "transformer": [ + "HunyuanVideo15Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-i2v" + ], + "guider": [ + "ClassifierFreeGuidance" + ], + "image_encoder": [ + "SiglipVisionModel" + ], + "feature_extractor": [ + "SiglipImageProcessor" + ] + } + } + }, + "info.dit.hunyuanimage-2": { + "diffusers": { + "repo": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanImagePipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanimage-2" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanimage-2" + ], + "transformer": [ + "HunyuanImageTransformer2DModel" + ] + } + } + }, + "info.dit.hunyuanimage-2-refiner": { + "diffusers": { + "repo": "hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanImageRefinerPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanimage-2-refiner" + ], + "transformer": [ + "HunyuanImageTransformer2DModel" + ] + } + } + }, + "info.unet.kandinsky-2-1": { + "prior": { + "repo": "kandinsky-community/kandinsky-2-1-prior", + "pkg": { + "0": { + "diffusers": "KandinskyPriorPipeline" + } + }, + "tasks": [ + "Kandinsky3Img2ImgPipeline", + "Kandinsky3Pipeline", + "KandinskyCombinedPipeline", + "KandinskyImg2ImgCombinedPipeline", + "KandinskyImg2ImgPipeline", + "KandinskyInpaintCombinedPipeline", + "KandinskyInpaintPipeline", + "KandinskyPipeline", + "KandinskyV22CombinedPipeline", + "KandinskyV22Img2ImgCombinedPipeline", + "KandinskyV22Img2ImgPipeline", + "KandinskyV22InpaintCombinedPipeline", + "KandinskyV22InpaintPipeline", + "KandinskyV22Pipeline" + ], + "pipe_names": { + "prior": [ + "PriorTransformer" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-2-1" + ], + "scheduler": [ + "ops.scheduler.unclip", + "scheduler" + ], + "image_processor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.unet.kandinsky-2-2": { + "prior": { + "repo": "kandinsky-community/kandinsky-2-2-prior", + "pkg": { + "0": { + "diffusers": "KandinskyPriorPipeline" + } + }, + "tasks": [ + "Kandinsky3Img2ImgPipeline", + "Kandinsky3Pipeline", + "KandinskyCombinedPipeline", + "KandinskyImg2ImgCombinedPipeline", + "KandinskyImg2ImgPipeline", + "KandinskyInpaintCombinedPipeline", + "KandinskyInpaintPipeline", + "KandinskyPipeline", + "KandinskyV22CombinedPipeline", + "KandinskyV22Img2ImgCombinedPipeline", + "KandinskyV22Img2ImgPipeline", + "KandinskyV22InpaintCombinedPipeline", + "KandinskyV22InpaintPipeline", + "KandinskyV22Pipeline" + ], + "pipe_names": { + "prior": [ + "PriorTransformer" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-2-2" + ], + "scheduler": [ + "ops.scheduler.unclip", + "scheduler" + ], + "image_processor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.dit.latte-1": { + "*": { + "repo": "maxin-cn/Latte-1", + "pkg": { + "0": { + "diffusers": "LattePipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "latte-1" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "LatteTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + } + } + }, + "info.dit.ltx-video": { + "*": { + "repo": "Lightricks/LTX-Video", + "pkg": { + "0": { + "diffusers": "LTXImageToVideoPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "ltx-video" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ltx-video" + ], + "transformer": [ + "LTXVideoTransformer3DModel" + ] + } + } + }, + "info.dit.ltx-video-09": { + "*": { + "repo": "Lightricks/LTX-Video-0.9.5", + "pkg": { + "0": { + "diffusers": "LTXConditionPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "ltx-video" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ltx-video-09" + ], + "transformer": [ + "LTXVideoTransformer3DModel" + ] + } + } + }, + "info.dit.lumina-next-sft": { + "diffusers": { + "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", + "pkg": { + "0": { + "diffusers": "LuminaPipeline" + } + }, + "tasks": [ + "Lumina2Pipeline", + "LuminaPipeline" + ], + "pipe_names": { + "transformer": [ + "LuminaNextDiT2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "GemmaPreTrainedModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "lumina-next-sft" + ] + } + } + }, + "info.dit.lumina-image-2": { + "*": { + "repo": "Alpha-VLLM/Lumina-Image-2.0", + "pkg": { + "0": { + "diffusers": "Lumina2Pipeline" + } + }, + "tasks": [ + "Lumina2Pipeline" + ], + "pipe_names": { + "transformer": [ + "Lumina2Transformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Gemma2PreTrainedModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "lumina-image-2" + ] + } + }, + "illustrious-lumina-v3": { + "repo": "OnomaAIResearch/Illustrious-Lumina-v0.03", + "file_256": [ + "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", + "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214" + ], + "layer_256": [ + "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", + "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828" + ], + "layer_b3": [ + "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", + "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c" + ] + } + }, + "info.dit.longcat-image": { + "*": { + "repo": "meituan-longcat/LongCat-Image", + "pkg": { + "0": { + "diffusers": "LongCatImagePipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "longcat-image" + ], + "text_processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "LongCatImageTransformer2DModel" + ] + } + } + }, + "info.dit.longcat-image-edit": { + "*": { + "repo": "meituan-longcat/LongCat-Image-Edit", + "pkg": { + "0": { + "diffusers": "LongCatImageEditPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "longcat-image-edit" + ], + "text_processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "LongCatImageTransformer2DModel" + ] + } + } + }, + "info.dit.mochi-1": { + "*": { + "repo": "genmo/mochi-1-preview", + "pkg": { + "0": { + "diffusers": "MochiPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "mochi-1" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "mochi-1" + ], + "transformer": [ + "MochiTransformer3DModel" + ] + } + } + }, + "info.unet.musicldm": { + "*": { + "repo": "ucsd-reach/musicldm", + "pkg": { + "0": { + "diffusers": "MusicLDMPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "ClapTextModelWithProjection", + "ClapModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "musicldm" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vocoder": [ + "SpeechT5HifiGan" + ] + } + } + }, + "info.dit.omnigen-v1": { + "diffusers": { + "repo": "Shitao/OmniGen-v1-diffusers", + "pkg": { + "0": { + "diffusers": "OmniGenPipeline" + } + }, + "pipe_names": { + "transformer": [ + "OmniGenTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "omnigen-v1" + ] + } + } + }, + "info.dit.ovis-image": { + "*": { + "repo": "AIDC-AI/Ovis-Image-7B", + "pkg": { + "0": { + "diffusers": "OvisImagePipeline" + } + }, + "tasks": [ + "OvisImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Qwen3Model" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ovis-image" + ], + "transformer": [ + "OvisImageTransformer2DModel" + ] + } + } + }, + "info.dit.visualclozepipeline-384": { + "*": { + "repo": "VisualCloze/VisualClozePipeline-384", + "pkg": { + "0": { + "diffusers": "VisualClozeGenerationPipeline" + } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "visualclozepipeline-384" + ], + "text_encoder_2": [ + "T5EncoderModel" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "visualclozepipeline-384" + ], + "transformer": [ + "FluxTransformer2DModel" + ] + } + } + }, + "info.dit.pixart-xl-2-1024-ms": { + "*": { + "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", + "pkg": { + "0": { + "diffusers": "PixArtAlphaPipeline" + } + }, + "tasks": [ + "PixArtAlphaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "pixart-xl-2-1024-ms" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "PixArtTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] + } + } + }, + "info.dit.pixart-sigma-xl-2-1024-ms": { + "*": { + "repo": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", + "pkg": { + "0": { + "diffusers": "PixArtSigmaPipeline" + } + }, + "tasks": [ + "PixArtAlphaPipeline", + "PixArtSigmaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "pixart-sigma-xl-2-1024-ms" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "PixArtTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + } + } + }, + "info.dit.sana-1024px-bf16": { + "diffusers": { + "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", + "pkg": { + "0": { + "diffusers": "SanaPipeline" + } + }, + "tasks": [ + "SanaPAGPipeline", + "SanaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "sana-1024px-bf16" + ], + "text_encoder": [ + "Gemma2PreTrainedModel" + ], + "vae": [ + "info.vae.dc", + "sana-1024px-bf16" + ], + "transformer": [ + "SanaTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] + } + } + }, + "info.controlnet.sana-1024px-controlnet": { + "diffusers": { + "repo": "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers", + "pkg": { + "0": { + "diffusers": "SanaControlNetPipeline" + } + } + } + }, + "info.dit.sana-sprint-1024px": { + "diffusers": { + "repo": "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", + "pkg": { + "0": { + "diffusers": "SanaSprintPipeline" + } + }, + "tasks": [ + "SanaPAGPipeline", + "SanaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "sana-sprint-1024px" + ], + "text_encoder": [ + "Gemma2PreTrainedModel" + ], + "vae": [ + "info.vae.dc", + "sana-1024px-bf16" + ], + "transformer": [ + "SanaTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] + } + } + }, + "info.dit.sana-video": { + "*": { + "repo": "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", + "pkg": { + "0": { + "diffusers": "SanaImageToVideoPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "sana-video" + ], + "text_encoder": [ + "Gemma2PreTrainedModel" + ], + "vae": [ + [ + "info.vae.dc", + "sana-1024px-bf16" + ], + [ + "info.vae.kl", + "audioldm-s-v2" + ] + ], + "transformer": [ + "SanaVideoTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.unet.shap-e": { + "*": { + "repo": "openai/shap-e", + "pkg": { + "0": { + "diffusers": "ShapEPipeline" + } + }, + "pipe_names": { + "prior": [ + "PriorTransformer" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "shap-e" + ], + "scheduler": [ + "ops.scheduler.heun", + "discrete" + ], + "shap_e_renderer": [ + "ShapERenderer" + ] + } + } + }, + "info.dit.stable-audio-open-1": { + "*": { + "repo": "stabilityai/stable-audio-open-1.0", + "pkg": { + "0": { + "diffusers": "StableAudioPipeline" + } + }, + "pipe_names": { + "vae": [ + "info.vae.oobleck", + "stable-audio-open-1" + ], + "text_encoder": [ + "T5EncoderModel" + ], + "projection_model": [ + "StableAudioProjectionModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-audio-open-1" + ], + "transformer": [ + "StableAudioDiTModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] + } + } + }, + "info.unet.stable-cascade": { + "prior": { + "repo": "stabilityai/stable-cascade-prior", + "pkg": { + "0": { + "diffusers": "StableCascadePriorPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "stable-cascade" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "prior": [ + "StableCascadeUNet" + ], + "scheduler": [ + "ops.scheduler.ddpmwuerstchen", + "scheduler" + ] + } + } + }, + "info.unet.flux1-dev": { + "decoder": { + "repo": "black-forest-labs/FLUX.1-dev", + "pkg": { + "0": { + "diffusers": "WuerstchenDecoderPipeline" + } + }, + "tasks": [ + "WuerstchenCombinedPipeline", + "WuerstchenDecoderPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-dev" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "decoder": [ + "WuerstchenDiffNeXt" + ], + "scheduler": [ + "ops.scheduler.ddpmwuerstchen", + "scheduler" + ], + "vqgan": [ + "PaellaVQModel" + ] + } + } + }, + "info.dit.auraflow": { + "*": { + "repo": "fal/AuraFlow", + "pkg": { + "0": { + "diffusers": "AuraFlowPipeline" + } + }, + "tasks": [ + "AuraFlowPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "auraflow" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "AuraFlowTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.stable-diffusion-3": { + "*": { + "repo": "stabilityai/stable-diffusion-3.5-medium", + "pkg": { + "0": { + "diffusers": "StableDiffusion3Pipeline" + } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline" + ], + "pipe_names": { + "transformer": [ + "SD3Transformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.tae", + "stable-diffusion-3" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-3" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "stable-diffusion-3" + ], + "text_encoder_3": [ + "T5EncoderModel" + ], + "tokenizer_3": [ + "info.encoder.tokenizer", + "stable-diffusion-3" + ], + "image_encoder": [ + "SiglipVisionModel" + ], + "feature_extractor": [ + "SiglipImageProcessor" + ] + } + }, + "stable-diffusion-3-turbo": { + "repo": "tensorart/stable-diffusion-3.5-medium-turbo", + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "num_inference_steps": 8, + "guidance_scale": 1.5, + "height": 1024, + "width": 768 + } + } + }, + "file_256": [ + "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", + "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", + "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", + "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e" + ], + "layer_256": [ + "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", + "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", + "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", + "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" + ], + "layer_b3": [ + "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", + "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", + "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", + "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" + ] + } + }, + "info.unet.gligen-1-4-inpainting-text-box": { + "*": { + "repo": "masterful/gligen-1-4-inpainting-text-box", + "pkg": { + "0": { + "diffusers": "StableDiffusionGLIGENPipeline" + } + } + } + }, + "info.unet.gligen-inpainting-text-image": { + "*": { + "repo": "anhnct/Gligen_Inpainting_Text_Image", + "pkg": { + "0": { + "diffusers": "StableDiffusionGLIGENTextImagePipeline" + } + } + } + }, + "info.unet.stable-video-diffusion-img2vid-xt": { + "*": { + "repo": "stabilityai/stable-video-diffusion-img2vid-xt", + "pkg": { + "0": { + "diffusers": "StableVideoDiffusionPipeline" + } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "unet": [ + "UNetSpatioTemporalConditionModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.unet.ldm3d-4c": { + "*": { + "repo": "Intel/ldm3d-4c", + "pkg": { + "0": { + "diffusers": "StableDiffusionLDM3DPipeline" + } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ldm3d-4c" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "safety_checker": [ + "StableDiffusionSafetyChecker" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.unet.i2vgen-xl": { + "*": { + "repo": "ali-vilab/i2vgen-xl", + "pkg": { + "0": { + "diffusers": "I2VGenXLPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "i2vgen-xl" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ], + "unet": [ + "I2VGenXLUNet" + ], + "scheduler": [ + "ops.scheduler.ddim", + "scheduler" + ] + } + } + }, + "info.unet.wuerstchen": { + "prior": { + "repo": "warp-ai/wuerstchen-prior", + "pkg": { + "0": { + "diffusers": "WuerstchenPriorPipeline" + } + }, + "tasks": [ + "WuerstchenCombinedPipeline", + "WuerstchenDecoderPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wuerstchen" + ], + "text_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "prior": [ + "WuerstchenPrior" + ], + "scheduler": [ + "ops.scheduler.ddpmwuerstchen", + "scheduler" + ] + } + } + }, + "info.dit.wan2-t2v": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanPipeline" + } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan2-t2v" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.wan-animate": { + "diffusers": { + "repo": "Wan-AI/Wan2.2-Animate-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanAnimatePipeline" + } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan-animate" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ], + "image_processor": [ + "CLIPImageProcessor" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "transformer": [ + "WanAnimateTransformer3DModel" + ] + } + } + }, + "info.dit.wan2-i2v-480p": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", + "pkg": { + "0": { + "diffusers": "WanImageToVideoPipeline" + } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan2-i2v-480p" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "vae": [ + "info.vae.wan", + "wan2-i2v-480p" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "image_processor": [ + "CLIPImageProcessor" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "transformer": [ + "WanTransformer3DModel" + ], + "transformer_2": [ + "WanTransformer3DModel" + ] + } + } + }, + "info.dit.wan21-vace": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-VACE-1.3B-diffusers", + "pkg": { + "0": { + "diffusers": "WanVACEPipeline" + } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan21-vace" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "transformer": [ + "WanVACETransformer3DModel" + ], + "transformer_2": [ + "WanVACETransformer3DModel" + ] + } + } + }, + "info.dit.wan21-t2v": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanVideoToVideoPipeline" + } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan21-t2v" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "transformer": [ + "WanTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.kandinsky-5-t2v-lite-sft-5s": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5T2VPipeline" + } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-t2v-lite-sft-5s" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-t2v-lite-sft-5s" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.kandinsky-5-i2i-lite-sft": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5I2IPipeline" + } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-i2i-lite-sft" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-i2i-lite-sft" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.kandinsky-5-i2v-sft-5s": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5I2VPipeline" + } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-i2v-sft-5s" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-i2v-sft-5s" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.kandinsky-5-t2i-lite-sft": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5T2IPipeline" + } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-t2i-lite-sft" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch14", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-t2i-lite-sft" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.dit.z-image-turbo": { + "*": { + "repo": "Z-a-o/Z-Image-Turbo", + "pkg": { + "0": { + "diffusers": "ZImageOmniPipeline" + } + }, + "tasks": [ + "ZImageControlNetInpaintPipeline", + "ZImageControlNetPipeline", + "ZImageImg2ImgPipeline", + "ZImageOmniPipeline", + "ZImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "PreTrainedModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "z-image-turbo" + ], + "transformer": [ + "ZImageTransformer2DModel" + ], + "siglip": [ + "Siglip2VisionModel" + ], + "siglip_processor": [ + "Siglip2ImageProcessorFast" + ] + } + } + }, + "info.controlnet.z-image-turbo": { + "*": { + "repo": "Tongyi-MAI/Z-Image-Turbo", + "pkg": { + "0": { + "diffusers": "ZImageControlNetInpaintPipeline" + } + } + } + }, + "info.dit.skyreels-v2-t2v-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2Pipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-t2v-720p" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] + } + } + }, + "info.dit.skyreels-v2-df-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-DF-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-df-720p" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] + } + } + }, + "info.dit.skyreels-v2-i2v-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-I2V-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2ImageToVideoPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-i2v-720p" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "image_processor": [ + "CLIPProcessor" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] + } + } + }, + "info.dit.qwen-image": { + "*": { + "repo": "Qwen/Qwen-Image", + "pkg": { + "0": { + "diffusers": "QwenImageInpaintPipeline" + } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image" + ], + "transformer": [ + "QwenImageTransformer2DModel" + ] + } + } + }, + "info.controlnet.qwen-image-controlnet-union": { + "*": { + "repo": "InstantX/Qwen-Image-ControlNet-Union", + "pkg": { + "0": { + "diffusers": "QwenImageControlNetModel" + } + } + } + }, + "info.controlnet.qwen-image-controlnet-inpainting": { + "*": { + "repo": "InstantX/Qwen-Image-ControlNet-Inpainting", + "pkg": { + "0": { + "diffusers": "QwenImageControlNetModel" + } + } + } + }, + "info.dit.qwen-image-edit": { + "*": { + "repo": "Qwen/Qwen-Image-Edit", + "pkg": { + "0": { + "diffusers": "QwenImageEditInpaintPipeline" + } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-edit" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "QwenImageTransformer2DModel" + ] + } + } + }, + "info.dit.qwen-image-edit-2509": { + "*": { + "repo": "Qwen/Qwen-Image-Edit-2509", + "pkg": { + "0": { + "diffusers": "QwenImageEditPlusPipeline" + } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-edit-2509" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "QwenImageTransformer2DModel" + ] + } + } + }, + "info.dit.qwen-image-layered": { + "*": { + "repo": "Qwen/Qwen-Image-Layered", + "pkg": { + "0": { + "diffusers": "QwenImageLayeredPipeline" + } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-layered" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "QwenImageTransformer2DModel" + ] + } + } + }, + "info.dit.chronoedit": { + "diffusers": { + "repo": "nvidia/ChronoEdit-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "ChronoEditPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "chronoedit" + ], + "text_encoder": [ + "UMT5EncoderModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "image_processor": [ + "CLIPImageProcessor" + ], + "transformer": [ + "ChronoEditTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, + "info.unet.kolors": { + "diffusers": { + "repo": "Kwai-Kolors/Kolors-diffusers", + "pkg": { + "0": { + "diffusers": "KolorsPipeline" + } + }, + "tasks": [ + "KolorsImg2ImgPipeline", + "KolorsPAGPipeline", + "KolorsPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "ChatGLMModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kolors" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_encoder": [ + "info.vit.clip-vit-patch14", + "*" + ], + "feature_extractor": [ + "CLIPImageProcessor" + ] + } + } + }, + "info.encoder.tokenizer": { + "omdet-turbo-swin-hf": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "blip2-opt": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "deberta-v2-x": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "bert-for-seq-generation-l-24-bbc-encoder": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "20": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "21": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "22": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "wav2vec2-bert-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "nllb-moe": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "efficient-mlm-m0-0": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "xlm-roberta": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "mgp-str": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "blenderbot": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "20": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "21": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "22": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "23": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "xlm-roberta-xl": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "megatron-bert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "grounding-dino": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "funnel": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "wav2vec2-conformer-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "mm-grounding-dino-o365v1-goldg-v3det": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "gpt2": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + } + }, + "info.detr.omdet-turbo-swin-hf": { + "*": { + "repo": "omlab/omdet-turbo-swin-tiny-hf", + "pkg": { + "0": { + "transformers": "OmDetTurboForObjectDetection" + } + }, + "tasks": [ + "OmDetTurboForObjectDetection", + "OmDetTurboPreTrainedModel" + ] + } + }, + "info.vit.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2Model" + } + }, + "tasks": [ + "Blip2Model", + "Blip2VisionModelWithProjection", + "Blip2QFormerModel", + "Blip2PreTrainedModel", + "Blip2ForConditionalGeneration", + "Blip2ForImageTextRetrieval", + "Blip2VisionModel", + "Blip2TextModelWithProjection" + ] + } + }, + "info.art.deberta-v2-x": { + "*": { + "repo": "microsoft/deberta-v2-xlarge", + "pkg": { + "0": { + "transformers": "DebertaV2Model" + } + }, + "tasks": [ + "DebertaV2ForMaskedLM", + "DebertaV2ForMultipleChoice", + "DebertaV2ForQuestionAnswering", + "DebertaV2ForSequenceClassification", + "DebertaV2ForTokenClassification", + "DebertaV2Model", + "DebertaV2PreTrainedModel" + ] + } + }, + "info.vit.ast-finetuned-audioset-10-10-0593": { + "*": { + "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "pkg": { + "0": { + "transformers": "ASTModel" + } + }, + "tasks": [ + "ASTForAudioClassification", + "ASTModel", + "ASTPreTrainedModel" + ] + } + }, + "info.detr.dab-detr": { + "*": { + "repo": "IDEA-Research/dab-detr-resnet-50", + "pkg": { + "0": { + "transformers": "DabDetrModel" + } + }, + "tasks": [ + "DabDetrForObjectDetection", + "DabDetrModel", + "DabDetrPreTrainedModel" + ] + } + }, + "info.aet.sew-d": { + "*": { + "repo": "asapp/sew-d-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWDModel" + } + }, + "tasks": [ + "SEWDForCTC", + "SEWDForSequenceClassification", + "SEWDModel", + "SEWDPreTrainedModel" + ] + } + }, + "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "*": { + "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "pkg": { + "0": { + "transformers": "BertGenerationEncoder" + } + }, + "tasks": [ + "BertGenerationDecoder", + "BertGenerationEncoder", + "BertGenerationPreTrainedModel" + ] + } + }, + "info.aet.wav2vec2-bert-rel-pos": { + "*": { + "repo": "facebook/w2v-bert-2.0", + "pkg": { + "0": { + "transformers": "Wav2Vec2BertModel" + } + }, + "tasks": [ + "Wav2Vec2BertForAudioFrameClassification", + "Wav2Vec2BertForCTC", + "Wav2Vec2BertForSequenceClassification", + "Wav2Vec2BertForXVector", + "Wav2Vec2BertModel", + "Wav2Vec2BertPreTrainedModel" + ] + } + }, + "info.stst.nllb-moe": { + "*": { + "repo": "facebook/nllb-moe-54b", + "pkg": { + "0": { + "transformers": "NllbMoeModel" + } + }, + "tasks": [ + "NllbMoeForConditionalGeneration", + "NllbMoeModel", + "NllbMoePreTrainedModel", + "NllbMoeTop2Router", + "NllbMoeSparseMLP" + ] + } + }, + "info.art.efficient-mlm-m0-0": { + "*": { + "repo": "andreasmadsen/efficient_mlm_m0.40", + "pkg": { + "0": { + "transformers": "RobertaPreLayerNormModel" + } + }, + "tasks": [ + "RobertaPreLayerNormForCausalLM", + "RobertaPreLayerNormForMaskedLM", + "RobertaPreLayerNormForMultipleChoice", + "RobertaPreLayerNormForQuestionAnswering", + "RobertaPreLayerNormForSequenceClassification", + "RobertaPreLayerNormForTokenClassification", + "RobertaPreLayerNormModel", + "RobertaPreLayerNormPreTrainedModel" + ] + } + }, + "info.art.xlm-roberta": { + "*": { + "repo": "FacebookAI/xlm-roberta-base", + "pkg": { + "0": { + "transformers": "XLMRobertaModel" + } + }, + "tasks": [ + "XLMRobertaForCausalLM", + "XLMRobertaForMaskedLM", + "XLMRobertaForMultipleChoice", + "XLMRobertaForQuestionAnswering", + "XLMRobertaForSequenceClassification", + "XLMRobertaForTokenClassification", + "XLMRobertaModel", + "XLMRobertaPreTrainedModel" + ] + } + }, + "info.vit.mgp-str": { + "*": { + "repo": "alibaba-damo/mgp-str-base", + "pkg": { + "0": { + "transformers": "MgpstrForSceneTextRecognition" + } + }, + "tasks": [ + "MgpstrModel", + "MgpstrPreTrainedModel", + "MgpstrForSceneTextRecognition" + ] + } + }, + "info.stst.blenderbot": { + "*": { + "repo": "facebook/blenderbot_small-90M", + "pkg": { + "0": { + "transformers": "BlenderbotSmallModel" + } + }, + "tasks": [ + "BlenderbotSmallForCausalLM", + "BlenderbotSmallForConditionalGeneration", + "BlenderbotSmallModel", + "BlenderbotSmallPreTrainedModel" + ] + } + }, + "info.art.xlm-roberta-xl": { + "*": { + "repo": "facebook/xlm-roberta-xl", + "pkg": { + "0": { + "transformers": "XLMRobertaXLModel" + } + }, + "tasks": [ + "XLMRobertaXLForCausalLM", + "XLMRobertaXLForMaskedLM", + "XLMRobertaXLForMultipleChoice", + "XLMRobertaXLForQuestionAnswering", + "XLMRobertaXLForSequenceClassification", + "XLMRobertaXLForTokenClassification", + "XLMRobertaXLModel", + "XLMRobertaXLPreTrainedModel" + ] + } + }, + "info.art.megatron-bert-uncased": { + "*": { + "repo": "nvidia/megatron-bert-uncased-345m", + "pkg": { + "0": { + "transformers": "MegatronBertModel" + } + }, + "tasks": [ + "MegatronBertForCausalLM", + "MegatronBertForMaskedLM", + "MegatronBertForMultipleChoice", + "MegatronBertForNextSentencePrediction", + "MegatronBertForPreTraining", + "MegatronBertForQuestionAnswering", + "MegatronBertForSequenceClassification", + "MegatronBertForTokenClassification", + "MegatronBertModel", + "MegatronBertPreTrainedModel" + ] + } + }, + "info.detr.grounding-dino": { + "*": { + "repo": "IDEA-Research/grounding-dino-tiny", + "pkg": { + "0": { + "transformers": "GroundingDinoModel" + } + }, + "tasks": [ + "GroundingDinoForObjectDetection", + "GroundingDinoModel", + "GroundingDinoPreTrainedModel" + ] + } + }, + "info.detr.table-transformer-detection": { + "*": { + "repo": "microsoft/table-transformer-detection", + "pkg": { + "0": { + "transformers": "TableTransformerModel" + } + }, + "tasks": [ + "TableTransformerForObjectDetection", + "TableTransformerModel", + "TableTransformerPreTrainedModel" + ] + } + }, + "info.aet.funnel": { + "*": { + "repo": "funnel-transformer/small", + "pkg": { + "0": { + "transformers": "FunnelModel" + } + }, + "tasks": [ + "FunnelBaseModel", + "FunnelForMaskedLM", + "FunnelForMultipleChoice", + "FunnelForPreTraining", + "FunnelForQuestionAnswering", + "FunnelForSequenceClassification", + "FunnelForTokenClassification", + "FunnelModel", + "FunnelPreTrainedModel" + ] + } + }, + "info.aet.unispeech-sat-100h-libri-ft": { + "*": { + "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "pkg": { + "0": { + "transformers": "UniSpeechSatModel" + } + }, + "tasks": [ + "UniSpeechSatForAudioFrameClassification", + "UniSpeechSatForCTC", + "UniSpeechSatForPreTraining", + "UniSpeechSatForSequenceClassification", + "UniSpeechSatForXVector", + "UniSpeechSatModel", + "UniSpeechSatPreTrainedModel" + ] + } + }, + "info.aet.wav2vec2-conformer-rel-pos": { + "*": { + "repo": "facebook/wav2vec2-conformer-rel-pos-large", + "pkg": { + "0": { + "transformers": "Wav2Vec2ConformerModel" + } + }, + "tasks": [ + "Wav2Vec2ConformerForAudioFrameClassification", + "Wav2Vec2ConformerForCTC", + "Wav2Vec2ConformerForPreTraining", + "Wav2Vec2ConformerForSequenceClassification", + "Wav2Vec2ConformerForXVector", + "Wav2Vec2ConformerModel", + "Wav2Vec2ConformerPreTrainedModel" + ] + } + }, + "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "*": { + "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "pkg": { + "0": { + "transformers": "MMGroundingDinoModel" + } + }, + "tasks": [ + "MMGroundingDinoForObjectDetection", + "MMGroundingDinoModel", + "MMGroundingDinoPreTrainedModel" + ] + } + }, + "info.art.gpt2": { + "*": { + "repo": "openai-community/gpt2", + "pkg": { + "0": { + "transformers": "GPT2Model" + } + }, + "tasks": [ + "GPT2DoubleHeadsModel", + "GPT2ForQuestionAnswering", + "GPT2ForSequenceClassification", + "GPT2ForTokenClassification", + "GPT2LMHeadModel", + "GPT2Model", + "GPT2PreTrainedModel" + ] + } + }, + "ops.precision.uint": { + "U8": { + "pkg": { + "0": { + "torch": { + "uint8": { + "variant": "uint8" + } + } + } + } + }, + "U16": { + "pkg": { + "0": { + "torch": { + "uint16": { + "variant": "uint16" + } + } + } + } + }, + "U32": { + "pkg": { + "0": { + "torch": { + "uint32": { + "variant": "uint32" + } + } + } + } + }, + "U64": { + "pkg": { + "0": { + "torch": { + "uint64": { + "variant": "uint64" + } + } + } + } + }, + "U1": { + "pkg": { + "0": { + "torch": { + "uint1": { + "variant": "uint1" + } + } + } + } + }, + "U2": { + "pkg": { + "0": { + "torch": { + "uint2": { + "variant": "uint2" + } + } + } + } + }, + "U3": { + "pkg": { + "0": { + "torch": { + "uint3": { + "variant": "uint3" + } + } + } + } + }, + "U4": { + "pkg": { + "0": { + "torch": { + "uint4": { + "variant": "uint4" + } + } + } + } + }, + "U5": { + "pkg": { + "0": { + "torch": { + "uint5": { + "variant": "uint5" + } + } + } + } + }, + "U6": { + "pkg": { + "0": { + "torch": { + "uint6": { + "variant": "uint6" + } + } + } + } + }, + "U7": { + "pkg": { + "0": { + "torch": { + "uint7": { + "variant": "uint7" + } + } + } + } + } + }, + "ops.precision.int": { + "I8": { + "pkg": { + "0": { + "torch": { + "int8": { + "variant": "int8" + } + } + } + } + }, + "I16": { + "pkg": { + "0": { + "torch": { + "int16": { + "variant": "int16" + } + } + } + } + }, + "I32": { + "pkg": { + "0": { + "torch": { + "int32": { + "variant": "int32" + } + } + } + } + }, + "I64": { + "pkg": { + "0": { + "torch": { + "int64": { + "variant": "int64" + } + } + } + } + }, + "Q8": { + "pkg": { + "0": { + "torch": { + "qint8": { + "variant": "qint8" + } + } + } + } + }, + "Q32": { + "pkg": { + "0": { + "torch": { + "qint32": { + "variant": "qint32" + } + } + } + } + }, + "I1": { + "pkg": { + "0": { + "torch": { + "int1": { + "variant": "int1" + } + } + } + } + }, + "I2": { + "pkg": { + "0": { + "torch": { + "int2": { + "variant": "int2" + } + } + } + } + }, + "I3": { + "pkg": { + "0": { + "torch": { + "int3": { + "variant": "int3" + } + } + } + } + }, + "I4": { + "pkg": { + "0": { + "torch": { + "int4": { + "variant": "int4" + } + } + } + } + }, + "I5": { + "pkg": { + "0": { + "torch": { + "int5": { + "variant": "int5" + } + } + } + } + }, + "I6": { + "pkg": { + "0": { + "torch": { + "int6": { + "variant": "int6" + } + } + } + } + }, + "I7": { + "pkg": { + "0": { + "torch": { + "int7": { + "variant": "int7" + } + } + } + } + } + }, + "ops.precision.float": { + "F16": { + "pkg": { + "0": { + "torch": { + "float16": { + "variant": "fp16" + } + } + } + } + }, + "F32": { + "pkg": { + "0": { + "torch": { + "float32": { + "variant": "fp32" + } + } + } + } + }, + "F64": { + "pkg": { + "0": { + "torch": { + "float64": { + "variant": "fp64" + } + } + } + } + }, + "F8_E5M2": { + "pkg": { + "0": { + "torch": { + "float8_e5m2": { + "variant": "fp8_e5m2" + } + } + } + } + }, + "F8_E4M3": { + "pkg": { + "0": { + "torch": { + "float8_e4m3fn": { + "variant": "fp8_e4m3fn" + } + } + } + } + }, + "F8_E5M2FNUZ": { + "pkg": { + "0": { + "torch": { + "float8_e5m2fnuz": { + "variant": "fp8_e5m2fnuz" + } + } + } + } + }, + "F8_E4M3FNUZ": { + "pkg": { + "0": { + "torch": { + "float8_e4m3fnuz": { + "variant": "fp8_e4m3fnuz" + } + } + } + } + }, + "F8_E8M0FNU": { + "pkg": { + "0": { + "torch": { + "float8_e8m0fnu": { + "variant": "fp8_e8m0fnu" + } + } + } + } + }, + "F8_E2M1": { + "pkg": { + "0": { + "torch": { + "float4_e2m1fn_x2": { + "variant": "fp4_e2m1fn_x2" + } + } + } + } + } + }, + "ops.precision.complex": { + "C32": { + "pkg": { + "0": { + "torch": { + "complex32": { + "variant": "complex32" + } + } + } + } + }, + "C64": { + "pkg": { + "0": { + "torch": { + "complex64": { + "variant": "complex64" + } + } + } + } + }, + "C128": { + "pkg": { + "0": { + "torch": { + "complex128": { + "variant": "complex128" + } + } + } + } + } + }, + "ops.precision.bool": { + "Bbool": { + "pkg": { + "0": { + "torch": { + "bool": { + "variant": "bool" + } + } + } + } + } + }, + "ops.precision.quint": { + "Q8": { + "pkg": { + "0": { + "torch": { + "quint8": { + "variant": "quint8" + } + } + } + } + }, + "Q4x2": { + "pkg": { + "0": { + "torch": { + "quint4x2": { + "variant": "quint4x2" + } + } + } + } + }, + "Q2x4": { + "pkg": { + "0": { + "torch": { + "quint2x4": { + "variant": "quint2x4" + } + } + } + } + } + }, + "ops.precision.bfloat": { + "B16": { + "pkg": { + "0": { + "torch": { + "bfloat16": { + "variant": "bf16" + } + } + } + } + } + }, + "ops.precision.bits": { + "B1x8": { + "pkg": { + "0": { + "torch": { + "bits1x8": { + "variant": "bits1x8" + } + } + } + } + }, + "B2x4": { + "pkg": { + "0": { + "torch": { + "bits2x4": { + "variant": "bits2x4" + } + } + } + } + }, + "B4x2": { + "pkg": { + "0": { + "torch": { + "bits4x2": { + "variant": "bits4x2" + } + } + } + } + }, + "B8": { + "pkg": { + "0": { + "torch": { + "bits8": { + "variant": "bits8" + } + } + } + } + }, + "B16": { + "pkg": { + "0": { + "torch": { + "bits16": { + "variant": "bits16" + } + } + } + } + } + }, + "ops.scheduler.amused": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "AmusedScheduler", + "module_path": "diffusers.schedulers.scheduling_amused" + } + } + } + }, + "ops.scheduler.cmstochasticiterative": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CMStochasticIterativeScheduler", + "module_path": "diffusers.schedulers.scheduling_consistency_models" + } + } + } + }, + "ops.scheduler.cogvideoxddim": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CogVideoXDDIMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_cogvideox" + } + } + } + }, + "ops.scheduler.cogvideoxdpm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CogVideoXDPMScheduler", + "module_path": "diffusers.schedulers.scheduling_dpm_cogvideox" + } + } + } + }, + "ops.scheduler.ddiminverse": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMInverseScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_inverse" + } + } + } + }, + "ops.scheduler.ddimparallel": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMParallelScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_parallel" + } + } + } + }, + "ops.scheduler.ddim": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim" + } + } + } + }, + "ops.scheduler.ddpmparallel": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMParallelScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm_parallel" + } + } + } + }, + "ops.scheduler.ddpm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm" + } + } + } + }, + "ops.scheduler.ddpmwuerstchen": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMWuerstchenScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm_wuerstchen" + } + } + } + }, + "ops.scheduler.deis": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DEISMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_deis_multistep" + } + } + } + }, + "ops.scheduler.dpminverse": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DPMSolverMultistepInverseScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep_inverse" + } + } + } + }, + "ops.scheduler.dpm": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DPMSolverMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep" + } + } + } + }, + "ops.scheduler.dpmsinglestep": { + "solver": { + "pkg": { + "0": { + "diffusers": "DPMSolverSinglestepScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_singlestep" + } + } + } + }, + "ops.scheduler.edmdpm": { + "multistep": { + "pkg": { + "0": { + "diffusers": "EDMDPMSolverMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_edm_dpmsolver_multistep" + } + } + } + }, + "ops.scheduler.edmeuler": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "EDMEulerScheduler", + "module_path": "diffusers.schedulers.scheduling_edm_euler" + } + } + } + }, + "ops.scheduler.eulerancestral": { + "discrete": { + "pkg": { + "0": { + "diffusers": "EulerAncestralDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_euler_ancestral_discrete" + } + } + } + }, + "ops.scheduler.euler": { + "discrete": { + "pkg": { + "0": { + "diffusers": "EulerDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_euler_discrete" + } + } + } + }, + "ops.scheduler.flowmatcheuler": { + "discrete": { + "pkg": { + "0": { + "diffusers": "FlowMatchEulerDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_euler_discrete" + } + } + } + }, + "ops.scheduler.flowmatchheun": { + "discrete": { + "pkg": { + "0": { + "diffusers": "FlowMatchHeunDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_heun_discrete" + } + } + } + }, + "ops.scheduler.flowmatchlcm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "FlowMatchLCMScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_lcm" + } + } + } + }, + "ops.scheduler.heun": { + "discrete": { + "pkg": { + "0": { + "diffusers": "HeunDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_heun_discrete" + } + } + } + }, + "ops.scheduler.ipndm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "IPNDMScheduler", + "module_path": "diffusers.schedulers.scheduling_ipndm" + } + } + } + }, + "ops.scheduler.karrasve": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "KarrasVeScheduler", + "module_path": "diffusers.schedulers.deprecated.scheduling_karras_ve" + } + } + } + }, + "ops.scheduler.kdpm2ancestral": { + "discrete": { + "pkg": { + "0": { + "diffusers": "KDPM2AncestralDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete" + } + } + } + }, + "ops.scheduler.kdpm2": { + "discrete": { + "pkg": { + "0": { + "diffusers": "KDPM2DiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_k_dpm_2_discrete" + } + } + } + }, + "ops.scheduler.lcm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "LCMScheduler", + "module_path": "diffusers.schedulers.scheduling_lcm" + } + } + } + }, + "ops.scheduler.pndm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "PNDMScheduler", + "module_path": "diffusers.schedulers.scheduling_pndm" + } + } + } + }, + "ops.scheduler.repaint": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "RePaintScheduler", + "module_path": "diffusers.schedulers.scheduling_repaint" + } + } + } + }, + "ops.scheduler.sa": { + "solver": { + "pkg": { + "0": { + "diffusers": "SASolverScheduler", + "module_path": "diffusers.schedulers.scheduling_sasolver" + } + } + } + }, + "ops.scheduler.scm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "SCMScheduler", + "module_path": "diffusers.schedulers.scheduling_scm" + } + } + } + }, + "ops.scheduler.scoresdeve": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "ScoreSdeVeScheduler", + "module_path": "diffusers.schedulers.scheduling_sde_ve" + } + } + } + }, + "ops.scheduler.tcd": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "TCDScheduler", + "module_path": "diffusers.schedulers.scheduling_tcd" + } + } + } + }, + "ops.scheduler.unclip": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "UnCLIPScheduler", + "module_path": "diffusers.schedulers.scheduling_unclip" + } + } + } + }, + "ops.scheduler.unipc": { + "multistep": { + "pkg": { + "0": { + "diffusers": "UniPCMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_unipc_multistep" + } + } + } + }, + "ops.scheduler.vqdiffusion": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "VQDiffusionScheduler", + "module_path": "diffusers.schedulers.scheduling_vq_diffusion" + } + } + } + }, + "ops.scheduler.karrasdiffusion": { + "schedulers": { + "pkg": { + "0": { + "diffusers": "KarrasDiffusionSchedulers", + "module_path": "diffusers.schedulers.scheduling_utils" + } + } + } + }, + "info.lora.dmd": { + "stable-diffusion-xl-1": { + "repo": "tianweiy/DMD2", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0, + "timesteps": [ + 999, + 749, + 499, + 249 + ] + }, + "scheduler": { + "ops.scheduler.lcm": "" + } + } + }, + "file_256": [ + "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", + "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb" + ] + } + }, + "info.lora.dpo": { + "stable-diffusion-xl-1": { + "repo": "radames/sdxl-DPO-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 7.5, + "num_inference_steps": 4 + }, + "scheduler": { + "ops.scheduler.dpm": { + "algorithm_type": "sde-dpmsolver++", + "use_karras_sigmas": true, + "order": 2 + } + } + } + }, + "file_256": [ + "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", + "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad" + ] + } + }, + "info.lora.flash": { + "stable-diffusion-xl-1": { + "repo": "jasperai/flash-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "scheduler": "ops.scheduler.lcm" + } + }, + "file_256": [ + "afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7" + ] + }, + "pixart-alpha": { + "repo": "jasperai/flash-pixart", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b" + ] + }, + "stable-diffusion-3": { + "repo": "jasperai/flash-sd3", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15" + ] + }, + "stable-diffusion-v1-5": { + "repo": "jasperai/flash-sd", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0 + } + } + }, + "file_256": [ + "99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f" + ] + } + }, + "info.lora.hyper": { + "stable-diffusion-xl-1": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + } + } + }, + "file_256": { + "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": { + "num_inference_steps": 12 + }, + "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": { + "num_inference_steps": 8 + }, + "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": { + "num_inference_steps": 1, + "guidance_scale": 0.0 + }, + "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "flux1-dev": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + } + } + }, + "file_256": { + "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-3": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + } + } + }, + "file_256": { + "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": { + "num_inference_steps": 16 + }, + "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": { + "num_inference_steps": 4 + }, + "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": { + "num_inference_steps": 8 + } + } + }, + "stable-diffusion-v1-5": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": { + "num_inference_steps": 12 + }, + "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": { + "num_inference_steps": 8 + }, + "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": { + "num_inference_steps": 1, + "guidance_scale": 0.0 + }, + "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + } + }, + "info.lora.lcm": { + "stable-diffusion-xl-1": { + "repo": "latent-consistency/lcm-lora-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + }, + "scheduler": { + "ops.scheduler.lcm": { + "timestep_spacing": "trailing" + } + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141" + ] + }, + "ssd": { + "repo": "latent-consistency/lcm-lora-ssd-1b", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b" + ] + }, + "segmind-vega": { + "repo": "segmind/Segmind-VegaRT", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "gen_kwargs": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb" + ] + }, + "stable-diffusion-v1-5": { + "repo": "latent-consistency/lcm-lora-sdv1-5", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4" + ] + } + }, + "info.lora.lightning": { + "stable-diffusion-xl-1": { + "repo": "ByteDance/SDXL-Lightning", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0 + } + } + } + } + }, + "info.lora.pcm": { + "stable-diffusion-xl-1": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": { + "num_inference_steps": 16 + }, + "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": { + "num_inference_steps": 16 + }, + "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": { + "num_inference_steps": 4 + }, + "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": { + "num_inference_steps": 4 + }, + "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": { + "num_inference_steps": 8 + }, + "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": { + "num_inference_steps": 8 + }, + "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + }, + "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-v1-5": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": { + "num_inference_steps": 16 + }, + "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": { + "num_inference_steps": 4 + }, + "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": { + "num_inference_steps": 8 + }, + "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-3": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": { + "num_inference_steps": 2, + "guidance_scale": 1.2 + }, + "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + }, + "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + }, + "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + } + } + } + }, + "info.lora.slam": { + "stable-diffusion-xl-1": { + "repo": "alimama-creative/slam-lora-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "scheduler": { + "ops.scheduler.lcm": { + "timestep_spacing": "trailing" + } + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 1 + } + } + }, + "file_256": [ + "22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91" + ] + }, + "stable-diffusion-v1-5": { + "repo": "alimama-creative/slam-sd1.5", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + } + } + }, + "info.lora.spo": { + "stable-diffusion-xl-1": { + "repo": "SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 5.0 + } + } + }, + "file_256": [ + "0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df" + ] + }, + "stable-diffusion-v1-5": { + "repo": "SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 7.5 + } + } + }, + "file_256": [ + "1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4" + ] + } + }, + "info.lora.tcd": { + "stable-diffusion-xl-1": { + "repo": "h1t/TCD-SDXL-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0, + "eta": 0.3 + }, + "scheduler": { + "ops.scheduler.tcd": {} + } + } + }, + "file_256": [ + "2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba" + ] + }, + "stable-diffusion-v1-5": { + "repo": "h1t/TCD-SD15-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232" + ], + "layer_256": [ + "e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75" + ], + "layer_b3": [ + "90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b" + ] + } + }, + "info.lora.turbo": { + "stable-diffusion-xl-1": { + "file_256": [ + "a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69" + ] + }, + "flux1-dev": { + "repo": "alimama-creative/FLUX.1-Turbo-Alpha", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + }, + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 8, + "max_sequence_length": 512 + } + } + }, + "file_256": [ + "77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff" + ] + }, + "stable-diffusion-3": { + "repo": "tensorart/stable-diffusion-3.5-large-TurboX", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + }, + "scheduler": { + "ops.scheduler.flow-match": { + "shift": 5 + } + } + } + }, + "file_256": { + "fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": { + "num_inference_steps": "8" + } + } + } + }, + "info.art.audiogen": { + "*": { + "repo": "facebook/audiogen-medium", + "pkg": { + "0": { + "audiocraft": "models.AudioGen", + "generation": { + "duration": 5 + }, + "stage_2": { + "audiocraft": ".data.audioaudio_write", + "generation": { + "strategy": "loudness", + "loudness_compressor": true + } + } + } + } + } + }, + "info.art.parler-tts-v1": { + "*": { + "repo": "parler-tts/parler-tts-large-v1", + "pkg": { + "0": { + "parler_tts": "ParlerTTSForConditionalGeneration", + "generation": { + "return_tensors": "pt" + } + } + } + } + }, + "info.gan.snac-st": { + "*": { + "repo": "Zuellni/snac-24khz-ST", + "pkg": { + "0": { + "snac": "SNAC" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio" + } + }, + "file_256": [ + "e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", + "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d" + ], + "layer_256": [ + "35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", + "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841" + ], + "layer_b3": [ + "18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", + "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119" + ] + } + }, + "info.gan.kokoro": { + "*": { + "repo": "hexgrad/Kokoro-82M", + "pkg": { + "0": { + "kokoro": "KPipeline" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + }, + "file_256": [ + "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", + "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4" + ], + "layer_256": [ + "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", + "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b" + ], + "layer_b3": [ + "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", + "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", + "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e932dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92" + ] + } + }, + "info.stst.silero-vad": { + "*": { + "repo": "freddyaboulton/silero-vad", + "pkg": { + "0": { + "onnx": "onnx" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + }, + "file_256": [ + "591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9" + ], + "layer_256": [ + "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd" + ], + "layer_b3": [ + "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", + "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", + "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", + "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e" + ] + } + }, + "info.stst.wav2vec2-conformer-rope-960h-ft": { + "*": { + "repo": "facebook/wav2vec2-conformer-rope-large-960h-ft", + "pkg": { + "0": { + "transformers": "Wav2Vec2ConformerForCTC" + } + }, + "file_256": [ + "97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d" + ], + "layer_256": [ + "1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d" + ], + "layer_b3": [ + "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" + ], + "tasks": [ + "Wav2Vec2ConformerForAudioFrameClassification", + "Wav2Vec2ConformerForCTC", + "Wav2Vec2ConformerForPreTraining", + "Wav2Vec2ConformerForSequenceClassification", + "Wav2Vec2ConformerForXVector", + "Wav2Vec2ConformerModel", + "Wav2Vec2ConformerPreTrainedModel" + ] + } + }, + "info.art.orpheus-0-ft": { + "*": { + "repo": "canopylabs/orpheus-3b-0.1-ft", + "pkg": { + "0": { + "orpheus_tts": "OrpheusModel", + "generation": { + "max_model_len": 2048 + } + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + } + } + }, + "info.art.outetts-0": { + "*": { + "repo": "OuteAI/OuteTTS-0.3-1B", + "pkg": { + "0": { + "outetts": "InterfaceHF" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + } + } + }, + "info.gan.speecht5-hifigan": { + "*": { + "file_256": [ + "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c" + ], + "layer_256": [ + "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770" + ], + "layer_b3": [ + "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956" + ] + } + }, + "info.dit.wan2-flf2v-720p": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", + "file_256": [ + "", + "" + ], + "layer_256": [ + "" + ], + "layer_b3": [ + "" + ] + } + }, + "ops.patch.hidiffusion": { + "stable-diffusion-xl-1": { + "pkg": { + "0": { + "hidiffusion": { + "apply_hidiffusion": { + "timesteps": "StableDiffusionXLTimesteps" + } + }, + "generation": { + "height": 2048, + "width": 2048, + "eta": 1.0, + "guidance_scale": 7.5, + "num_inference_steps": 10 + } + } + } + } + }, + "ops.scheduler.align-your-steps": { + "stable-diffusion-xl-1": { + "pkg": { + "0": { + "diffusers": "schedulers.scheduling_utils.AysSchedules", + "generation": { + "timesteps": "StableDiffusionXLTimesteps", + "num_inference_steps": 10 + } + } + } + } + }, + "info.art.chameleon": { + "lumina-mgpt-1024": { + "repo": "Alpha-VLLM/Lumina-mGPT-7B-1024", + "pkg": { + "0": { + "inference_solver": { + "FlexARInferenceSolver": { + "precision": "bf16", + "target_size": 768 + } + }, + "generation": { + "images": [], + "qas": [ + [ + "q1", + null + ] + ], + "max_gen_len": 8192, + "temperature": 1.0 + } + }, + "1": { + "inference_solver": "ChameleonXLLMXForConditionalGeneration" + } + }, + "file_256": [ + "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", + "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", + "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", + "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b" + ], + "layer_256": [ + "eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25" + ], + "layer_b3": [ + "6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656" + ] + } + }, + "info.vit.clip-vit-patch14": { + "*": { + "repo": "openai/clip-vit-large-patch14", + "pkg": { + "0": { + "transformers": "CLIPTextModel" + } + }, + "file_256": [ + "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", + "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", + "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", + "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", + "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", + "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", + "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", + "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", + "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", + "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", + "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", + "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", + "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", + "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", + "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", + "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", + "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", + "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", + "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1" + ], + "layer_256": [ + "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", + "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", + "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", + "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", + "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", + "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", + "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", + "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", + "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", + "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", + "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", + "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", + "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", + "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", + "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3" + ], + "layer_b3": [ + "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", + "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", + "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", + "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", + "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", + "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", + "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", + "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", + "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", + "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", + "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", + "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", + "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", + "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", + "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", + "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" + ] + } + }, + "info.vit.clip-vit-g-14-laion-s-b": { + "*": { + "repo": "laion/CLIP-ViT-g-14-laion2B-s12B-b42K", + "pkg": { + "0": { + "transformers": "CLIPTextModelWithProjection" + } + }, + "file_256": [ + "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", + "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", + "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", + "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", + "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", + "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", + "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", + "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", + "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", + "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b" + ], + "layer_256": [ + "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", + "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", + "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", + "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", + "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", + "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", + "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46" + ], + "layer_b3": [ + "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", + "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", + "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", + "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", + "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", + "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", + "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" + ] + } + }, + "info.vit.clip-vit-h-14-laion-s-b": { + "*": { + "repo": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K", + "pkg": { + "0": { + "transformers": "CLIPModel" + } + }, + "file_256": [ + "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", + "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", + "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161" + ], + "layer_256": [ + "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", + "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", + "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c" + ], + "layer_b3": [ + "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", + "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", + "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" + ] + } + }, + "info.aet.chatglm3": { + "*": { + "repo": "zai-org/chatglm3-6b", + "pkg": { + "0": { + "transformers": "AutoModel" + } + }, + "file_256": [ + "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", + "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d" + ], + "layer_256": [ + "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44" + ], + "layer_b3": [ + "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481" + ] + } + }, + "info.art.qwen2": { + "bagel-mot": { + "repo": "ByteDance-Seed/BAGEL-7B-MoT", + "pkg": { + "0": { + "Bagel": "app" + } + } + } + }, + "info.vae.tae": { + "stable-diffusion-3": { + "repo": "madebyollin/taesd3", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399" + ] + }, + "stable-diffusion-xl-1": { + "repo": "madebyollin/taesdxl", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f" + ] + }, + "stable-diffusion-v1-5": { + "repo": "madebyollin/taesd", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549" + ] + }, + "flux1-dev": { + "repo": "madebyollin/taef1", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449" + ] + } + }, + "info.vae.kl": { + "qwen-image": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLQwenImage" + } + }, + "file_256": [ + "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344" + ], + "layer_256": [ + "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc" + ], + "layer_b3": [ + "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b" + ] + }, + "ltx-video": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLLTXVideo" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "allegro": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLAllegro" + } + }, + "file_256": [ + "47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a" + ], + "layer_256": [ + "bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f" + ], + "layer_b3": [ + "93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0" + ] + }, + "cosmos-1-diffusion-video2world": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLCosmos" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "easyanimatev5-zh": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLMagvit" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "hunyuanvideo-i2v": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLHunyuanVideo" + } + }, + "file_256": [ + "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", + "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", + "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", + "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0" + ] + }, + "mochi-1": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLMochi" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "audioldm-s-v2": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5" + ], + "layer_256": [ + "54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6" + ], + "layer_b3": [ + "00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de" + ] + }, + "stable-video-diffusion-img2vid-xt": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLTemporalDecoder" + } + } + }, + "stable-diffusion-xl-1": { + "repo": "madebyollin/sdxl-vae-fp16-fix", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", + "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", + "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", + "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", + "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", + "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", + "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", + "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88" + ], + "layer_256": [ + "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", + "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" + ], + "layer_b3": [ + "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", + "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0" + ] + }, + "stable-diffusion-xl-1*": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", + "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", + "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", + "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff" + ], + "layer_256": [ + "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", + "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" + ], + "layer_b3": [ + "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74" + ] + }, + "shuttle-jaguar": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904" + ], + "layer_256": [ + "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b" + ], + "layer_b3": [ + "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", + "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0" + ] + }, + "flux1-dev": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", + "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", + "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", + "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc" + ], + "layer_256": [ + "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", + "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", + "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", + "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80" + ], + "layer_b3": [ + "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", + "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903" + ] + }, + "musicldm": { + "file_256": [ + "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4" + ], + "layer_256": [ + "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f" + ], + "layer_b3": [ + "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0" + ] + }, + "stable-diffusion-v1-5": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", + "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", + "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", + "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", + "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", + "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", + "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", + "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c" + ], + "layer_256": [ + "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", + "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3" + ], + "layer_b3": [ + "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", + "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833" + ] + } + }, + "info.vae.wan": { + "wan2-i2v-480p": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLWan", + "precision": "ops.precision.float.F32" + } + }, + "file_256": [ + "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", + "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b" + ], + "layer_256": [ + "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", + "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e" + ], + "layer_b3": [ + "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", + "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433" + ] + }, + "skyreels-v2-t2v-720p": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "skyreels-v2-i2v-720p": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + } + }, + "info.vae.cogvideox": { + "cogvideox-i2v": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLCogVideoX" + } + }, + "file_256": [ + "a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e" + ], + "layer_256": [ + "43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e" + ], + "layer_b3": [ + "246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb" + ] + }, + "cogvideox-fun-v-pose": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "consisid": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + } + }, + "info.vae.dc": { + "sana-1024px-bf16": { + "pkg": { + "0": { + "diffusers": "AutoencoderDC" + } + }, + "file_256": [ + "15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f" + ], + "layer_256": [ + "abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde" + ], + "layer_b3": [ + "cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0" + ] + } + }, + "info.vae.oobleck": { + "stable-audio-open-1": { + "pkg": { + "0": { + "diffusers": "AutoencoderOobleck" + } + } + } + }, + "info.vae.eq": { + "stable-diffusion-xl-1": { + "repo": "KBlueLeaf/EQ-SDXL-VAE", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + } + } + }, + "info.vae.ms-lc-eq": { + "stable-diffusion-xl-1": { + "repo": "Anzhc/MS-LC-EQ-D-VR_VAE", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + } + } + } +} \ No newline at end of file diff --git a/mir/automata.py b/mir/automata.py index 595125c..227f4ab 100644 --- a/mir/automata.py +++ b/mir/automata.py @@ -18,17 +18,17 @@ from mir.config.conversion import slice_number from mir.indexers import diffusers_index, transformers_index from mir.maid import MIRDatabase -from mir.spec.mir import mir_entry -from mir.tag import make_mir_tag, make_scheduler_tag, tag_base_model, tag_pipe +from mir.spec import mir_entry +from mir.tag import tag_model_from_repo, tag_scheduler, tag_base_model, tag_pipe -sd1_series, sd1_comp = make_mir_tag("stable-diffusion-v1-5/stable-diffusion-v1-5") -sdxl_series, sdxl_comp = make_mir_tag("stabilityai/stable-diffusion-xl-base-1.0") -dev_series, dev_comp = make_mir_tag("black-forest-labs/FLUX.1-dev") -schnell_series, schnell_comp = make_mir_tag("black-forest-labs/FLUX.1-schnell") -ssd_series, ssd_comp = make_mir_tag("segmind/SSD-1B") -vega_series, vega_comp = make_mir_tag("segmind/Segmind-Vega") -sd3_series, sd3_comp = make_mir_tag("stable-diffusion-3.5-medium") # +sd1_series, sd1_comp = tag_model_from_repo("stable-diffusion-v1-5/stable-diffusion-v1-5") +sdxl_series, sdxl_comp = tag_model_from_repo("stabilityai/stable-diffusion-xl-base-1.0") +dev_series, dev_comp = tag_model_from_repo("black-forest-labs/FLUX.1-dev") +schnell_series, schnell_comp = tag_model_from_repo("black-forest-labs/FLUX.1-schnell") +ssd_series, ssd_comp = tag_model_from_repo("segmind/SSD-1B") +vega_series, vega_comp = tag_model_from_repo("segmind/Segmind-Vega") +sd3_series, sd3_comp = tag_model_from_repo("stable-diffusion-3.5-medium") # # def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet # from diffusers.models.attention_processor import AttentionProcessor @@ -214,7 +214,7 @@ def add_mir_schedulers(mir_db: MIRDatabase): for class_name in _import_structure["schedulers"]: if class_name != "SchedulerMixin": - series_name, comp_name = make_scheduler_tag(class_name) + series_name, comp_name = tag_scheduler(class_name) class_obj = import_module("diffusers.schedulers") class_path = getattr(class_obj, class_name).__module__ mir_db.add( @@ -233,7 +233,7 @@ def add_mir_schedulers(mir_db: MIRDatabase): ) class_name = "KarrasDiffusionSchedulers" - series_name, comp_name = make_scheduler_tag(class_name) + series_name, comp_name = tag_scheduler(class_name) class_obj = import_module("diffusers.schedulers.scheduling_utils") class_path = getattr(class_obj, class_name).__module__ mir_db.add( @@ -528,35 +528,6 @@ def mir_update(mir_db: MIRDatabase, task_list: list = None, pipe_list: list = No ], }, ), - ( - "Kwai-Kolors/Kolors-diffusers", - "KolorsPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": { - "negative_prompt": "", - "guidance_scale": 5.0, - "num_inference_steps": 50, - "width": 1024, - "height": 1024, - }, - }, - 1: {"diffusers": "DiffusionPipeline"}, - }, - "file_256": [ - "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c", # fp16, - ], - "layer_b3": [ - "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414", # fp16 - ], - "layer_256": [ - "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd", # fp16 - ], - "identifiers": [".DenseReluDense.wi.weight", "encoder_hid_proj.weight"], - }, - ), ( "stabilityai/stable-cascade-prior", "StableCascadePriorPipeline", @@ -981,20 +952,6 @@ def mir_update(mir_db: MIRDatabase, task_list: list = None, pipe_list: list = No "layer_256": ["ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb"], }, ), - ( - "tencent-hunyuan/hunyuandiT-v1.2-diffusers", - "HunyuanDiTPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - } - }, - "file_256": ["7d31ac8fa389ff39dd0a81430010e52c43b59f15adc00c83625a47881e16830e"], - "layer_b3": ["bccd37ecc9f85d132b46d0bb67b4facb49fc6c091428a4feba9ab9a93140f5fe"], - "layer_256": ["ed25d241d58ca298d28abd5919e70341ad194e77dce4859436b52ea4d8fcb616"], - }, - ), ( "Alpha-VLLM/Lumina-Image-2.0", "Lumina2Pipeline", @@ -1098,6 +1055,49 @@ def mir_update(mir_db: MIRDatabase, task_list: list = None, pipe_list: list = No } }, ), + ( + "Kwai-Kolors/Kolors-diffusers", + "KolorsPipeline", + { + "pkg": { + 0: { + "precision": "ops.precision.float.F16", + "generation": { + "negative_prompt": "", + "guidance_scale": 5.0, + "num_inference_steps": 50, + "width": 1024, + "height": 1024, + }, + }, + 1: {"diffusers": "DiffusionPipeline"}, + }, + "file_256": [ + "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c", # fp16, + ], + "layer_b3": [ + "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414", # fp16 + ], + "layer_256": [ + "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd", # fp16 + ], + "identifiers": [".DenseReluDense.wi.weight", "encoder_hid_proj.weight"], + }, + ), + ( + "tencent-hunyuan/hunyuandiT-v1.2-diffusers", + "HunyuanDiTPipeline", + { + "pkg": { + 0: { + "precision": "ops.precision.float.F16", + } + }, + "file_256": ["7d31ac8fa389ff39dd0a81430010e52c43b59f15adc00c83625a47881e16830e"], + "layer_b3": ["bccd37ecc9f85d132b46d0bb67b4facb49fc6c091428a4feba9ab9a93140f5fe"], + "layer_256": ["ed25d241d58ca298d28abd5919e70341ad194e77dce4859436b52ea4d8fcb616"], + }, + ), ] transformers_addons = [ @@ -1458,7 +1458,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): """Create MIR entries missing from the database""" repo = "microsoft/speecht5_hifigan" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -1476,14 +1476,14 @@ def add_mir_diffusion(mir_db: MIRDatabase): ], ) ) - series, comp = make_mir_tag("lodestones/Chroma") + series, comp = tag_model_from_repo("lodestones/Chroma") repo = "lodestones/Chroma1-HD" mir_db.add( mir_entry( domain="info", arch="dit", series=series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ "0": { @@ -1514,7 +1514,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ "0": { @@ -1572,7 +1572,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="unet", series=sdxl_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", # v4 @@ -1600,7 +1600,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="unet", series=sdxl_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", # v2 @@ -1631,7 +1631,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="unet", series=sdxl_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", # 2.5 diffusers @@ -1677,7 +1677,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="unet", series=sdxl_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", # modelspec sai @@ -1703,7 +1703,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="unet", series=sdxl_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", # modelspec sai @@ -1734,7 +1734,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=schnell_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ 2: { @@ -1762,7 +1762,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=schnell_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ 2: { @@ -1794,7 +1794,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={0: {"generation": {"num_inference_steps": 16, "guidance_scale": 7.5, "width": 768, "height": 1024}}}, file_256=[ @@ -1815,7 +1815,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=schnell_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ 2: { @@ -1842,7 +1842,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={0: {"generation": {"num_inference_steps": 28}}}, file_256=[ @@ -1863,7 +1863,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, ) @@ -1874,7 +1874,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, ) @@ -1885,7 +1885,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, ) @@ -1896,7 +1896,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=["4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee"], layer_b3=["c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3"], @@ -1909,7 +1909,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", # modelspec sai @@ -1929,7 +1929,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=dev_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", # modelspec sai @@ -1949,7 +1949,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): domain="info", arch="dit", series=sd3_series, - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], repo=repo, pkg={ 0: { @@ -1978,7 +1978,7 @@ def add_mir_diffusion(mir_db: MIRDatabase): ), ) repo = "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2001,8 +2001,8 @@ def add_mir_diffusion(mir_db: MIRDatabase): mir_entry( domain="info", arch="dit", - series=make_mir_tag("Alpha-VLLM/Lumina-Image-2.0")[0], - comp=make_mir_tag(repo)[0], + series=tag_model_from_repo("Alpha-VLLM/Lumina-Image-2.0")[0], + comp=tag_model_from_repo(repo)[0], repo=repo, file_256=[ "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", # 2b 22100 ema unified fp32 @@ -2053,11 +2053,11 @@ def add_mir_diffusion(mir_db: MIRDatabase): def add_mir_llm(mir_db: MIRDatabase): base_arch, base_series, base_comp = tag_base_model(repo_path="facebook/chameleon-7b", class_name="ChameleonModel") repo = "Alpha-VLLM/Lumina-mGPT-7B-1024" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", - arch=base_arch, + arch="art", series=base_series, comp=series, repo=repo, @@ -2080,7 +2080,7 @@ def add_mir_llm(mir_db: MIRDatabase): ), ) repo = "openai/clip-vit-large-patch14" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2149,7 +2149,7 @@ def add_mir_llm(mir_db: MIRDatabase): ) ) repo = "laion/CLIP-ViT-g-14-laion2B-s12B-b42K" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2192,7 +2192,7 @@ def add_mir_llm(mir_db: MIRDatabase): ) ) repo = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2221,7 +2221,7 @@ def add_mir_llm(mir_db: MIRDatabase): ) ) repo = "zai-org/chatglm3-6b" # formerly THUDM - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2246,11 +2246,11 @@ def add_mir_llm(mir_db: MIRDatabase): ) base_arch, base_series, base_comp = tag_base_model(repo_path="Qwen/Qwen2-7B-beta", class_name="Qwen2Model") repo = "ByteDance-Seed/BAGEL-7B-MoT" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", - arch=base_arch, + arch="art", series=base_series, comp=series, repo=repo, @@ -2262,7 +2262,7 @@ def add_mir_llm(mir_db: MIRDatabase): def add_mir_audio(mir_db: MIRDatabase): """Create MIR audio modality entries""" repo = "facebook/audiogen-medium" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2283,7 +2283,7 @@ def add_mir_audio(mir_db: MIRDatabase): ) ) repo = "parler-tts/parler-tts-tiny-v1" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2300,7 +2300,7 @@ def add_mir_audio(mir_db: MIRDatabase): ) ) repo = "Zuellni/snac-24khz-ST" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) ( mir_db.add( mir_entry( @@ -2324,7 +2324,7 @@ def add_mir_audio(mir_db: MIRDatabase): ), ) repo = "parler-tts/parler-tts-large-v1" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2341,7 +2341,7 @@ def add_mir_audio(mir_db: MIRDatabase): ) ) repo = "hexgrad/Kokoro-82M" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2373,7 +2373,7 @@ def add_mir_audio(mir_db: MIRDatabase): ) ) repo = "freddyaboulton/silero-vad" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2405,7 +2405,7 @@ def add_mir_audio(mir_db: MIRDatabase): ), ) repo = "facebook/wav2vec2-conformer-rope-large-960h-ft" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2424,7 +2424,7 @@ def add_mir_audio(mir_db: MIRDatabase): ), ) repo = "canopylabs/orpheus-3b-0.1-ft" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2445,7 +2445,7 @@ def add_mir_audio(mir_db: MIRDatabase): ) ) repo = "OuteAI/OuteTTS-0.3-1B" - series, comp = make_mir_tag(repo) + series, comp = tag_model_from_repo(repo) mir_db.add( mir_entry( domain="info", @@ -2923,7 +2923,7 @@ def add_mir_vae(mir_db: MIRDatabase): file_256=["927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449"], ) ) - series, comp = make_mir_tag("Qwen/Qwen-Image") + series, comp = tag_model_from_repo("Qwen/Qwen-Image") mir_db.add( mir_entry( domain="info", @@ -2945,9 +2945,9 @@ def add_mir_vae(mir_db: MIRDatabase): ], ) ) - series, comp = make_mir_tag("Wan-AI/Wan2.1-I2V-14B-480P-Diffusers") - sr_series_text2v, _ = make_mir_tag("Skywork/SkyReels-V2-T2V-14B-720P-Diffusers") - sr_series_image2v, _ = make_mir_tag("Skywork/SkyReels-V2-I2V-14B-720P-Diffusers") + series, comp = tag_model_from_repo("Wan-AI/Wan2.1-I2V-14B-480P-Diffusers") + sr_series_text2v, _ = tag_model_from_repo("Skywork/SkyReels-V2-T2V-14B-720P-Diffusers") + sr_series_image2v, _ = tag_model_from_repo("Skywork/SkyReels-V2-I2V-14B-720P-Diffusers") mir_db.add( mir_entry( domain="info", @@ -2999,7 +2999,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("Lightricks/LTX-Video") + series, comp = tag_model_from_repo("Lightricks/LTX-Video") mir_db.add( mir_entry( domain="info", @@ -3015,7 +3015,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("rhymes-ai/Allegro") + series, comp = tag_model_from_repo("rhymes-ai/Allegro") mir_db.add( mir_entry( domain="info", @@ -3031,9 +3031,9 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("zai-org/CogVideoX-5b-I2V") - series_fun, _ = make_mir_tag("alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose") - series_wish, _ = make_mir_tag("BestWishYsh/ConsisID-preview") + series, comp = tag_model_from_repo("zai-org/CogVideoX-5b-I2V") + series_fun, _ = tag_model_from_repo("alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose") + series_wish, _ = tag_model_from_repo("BestWishYsh/ConsisID-preview") mir_db.add( mir_entry( domain="info", @@ -3073,7 +3073,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("nvidia/Cosmos-1.0-Diffusion-7B-Video2World") + series, comp = tag_model_from_repo("nvidia/Cosmos-1.0-Diffusion-7B-Video2World") mir_db.add( mir_entry( domain="info", @@ -3089,7 +3089,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers") + series, comp = tag_model_from_repo("alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers") mir_db.add( mir_entry( domain="info", @@ -3105,7 +3105,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("hunyuanvideo-community/HunyuanVideo-I2V") + series, comp = tag_model_from_repo("hunyuanvideo-community/HunyuanVideo-I2V") mir_db.add( mir_entry( domain="info", @@ -3126,7 +3126,7 @@ def add_mir_vae(mir_db: MIRDatabase): # layer_256=[], ) ) - series, comp = make_mir_tag("genmo/mochi-1-preview") + series, comp = tag_model_from_repo("genmo/mochi-1-preview") mir_db.add( mir_entry( domain="info", @@ -3142,7 +3142,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=[], ) ) - series, comp = make_mir_tag("rhymes-ai/Allegro") + series, comp = tag_model_from_repo("rhymes-ai/Allegro") mir_db.add( mir_entry( domain="info", @@ -3160,7 +3160,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=["bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f"], ) ) - series, comp = make_mir_tag("cvssp/audioldm-s-full-v2") + series, comp = tag_model_from_repo("cvssp/audioldm-s-full-v2") mir_db.add( mir_entry( domain="info", @@ -3179,7 +3179,7 @@ def add_mir_vae(mir_db: MIRDatabase): ) ) - series, comp = make_mir_tag("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers") + series, comp = tag_model_from_repo("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers") mir_db.add( mir_entry( domain="info", @@ -3195,7 +3195,7 @@ def add_mir_vae(mir_db: MIRDatabase): layer_256=["abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde"], ) ) - series, comp = make_mir_tag("stabilityai/stable-audio-open-1.0") + series, comp = tag_model_from_repo("stabilityai/stable-audio-open-1.0") mir_db.add( mir_entry( domain="info", @@ -3211,7 +3211,7 @@ def add_mir_vae(mir_db: MIRDatabase): # layer_256=[], ) ) - series, comp = make_mir_tag("stable-video-diffusion-img2vid-xt") + series, comp = tag_model_from_repo("stable-video-diffusion-img2vid-xt") mir_db.add( mir_entry( domain="info", @@ -3295,7 +3295,7 @@ def add_mir_vae(mir_db: MIRDatabase): domain="info", arch="vae", series="kl", - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], # no repo here, may conflict pkg={ 0: {"diffusers": "AutoencoderKL"}, @@ -3373,7 +3373,7 @@ def add_mir_vae(mir_db: MIRDatabase): domain="info", arch="vae", series="kl", - comp=make_mir_tag(repo)[0], + comp=tag_model_from_repo(repo)[0], # no repo here, may conflict file_256=[ "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4", diff --git a/mir/config/constants.py b/mir/config/constants.py index 07dd812..5736e52 100644 --- a/mir/config/constants.py +++ b/mir/config/constants.py @@ -1,65 +1,133 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import List, Optional, Union -from mir.config.json_io import read_json_file import os +from dataclasses import dataclass, field +from typing import Callable, List -from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES -from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES import transformers +from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES +from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES + +from mir.config.json_io import read_json_file + def mapped_cls(model_identifier: str): - """Get model class from identifier without calling huggingface_hub. - + """Get model class from identifier without calling huggingface_hub.\n :param model_identifier: Model identifier like "bert-base-uncased" or "gpt2" :return: Model class (e.g., BertModel, GPT2Model) """ - # Extract code name from model identifier (e.g., "bert-base-uncased" -> "bert") - # Handle various formats: "bert-base-uncased", "gpt2", "microsoft/DialoGPT-medium" code_name = model_identifier.split("/")[-1].split("-")[0].lower() - - # Method 1: Direct lookup via MODEL_MAPPING_NAMES (simplest) + model_class_name = MODEL_MAPPING_NAMES.get(code_name, None) - - # Method 2: Via config class lookup (matches _get_model_class behavior more closely) config_class_name = CONFIG_MAPPING_NAMES.get(code_name) if config_class_name: config_class = getattr(transformers, config_class_name, None) if config_class: - # Look up in MODEL_MAPPING using config class model_class = MODEL_MAPPING.get(config_class, None) if model_class: if isinstance(model_class, tuple): model_class = model_class[0] return model_class - - # Fallback: try with normalized code name (handle underscores/dashes) + normalized = code_name.replace("_", "-") if normalized != code_name: - print(f"normalized: {normalized}") - model_class_name = MODEL_MAPPING_NAMES.get(normalized, None) - if model_class_name: + if model_class_name := MODEL_MAPPING_NAMES.get(normalized, None): + if isinstance(model_class_name, tuple): + model_class_name = model_class_name[0] return getattr(transformers, model_class_name, None) - if model_class_name: - if isinstance(model_class_name, tuple): - model_class_name = model_class_name[0] - return getattr(transformers, model_class_name, None) return None +def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable: + """Convert two strings into a callable function or property\n + :param module: The name of the module to import + :param library_path: Base package for the module + :return: The callable attribute or property + """ + from importlib import import_module + + module = module_name.strip() + library = pkg_name_or_abs_path.strip() + base_library = import_module(library, module) + module = getattr(base_library, module) + return module + + +def extract_init_params(module: Callable | str, package_name: str | None = None) -> dict[str, list[str]]: + """Pick apart a Diffusers or Transformers pipeline class and find its constituent parts (formerly root_class)\n + :param module: Origin pipeline as a class or as a string + :param library: name of a library to import the class from, only if a string is provided + :return: Dictionary of sub-classes from the `module`""" + + import inspect + + if package_name and isinstance(module, str): + module_obj: Callable = import_submodules(module, package_name) + else: + assert isinstance(module, Callable) + module_obj = module + signature = inspect.signature(module_obj.__init__) + class_names = {} + for folder, param in signature.parameters.items(): + if folder not in ["self", "kwargs", "use_cache"]: + sub_module = str(param.annotation).split("'") + if len(sub_module) > 1 and sub_module[1] not in [ + "bool", + "int", + "float", + "complex", + "str", + "list", + "tuple", + "dict", + "set", + "inspect", + "_empty", + ]: + class_names.setdefault(folder, sub_module[1].split(".")) + return class_names + + +@dataclass +class ClassMapEntry: + """Represents a structured entry of the name of the class and its associated attributes.""" + + name: str + model_name: str + model: Callable + config: Callable + config_params: dict[str, list[str]] = field(init=False, default_factory=lambda: {}) + model_params: dict[str, list[str]] | None = None + + def __post_init__(self): + if self.model: + self.model_params = extract_init_params(self.model) + if self.config: + self.config_params = extract_init_params(self.config) + + +@dataclass +class DocStringEntry: + """Represents a structured entry of package name, file name, and docstring.""" + + package_name: str + file_name: str + doc_string: str + + class DocParseData: pipe_class: str pipe_repo: str - staged_class: Optional[str] = None - staged_repo: Optional[str] = None + staged_class: str | None = None + staged_repo: str | None = None - def __init__(self, pipe_class, pipe_repo, staged_class=None, staged_repo=None): - self.pipe_class: str = pipe_class - self.pipe_repo: str = pipe_repo - self.staged_class: str = staged_class - self.staged_repo: str = staged_repo + def __init__(self, pipe_class: str, pipe_repo: str, staged_class: str | None = None, staged_repo: str | None = None): + self.pipe_class = pipe_class + self.pipe_repo = pipe_repo + self.staged_class = staged_class + self.staged_repo = staged_repo class DocStringParserConstants: @@ -100,7 +168,6 @@ class DocStringParserConstants: root_path = os.path.join(os.getcwd(), "mir") versions = read_json_file(os.path.join(root_path, "spec", "versions.json")) template = read_json_file(os.path.join(root_path, "spec", "template.json")) -print(root_path) MIR_PATH_NAMED = os.path.join(root_path, "mir.json") BREAKING_SUFFIX = r".*(?:-)(prior)$|.*(?:-)(diffusers)$|.*[_-](\d{3,4}px|-T2V$|-I2V$)" diff --git a/mir/config/conversion.py b/mir/config/conversion.py index ab5d98c..beaee14 100644 --- a/mir/config/conversion.py +++ b/mir/config/conversion.py @@ -1,108 +1,71 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import Callable, Optional, Union, Type, List, Iterator, Tuple, Dict -from mir.config.console import dbuq, nfo +from typing import Callable, Optional, Union, Type, List, Generator, Dict -def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Optional[Callable]: - """Convert two strings into a callable function or property\n - :param module: The name of the module to import - :param library_path: Base package for the module - :return: The callable attribute or property - """ - from importlib import import_module - - module = module_name.strip() - library = pkg_name_or_abs_path.strip() - base_library = import_module(library, module) - try: - module = getattr(base_library, module) - return module - except AttributeError: # as error_log: - # dbuq(error_log) - return base_library - - -def code_name_to_class_name( - code_name: Optional[Union[str, Type]] = None, - pkg_name: Optional[str] = "transformers", -) -> Union[List[str], str]: - """Fetch class names from code names from Diffusers or Transformers\n - :param class_name: To return only one class, defaults to None - :param pkg_name: optional field for library, defaults to "transformers" - :return: A list of all code names, or the one corresponding to the provided class""" - from mir.config.constants import package_map - - pkg_name = pkg_name.lower() - MAPPING_NAMES = import_submodules(*package_map[pkg_name]) - if code_name: - return MAPPING_NAMES.get(code_name) - return list(MAPPING_NAMES.keys()) - - -def pkg_path_to_docstring(pkg_name: str, folder_path: bool) -> Iterator[Tuple[str, str, str]]: - """Processes package folder paths to yield example doc strings if available.\n - :param pkg_name: The name of the package under diffusers.pipelines. - :param file_specific: A flag indicating whether processing is specific to certain files. - :yield: A tuple containing (pkg_name, file_name, EXAMPLE_DOC_STRING) if found. +from mir.config.console import dbuq, nfo +from mir.config.constants import DocStringEntry, ClassMapEntry, import_submodules + + +def retrieve_diffusers_docstrings( + package_name: str, + file_names: list[str], +) -> Generator[DocStringEntry]: + """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n + :param pkg_name: Package under ``diffusers.pipelines``.\n + :param file_names: A list of related file names.\n + :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n + :return: DocString Entry class.\n """ import os from importlib import import_module - file_names = list(getattr(folder_path, "_import_structure").keys()) - module_path = os.path.dirname(import_module("diffusers.pipelines").__file__) + module_location: str | None = import_module("diffusers.pipelines").__file__ + module_path = os.path.dirname(module_location) + for file_name in file_names: + assert isinstance(file_name, str) if file_name == "pipeline_stable_diffusion_xl_inpaint": continue - try: - pkg_path = f"diffusers.pipelines.{str(pkg_name)}.{file_name}" - dbuq(pkg_path) - path_exists = os.path.exists(os.path.join(module_path, pkg_name, file_name + ".py")) - if path_exists: - print(f"file_name, pkg_path): {file_name, pkg_path}") - pipe_file = import_submodules(file_name, pkg_path) - except ModuleNotFoundError: - if pkg_name != "skyreels_v2": - nfo(f"Module Not Found for {pkg_name}") - pipe_file = None - - try: - if pipe_file and hasattr(pipe_file, "EXAMPLE_DOC_STRING"): - yield (pkg_name, file_name, pipe_file.EXAMPLE_DOC_STRING) - else: - if path_exists: - pipe_file = import_module(pkg_path) - except (ModuleNotFoundError, AttributeError): - if pkg_name != "skyreels_v2": - nfo(f"Doc String Not Found for {pipe_file} {pkg_name}") - - -def file_name_to_docstring(pkg_name: str, file_specific: bool) -> Iterator[Tuple[str, str, str]]: - """Processes package using file name to yield example doc strings if available.\n - :param pkg_name: The name of the package under diffusers.pipelines. - :param file_specific: A flag indicating whether processing is specific to certain files. - :yield: A tuple containing (pkg_name, file_name, EXAMPLE_DOC_STRING) if found. - """ - from importlib import import_module - file_name = f"pipeline_{file_specific}" - try: - pkg_path = f"diffusers.pipelines.{str(pkg_name)}" - pipe_file = import_submodules(file_name, pkg_path) - except ModuleNotFoundError: - if pkg_name != "skyreels_v2": - nfo(f"Module Not Found for {pkg_name}") - pipe_file = None - try: - if pipe_file and hasattr(pipe_file, "EXAMPLE_DOC_STRING"): - yield (pkg_name, file_name, pipe_file.EXAMPLE_DOC_STRING) + pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" + dbuq(pkg_path) + + if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): + pipe_file = import_submodules(file_name, pkg_path) or import_module(pkg_path) or nfo(f"Failed to import {pkg_path}") + if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): + yield DocStringEntry(package_name=package_name, file_name=file_name, doc_string=doc_string) + else: + nfo(f"Doc string attribute missing for {package_name}/{file_name}") else: - pipe_file = import_module(pkg_path) + nfo(f"Path not found for {package_name}/{file_name}") + + return + - except AttributeError: - if pkg_name != "skyreels_v2": - nfo(f"Doc String Not Found for {pipe_file} {pkg_name}") +def get_repo_from_class_map(class_map: ClassMapEntry) -> str | None: + """The name of the repository that is associated with a transformers configuration class + :param class_map: Transformers class information extracted from dependency + :returns: A string matching the repo path for the class""" + + import re + + doc_attempt = [] + if hasattr(class_map.config, "forward"): + doc_attempt = [getattr(class_map.config, "forward")] + doc_attempt.append(class_map.config) + for pattern in doc_attempt: + doc_string = pattern.__doc__ + matches = re.findall(r"\[([^\]]+)\]", doc_string) + if matches: + try: + repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + nfo(f"ERROR >>{matches} : LOG >> {error_log}") + continue + return repo_path + return None def class_to_mir_tag(mir_db: Dict[str, str], code_name: str) -> Optional[str]: diff --git a/mir/doc_parser.py b/mir/doc_parser.py index 0455b08..9bf6181 100644 --- a/mir/doc_parser.py +++ b/mir/doc_parser.py @@ -8,13 +8,6 @@ from mir.config.constants import DocParseData, DocStringParserConstants -def parse_docs(doc_string: str) -> Tuple[Optional[str], Optional[str], Optional[str], Optional[str]]: - parser = DocStringParser(doc_string=doc_string) - result = parser.parse() - if result is not None: - return result - - class DocStringValidator: """Handles validation of docstring data and extracted values.""" @@ -62,7 +55,7 @@ class DocStringParser(BaseModel): def normalize_doc(cls, docs: str) -> str: return DocStringValidator.normalize_doc_string(docs) - def doc_match(self, prefix_set: List[str] = None): + def doc_match(self, prefix_set: List[str] | None = None): if prefix_set is None: prefix_set = DocStringParserConstants.pipe_prefixes candidate = None @@ -160,3 +153,8 @@ def _resolve_variable(self, reference: str, prior_text: str) -> Optional[str]: nfo(f"Warning: {search} not found in docstring.") return None + + +def parse_docs(doc_string: str) -> DocParseData: + parser = DocStringParser(doc_string=doc_string) + return parser.parse() diff --git a/mir/indexers.py b/mir/indexers.py index d173085..7d78c6a 100644 --- a/mir/indexers.py +++ b/mir/indexers.py @@ -5,12 +5,13 @@ # pylint:disable=no-name-in-module import sys -from typing import Any, Callable, Dict, List, Optional -from mir.doc_parser import parse_docs -from mir.tag import make_mir_tag -from mir.inspect.classes import resolve_code_names, extract_init_params +from typing import Any, Callable + from mir.config.console import nfo -from mir.config.conversion import import_submodules +from mir.config.constants import ClassMapEntry, extract_init_params +from mir.config.conversion import get_repo_from_class_map, import_submodules +from mir.doc_parser import parse_docs +from mir.tag import mir_prefix_from_forward_pass, mir_tag_from_config, tag_model_from_repo if "pytest" in sys.modules: import diffusers # noqa # pyright:ignore[reportMissingImports] # pylint:disable=unused-import @@ -20,63 +21,20 @@ def check_migrations(repo_path: str): """Replaces old organization names in repository paths with new ones.\n :param repo_path: Original repository path containing old organization names :return: Updated repository path with new organization names""" - org_migration: dict[str, str] = { - "/helium-2b": "/helium-1-2b", - "allenai/Olmo2-7B-1124-hf": "allenai/Olmo-2-1124-7B", - "apple/mobilevitv2-1.0": "apple/mobilevitv2-1.0-imagenet1k-256", - "caidas/swin2SR-classical-sr-x2-64": "caidas/swin2SR-classical-sr-x2-64", - "facebook/hiera-base-224": "facebook/hiera-base-224-hf", - "facebook/sam_hq-vit-huge": "syscv-community/sam-hq-vit-huge", - "facebook/vit_msn_base": "facebook/vit-msn-base", - "facebook/wav2vec2-bert-rel-pos-large": "facebook/w2v-bert-2.0", - "google/gemma-3-4b": "google/gemma-3-4b-it", - "google/gemma2-7b": "google/gemma-2-9b", - "google/gemma3_text-7b": "google/gemma-3-12b-it", - "IDEA-Research/dab_detr-base": "IDEA-Research/dab-detr-resnet-50", - "LGAI-EXAONE/EXAONE-4.0-Instruct": "LGAI-EXAONE/EXAONE-4.0-32B", - "meta/chameleon-7B'": "facebook/chameleon-7b", - "mixtralai/Mixtral-8x7B": "mistralai/Mixtral-8x7B-v0.1", - "paligemma-hf/paligemma-2b": "google/paligemma2-3b-mix-224", - "pixtral-hf/pixtral-9b": "mistralai/Pixtral-12B-Base-2409", - "Qwen/Qwen2-7B-beta": "Qwen/Qwen2-7B", - "Qwen/Qwen3-15B-A2B": "Qwen/Qwen3-30B-A3B", - "s-JoL/Open-Llama-V1": "openlm-research/open_llama_3b", - "Salesforce/instruct-blip-flan-t5": "Salesforce/instructblip-flan-t5-xl", - "state-spaces/mamba2-2.8b": "AntonV/mamba2-2.7b-hf", - "ibm-fms/FalconH1-9.8b-2.2T-hf": "tiiuae/Falcon-H1-34B-Instruct", - "nvidia/nemotron-3-8b-base-4k-hf": "mgoin/nemotron-3-8b-chat-4k-sft-hf", - "THUDM/": "zai-org/", - "THUDM/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", - "zai-org/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", - } - for old_name, new_name in org_migration.items(): - if old_name in repo_path: - repo_path = repo_path.replace(old_name, new_name) - # print(repo_path) - return repo_path - + import os -def flag_config(transformers: bool = False, data: dict = None, **kwargs): - """Set type of MIR prefix depending on model type\n - :param transformers: Use transformers data instead of diffusers data, defaults to False - :raises ValueError: Model type not detected - :return: MIR prefix based on model configuration""" from mir.config.json_io import read_json_file - data = read_json_file("mir/spec/template.json") - - if transformers: - flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object - else: - flags = data["arch"]["diffuser"] # pylint:disable=unsubscriptable-object - for mir_prefix, key_match in flags.items(): - if any(kwargs.get(param) for param in key_match): - return mir_prefix - return None - # nfo(f"Unrecognized model type with {kwargs}\n" ) + root_folder = os.path.dirname(__file__) + migration_file = os.path.join(os.path.join(root_folder, "spec", "repo_migrations.json")) + repo_migrations = read_json_file(migration_file) + for old_name, new_name in repo_migrations.items(): + if old_name in repo_path: + repo_path = repo_path.replace(old_name, new_name) + return repo_path -def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Optional[Callable] = None) -> tuple[str, Dict[str, Dict[Any, Any]]]: +def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n :param repo_path (str): Repository path. :param model_class_obj (str): The model class function @@ -105,7 +63,7 @@ def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Optional elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): mir_prefix = "info.controlnet" else: - mir_prefix = flag_config(**sub_segments) + mir_prefix = mir_prefix_from_forward_pass(**sub_segments) if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: nfo(f"Failed to detect type for {class_name} {list(sub_segments)}\n") else: @@ -115,7 +73,7 @@ def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Optional repo_path = "stabilityai/stable-diffusion-3.5-medium" if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: class_name = "HunyuanVideoPipeline" - mir_series, mir_comp = list(make_mir_tag(repo_path, decoder)) + mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) mir_series = mir_prefix + "." + mir_series repo_path = check_migrations(repo_path) # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) @@ -127,7 +85,7 @@ def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Optional return mir_series, {mir_comp: prefixed_data} -def diffusers_index() -> Dict[str, Dict[str, Dict[str, Any]]]: +def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: """Generate diffusion model data for MIR index\n :return: Dictionary ready to be applied to MIR data fields """ @@ -140,45 +98,53 @@ def diffusers_index() -> Dict[str, Dict[str, Dict[str, Any]]]: "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt "ChromaPipeline": "lodestones/Chroma", } - from mir.inspect.metadata import gather_diffusers_metadata - extracted_docs = list(gather_diffusers_metadata()) + from mir.inspect.metadata import find_diffusers_docstrings + + extracted_docstrings = find_diffusers_docstrings() + model_info = [ + extract # + for pipeline in extracted_docstrings + for extract in pipeline + ] pipe_data = {} # pipeline_stable_diffusion_xl_inpaint - print(f"extracted_docs: {extracted_docs}") - for code_name, file_name, docs in extracted_docs: - parse_result = parse_docs(docs) - print(f"parse_result: {parse_result}") - if parse_result: - pipe_class = parse_result.pipe_class - pipe_repo = parse_result.pipe_repo - staged_class = parse_result.staged_class - staged_repo = parse_result.staged_repo - for class_name, swap_repo in special_classes.items(): - if pipe_class == class_name: - pipe_repo = swap_repo - break - model_class_obj = import_submodules(pipe_class, f"diffusers.pipelines.{code_name}.{file_name}") - extract_init_params(model_class_obj) + + for extract in model_info: + pipe = parse_docs(extract.doc_string) + if not pipe: + nfo(f"Doc string not found in '{extract.package_name}' in {extract.file_name}") + continue + for class_name, swap_repo in special_classes.items(): + if pipe.pipe_class == class_name: + pipe.pipe_repo = swap_repo + break + model_class_obj = import_submodules(pipe.pipe_class, f"diffusers.pipelines.{extract.package_name}.{extract.file_name}") + extract_init_params(model_class_obj) + try: + series, comp_data = create_pipe_entry(pipe.pipe_repo, pipe.pipe_class) + except TypeError: + pass # Attempt 1 + if pipe_data.get(series): + if "img2img" in pipe.pipe_class.lower(): + continue + pipe_data.setdefault(series, {}).update(comp_data) + special_conditions = special_repos | special_classes + if pipe.staged_class or pipe.pipe_repo in list(special_conditions): + test = special_conditions.get(pipe.pipe_repo) + if test: + staged_repo = test + pipe.staged_class = pipe.pipe_class try: - series, comp_data = create_pipe_entry(pipe_repo, pipe_class) - except TypeError: - pass # Attempt 1 - if pipe_data.get(series): - if "img2img" in pipe_class.lower(): - continue + series, comp_data = create_pipe_entry( + staged_repo if pipe.staged_repo else pipe.pipe_repo, + pipe.staged_class # + if pipe.staged_class + else pipe.pipe_class, + ) + except TypeError as error_log: + nfo(series, comp_data) + nfo(error_log) + continue # Attempt 2, pipe_data.setdefault(series, {}).update(comp_data) - special_conditions = special_repos | special_classes - if staged_class or pipe_repo in list(special_conditions): - test = special_conditions.get(pipe_repo) - if test: - staged_repo = test - staged_class = pipe_class - try: - series, comp_data = create_pipe_entry(staged_repo if staged_repo else pipe_repo, staged_class if staged_class else pipe_class) - except TypeError as error_log: - print(series, comp_data) - print(error_log) - continue # Attempt 2, - pipe_data.setdefault(series, {}).update(comp_data) return dict(pipe_data) @@ -186,107 +152,37 @@ def transformers_index(): """Generate LLM model data for MIR index\n :return: Dictionary ready to be applied to MIR data fields""" - import re + import os - import transformers from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING_NAMES - from mir.inspect.metadata import gather_transformers_metadata - - corrections: dict[dict[str, str | dict[str, list[str]]]] = { # models with incorrect repos or config - "BarkModel": { - "repo_path": "suno/bark", - "sub_segments": {"n_head": [""]}, - }, - "GraniteSpeechForConditionalGeneration": { - "repo_path": "ibm-granite/granite-speech-3.3-8b", - "sub_segments": {"encoder_layers": [""], "decoder_layers": [""]}, - }, - "GptOssModel": { - "repo_path": "openai/gpt-oss-120b", - }, - "GraniteModel": { - "repo_path": "ibm-granite/granite-3.3-2b-base", - "sub_segments": {"rope_theta": [""]}, - }, - "DPRQuestionEncoder": { - "repo_path": "facebook/dpr-question_encoder-single-nq-base", - "sub_segments": {"local_attention": [""], "classifier_proj_size": [""]}, - }, - "CohereModel": { - "repo_path": "CohereForAI/c4ai-command-r-v01", - "sub_segments": {"attn_config": [""], "num_codebooks": [""]}, - }, - "Cohere2Model": { - "repo_path": "CohereLabs/c4ai-command-r7b-12-2024", - "sub_segments": {"attn_config": [""], "num_codebooks": [""]}, - }, - "GraniteMoeHybridModel": { - "repo_path": "ibm-research/PowerMoE-3b", - }, - "BertForMaskedLM": { - "repo_path": "google-bert/bert-base-uncased", - }, - "DistilBertModel": { - "repo_path": "distilbert-base-uncased", - }, - "GraniteMoeModel": { - "repo_path": "ibm-research/PowerMoE-3b", - }, - "AriaModel": { - "repo_path": "rhymes-ai/Aria-Chat", - "sub_segments": {"vision_config": [""], "text_config": [""]}, - }, - "TimmWrapperModel": { - "repo_path": "timm/resnet18.a1_in1k", - "sub_segments": {"_resnet_": [""]}, - }, - "FunnelModel": { - "repo_path": "funnel-transformer/small", - "sub_segments": {"separate_cls": [""]}, - }, - } + from mir.config.json_io import read_json_file + + root_folder = os.path.dirname(__file__) + params_file = os.path.join(os.path.join(root_folder, "spec", "missing_params.json")) + missing_config_params = read_json_file(params_file) + from mir.inspect.metadata import map_transformers_classes mir_data = {} - # transformers_data = stock_llm_data() - transformers_data: Dict[Callable, List[str]] = gather_transformers_metadata() - for model_class_obj, model_data in transformers_data.items(): - class_name = model_class_obj.__name__ - if class_name in list(corrections): # conditional correction from mappings above: `extract_init_params` doesn't return anything in these cases - repo_path = corrections[class_name]["repo_path"] - sub_segments = corrections[class_name].get("sub_segments", extract_init_params(model_data["config"][-1], "transformers")) - else: - repo_path = "" - if model_data.get("config"): - doc_attempt = [getattr(transformers, model_data["config"][-1]), model_class_obj.forward] - for pattern in doc_attempt: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) - if matches: - try: - repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - nfo(f"ERROR >>{matches} : LOG >> {error_log}") - pass - break - sub_segments: Dict[str, List[str]] = extract_init_params(model_data["config"][-1], "transformers") - if sub_segments and list(sub_segments) != ["kwargs"] and list(sub_segments) != ["use_cache", "kwargs"] and repo_path is not None: - mir_prefix = flag_config(transformers=True, **sub_segments) - if mir_prefix is None: - nfo(f"Failed to detect type for {class_name} {list(sub_segments)}\n") - continue - else: - mir_prefix = "info." + mir_prefix - code_name = resolve_code_names(class_name) - if code_name != "funnel": - mir_suffix, mir_comp = list(make_mir_tag(repo_path)) - else: - mir_suffix, mir_comp = ["funnel", "*"] - mir_series = mir_prefix + "." + mir_suffix + transformers_data: list[ClassMapEntry] = map_transformers_classes() + for entry in transformers_data: + print(entry) + repo_path = get_repo_from_class_map(entry) + if config := missing_config_params.get(entry.name, {}): + entry.config_params = config.get("params", entry.config_params) + if not repo_path: + repo_path = config["repo_path"] + if not repo_path: + raise ValueError(f"Unable to determine repo from {entry}") + if entry.config_params and list(entry.config_params) != ["use_cache", "kwargs"]: + mir_series, mir_comp, mir_suffix = mir_tag_from_config(entry, repo_path) # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) repo_path = check_migrations(repo_path) tk_pkg = {} - tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(code_name) + tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) + if isinstance(tokenizer_classes, str): + tokenizer_classes = [tokenizer_classes] + print(type(tokenizer_classes)) # mode = modalities.get("mode") if tokenizer_classes: index = 0 @@ -309,7 +205,7 @@ def transformers_index(): mir_comp: { "repo": repo_path, "pkg": { - 0: {"transformers": class_name}, + 0: {"transformers": entry.model_name}, }, # "mode": mode, }, diff --git a/mir/inspect/classes.py b/mir/inspect/classes.py index 30a1681..23b955c 100644 --- a/mir/inspect/classes.py +++ b/mir/inspect/classes.py @@ -80,36 +80,6 @@ def extract_inherited_classes(model_class: Union[Callable, str], pkg_name: Optio return class_names -def extract_init_params(module: Union[Callable, str], pkg_name: Optional[str] = None) -> Dict[str, List[str]]: - """Pick apart a Diffusers or Transformers pipeline class and find its constituent parts (formerly root_class)\n - :param module: Origin pipeline as a class or as a string - :param library: name of a library to import the class from, only if a string is provided - :return: Dictionary of sub-classes from the `module`""" - - import inspect - - if pkg_name and isinstance(module, str): - module = import_submodules(module, pkg_name) - signature = inspect.signature(module.__init__) - class_names = {} - for folder, param in signature.parameters.items(): - if folder != "self": - sub_module = str(param.annotation).split("'") - if len(sub_module) > 1 and sub_module[1] not in [ - "bool", - "int", - "float", - "complex", - "str", - "list", - "tuple", - "dict", - "set", - ]: - class_names.setdefault(folder, sub_module[1].split(".")) - return class_names - - # def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: # from nnll.download.hub_cache import download_hub_file diff --git a/mir/inspect/metadata.py b/mir/inspect/metadata.py index 1b0befa..190d61b 100644 --- a/mir/inspect/metadata.py +++ b/mir/inspect/metadata.py @@ -1,147 +1,98 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -import pkgutil -from typing import Dict, Generator, List +from typing import Callable, Generator import diffusers +from mir.config.constants import ClassMapEntry, DocStringEntry, extract_init_params +from mir.config.conversion import retrieve_diffusers_docstrings -from mir.inspect.classes import extract_init_params -from mir.config.conversion import pkg_path_to_docstring, file_name_to_docstring +# if code_name and "__" not in code_name: +# tasks = TaskAnalyzer.show_transformers_tasks(code_name=code_name) +# if tasks and isinstance(tasks, list): # Ensure tasks is a list +# task_pipe = next(iter(tasks)) +# if isinstance(task_pipe, tuple): +# task_pipe = task_pipe[0] +# if task_pipe not in exclude_list: +# model_class = getattr(__import__("transformers"), task_pipe) # this is done to get the path to the config +# model_data = extract_init_params(model_class) +# if model_data and ("inspect" not in model_data["config"]) and ("deprecated" not in list(model_data["config"])): +# transformer_data.setdefault(model_class, model_data) +# else: +# model_data = None +# # Reset task_pipe if tasks was None or not a list +# if not tasks or not isinstance(tasks, list): +# task_pipe = None -def gather_transformers_metadata() -> Dict[str, List[str]]: +# if not model_data and code_name not in second_exclude_list: # second attempt +# if code_name == "donut": +# code_name = "donut-swin" +# if not task_pipe and code_name and MODEL_MAPPING_NAMES.get(code_name.replace("_", "-")): +# model_class = getattr(__import__("transformers"), MODEL_MAPPING_NAMES[code_name.replace("_", "-")], None) +# elif task_pipe: +# model_class = getattr(__import__("transformers"), task_pipe) +# config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("_", "-")) +# if not config_class: +# config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("-", "_")) +# if config_class: +# config_class_obj = getattr(__import__("transformers"), config_class) +# model_data = {"config": str(config_class_obj.__module__ + "." + config_class_obj.__name__).split(".")} +# if model_data and ("inspect" not in model_data) and ("deprecated" not in model_data) and model_class: +# transformer_data.setdefault(model_class, model_data) +# return transformer_data + + +def map_transformers_classes() -> list[ClassMapEntry]: """Eat the 🤗Transformers classes as a treat, leaving any tasty subclass class morsels neatly arranged as a dictionary.\n Nom. :return: Tasty mapping of subclasses to their class references""" + from transformers.models.auto.configuration_auto import CONFIG_MAPPING + from transformers.models.auto.modeling_auto import MODEL_MAPPING # config: model map - transformer_data = {} - exclude_list = [ - "DecisionTransformerModel", - "DistilBertModel", - "GraphormerModel", - "GPTBigCodeModel", - "TimmBackbone", - "PerceptionEncoder", - "SeamlessM4Tv2Model", - "SeamlessM4TModel", - "VisionTextDualEncoderModel", - ] - second_exclude_list = [ - "vision-text-dual-encoder", - "vision_text_dual_encoder", - "gpt_bigcode", - "data2vec", - "vision-text", - "mllama" - "bert_japanese", - "cpm", - "dab_detr", - "decision_transformer", - "timm_backbone", - ] # there just isnt a repo in this one - import os - - import transformers - from transformers.models.auto.modeling_auto import CONFIG_MAPPING_NAMES, MODEL_MAPPING_NAMES - - from mir.inspect.tasks import TaskAnalyzer - - model_data = None - task_pipe = None - model_names = list(dict(MODEL_MAPPING_NAMES).keys()) - folder_data = {*model_names} - models_folder = os.path.join(os.path.dirname(transformers.__file__), "models") - folder_data = folder_data.union(os.listdir(models_folder)) - for code_name in folder_data: - model_class = None - if code_name and "__" not in code_name: - tasks = TaskAnalyzer.show_transformers_tasks(code_name=code_name) - if tasks and isinstance(tasks, list): # Ensure tasks is a list - task_pipe = next(iter(tasks)) - if isinstance(task_pipe, tuple): - task_pipe = task_pipe[0] - if task_pipe not in exclude_list: - model_class = getattr(__import__("transformers"), task_pipe) # this is done to get the path to the config - model_data = extract_init_params(model_class) - if model_data and ("inspect" not in model_data["config"]) and ("deprecated" not in list(model_data["config"])): - transformer_data.setdefault(model_class, model_data) - else: - model_data = None - # Reset task_pipe if tasks was None or not a list - if not tasks or not isinstance(tasks, list): - task_pipe = None - - if not model_data and code_name not in second_exclude_list: # second attempt - if code_name == "donut": - code_name = "donut-swin" - if not task_pipe and code_name and MODEL_MAPPING_NAMES.get(code_name.replace("_", "-")): - model_class = getattr(__import__("transformers"), MODEL_MAPPING_NAMES[code_name.replace("_", "-")], None) - elif task_pipe: - model_class = getattr(__import__("transformers"), task_pipe) - config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("_", "-")) - if not config_class: - config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("-", "_")) - if config_class: - config_class_obj = getattr(__import__("transformers"), config_class) - model_data = {"config": str(config_class_obj.__module__ + "." + config_class_obj.__name__).split(".")} - if model_data and ("inspect" not in model_data) and ("deprecated" not in model_data) and model_class: - transformer_data.setdefault(model_class, model_data) - return transformer_data + model_data = [] + for config_name, config_obj in CONFIG_MAPPING.items(): + model_params = None + if model_obj := MODEL_MAPPING.get(config_obj, None): + if isinstance(model_obj, Callable): + model_obj = (model_obj,) + assert isinstance(model_obj, tuple) + for model_class in model_obj: + if model_params and ("inspect" not in model_params["config"]) and ("deprecated" not in list(model_params["config"])): + pass + else: + model_params = None + model_name = model_class.__name__ + model_data.append( + ClassMapEntry( + name=config_name, + model_name=model_name.split(".")[-1], + model=model_class, # type: ignore + config=config_obj, + ), + ) + return model_data -def gather_diffusers_metadata() -> Generator: - """Draw down docstrings from 🤗Diffusers library, minimizing internet requests\n +def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: + """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n :return: Docstrings for common diffusers models""" + import os - non_standard = { - "cogvideo": "cogvideox", - "cogview3": "cogview3plus", - "deepfloyd_if": "if", - "cosmos": "cosmos2_text2image", # search folder for all files containing 'EXAMPLE DOC STRING' - "visualcloze": "visualcloze_generation", - } + from diffusers.pipelines import _import_structure - exclusion_list = [ # no doc string or other issues. all can be be gathered by other means - "autopipeline", # - "dance_diffusion", # no doc_string - "ddim", - "ddpm", - "deprecated", - "diffusionpipeline", # - "dit", - "latent_consistency_models", # "latent_consistency_text2img", - "latent_diffusion", # no doc_string - "ledits_pp", # "leditspp_stable_diffusion", - "marigold", # specific processing routines - "omnigen", # tries to import torchvision - "pag", # not model based - "paint_by_example", # no docstring - "pia", # lora adapter - "semantic_stable_diffusion", # no_docstring - "stable_diffusion_attend_and_excite", - "stable_diffusion_diffedit", - "stable_diffusion_k_diffusion", # tries to import k_diffusion - "stable_diffusion_panorama", - "stable_diffusion_safe", # impossible - "stable_diffusion_sag", # - "t2i_adapter", - "text_to_video_synthesis", - "unclip", - "unidiffuser", - "controlnet_hunyuandit", - "hunyuandit", - # these are uncommon afaik - ] + from mir.config.json_io import read_json_file - for _, pkg_name, is_pkg in pkgutil.iter_modules(diffusers.pipelines.__path__): - if is_pkg and pkg_name not in exclusion_list: - file_specific = non_standard.get(pkg_name, pkg_name) - folder_name = getattr(diffusers.pipelines, str(pkg_name)) - if folder_name: - if hasattr(folder_name, "_import_structure"): - yield from pkg_path_to_docstring(pkg_name, folder_name) - else: - yield from file_name_to_docstring(pkg_name, file_specific) + project_root = os.path.dirname(os.path.dirname(__file__)) + pattern_file = os.path.join(project_root, "spec", "docstring_patterns.json") + docstring_patterns = read_json_file(pattern_file) + exclusion_list = docstring_patterns["exclusion_list"] + uncommon_naming = docstring_patterns["uncommon_naming"] + for pipe_name in _import_structure.keys(): + if pipe_name not in exclusion_list: + file_specific = uncommon_naming.get(pipe_name, pipe_name) + if import_name := getattr(diffusers.pipelines, str(pipe_name)): + file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] + yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) else: continue diff --git a/mir/inspect/pipes.py b/mir/inspect/pipes.py index 8bcc738..8ef1d06 100644 --- a/mir/inspect/pipes.py +++ b/mir/inspect/pipes.py @@ -4,23 +4,22 @@ from typing import List, Optional -def get_transformer_config_classes(parameter_filter: Optional[str] = None) -> List[str]: +def show_shared_hyperparameters(parameter_filter: Optional[str] = None) -> List[str]: """Show all config classes in the Transformer package with the specified init annotation\n :param from_match: Narrow the classes to only those with an exact key inside :return: A list of all Classes""" - from mir.inspect.metadata import gather_transformers_metadata - from mir.inspect.classes import extract_init_params + from mir.inspect.metadata import map_transformers_classes + from mir.config.constants import extract_init_params - transformers_data = gather_transformers_metadata() + transformers_data = map_transformers_classes() config_data = [] - for model_path in list(transformers_data.values()): - config_class = model_path["config"][-1] + for entry in transformers_data: if parameter_filter: - segments = extract_init_params(config_class, pkg_name="transformers") + segments = extract_init_params(module=entry.config, package_name="transformers") if parameter_filter in list(segments): - config_data.append(config_class) + config_data.append(entry.config) else: - config_data.append(config_class) + config_data.append(entry.config) return config_data diff --git a/mir/inspect/tasks.py b/mir/inspect/tasks.py index 1e10cc4..3356ef5 100644 --- a/mir/inspect/tasks.py +++ b/mir/inspect/tasks.py @@ -69,6 +69,7 @@ def show_transformers_tasks(class_name: str | None = None, code_name: str | None elif code_name: from mir.config.constants import mapped_cls from httpx import HTTPStatusError + try: model_class = mapped_cls(code_name) if model_class is not None: @@ -181,13 +182,13 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir :param mir_db: MIRDatabase instance for querying tags/IDs :return: Tuple containing MIR tag and class name""" - from mir.tag import make_scheduler_tag + from mir.tag import tag_scheduler mir_tag = None class_name = pipe_class.__name__ if pipe_role in ["scheduler", "image_noising_scheduler", "prior_scheduler"]: sub_field = pipe_class.__module__.split(".")[0] - scheduler_series, scheduler_comp = make_scheduler_tag(class_name) + scheduler_series, scheduler_comp = tag_scheduler(class_name) mir_tag = [f"ops.scheduler.{scheduler_series}", scheduler_comp] if not mir_db.database.get(mir_tag[0], {}).get(mir_tag[1]): mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="ops.scheduler") @@ -266,3 +267,65 @@ def trace_classes(pipe_class: str, pkg_name: str) -> Dict[str, List[str]]: related_pipes = set(related_pipes) related_pipes.update(tuple(x) for x in extract_inherited(model_class=pipe_class, pkg_name=pkg_name)) return related_pipes + + +def main(mir_db: MIRDatabase = None): + """Parse arguments to feed to dict header reader""" + import argparse + import asyncio + from mir.automata import assimilate + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", + usage="mir-tasks", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + if not mir_db: + mir_db = MIRDatabase() + + auto_pkg = TaskAnalyzer() + task_tuple = asyncio.run(auto_pkg.detect_tasks(mir_db)) + + assimilate(mir_db, [task for task in task_tuple]) + + mir_db.write_to_disk() + return mir_db + + +def run_task(): + main() + + +def pipe(mir_db: MIRDatabase = None): + import argparse + import asyncio + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", + usage="mir-pipe", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + from mir.automata import assimilate + + if not mir_db: + mir_db = MIRDatabase() + + auto_pkg = TaskAnalyzer() + pipe_tuple = asyncio.run(auto_pkg.detect_pipes(mir_db)) + assimilate(mir_db, [pipe for pipe in pipe_tuple]) + mir_db.write_to_disk() + return mir_db + + +if __name__ == "__main__": + pipe() diff --git a/mir/maid.py b/mir/maid.py index e26a7fd..a25a3eb 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -20,7 +20,7 @@ def __init__(self, database: dict | None = None) -> None: if not database: try: - self.database = read_json_file(MIR_PATH_NAMED) + self.database: dict[str, Any] = read_json_file(MIR_PATH_NAMED) except JSONDecodeError as error_log: dbuq(error_log) self.database = {} @@ -32,7 +32,7 @@ def add(self, resource: dict[str, Any]) -> None: parent_key = next(iter(resource)) if self.database is not None: if self.database.get(parent_key, 0): - self.database[parent_key] = {**self.database[parent_key], **resource[parent_key]} + self.database[parent_key] = self.database[parent_key] | resource[parent_key] else: self.database[parent_key] = resource[parent_key] @@ -65,7 +65,7 @@ def read_from_disk(self, data: Optional[dict] = None) -> dict[str, Any]: self.database = read_json_file(MIR_PATH_NAMED) return self.database - def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibility: str) -> List[str]: + def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibility: str) -> list[str | bool]: """Process a single value for matching against the target\n :param value: An unknown string value :param target: The search target @@ -79,7 +79,7 @@ def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibilit results = [] if isinstance(maybe_match, str): - maybe_match = [maybe_match] + maybe_match: list[str] = [maybe_match] elif isinstance(maybe_match, dict): if isinstance(next(iter(maybe_match)), int): maybe_match = list(maybe_match.values()) @@ -97,7 +97,7 @@ def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibilit return results @staticmethod - def grade_maybes(matches: List[List[str]], target: str) -> list[str, str]: + def grade_maybes(matches: List[List[str]], target: str) -> list[str] | None: """Evaluate and select the best match from a list of potential matches\n :param matches: Possible matches to compare :param target: Desired entry to match @@ -151,7 +151,6 @@ def find_tag(self, field: str, target: str, sub_field: Optional[str] = None, dom parameters = r"-gguf|-exl2|-exl3|-onnx|-awq|-mlx|-ov" # target = target.lower().strip("-") target = re.sub(parameters, "", target) - self.matches = None self.matches = [] for series, comp in self.database.items(): @@ -229,6 +228,9 @@ def main(mir_db: Callable | None = None, remake: bool = True) -> None: add_mir_diffusion(mir_db) add_mir_llm(mir_db) add_mir_vae(mir_db) + mir_db.write_to_disk() + mir_db = MIRDatabase() + mir_db = MIRDatabase() mir_update(mir_db) mir_db.write_to_disk() @@ -243,8 +245,6 @@ def main(mir_db: Callable | None = None, remake: bool = True) -> None: if "pytest" not in sys_modules: # import argparse - from mir.config.console import nfo - parser = argparse.ArgumentParser( formatter_class=argparse.RawTextHelpFormatter, description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", @@ -283,6 +283,7 @@ def main(mir_db: Callable | None = None, remake: bool = True) -> None: pipes = not args.pipes_off main(remake=remake) + update_mir() from mir.inspect.tasks import pipe, run_task mir_db = run_task() diff --git a/mir/mir.json b/mir/mir.json index 59ae13b..78868b2 100644 --- a/mir/mir.json +++ b/mir/mir.json @@ -1,3 +1,5027 @@ { - "expected": "data" + "info.controlnet.sd-controlnet-canny": { + "*": { + "repo": "lllyasviel/sd-controlnet-canny", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.blipdiffusion-controlnet": { + "*": { + "repo": "Salesforce/blipdiffusion-controlnet", + "pkg": { + "0": { + "diffusers": "BlipDiffusionControlNetPipeline" + } + } + } + }, + "info.controlnet.control-v11p-sd15-inpaint": { + "*": { + "repo": "lllyasviel/control_v11p_sd15_inpaint", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-canny-sdxl-1": { + "*": { + "repo": "diffusers/controlnet-canny-sdxl-1.0", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-depth-sdxl-1": { + "*": { + "repo": "diffusers/controlnet-depth-sdxl-1.0-small", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.controlnet.controlnet-union-sdxl-1": { + "*": { + "repo": "xinsir/controlnet-union-sdxl-1.0", + "pkg": { + "0": { + "diffusers": "ControlNetUnionModel" + } + } + } + }, + "info.controlnet.sd3-controlnet-canny": { + "*": { + "repo": "InstantX/SD3-Controlnet-Canny", + "pkg": { + "0": { + "diffusers": "SD3ControlNetModel" + } + } + } + }, + "info.controlnet.sd3-controlnet-inpainting": { + "*": { + "repo": "alimama-creative/SD3-Controlnet-Inpainting", + "pkg": { + "0": { + "diffusers": "SD3ControlNetModel" + } + } + } + }, + "info.controlnet.testing-conrolnetxs-sd2-canny": { + "*": { + "repo": "UmerHA/Testing-ConrolNetXS-SD2.1-canny", + "pkg": { + "0": { + "diffusers": "ControlNetXSAdapter" + } + } + } + }, + "info.controlnet.testing-conrolnetxs-sdxl-canny": { + "*": { + "repo": "UmerHA/Testing-ConrolNetXS-SDXL-canny", + "pkg": { + "0": { + "diffusers": "ControlNetXSAdapter" + } + } + } + }, + "info.unet.stable-diffusion-v1-5": { + "*": { + "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", + "pkg": { + "0": { + "diffusers": "StableDiffusionPipeline" + } + } + } + }, + "info.unet.stable-unclip-2-1-l": { + "*": { + "repo": "fusing/stable-unclip-2-1-l", + "pkg": { + "0": { + "diffusers": "StableUnCLIPPipeline" + } + } + } + }, + "info.unet.stable-diffusion-2-1-unclip": { + "*": { + "repo": "stabilityai/stable-diffusion-2-1-unclip-small", + "pkg": { + "0": { + "diffusers": "StableUnCLIPImg2ImgPipeline" + } + } + } + }, + "info.unet.stable-diffusion-xl-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-base-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLPipeline" + } + } + }, + "pony-diffusion": { + "file_256": [ + "67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3" + ], + "layer_256": [ + "465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e" + ], + "layer_b3": [ + "bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071" + ] + }, + "pony-diffusion-turbo": { + "file_256": [ + "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", + "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2" + ], + "layer_256": [ + "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", + "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52" + ], + "layer_b3": [ + "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", + "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc" + ] + }, + "animagine-xl-4": { + "repo": "cagliostrolab/animagine-xl-4.0", + "file_256": [ + "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", + "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", + "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", + "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0" + ], + "layer_256": [ + "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", + "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", + "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", + "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65" + ], + "layer_b3": [ + "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", + "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", + "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", + "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447" + ] + }, + "illustrious-xl-v2": { + "repo": "OnomaAIResearch/Illustrious-XL-v2.0", + "file_256": [ + "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", + "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", + "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", + "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", + "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd" + ], + "layer_256": [ + "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", + "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", + "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", + "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", + "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10" + ], + "layer_b3": [ + "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", + "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", + "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", + "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", + "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c" + ] + }, + "playground-v2---aesthetic": { + "repo": "playgroundai/playground-v2.5-1024px-aesthetic", + "pkg": { + "0": { + "diffusers": "DiffusionPipeline", + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 50, + "guidance_scale": 3 + } + } + }, + "file_256": [ + "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", + "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", + "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", + "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", + "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", + "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a" + ], + "layer_256": [ + "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", + "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", + "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", + "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", + "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c" + ], + "layer_b3": [ + "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", + "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", + "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", + "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", + "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", + "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" + ] + }, + "segmind-vega": { + "repo": "segmind/Segmind-Vega", + "file_256": [ + "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", + "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", + "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2" + ], + "layer_256": [ + "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", + "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", + "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741" + ], + "layer_b3": [ + "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", + "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", + "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1" + ] + }, + "ssd": { + "repo": "segmind/SSD-1B", + "file_256": [ + "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", + "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", + "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", + "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", + "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a" + ], + "layer_256": [ + "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", + "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", + "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", + "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", + "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" + ], + "layer_b3": [ + "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", + "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", + "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", + "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", + "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" + ] + } + }, + "info.unet.stable-diffusion-xl-refiner-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-refiner-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLImg2ImgPipeline" + } + } + } + }, + "info.unet.sdxl-pix2pix-768": { + "*": { + "repo": "diffusers/sdxl-instructpix2pix-768", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLInstructPix2PixPipeline" + } + } + } + }, + "info.dit.allegro": { + "*": { + "repo": "rhymes-ai/Allegro", + "pkg": { + "0": { + "diffusers": "AllegroPipeline" + } + } + } + }, + "info.dit.amused-512": { + "*": { + "repo": "amused/amused-512", + "pkg": { + "0": { + "diffusers": "AmusedInpaintPipeline" + } + } + } + }, + "info.lora.animatediff-motion-adapter-v1-5-2": { + "*": { + "repo": "guoyww/animatediff-motion-adapter-v1-5-2", + "pkg": { + "0": { + "diffusers": "AnimateDiffVideoToVideoPipeline" + } + } + } + }, + "info.lora.animatediff-motion-adapter-sdxl": { + "*": { + "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", + "pkg": { + "0": { + "diffusers": "AnimateDiffSDXLPipeline" + } + } + } + }, + "info.controlnet.animatediff-sparsectrl-scribble": { + "*": { + "repo": "guoyww/animatediff-sparsectrl-scribble", + "pkg": { + "0": { + "diffusers": "SparseControlNetModel" + } + } + } + }, + "info.controlnet.animatelcm": { + "*": { + "repo": "wangfuyun/AnimateLCM", + "pkg": { + "0": { + "diffusers": "ControlNetModel" + } + } + } + }, + "info.dit.bria-3": { + "*": { + "repo": "briaai/BRIA-3.2", + "pkg": { + "0": { + "diffusers": "BriaPipeline" + } + } + } + }, + "info.dit.flux2-dev": { + "*": { + "repo": "black-forest-labs/FLUX.2-dev", + "pkg": { + "0": { + "diffusers": "Flux2Pipeline" + } + } + } + }, + "info.dit.flux1-schnell": { + "*": { + "repo": "black-forest-labs/FLUX.1-schnell", + "pkg": { + "0": { + "diffusers": "FluxInpaintPipeline" + } + } + }, + "shuttle-3-aesthetic": { + "repo": "shuttleai/shuttle-3.1-aesthetic", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", + "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" + ], + "layer_256": [ + "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", + "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a" + ], + "layer_b3": [ + "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", + "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c" + ] + }, + "shuttle-3-diffusion": { + "repo": "shuttleai/shuttle-3-diffusion", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", + "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", + "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", + "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8" + ], + "layer_256": [ + "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", + "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", + "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c" + ], + "layer_b3": [ + "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", + "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", + "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd" + ] + }, + "shuttle-jaguar": { + "repo": "shuttleai/shuttle-jaguar", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", + "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f" + ], + "layer_b3": [ + "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", + "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672" + ] + } + }, + "info.controlnet.flux1-canny-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Canny-dev", + "pkg": { + "0": { + "diffusers": "FluxControlPipeline" + } + } + } + }, + "info.controlnet.flux1-dev-controlnet-canny": { + "*": { + "repo": "InstantX/FLUX.1-dev-controlnet-canny", + "pkg": { + "0": { + "diffusers": "FluxControlNetModel" + } + } + } + }, + "info.controlnet.flux1-dev-controlnet-canny-alpha": { + "*": { + "repo": "InstantX/FLUX.1-dev-Controlnet-Canny-alpha", + "pkg": { + "0": { + "diffusers": "FluxControlNetModel" + } + } + } + }, + "info.dit.flux1-fill-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Fill-dev", + "pkg": { + "0": { + "diffusers": "FluxFillPipeline" + } + } + } + }, + "info.dit.flux1-kontext-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Kontext-dev", + "pkg": { + "0": { + "diffusers": "FluxKontextInpaintPipeline" + } + } + } + }, + "info.dit.flux1-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-dev", + "pkg": { + "0": { + "diffusers": "FluxPipeline" + } + } + }, + "mystic": { + "repo": "enhanceaiteam/Mystic", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 16, + "guidance_scale": 7.5, + "width": 768, + "height": 1024 + } + } + }, + "file_256": [ + "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", + "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" + ], + "layer_256": [ + "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" + ], + "layer_b3": [ + "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" + ] + }, + "flux1-lite": { + "repo": "freepik/flux.1-lite-8b", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 28 + } + } + }, + "file_256": [ + "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", + "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" + ], + "layer_256": [ + "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" + ], + "layer_b3": [ + "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" + ] + }, + "f-lite": { + "repo": "freepik/f-lite", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "f-lite-texture": { + "repo": "freepik/f-lite-texture", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "flux": { + "repo": "TencentARC/flux-mini", + "file_256": [ + "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" + ], + "layer_256": [ + "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" + ], + "layer_b3": [ + "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" + ] + }, + "flex2": { + "repo": "ostris/Flex.2-preview", + "file_256": [ + "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", + "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" + ], + "layer_256": [ + "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" + ], + "layer_b3": [ + "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" + ] + }, + "flex1-alpha": { + "repo": "ostris/Flex.1-alpha", + "file_256": [ + "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", + "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" + ], + "layer_256": [ + "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" + ], + "layer_b3": [ + "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" + ] + } + }, + "info.dit.prx-512-t2i-sft": { + "*": { + "repo": "Photoroom/prx-512-t2i-sft", + "pkg": { + "0": { + "diffusers": "PRXPipeline" + } + } + } + }, + "info.unet.audioldm-s-v2": { + "*": { + "repo": "cvssp/audioldm-s-full-v2", + "pkg": { + "0": { + "diffusers": "AudioLDMPipeline" + } + } + } + }, + "info.unet.audioldm2": { + "*": { + "repo": "cvssp/audioldm2", + "pkg": { + "0": { + "diffusers": "AudioLDM2Pipeline" + } + } + } + }, + "info.unet.blipdiffusion": { + "*": { + "repo": "Salesforce/blipdiffusion", + "pkg": { + "0": { + "diffusers": "BlipDiffusionPipeline" + } + } + } + }, + "info.dit.chroma": { + "*": { + "repo": "lodestones/Chroma", + "pkg": { + "0": { + "diffusers": "ChromaPipeline" + } + } + }, + "chroma1-hd": { + "repo": "lodestones/Chroma1-HD", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 40 + } + } + }, + "file_256": [ + "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", + "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", + "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc" + ] + }, + "chroma1-flash": { + "repo": "lodestones/Chroma1-Flash", + "pkg": { + "0": { + "diffusers": "ChromaPipeline", + "generation": { + "num_inference_steps": 8, + "guidance_scale": 1.0, + "num_images_per_prompt": 1 + } + } + }, + "file_256": [ + "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", + "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", + "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" + ] + } + }, + "info.dit.chroma1-hd": { + "*": { + "repo": "lodestones/Chroma1-HD", + "pkg": { + "0": { + "diffusers": "ChromaImg2ImgPipeline" + } + } + } + }, + "info.dit.cogvideox": { + "*": { + "repo": "zai-org/CogVideoX-2b", + "pkg": { + "0": { + "diffusers": "CogVideoXPipeline" + } + } + } + }, + "info.controlnet.cogvideox-fun-v-pose": { + "*": { + "repo": "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", + "pkg": { + "0": { + "diffusers": "CogVideoXFunControlPipeline" + } + } + } + }, + "info.dit.cogvideox-i2v": { + "*": { + "repo": "zai-org/CogVideoX-5b-I2V", + "pkg": { + "0": { + "diffusers": "CogVideoXImageToVideoPipeline" + } + } + } + }, + "info.dit.cogview3": { + "*": { + "repo": "zai-org/CogView3-Plus-3B", + "pkg": { + "0": { + "diffusers": "CogView3PlusPipeline" + } + } + } + }, + "info.dit.cogview4": { + "*": { + "repo": "zai-org/CogView4-6B", + "pkg": { + "0": { + "diffusers": "CogView4Pipeline" + } + } + } + }, + "info.controlnet.cogview4-control": { + "*": { + "repo": "zai-org/CogView4-6B-Control", + "pkg": { + "0": { + "diffusers": "CogView4ControlPipeline" + } + } + } + }, + "info.dit.pre-trianed": { + "*": { + "repo": "model_id, revision=\"diffusers/base/pre-trianed", + "pkg": { + "0": { + "diffusers": "Cosmos2_5_PredictBasePipeline" + } + } + } + }, + "info.dit.cosmos-predict2-text2image": { + "*": { + "repo": "nvidia/Cosmos-Predict2-2B-Text2Image", + "pkg": { + "0": { + "diffusers": "Cosmos2TextToImagePipeline" + } + } + } + }, + "info.dit.cosmos-predict2-video2world": { + "*": { + "repo": "nvidia/Cosmos-Predict2-2B-Video2World", + "pkg": { + "0": { + "diffusers": "Cosmos2VideoToWorldPipeline" + } + } + } + }, + "info.dit.cosmos-1-diffusion-text2world": { + "*": { + "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Text2World", + "pkg": { + "0": { + "diffusers": "CosmosTextToWorldPipeline" + } + } + } + }, + "info.dit.cosmos-1-diffusion-video2world": { + "*": { + "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Video2World", + "pkg": { + "0": { + "diffusers": "CosmosVideoToWorldPipeline" + } + } + } + }, + "info.unet.if-i-xl-v1": { + "*": { + "repo": "DeepFloyd/IF-I-XL-v1.0", + "pkg": { + "0": { + "diffusers": "IFPipeline" + } + } + } + }, + "info.dit.easyanimatev5-zh": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimatePipeline" + } + } + } + }, + "info.controlnet.easyanimatev5-zh-control": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-Control-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimateControlPipeline" + } + } + } + }, + "info.dit.easyanimatev5-zh-inp": { + "diffusers": { + "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-InP-diffusers", + "pkg": { + "0": { + "diffusers": "EasyAnimateInpaintPipeline" + } + } + } + }, + "info.dit.hidream-i1": { + "*": { + "repo": "HiDream-ai/HiDream-I1-Full", + "pkg": { + "0": { + "diffusers": "HiDreamImagePipeline" + } + } + } + }, + "info.dit.hunyuandit-v1": { + "diffusers": { + "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanDiTPipeline" + } + } + } + }, + "info.dit.hunyuanvideo": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo", + "pkg": { + "0": { + "diffusers": "HunyuanVideoPipeline" + } + } + } + }, + "info.dit.hunyuanvideo-i2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-I2V", + "pkg": { + "0": { + "diffusers": "HunyuanVideoImageToVideoPipeline" + } + } + } + }, + "info.dit.hunyuanvideo-1-480p-t2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_t2v", + "pkg": { + "0": { + "diffusers": "HunyuanVideo15Pipeline" + } + } + } + }, + "info.dit.hunyuanvideo-1-480p-i2v": { + "*": { + "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_i2v", + "pkg": { + "0": { + "diffusers": "HunyuanVideo15ImageToVideoPipeline" + } + } + } + }, + "info.dit.hunyuanimage-2": { + "diffusers": { + "repo": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanImagePipeline" + } + } + } + }, + "info.dit.hunyuanimage-2-refiner": { + "diffusers": { + "repo": "hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", + "pkg": { + "0": { + "diffusers": "HunyuanImageRefinerPipeline" + } + } + } + }, + "info.unet.kandinsky-2-1": { + "prior": { + "repo": "kandinsky-community/kandinsky-2-1-prior", + "pkg": { + "0": { + "diffusers": "KandinskyPriorPipeline" + } + } + } + }, + "info.unet.kandinsky-2-2": { + "prior": { + "repo": "kandinsky-community/kandinsky-2-2-prior", + "pkg": { + "0": { + "diffusers": "KandinskyPriorPipeline" + } + } + } + }, + "info.dit.latte-1": { + "*": { + "repo": "maxin-cn/Latte-1", + "pkg": { + "0": { + "diffusers": "LattePipeline" + } + } + } + }, + "info.dit.ltx-video": { + "*": { + "repo": "Lightricks/LTX-Video", + "pkg": { + "0": { + "diffusers": "LTXImageToVideoPipeline" + } + } + } + }, + "info.dit.ltx-video-09": { + "*": { + "repo": "Lightricks/LTX-Video-0.9.5", + "pkg": { + "0": { + "diffusers": "LTXConditionPipeline" + } + } + } + }, + "info.dit.lumina-next-sft": { + "diffusers": { + "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", + "pkg": { + "0": { + "diffusers": "LuminaPipeline" + } + } + } + }, + "info.dit.lumina-image-2": { + "*": { + "repo": "Alpha-VLLM/Lumina-Image-2.0", + "pkg": { + "0": { + "diffusers": "Lumina2Pipeline" + } + } + }, + "illustrious-lumina-v3": { + "repo": "OnomaAIResearch/Illustrious-Lumina-v0.03", + "file_256": [ + "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", + "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214" + ], + "layer_256": [ + "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", + "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828" + ], + "layer_b3": [ + "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", + "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c" + ] + } + }, + "info.dit.longcat-image": { + "*": { + "repo": "meituan-longcat/LongCat-Image", + "pkg": { + "0": { + "diffusers": "LongCatImagePipeline" + } + } + } + }, + "info.dit.longcat-image-edit": { + "*": { + "repo": "meituan-longcat/LongCat-Image-Edit", + "pkg": { + "0": { + "diffusers": "LongCatImageEditPipeline" + } + } + } + }, + "info.dit.mochi-1": { + "*": { + "repo": "genmo/mochi-1-preview", + "pkg": { + "0": { + "diffusers": "MochiPipeline" + } + } + } + }, + "info.unet.musicldm": { + "*": { + "repo": "ucsd-reach/musicldm", + "pkg": { + "0": { + "diffusers": "MusicLDMPipeline" + } + } + } + }, + "info.dit.omnigen-v1": { + "diffusers": { + "repo": "Shitao/OmniGen-v1-diffusers", + "pkg": { + "0": { + "diffusers": "OmniGenPipeline" + } + } + } + }, + "info.dit.ovis-image": { + "*": { + "repo": "AIDC-AI/Ovis-Image-7B", + "pkg": { + "0": { + "diffusers": "OvisImagePipeline" + } + } + } + }, + "info.dit.visualclozepipeline-384": { + "*": { + "repo": "VisualCloze/VisualClozePipeline-384", + "pkg": { + "0": { + "diffusers": "VisualClozeGenerationPipeline" + } + } + } + }, + "info.dit.pixart-xl-2-1024-ms": { + "*": { + "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", + "pkg": { + "0": { + "diffusers": "PixArtAlphaPipeline" + } + } + } + }, + "info.dit.pixart-sigma-xl-2-1024-ms": { + "*": { + "repo": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", + "pkg": { + "0": { + "diffusers": "PixArtSigmaPipeline" + } + } + } + }, + "info.dit.sana-1024px-bf16": { + "diffusers": { + "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", + "pkg": { + "0": { + "diffusers": "SanaPipeline" + } + } + } + }, + "info.controlnet.sana-1024px-controlnet": { + "diffusers": { + "repo": "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers", + "pkg": { + "0": { + "diffusers": "SanaControlNetPipeline" + } + } + } + }, + "info.dit.sana-sprint-1024px": { + "diffusers": { + "repo": "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", + "pkg": { + "0": { + "diffusers": "SanaSprintPipeline" + } + } + } + }, + "info.dit.sana-video": { + "*": { + "repo": "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", + "pkg": { + "0": { + "diffusers": "SanaImageToVideoPipeline" + } + } + } + }, + "info.unet.shap-e": { + "*": { + "repo": "openai/shap-e", + "pkg": { + "0": { + "diffusers": "ShapEPipeline" + } + } + } + }, + "info.dit.stable-audio-open-1": { + "*": { + "repo": "stabilityai/stable-audio-open-1.0", + "pkg": { + "0": { + "diffusers": "StableAudioPipeline" + } + } + } + }, + "info.unet.stable-cascade": { + "prior": { + "repo": "stabilityai/stable-cascade-prior", + "pkg": { + "0": { + "diffusers": "StableCascadePriorPipeline" + } + } + } + }, + "info.unet.flux1-dev": { + "decoder": { + "repo": "black-forest-labs/FLUX.1-dev", + "pkg": { + "0": { + "diffusers": "WuerstchenDecoderPipeline" + } + } + } + }, + "info.dit.auraflow": { + "*": { + "repo": "fal/AuraFlow", + "pkg": { + "0": { + "diffusers": "AuraFlowPipeline" + } + } + } + }, + "info.dit.stable-diffusion-3": { + "*": { + "repo": "stabilityai/stable-diffusion-3.5-medium", + "pkg": { + "0": { + "diffusers": "StableDiffusion3Pipeline" + } + } + }, + "stable-diffusion-3-turbo": { + "repo": "tensorart/stable-diffusion-3.5-medium-turbo", + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "num_inference_steps": 8, + "guidance_scale": 1.5, + "height": 1024, + "width": 768 + } + } + }, + "file_256": [ + "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", + "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", + "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", + "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e" + ], + "layer_256": [ + "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", + "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", + "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", + "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" + ], + "layer_b3": [ + "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", + "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", + "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", + "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" + ] + } + }, + "info.unet.gligen-1-4-inpainting-text-box": { + "*": { + "repo": "masterful/gligen-1-4-inpainting-text-box", + "pkg": { + "0": { + "diffusers": "StableDiffusionGLIGENPipeline" + } + } + } + }, + "info.unet.gligen-inpainting-text-image": { + "*": { + "repo": "anhnct/Gligen_Inpainting_Text_Image", + "pkg": { + "0": { + "diffusers": "StableDiffusionGLIGENTextImagePipeline" + } + } + } + }, + "info.unet.stable-video-diffusion-img2vid-xt": { + "*": { + "repo": "stabilityai/stable-video-diffusion-img2vid-xt", + "pkg": { + "0": { + "diffusers": "StableVideoDiffusionPipeline" + } + } + } + }, + "info.unet.ldm3d-4c": { + "*": { + "repo": "Intel/ldm3d-4c", + "pkg": { + "0": { + "diffusers": "StableDiffusionLDM3DPipeline" + } + } + } + }, + "info.unet.i2vgen-xl": { + "*": { + "repo": "ali-vilab/i2vgen-xl", + "pkg": { + "0": { + "diffusers": "I2VGenXLPipeline" + } + } + } + }, + "info.unet.wuerstchen": { + "prior": { + "repo": "warp-ai/wuerstchen-prior", + "pkg": { + "0": { + "diffusers": "WuerstchenPriorPipeline" + } + } + } + }, + "info.dit.wan2-t2v": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanPipeline" + } + } + } + }, + "info.dit.wan-animate": { + "diffusers": { + "repo": "Wan-AI/Wan2.2-Animate-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanAnimatePipeline" + } + } + } + }, + "info.dit.wan2-i2v-480p": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", + "pkg": { + "0": { + "diffusers": "WanImageToVideoPipeline" + } + } + } + }, + "info.dit.wan21-vace": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-VACE-1.3B-diffusers", + "pkg": { + "0": { + "diffusers": "WanVACEPipeline" + } + } + } + }, + "info.dit.wan21-t2v": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", + "pkg": { + "0": { + "diffusers": "WanVideoToVideoPipeline" + } + } + } + }, + "info.dit.kandinsky-5-t2v-lite-sft-5s": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5T2VPipeline" + } + } + } + }, + "info.dit.kandinsky-5-i2i-lite-sft": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5I2IPipeline" + } + } + } + }, + "info.dit.kandinsky-5-i2v-sft-5s": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5I2VPipeline" + } + } + } + }, + "info.dit.kandinsky-5-t2i-lite-sft": { + "diffusers": { + "repo": "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers", + "pkg": { + "0": { + "diffusers": "Kandinsky5T2IPipeline" + } + } + } + }, + "info.dit.z-image-turbo": { + "*": { + "repo": "Z-a-o/Z-Image-Turbo", + "pkg": { + "0": { + "diffusers": "ZImageOmniPipeline" + } + } + } + }, + "info.controlnet.z-image-turbo": { + "*": { + "repo": "Tongyi-MAI/Z-Image-Turbo", + "pkg": { + "0": { + "diffusers": "ZImageControlNetInpaintPipeline" + } + } + } + }, + "info.dit.skyreels-v2-t2v-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2Pipeline" + } + } + } + }, + "info.dit.skyreels-v2-df-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-DF-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" + } + } + } + }, + "info.dit.skyreels-v2-i2v-720p": { + "diffusers": { + "repo": "Skywork/SkyReels-V2-I2V-14B-720P-Diffusers", + "pkg": { + "0": { + "diffusers": "SkyReelsV2ImageToVideoPipeline" + } + } + } + }, + "info.dit.qwen-image": { + "*": { + "repo": "Qwen/Qwen-Image", + "pkg": { + "0": { + "diffusers": "QwenImageInpaintPipeline" + } + } + } + }, + "info.controlnet.qwen-image-controlnet-union": { + "*": { + "repo": "InstantX/Qwen-Image-ControlNet-Union", + "pkg": { + "0": { + "diffusers": "QwenImageControlNetModel" + } + } + } + }, + "info.controlnet.qwen-image-controlnet-inpainting": { + "*": { + "repo": "InstantX/Qwen-Image-ControlNet-Inpainting", + "pkg": { + "0": { + "diffusers": "QwenImageControlNetModel" + } + } + } + }, + "info.dit.qwen-image-edit": { + "*": { + "repo": "Qwen/Qwen-Image-Edit", + "pkg": { + "0": { + "diffusers": "QwenImageEditInpaintPipeline" + } + } + } + }, + "info.dit.qwen-image-edit-2509": { + "*": { + "repo": "Qwen/Qwen-Image-Edit-2509", + "pkg": { + "0": { + "diffusers": "QwenImageEditPlusPipeline" + } + } + } + }, + "info.dit.qwen-image-layered": { + "*": { + "repo": "Qwen/Qwen-Image-Layered", + "pkg": { + "0": { + "diffusers": "QwenImageLayeredPipeline" + } + } + } + }, + "info.dit.chronoedit": { + "diffusers": { + "repo": "nvidia/ChronoEdit-14B-Diffusers", + "pkg": { + "0": { + "diffusers": "ChronoEditPipeline" + } + } + } + }, + "info.unet.kolors": { + "diffusers": { + "repo": "Kwai-Kolors/Kolors-diffusers", + "pkg": { + "0": { + "diffusers": "KolorsPipeline" + } + } + } + }, + "info.encoder.tokenizer": { + "funnel": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "nllb-moe": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "deberta-v2-x": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "xlm-roberta": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "gpt2": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "megatron-bert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "blenderbot": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "20": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "21": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "22": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "23": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "omdet-turbo-swin-hf": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "mgp-str": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "blip2-opt": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "efficient-mlm-m0-0": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "wav2vec2-conformer-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "wav2vec2-bert-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "mm-grounding-dino-o365v1-goldg-v3det": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "bert-for-seq-generation-l-24-bbc-encoder": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "19": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "20": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "21": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "22": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "grounding-dino": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + }, + "xlm-roberta-xl": { + "pkg": { + "0": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "1": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "2": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "3": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "4": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "5": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "6": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "7": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "8": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "9": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "10": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "11": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "12": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "13": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "14": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "15": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "16": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "17": { + "transformers": "transformers.utils.import_utils.transformers" + }, + "18": { + "transformers": "transformers.utils.import_utils.transformers" + } + } + } + }, + "info.aet.funnel": { + "*": { + "repo": "funnel-transformer/small", + "pkg": { + "0": { + "transformers": "FunnelModel" + } + } + } + }, + "info.stst.nllb-moe": { + "*": { + "repo": "facebook/nllb-moe-54b", + "pkg": { + "0": { + "transformers": "NllbMoeModel" + } + } + } + }, + "info.art.deberta-v2-x": { + "*": { + "repo": "microsoft/deberta-v2-xlarge", + "pkg": { + "0": { + "transformers": "DebertaV2Model" + } + } + } + }, + "info.art.xlm-roberta": { + "*": { + "repo": "FacebookAI/xlm-roberta-base", + "pkg": { + "0": { + "transformers": "XLMRobertaModel" + } + } + } + }, + "info.art.gpt2": { + "*": { + "repo": "openai-community/gpt2", + "pkg": { + "0": { + "transformers": "GPT2Model" + } + } + } + }, + "info.art.megatron-bert-uncased": { + "*": { + "repo": "nvidia/megatron-bert-uncased-345m", + "pkg": { + "0": { + "transformers": "MegatronBertModel" + } + } + } + }, + "info.stst.blenderbot": { + "*": { + "repo": "facebook/blenderbot_small-90M", + "pkg": { + "0": { + "transformers": "BlenderbotSmallModel" + } + } + } + }, + "info.detr.omdet-turbo-swin-hf": { + "*": { + "repo": "omlab/omdet-turbo-swin-tiny-hf", + "pkg": { + "0": { + "transformers": "OmDetTurboForObjectDetection" + } + } + } + }, + "info.vit.ast-finetuned-audioset-10-10-0593": { + "*": { + "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "pkg": { + "0": { + "transformers": "ASTModel" + } + } + } + }, + "info.vit.mgp-str": { + "*": { + "repo": "alibaba-damo/mgp-str-base", + "pkg": { + "0": { + "transformers": "MgpstrForSceneTextRecognition" + } + } + } + }, + "info.vit.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2Model" + } + } + } + }, + "info.art.efficient-mlm-m0-0": { + "*": { + "repo": "andreasmadsen/efficient_mlm_m0.40", + "pkg": { + "0": { + "transformers": "RobertaPreLayerNormModel" + } + } + } + }, + "info.aet.wav2vec2-conformer-rel-pos": { + "*": { + "repo": "facebook/wav2vec2-conformer-rel-pos-large", + "pkg": { + "0": { + "transformers": "Wav2Vec2ConformerModel" + } + } + } + }, + "info.aet.unispeech-sat-100h-libri-ft": { + "*": { + "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "pkg": { + "0": { + "transformers": "UniSpeechSatModel" + } + } + } + }, + "info.detr.table-transformer-detection": { + "*": { + "repo": "microsoft/table-transformer-detection", + "pkg": { + "0": { + "transformers": "TableTransformerModel" + } + } + } + }, + "info.detr.dab-detr": { + "*": { + "repo": "IDEA-Research/dab-detr-resnet-50", + "pkg": { + "0": { + "transformers": "DabDetrModel" + } + } + } + }, + "info.aet.wav2vec2-bert-rel-pos": { + "*": { + "repo": "facebook/w2v-bert-2.0", + "pkg": { + "0": { + "transformers": "Wav2Vec2BertModel" + } + } + } + }, + "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "*": { + "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "pkg": { + "0": { + "transformers": "MMGroundingDinoModel" + } + } + } + }, + "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "*": { + "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "pkg": { + "0": { + "transformers": "BertGenerationEncoder" + } + } + } + }, + "info.detr.grounding-dino": { + "*": { + "repo": "IDEA-Research/grounding-dino-tiny", + "pkg": { + "0": { + "transformers": "GroundingDinoModel" + } + } + } + }, + "info.art.xlm-roberta-xl": { + "*": { + "repo": "facebook/xlm-roberta-xl", + "pkg": { + "0": { + "transformers": "XLMRobertaXLModel" + } + } + } + }, + "info.aet.sew-d": { + "*": { + "repo": "asapp/sew-d-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWDModel" + } + } + } + }, + "ops.precision.uint": { + "U8": { + "pkg": { + "0": { + "torch": { + "uint8": { + "variant": "uint8" + } + } + } + } + }, + "U16": { + "pkg": { + "0": { + "torch": { + "uint16": { + "variant": "uint16" + } + } + } + } + }, + "U32": { + "pkg": { + "0": { + "torch": { + "uint32": { + "variant": "uint32" + } + } + } + } + }, + "U64": { + "pkg": { + "0": { + "torch": { + "uint64": { + "variant": "uint64" + } + } + } + } + }, + "U1": { + "pkg": { + "0": { + "torch": { + "uint1": { + "variant": "uint1" + } + } + } + } + }, + "U2": { + "pkg": { + "0": { + "torch": { + "uint2": { + "variant": "uint2" + } + } + } + } + }, + "U3": { + "pkg": { + "0": { + "torch": { + "uint3": { + "variant": "uint3" + } + } + } + } + }, + "U4": { + "pkg": { + "0": { + "torch": { + "uint4": { + "variant": "uint4" + } + } + } + } + }, + "U5": { + "pkg": { + "0": { + "torch": { + "uint5": { + "variant": "uint5" + } + } + } + } + }, + "U6": { + "pkg": { + "0": { + "torch": { + "uint6": { + "variant": "uint6" + } + } + } + } + }, + "U7": { + "pkg": { + "0": { + "torch": { + "uint7": { + "variant": "uint7" + } + } + } + } + } + }, + "ops.precision.int": { + "I8": { + "pkg": { + "0": { + "torch": { + "int8": { + "variant": "int8" + } + } + } + } + }, + "I16": { + "pkg": { + "0": { + "torch": { + "int16": { + "variant": "int16" + } + } + } + } + }, + "I32": { + "pkg": { + "0": { + "torch": { + "int32": { + "variant": "int32" + } + } + } + } + }, + "I64": { + "pkg": { + "0": { + "torch": { + "int64": { + "variant": "int64" + } + } + } + } + }, + "Q8": { + "pkg": { + "0": { + "torch": { + "qint8": { + "variant": "qint8" + } + } + } + } + }, + "Q32": { + "pkg": { + "0": { + "torch": { + "qint32": { + "variant": "qint32" + } + } + } + } + }, + "I1": { + "pkg": { + "0": { + "torch": { + "int1": { + "variant": "int1" + } + } + } + } + }, + "I2": { + "pkg": { + "0": { + "torch": { + "int2": { + "variant": "int2" + } + } + } + } + }, + "I3": { + "pkg": { + "0": { + "torch": { + "int3": { + "variant": "int3" + } + } + } + } + }, + "I4": { + "pkg": { + "0": { + "torch": { + "int4": { + "variant": "int4" + } + } + } + } + }, + "I5": { + "pkg": { + "0": { + "torch": { + "int5": { + "variant": "int5" + } + } + } + } + }, + "I6": { + "pkg": { + "0": { + "torch": { + "int6": { + "variant": "int6" + } + } + } + } + }, + "I7": { + "pkg": { + "0": { + "torch": { + "int7": { + "variant": "int7" + } + } + } + } + } + }, + "ops.precision.float": { + "F16": { + "pkg": { + "0": { + "torch": { + "float16": { + "variant": "fp16" + } + } + } + } + }, + "F32": { + "pkg": { + "0": { + "torch": { + "float32": { + "variant": "fp32" + } + } + } + } + }, + "F64": { + "pkg": { + "0": { + "torch": { + "float64": { + "variant": "fp64" + } + } + } + } + }, + "F8_E5M2": { + "pkg": { + "0": { + "torch": { + "float8_e5m2": { + "variant": "fp8_e5m2" + } + } + } + } + }, + "F8_E4M3": { + "pkg": { + "0": { + "torch": { + "float8_e4m3fn": { + "variant": "fp8_e4m3fn" + } + } + } + } + }, + "F8_E5M2FNUZ": { + "pkg": { + "0": { + "torch": { + "float8_e5m2fnuz": { + "variant": "fp8_e5m2fnuz" + } + } + } + } + }, + "F8_E4M3FNUZ": { + "pkg": { + "0": { + "torch": { + "float8_e4m3fnuz": { + "variant": "fp8_e4m3fnuz" + } + } + } + } + }, + "F8_E8M0FNU": { + "pkg": { + "0": { + "torch": { + "float8_e8m0fnu": { + "variant": "fp8_e8m0fnu" + } + } + } + } + }, + "F8_E2M1": { + "pkg": { + "0": { + "torch": { + "float4_e2m1fn_x2": { + "variant": "fp4_e2m1fn_x2" + } + } + } + } + } + }, + "ops.precision.complex": { + "C32": { + "pkg": { + "0": { + "torch": { + "complex32": { + "variant": "complex32" + } + } + } + } + }, + "C64": { + "pkg": { + "0": { + "torch": { + "complex64": { + "variant": "complex64" + } + } + } + } + }, + "C128": { + "pkg": { + "0": { + "torch": { + "complex128": { + "variant": "complex128" + } + } + } + } + } + }, + "ops.precision.bool": { + "Bbool": { + "pkg": { + "0": { + "torch": { + "bool": { + "variant": "bool" + } + } + } + } + } + }, + "ops.precision.quint": { + "Q8": { + "pkg": { + "0": { + "torch": { + "quint8": { + "variant": "quint8" + } + } + } + } + }, + "Q4x2": { + "pkg": { + "0": { + "torch": { + "quint4x2": { + "variant": "quint4x2" + } + } + } + } + }, + "Q2x4": { + "pkg": { + "0": { + "torch": { + "quint2x4": { + "variant": "quint2x4" + } + } + } + } + } + }, + "ops.precision.bfloat": { + "B16": { + "pkg": { + "0": { + "torch": { + "bfloat16": { + "variant": "bf16" + } + } + } + } + } + }, + "ops.precision.bits": { + "B1x8": { + "pkg": { + "0": { + "torch": { + "bits1x8": { + "variant": "bits1x8" + } + } + } + } + }, + "B2x4": { + "pkg": { + "0": { + "torch": { + "bits2x4": { + "variant": "bits2x4" + } + } + } + } + }, + "B4x2": { + "pkg": { + "0": { + "torch": { + "bits4x2": { + "variant": "bits4x2" + } + } + } + } + }, + "B8": { + "pkg": { + "0": { + "torch": { + "bits8": { + "variant": "bits8" + } + } + } + } + }, + "B16": { + "pkg": { + "0": { + "torch": { + "bits16": { + "variant": "bits16" + } + } + } + } + } + }, + "ops.scheduler.amused": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "AmusedScheduler", + "module_path": "diffusers.schedulers.scheduling_amused" + } + } + } + }, + "ops.scheduler.cmstochasticiterative": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CMStochasticIterativeScheduler", + "module_path": "diffusers.schedulers.scheduling_consistency_models" + } + } + } + }, + "ops.scheduler.cogvideoxddim": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CogVideoXDDIMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_cogvideox" + } + } + } + }, + "ops.scheduler.cogvideoxdpm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "CogVideoXDPMScheduler", + "module_path": "diffusers.schedulers.scheduling_dpm_cogvideox" + } + } + } + }, + "ops.scheduler.ddiminverse": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMInverseScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_inverse" + } + } + } + }, + "ops.scheduler.ddimparallel": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMParallelScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim_parallel" + } + } + } + }, + "ops.scheduler.ddim": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDIMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddim" + } + } + } + }, + "ops.scheduler.ddpmparallel": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMParallelScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm_parallel" + } + } + } + }, + "ops.scheduler.ddpm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm" + } + } + } + }, + "ops.scheduler.ddpmwuerstchen": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "DDPMWuerstchenScheduler", + "module_path": "diffusers.schedulers.scheduling_ddpm_wuerstchen" + } + } + } + }, + "ops.scheduler.deis": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DEISMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_deis_multistep" + } + } + } + }, + "ops.scheduler.dpminverse": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DPMSolverMultistepInverseScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep_inverse" + } + } + } + }, + "ops.scheduler.dpm": { + "multistep": { + "pkg": { + "0": { + "diffusers": "DPMSolverMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep" + } + } + } + }, + "ops.scheduler.dpmsinglestep": { + "solver": { + "pkg": { + "0": { + "diffusers": "DPMSolverSinglestepScheduler", + "module_path": "diffusers.schedulers.scheduling_dpmsolver_singlestep" + } + } + } + }, + "ops.scheduler.edmdpm": { + "multistep": { + "pkg": { + "0": { + "diffusers": "EDMDPMSolverMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_edm_dpmsolver_multistep" + } + } + } + }, + "ops.scheduler.edmeuler": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "EDMEulerScheduler", + "module_path": "diffusers.schedulers.scheduling_edm_euler" + } + } + } + }, + "ops.scheduler.eulerancestral": { + "discrete": { + "pkg": { + "0": { + "diffusers": "EulerAncestralDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_euler_ancestral_discrete" + } + } + } + }, + "ops.scheduler.euler": { + "discrete": { + "pkg": { + "0": { + "diffusers": "EulerDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_euler_discrete" + } + } + } + }, + "ops.scheduler.flowmatcheuler": { + "discrete": { + "pkg": { + "0": { + "diffusers": "FlowMatchEulerDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_euler_discrete" + } + } + } + }, + "ops.scheduler.flowmatchheun": { + "discrete": { + "pkg": { + "0": { + "diffusers": "FlowMatchHeunDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_heun_discrete" + } + } + } + }, + "ops.scheduler.flowmatchlcm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "FlowMatchLCMScheduler", + "module_path": "diffusers.schedulers.scheduling_flow_match_lcm" + } + } + } + }, + "ops.scheduler.heun": { + "discrete": { + "pkg": { + "0": { + "diffusers": "HeunDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_heun_discrete" + } + } + } + }, + "ops.scheduler.ipndm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "IPNDMScheduler", + "module_path": "diffusers.schedulers.scheduling_ipndm" + } + } + } + }, + "ops.scheduler.karrasve": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "KarrasVeScheduler", + "module_path": "diffusers.schedulers.deprecated.scheduling_karras_ve" + } + } + } + }, + "ops.scheduler.kdpm2ancestral": { + "discrete": { + "pkg": { + "0": { + "diffusers": "KDPM2AncestralDiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete" + } + } + } + }, + "ops.scheduler.kdpm2": { + "discrete": { + "pkg": { + "0": { + "diffusers": "KDPM2DiscreteScheduler", + "module_path": "diffusers.schedulers.scheduling_k_dpm_2_discrete" + } + } + } + }, + "ops.scheduler.lcm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "LCMScheduler", + "module_path": "diffusers.schedulers.scheduling_lcm" + } + } + } + }, + "ops.scheduler.pndm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "PNDMScheduler", + "module_path": "diffusers.schedulers.scheduling_pndm" + } + } + } + }, + "ops.scheduler.repaint": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "RePaintScheduler", + "module_path": "diffusers.schedulers.scheduling_repaint" + } + } + } + }, + "ops.scheduler.sa": { + "solver": { + "pkg": { + "0": { + "diffusers": "SASolverScheduler", + "module_path": "diffusers.schedulers.scheduling_sasolver" + } + } + } + }, + "ops.scheduler.scm": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "SCMScheduler", + "module_path": "diffusers.schedulers.scheduling_scm" + } + } + } + }, + "ops.scheduler.scoresdeve": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "ScoreSdeVeScheduler", + "module_path": "diffusers.schedulers.scheduling_sde_ve" + } + } + } + }, + "ops.scheduler.tcd": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "TCDScheduler", + "module_path": "diffusers.schedulers.scheduling_tcd" + } + } + } + }, + "ops.scheduler.unclip": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "UnCLIPScheduler", + "module_path": "diffusers.schedulers.scheduling_unclip" + } + } + } + }, + "ops.scheduler.unipc": { + "multistep": { + "pkg": { + "0": { + "diffusers": "UniPCMultistepScheduler", + "module_path": "diffusers.schedulers.scheduling_unipc_multistep" + } + } + } + }, + "ops.scheduler.vqdiffusion": { + "scheduler": { + "pkg": { + "0": { + "diffusers": "VQDiffusionScheduler", + "module_path": "diffusers.schedulers.scheduling_vq_diffusion" + } + } + } + }, + "ops.scheduler.karrasdiffusion": { + "schedulers": { + "pkg": { + "0": { + "diffusers": "KarrasDiffusionSchedulers", + "module_path": "diffusers.schedulers.scheduling_utils" + } + } + } + }, + "info.lora.dmd": { + "stable-diffusion-xl-1": { + "repo": "tianweiy/DMD2", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0, + "timesteps": [ + 999, + 749, + 499, + 249 + ] + }, + "scheduler": { + "ops.scheduler.lcm": "" + } + } + }, + "file_256": [ + "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", + "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb" + ] + } + }, + "info.lora.dpo": { + "stable-diffusion-xl-1": { + "repo": "radames/sdxl-DPO-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 7.5, + "num_inference_steps": 4 + }, + "scheduler": { + "ops.scheduler.dpm": { + "algorithm_type": "sde-dpmsolver++", + "use_karras_sigmas": true, + "order": 2 + } + } + } + }, + "file_256": [ + "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", + "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad" + ] + } + }, + "info.lora.flash": { + "stable-diffusion-xl-1": { + "repo": "jasperai/flash-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "scheduler": "ops.scheduler.lcm" + } + }, + "file_256": [ + "afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7" + ] + }, + "pixart-alpha": { + "repo": "jasperai/flash-pixart", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b" + ] + }, + "stable-diffusion-3": { + "repo": "jasperai/flash-sd3", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15" + ] + }, + "stable-diffusion-v1-5": { + "repo": "jasperai/flash-sd", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0 + } + } + }, + "file_256": [ + "99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f" + ] + } + }, + "info.lora.hyper": { + "stable-diffusion-xl-1": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + } + } + }, + "file_256": { + "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": { + "num_inference_steps": 12 + }, + "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": { + "num_inference_steps": 8 + }, + "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": { + "num_inference_steps": 1, + "guidance_scale": 0.0 + }, + "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "flux1-dev": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + } + } + }, + "file_256": { + "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-3": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + } + } + }, + "file_256": { + "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": { + "num_inference_steps": 16 + }, + "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": { + "num_inference_steps": 4 + }, + "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": { + "num_inference_steps": 8 + } + } + }, + "stable-diffusion-v1-5": { + "repo": "ByteDance/Hyper-SD", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": { + "num_inference_steps": 12 + }, + "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": { + "num_inference_steps": 8 + }, + "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": { + "num_inference_steps": 1, + "guidance_scale": 0.0 + }, + "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + } + }, + "info.lora.lcm": { + "stable-diffusion-xl-1": { + "repo": "latent-consistency/lcm-lora-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + }, + "scheduler": { + "ops.scheduler.lcm": { + "timestep_spacing": "trailing" + } + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141" + ] + }, + "ssd": { + "repo": "latent-consistency/lcm-lora-ssd-1b", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b" + ] + }, + "segmind-vega": { + "repo": "segmind/Segmind-VegaRT", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "gen_kwargs": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb" + ] + }, + "stable-diffusion-v1-5": { + "repo": "latent-consistency/lcm-lora-sdv1-5", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 8 + } + } + }, + "file_256": [ + "8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4" + ] + } + }, + "info.lora.lightning": { + "stable-diffusion-xl-1": { + "repo": "ByteDance/SDXL-Lightning", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0 + } + } + } + } + }, + "info.lora.pcm": { + "stable-diffusion-xl-1": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": { + "num_inference_steps": 16 + }, + "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": { + "num_inference_steps": 16 + }, + "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": { + "num_inference_steps": 4 + }, + "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": { + "num_inference_steps": 4 + }, + "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": { + "num_inference_steps": 8 + }, + "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": { + "num_inference_steps": 8 + }, + "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + }, + "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-v1-5": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": { + "num_inference_steps": 16 + }, + "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": { + "num_inference_steps": 4 + }, + "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": { + "num_inference_steps": 8 + }, + "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": { + "num_inference_steps": 16, + "guidance_scale": 0.0 + }, + "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": { + "num_inference_steps": 2, + "guidance_scale": 0.0 + }, + "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": { + "num_inference_steps": 4, + "guidance_scale": 0.0 + }, + "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": { + "num_inference_steps": 8, + "guidance_scale": 0.0 + } + } + }, + "stable-diffusion-3": { + "repo": "wangfuyun/PCM_Weights", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": { + "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": { + "num_inference_steps": 2, + "guidance_scale": 1.2 + }, + "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + }, + "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + }, + "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": { + "num_inference_steps": 4, + "guidance_scale": 1.2 + } + } + } + }, + "info.lora.slam": { + "stable-diffusion-xl-1": { + "repo": "alimama-creative/slam-lora-sdxl", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "scheduler": { + "ops.scheduler.lcm": { + "timestep_spacing": "trailing" + } + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 1 + } + } + }, + "file_256": [ + "22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91" + ] + }, + "stable-diffusion-v1-5": { + "repo": "alimama-creative/slam-sd1.5", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + } + } + }, + "info.lora.spo": { + "stable-diffusion-xl-1": { + "repo": "SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 5.0 + } + } + }, + "file_256": [ + "0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df" + ] + }, + "stable-diffusion-v1-5": { + "repo": "SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "guidance_scale": 7.5 + } + } + }, + "file_256": [ + "1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4" + ] + } + }, + "info.lora.tcd": { + "stable-diffusion-xl-1": { + "repo": "h1t/TCD-SDXL-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + }, + "generation": { + "num_inference_steps": 4, + "guidance_scale": 0, + "eta": 0.3 + }, + "scheduler": { + "ops.scheduler.tcd": {} + } + } + }, + "file_256": [ + "2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba" + ] + }, + "stable-diffusion-v1-5": { + "repo": "h1t/TCD-SD15-LoRA", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": {} + } + } + }, + "file_256": [ + "eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232" + ], + "layer_256": [ + "e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75" + ], + "layer_b3": [ + "90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b" + ] + } + }, + "info.lora.turbo": { + "stable-diffusion-xl-1": { + "file_256": [ + "a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69" + ] + }, + "flux1-dev": { + "repo": "alimama-creative/FLUX.1-Turbo-Alpha", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 0.125 + } + }, + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 8, + "max_sequence_length": 512 + } + } + }, + "file_256": [ + "77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff" + ] + }, + "stable-diffusion-3": { + "repo": "tensorart/stable-diffusion-3.5-large-TurboX", + "pkg": { + "0": { + "diffusers": { + "load_lora_weights": { + "fuse": 1.0 + } + }, + "scheduler": { + "ops.scheduler.flow-match": { + "shift": 5 + } + } + } + }, + "file_256": { + "fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": { + "num_inference_steps": "8" + } + } + } + }, + "info.art.audiogen": { + "*": { + "repo": "facebook/audiogen-medium", + "pkg": { + "0": { + "audiocraft": "models.AudioGen", + "generation": { + "duration": 5 + }, + "stage_2": { + "audiocraft": ".data.audioaudio_write", + "generation": { + "strategy": "loudness", + "loudness_compressor": true + } + } + } + } + } + }, + "info.art.parler-tts-v1": { + "*": { + "repo": "parler-tts/parler-tts-large-v1", + "pkg": { + "0": { + "parler_tts": "ParlerTTSForConditionalGeneration", + "generation": { + "return_tensors": "pt" + } + } + } + } + }, + "info.gan.snac-st": { + "*": { + "repo": "Zuellni/snac-24khz-ST", + "pkg": { + "0": { + "snac": "SNAC" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio" + } + }, + "file_256": [ + "e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", + "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d" + ], + "layer_256": [ + "35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", + "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841" + ], + "layer_b3": [ + "18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", + "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119" + ] + } + }, + "info.gan.kokoro": { + "*": { + "repo": "hexgrad/Kokoro-82M", + "pkg": { + "0": { + "kokoro": "KPipeline" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + }, + "file_256": [ + "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", + "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4" + ], + "layer_256": [ + "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", + "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b" + ], + "layer_b3": [ + "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", + "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", + "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e932dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92" + ] + } + }, + "info.stst.silero-vad": { + "*": { + "repo": "freddyaboulton/silero-vad", + "pkg": { + "0": { + "onnx": "onnx" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + }, + "file_256": [ + "591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9" + ], + "layer_256": [ + "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd" + ], + "layer_b3": [ + "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", + "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", + "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", + "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e" + ] + } + }, + "info.stst.wav2vec2-conformer-rope-960h-ft": { + "*": { + "repo": "facebook/wav2vec2-conformer-rope-large-960h-ft", + "pkg": { + "0": { + "transformers": "Wav2Vec2ConformerForCTC" + } + }, + "file_256": [ + "97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d" + ], + "layer_256": [ + "1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d" + ], + "layer_b3": [ + "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" + ] + } + }, + "info.art.orpheus-0-ft": { + "*": { + "repo": "canopylabs/orpheus-3b-0.1-ft", + "pkg": { + "0": { + "orpheus_tts": "OrpheusModel", + "generation": { + "max_model_len": 2048 + } + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + } + } + }, + "info.art.outetts-0": { + "*": { + "repo": "OuteAI/OuteTTS-0.3-1B", + "pkg": { + "0": { + "outetts": "InterfaceHF" + }, + "1": { + "mlx_audio": "tts.generate.generate_audio", + "generation": { + "audio_format": "wav", + "join_audio": true, + "verbose": false + } + } + } + } + }, + "info.gan.speecht5-hifigan": { + "*": { + "file_256": [ + "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c" + ], + "layer_256": [ + "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770" + ], + "layer_b3": [ + "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956" + ] + } + }, + "info.dit.wan2-flf2v-720p": { + "diffusers": { + "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", + "file_256": [ + "", + "" + ], + "layer_256": [ + "" + ], + "layer_b3": [ + "" + ] + } + }, + "ops.patch.hidiffusion": { + "stable-diffusion-xl-1": { + "pkg": { + "0": { + "hidiffusion": { + "apply_hidiffusion": { + "timesteps": "StableDiffusionXLTimesteps" + } + }, + "generation": { + "height": 2048, + "width": 2048, + "eta": 1.0, + "guidance_scale": 7.5, + "num_inference_steps": 10 + } + } + } + } + }, + "ops.scheduler.align-your-steps": { + "stable-diffusion-xl-1": { + "pkg": { + "0": { + "diffusers": "schedulers.scheduling_utils.AysSchedules", + "generation": { + "timesteps": "StableDiffusionXLTimesteps", + "num_inference_steps": 10 + } + } + } + } + }, + "info.art.chameleon": { + "lumina-mgpt-1024": { + "repo": "Alpha-VLLM/Lumina-mGPT-7B-1024", + "pkg": { + "0": { + "inference_solver": { + "FlexARInferenceSolver": { + "precision": "bf16", + "target_size": 768 + } + }, + "generation": { + "images": [], + "qas": [ + [ + "q1", + null + ] + ], + "max_gen_len": 8192, + "temperature": 1.0 + } + }, + "1": { + "inference_solver": "ChameleonXLLMXForConditionalGeneration" + } + }, + "file_256": [ + "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", + "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", + "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", + "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b" + ], + "layer_256": [ + "eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25" + ], + "layer_b3": [ + "6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656" + ] + } + }, + "info.vit.clip-vit-patch14": { + "*": { + "repo": "openai/clip-vit-large-patch14", + "pkg": { + "0": { + "transformers": "CLIPTextModel" + } + }, + "file_256": [ + "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", + "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", + "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", + "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", + "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", + "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", + "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", + "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", + "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", + "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", + "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", + "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", + "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", + "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", + "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", + "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", + "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", + "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", + "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1" + ], + "layer_256": [ + "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", + "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", + "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", + "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", + "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", + "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", + "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", + "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", + "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", + "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", + "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", + "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", + "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", + "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", + "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3" + ], + "layer_b3": [ + "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", + "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", + "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", + "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", + "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", + "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", + "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", + "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", + "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", + "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", + "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", + "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", + "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", + "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", + "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", + "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" + ] + } + }, + "info.vit.clip-vit-g-14-laion-s-b": { + "*": { + "repo": "laion/CLIP-ViT-g-14-laion2B-s12B-b42K", + "pkg": { + "0": { + "transformers": "CLIPTextModelWithProjection" + } + }, + "file_256": [ + "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", + "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", + "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", + "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", + "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", + "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", + "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", + "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", + "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", + "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b" + ], + "layer_256": [ + "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", + "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", + "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", + "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", + "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", + "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", + "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46" + ], + "layer_b3": [ + "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", + "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", + "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", + "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", + "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", + "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", + "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" + ] + } + }, + "info.vit.clip-vit-h-14-laion-s-b": { + "*": { + "repo": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K", + "pkg": { + "0": { + "transformers": "CLIPModel" + } + }, + "file_256": [ + "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", + "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", + "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161" + ], + "layer_256": [ + "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", + "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", + "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c" + ], + "layer_b3": [ + "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", + "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", + "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" + ] + } + }, + "info.aet.chatglm3": { + "*": { + "repo": "zai-org/chatglm3-6b", + "pkg": { + "0": { + "transformers": "AutoModel" + } + }, + "file_256": [ + "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", + "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d" + ], + "layer_256": [ + "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44" + ], + "layer_b3": [ + "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481" + ] + } + }, + "info.art.qwen2": { + "bagel-mot": { + "repo": "ByteDance-Seed/BAGEL-7B-MoT", + "pkg": { + "0": { + "Bagel": "app" + } + } + } + }, + "info.vae.tae": { + "stable-diffusion-3": { + "repo": "madebyollin/taesd3", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399" + ] + }, + "stable-diffusion-xl-1": { + "repo": "madebyollin/taesdxl", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f" + ] + }, + "stable-diffusion-v1-5": { + "repo": "madebyollin/taesd", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549" + ] + }, + "flux1-dev": { + "repo": "madebyollin/taef1", + "pkg": { + "0": { + "diffusers": "AutoencoderTiny" + } + }, + "file_256": [ + "927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449" + ] + } + }, + "info.vae.kl": { + "qwen-image": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLQwenImage" + } + }, + "file_256": [ + "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344" + ], + "layer_256": [ + "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc" + ], + "layer_b3": [ + "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b" + ] + }, + "ltx-video": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLLTXVideo" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "allegro": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLAllegro" + } + }, + "file_256": [ + "47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a" + ], + "layer_256": [ + "bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f" + ], + "layer_b3": [ + "93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0" + ] + }, + "cosmos-1-diffusion-video2world": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLCosmos" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "easyanimatev5-zh": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLMagvit" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "hunyuanvideo-i2v": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLHunyuanVideo" + } + }, + "file_256": [ + "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", + "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", + "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", + "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0" + ] + }, + "mochi-1": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLMochi" + } + }, + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "audioldm-s-v2": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5" + ], + "layer_256": [ + "54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6" + ], + "layer_b3": [ + "00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de" + ] + }, + "stable-video-diffusion-img2vid-xt": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLTemporalDecoder" + } + } + }, + "stable-diffusion-xl-1": { + "repo": "madebyollin/sdxl-vae-fp16-fix", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", + "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", + "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", + "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", + "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", + "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", + "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", + "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88" + ], + "layer_256": [ + "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", + "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" + ], + "layer_b3": [ + "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", + "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0" + ] + }, + "stable-diffusion-xl-1*": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", + "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", + "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", + "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff" + ], + "layer_256": [ + "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", + "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" + ], + "layer_b3": [ + "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74" + ] + }, + "shuttle-jaguar": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904" + ], + "layer_256": [ + "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b" + ], + "layer_b3": [ + "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", + "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0" + ] + }, + "flux1-dev": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", + "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", + "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", + "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc" + ], + "layer_256": [ + "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", + "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", + "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", + "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80" + ], + "layer_b3": [ + "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", + "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903" + ] + }, + "musicldm": { + "file_256": [ + "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4" + ], + "layer_256": [ + "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f" + ], + "layer_b3": [ + "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0" + ] + }, + "stable-diffusion-v1-5": { + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + }, + "file_256": [ + "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", + "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", + "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", + "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", + "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", + "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", + "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", + "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c" + ], + "layer_256": [ + "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", + "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3" + ], + "layer_b3": [ + "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", + "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833" + ] + } + }, + "info.vae.wan": { + "wan2-i2v-480p": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLWan", + "precision": "ops.precision.float.F32" + } + }, + "file_256": [ + "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", + "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b" + ], + "layer_256": [ + "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", + "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e" + ], + "layer_b3": [ + "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", + "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433" + ] + }, + "skyreels-v2-t2v-720p": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "skyreels-v2-i2v-720p": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + } + }, + "info.vae.cogvideox": { + "cogvideox-i2v": { + "pkg": { + "0": { + "diffusers": "AutoencoderKLCogVideoX" + } + }, + "file_256": [ + "a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e" + ], + "layer_256": [ + "43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e" + ], + "layer_b3": [ + "246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb" + ] + }, + "cogvideox-fun-v-pose": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + }, + "consisid": { + "file_256": [], + "layer_256": [], + "layer_b3": [] + } + }, + "info.vae.dc": { + "sana-1024px-bf16": { + "pkg": { + "0": { + "diffusers": "AutoencoderDC" + } + }, + "file_256": [ + "15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f" + ], + "layer_256": [ + "abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde" + ], + "layer_b3": [ + "cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0" + ] + } + }, + "info.vae.oobleck": { + "stable-audio-open-1": { + "pkg": { + "0": { + "diffusers": "AutoencoderOobleck" + } + } + } + }, + "info.vae.eq": { + "stable-diffusion-xl-1": { + "repo": "KBlueLeaf/EQ-SDXL-VAE", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + } + } + }, + "info.vae.ms-lc-eq": { + "stable-diffusion-xl-1": { + "repo": "Anzhc/MS-LC-EQ-D-VR_VAE", + "pkg": { + "0": { + "diffusers": "AutoencoderKL" + } + } + } + } } \ No newline at end of file diff --git a/mir/spec/mir.py b/mir/spec/__init__.py similarity index 100% rename from mir/spec/mir.py rename to mir/spec/__init__.py diff --git a/mir/spec/docstring_patterns.json b/mir/spec/docstring_patterns.json new file mode 100644 index 0000000..691ab3c --- /dev/null +++ b/mir/spec/docstring_patterns.json @@ -0,0 +1,41 @@ +{ + "uncommon_naming": { + "blip_diffusion": "blip_diffusion", + "cogvideo": "cogvideox", + "cogview3": "cogview3plus", + "deepfloyd_if": "if", + "cosmos": "cosmos2_text2image", + "visualcloze": "visualcloze_generation", + "marigold": "marigold_depth" + }, + "exclusion_list": [ + "auto_pipeline", + "consistency_models", + "pipeline_utils", + "deprecated", + "ddim", + "ddpm", + "deprecated", + "autopipeline", + "dance_diffusion", + "diffusionpipeline", + "dit", + "latent_consistency_models", + "latent_diffusion", + "ledits_pp", + "pag", + "paint_by_example", + "semantic_stable_diffusion", + "stable_diffusion_attend_and_excite", + "stable_diffusion_diffedit", + "stable_diffusion_k_diffusion", + "stable_diffusion_panorama", + "stable_diffusion_safe", + "stable_diffusion_sag", + "t2i_adapter", + "text_to_video_synthesis", + "unclip", + "unidiffuser", + "controlnet_hunyuandit" + ] +} \ No newline at end of file diff --git a/mir/spec/missing_params.json b/mir/spec/missing_params.json new file mode 100644 index 0000000..de3dc44 --- /dev/null +++ b/mir/spec/missing_params.json @@ -0,0 +1,62 @@ +{ + "bark": { + "repo_path": "suno/bark", + "params": { + "n_head": [ + "" + ] + } + }, + "aria_text": { + "repo_path": "rhymes-ai/Aria-Chat", + "params": { + "vision_config": [ + "" + ], + "text_config": [ + "" + ] + } + }, + "cwm": { + "repo_path": "facebook/cwm", + "params": { + "n_head": [ + "" + ] + } + }, + "decision_transformer": { + "repo_path": "edbeeching/decision-transformer-gym-hopper-medium" + }, + "distilbert": { + "repo_path": "distilbert-base-uncased" + }, + "gpt_bigcode": { + "repo_path": "bigcode/gpt_bigcode-santacoder" + }, + "granite": { + "repo_path": "ibm-granite/granite-3.3-2b-base" + }, + "granitemoe": { + "repo_path": "ibm-research/PowerMoE-3b" + }, + "granitemoehybrid": { + "repo_path": "ibm-granite/granite-4.0-h-small" + }, + "musicgen": { + "repo_path": "facebook/musicgen-small" + }, + "seamless_m4t_v2": { + "repo_path": "facebook/seamless-m4t-v2-large" + }, + "timm_backbone": { + "repo_path": "microsoft/resnet-50" + }, + "timm_wrapper": { + "repo_path": "timm/resnet18.a1_in1k" + }, + "vision-text-dual-encoder": { + "repo_path": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" + } +} \ No newline at end of file diff --git a/mir/spec/repo_migrations.json b/mir/spec/repo_migrations.json new file mode 100644 index 0000000..799f906 --- /dev/null +++ b/mir/spec/repo_migrations.json @@ -0,0 +1,29 @@ +{ + "/helium-2b": "/helium-1-2b", + "allenai/Olmo2-7B-1124-hf": "allenai/Olmo-2-1124-7B", + "apple/mobilevitv2-1.0": "apple/mobilevitv2-1.0-imagenet1k-256", + "caidas/swin2SR-classical-sr-x2-64": "caidas/swin2SR-classical-sr-x2-64", + "facebook/hiera-base-224": "facebook/hiera-base-224-hf", + "facebook/sam_hq-vit-huge": "syscv-community/sam-hq-vit-huge", + "facebook/vit_msn_base": "facebook/vit-msn-base", + "facebook/wav2vec2-bert-rel-pos-large": "facebook/w2v-bert-2.0", + "google/gemma-3-4b": "google/gemma-3-4b-it", + "google/gemma2-7b": "google/gemma-2-9b", + "google/gemma3_text-7b": "google/gemma-3-12b-it", + "IDEA-Research/dab_detr-base": "IDEA-Research/dab-detr-resnet-50", + "LGAI-EXAONE/EXAONE-4.0-Instruct": "LGAI-EXAONE/EXAONE-4.0-32B", + "meta/chameleon-7b'": "facebook/chameleon-7b", + "mixtralai/Mixtral-8x7B": "mistralai/Mixtral-8x7B-v0.1", + "paligemma-hf/paligemma-2b": "google/paligemma2-3b-mix-224", + "pixtral-hf/pixtral-9b": "mistralai/Pixtral-12B-Base-2409", + "Qwen/Qwen2-7B-beta": "Qwen/Qwen2-7B", + "Qwen/Qwen3-15B-A2B": "Qwen/Qwen3-30B-A3B", + "s-JoL/Open-Llama-V1": "openlm-research/open_llama_3b", + "Salesforce/instruct-blip-flan-t5": "Salesforce/instructblip-flan-t5-xl", + "state-spaces/mamba2-2.8b": "AntonV/mamba2-2.7b-hf", + "ibm-fms/FalconH1-9.8b-2.2T-hf": "tiiuae/Falcon-H1-34B-Instruct", + "nvidia/nemotron-3-8b-base-4k-hf": "mgoin/nemotron-3-8b-chat-4k-sft-hf", + "THUDM/": "zai-org/", + "THUDM/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", + "zai-org/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air" +} \ No newline at end of file diff --git a/mir/spec/template.json b/mir/spec/template.json index 96fc4de..1381e19 100644 --- a/mir/spec/template.json +++ b/mir/spec/template.json @@ -51,6 +51,7 @@ "projection_dim", "vlm_config", "crop_size", + "fpn_hidden_size", "out_indices", "logit_scale_init_value", "image_size", @@ -77,7 +78,10 @@ "keypoint_detector_config", "local_attention", "act_dropout", - "max_source_positions" + "max_source_positions", + "classifier_pooling", + "audio_video_config", + "video_config" ], "stst": [ "is_encoder_decoder", @@ -85,12 +89,17 @@ "encoder_layers", "encoder_hidden_size", "encoder_config", + "ctc_loss_reduction", + "ctc_zero_infinity", "audio_token_index", "codebook_dim", "router_ignore_padding_tokens", "d_ff", "d_kv", - "audio_config" + "audio_config", + "convolution_bias", + "rope_parameters", + "hotstart_dup_thresh" ], "art": [ "ffn_dim", @@ -98,6 +107,7 @@ "vq_config", "attn_config", "n_head", + "act_dim", "n_heads", "n_layer", "rms_norm_eps", @@ -106,9 +116,12 @@ "layernorm_embedding", "hidden_dropout_prob", "rotary_pct", + "audio_encoder", "embed_dropout", "nb_priors", + "resid_pdrop", "embd_pdrop", + "action_tanh", "n_positions", "aux_loss_coef", "residual_dropout", diff --git a/mir/tag.py b/mir/tag.py index e869ad3..7b272fe 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -1,11 +1,11 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import List -from mir.config.constants import PARAMETERS_SUFFIX, BREAKING_SUFFIX +from typing import Any +from mir.config.constants import PARAMETERS_SUFFIX, BREAKING_SUFFIX, ClassMapEntry -def make_mir_tag(repo_title: str, decoder=False, data: dict = None) -> List[str]: +def tag_model_from_repo(repo_title: str, decoder=False, data: dict | None = None) -> tuple[str, Any]: """Create a mir label from a repo path\n :param mir_prefix: Known period-separated prefix and model type :param repo_path: Typical remote source repo path, A URL without domain @@ -45,7 +45,7 @@ def make_mir_tag(repo_title: str, decoder=False, data: dict = None) -> List[str] return (cleaned_string, suffix) -def make_scheduler_tag(series_name: str) -> tuple[str]: +def tag_scheduler(series_name: str) -> tuple[str, str]: """Create a mir label from a scheduler operation\n :param class_name: Known period-separated prefix and model type :return: The assembled mir tag with compatibility pre-separated""" @@ -64,23 +64,43 @@ def make_scheduler_tag(series_name: str) -> tuple[str]: for pattern in patterns: series_name = re.sub(pattern, "", series_name) series_name.lower() - # if not comp_name: - # comp_name = "*" + assert series_name is not None + assert comp_name is not None return series_name, comp_name -def tag_base_model(repo_path: str, class_name: str, addendum: dict | None = None) -> tuple[str]: +def mir_prefix_from_forward_pass(transformers: bool = False, **kwargs): + """Set type of MIR prefix depending on model type\n + :param transformers: Use transformers data instead of diffusers data, defaults to False + :raises ValueError: Model type not detected + :return: MIR prefix based on model configuration""" + from mir.config.json_io import read_json_file + + data = read_json_file("mir/spec/template.json") + + if transformers: + flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object + else: + flags = data["arch"]["diffuser"] # pylint:disable=unsubscriptable-object + for mir_prefix, key_match in flags.items(): + if any(kwargs.get(param, None) for param in key_match): + return mir_prefix + return None + + +def tag_base_model(repo_path: str, class_name: str, addendum: dict | None = None) -> tuple[str, str, str | dict[str, dict]]: """Convert model repo paths to MIR tags, classifying by feature\n :param name: Repo path :param class_name: The HF transformers class for the model :return: A segmented MIR tag useful for appending index entries""" from mir.inspect.classes import extract_init_params - from mir.indexers import flag_config - annotations = extract_init_params(class_name.replace("Model", "Config"), "transformers") - mir_prefix = flag_config(transformers=True, **annotations) - base_series, base_comp = make_mir_tag(repo_path) + annotations = extract_init_params(class_name.replace("Model", "Config"), "transformers") # remove default annotations from python + if not annotations: + raise TypeError("No mode type returned") + mir_prefix = mir_prefix_from_forward_pass(True, **annotations) + base_series, base_comp = tag_model_from_repo(repo_path) if not addendum: return mir_prefix, base_series, base_comp else: @@ -102,6 +122,28 @@ def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: return mir_prefix, mir_series, {mir_comp: addendum} +def mir_tag_from_config(class_map: ClassMapEntry, repo_path: str) -> tuple[str, str, str]: + """Change a transformers config class into a MIR series and comp + :param class_map: Transformers class information extracted from dependency""" + + mir_prefix = mir_prefix_from_forward_pass(transformers=True, **class_map.config_params) + if not mir_prefix: + if class_map.model_params: + if mir_prefix := mir_prefix_from_forward_pass(transformers=True, **class_map.model_params): + pass + else: + raise ValueError(f"Unable to determine MIR prefix from {class_map, repo_path}") + else: + raise ValueError(f"Unrecognized model type, no tag matched {class_map.name} with {class_map.config_params} or {class_map.model_params}") + mir_prefix = "info." + mir_prefix + if class_map.name != "funnel": + mir_suffix, mir_comp = tag_model_from_repo(repo_path) + else: + mir_suffix, mir_comp = ["funnel", "*"] + mir_series = mir_prefix + "." + mir_suffix + return mir_series, mir_comp, mir_suffix + + # def tag_mlx_model(repo_path: str, class_name: str, addendum: dict) -> tuple[str]: # dev_series, dev_comp = make_mir_tag("black-forest-labs/FLUX.1-dev") # schnell_series, schnell_comp = make_mir_tag("black-forest-labs/FLUX.1-schnell") diff --git a/pyproject.toml b/pyproject.toml index 3f4f11e..580736e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -25,8 +25,10 @@ classifiers = [ ] dependencies = [ "diffusers>=0.35.2", + "ftfy>=6.3.1", "huggingface-hub[hf-xet]>=1.1.7", "pydantic>=2.12.5", + "sentencepiece>=0.2.1", "tokenizers>=0.22.1", "torch>=2.9.1", "torchvision>=0.24.1", diff --git a/tests/test_find_docstring_run.py b/tests/test_find_docstring_run.py new file mode 100644 index 0000000..952c5a5 --- /dev/null +++ b/tests/test_find_docstring_run.py @@ -0,0 +1,5 @@ +from mir.inspect.metadata import find_diffusers_docstrings +from pprint import pprint + +find_diffusers_docstrings() +list(find_diffusers_docstrings()) diff --git a/tests/test_gather_diffusers_metadata.py b/tests/test_gather_diffusers_metadata.py index efbed0a..e628720 100644 --- a/tests/test_gather_diffusers_metadata.py +++ b/tests/test_gather_diffusers_metadata.py @@ -28,14 +28,14 @@ def mock_pkgutil_iter_modules(mocker): def test_list_diffusers_models(): - from mir.inspect.metadata import gather_diffusers_metadata + from mir.inspect.metadata import find_diffusers_docstrings - gather_diffusers_metadata() + find_diffusers_docstrings() -def test_gather_diffusers_metadata_excluded(mock_import_module, mock_pkgutil_iter_modules): +def test_find_docstrings_excluded(mock_import_module, mock_pkgutil_iter_modules): """Test that excluded modules are not processed.""" - from mir.inspect.metadata import gather_diffusers_metadata + from mir.inspect.metadata import find_diffusers_docstrings excluded_modules = ["ddpm"] @@ -45,5 +45,5 @@ def side_effect(import_name, *args, **kwargs): return Mock() mock_import_module.side_effect = side_effect - results = list(gather_diffusers_metadata()) # type: ignore # noqa + results = list(find_diffusers_docstrings()) # type: ignore # noqa assert not any("ddpm" in call_arg[0][0] for call_arg in mock_import_module.call_args_list) diff --git a/tests/test_mir_db_create_restore.py b/tests/test_mir_db_create_restore.py index 3aee25b..b927cb0 100644 --- a/tests/test_mir_db_create_restore.py +++ b/tests/test_mir_db_create_restore.py @@ -7,7 +7,7 @@ # def test_mir_creation(): -# from mir.spec.mir import mir_entry +# from mir.spec import mir_entry # from pprint import pprint # os.remove(MIR_PATH_NAMED) diff --git a/tests/test_mir_tagging.py b/tests/test_mir_tagging.py index ac97c02..272f157 100644 --- a/tests/test_mir_tagging.py +++ b/tests/test_mir_tagging.py @@ -1,6 +1,6 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from mir.tag import make_mir_tag +from mir.tag import tag_model_from_repo # def test_param_no_delimiter_version():BAH @@ -10,7 +10,7 @@ def test_split_hyphenated(): - result = make_mir_tag("xyz-15b") + result = tag_model_from_repo("xyz-15b") assert result == ("xyz", "*") print(result) @@ -21,24 +21,24 @@ def test_split_hyphenated(): def test_split_dot_version(): - assert make_mir_tag("xyz1.0") == ("xyz1", "*") + assert tag_model_from_repo("xyz1.0") == ("xyz1", "*") def test_split_hyphen_version(): - assert make_mir_tag("xyz1-0") == ("xyz1-0", "*") + assert tag_model_from_repo("xyz1-0") == ("xyz1-0", "*") def test_split_hyphen_v_version(): - assert make_mir_tag("xyzv1-0") == ("xyzv1-0", "*") + assert tag_model_from_repo("xyzv1-0") == ("xyzv1-0", "*") def test_no_split(): - assert make_mir_tag("flux.1-dev") == ("flux1-dev", "*") + assert tag_model_from_repo("flux.1-dev") == ("flux1-dev", "*") def test_no_split_again(): - assert make_mir_tag("blipdiffusion") == ("blipdiffusion", "*") + assert tag_model_from_repo("blipdiffusion") == ("blipdiffusion", "*") def test_no_version_dot_numeric_and_diffusers(): - assert make_mir_tag("EasyAnimateV5.1-7b-zh-diffusers") == ("easyanimatev5-zh", "diffusers") + assert tag_model_from_repo("EasyAnimateV5.1-7b-zh-diffusers") == ("easyanimatev5-zh", "diffusers") diff --git a/tests/test_regex_constants.py b/tests/test_regex_constants.py index b148c2d..70820a8 100644 --- a/tests/test_regex_constants.py +++ b/tests/test_regex_constants.py @@ -2,7 +2,7 @@ # from mir.config.constants import PARAMETERS_SUFFIX -from mir.tag import make_mir_tag +from mir.tag import tag_model_from_repo def test_constants(): @@ -23,5 +23,5 @@ def test_constants(): } # regex = PARAMETERS_SUFFIX for test, expected in data_tests.items(): - mir_tag = list(make_mir_tag(test)) + mir_tag = list(tag_model_from_repo(test)) assert mir_tag == expected diff --git a/uv.lock b/uv.lock index 0eec34b..c945785 100644 --- a/uv.lock +++ b/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 2 +revision = 3 requires-python = ">=3.11" resolution-markers = [ "python_full_version >= '3.12'", @@ -30,11 +30,11 @@ wheels = [ [[package]] name = "certifi" -version = "2025.11.12" +version = "2026.1.4" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/a2/8c/58f469717fa48465e4a50c014a0400602d3c437d7c0c468e17ada824da3a/certifi-2025.11.12.tar.gz", hash = "sha256:d8ab5478f2ecd78af242878415affce761ca6bc54a22a27e026d7c25357c3316", size = 160538, upload-time = "2025-11-12T02:54:51.517Z" } +sdist = { url = "https://files.pythonhosted.org/packages/e0/2d/a891ca51311197f6ad14a7ef42e2399f36cf2f9bd44752b3dc4eab60fdc5/certifi-2026.1.4.tar.gz", hash = "sha256:ac726dd470482006e014ad384921ed6438c457018f4b3d204aea4281258b2120", size = 154268, upload-time = "2026-01-04T02:42:41.825Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/70/7d/9bc192684cea499815ff478dfcdc13835ddf401365057044fb721ec6bddb/certifi-2025.11.12-py3-none-any.whl", hash = "sha256:97de8790030bbd5c2d96b7ec782fc2f7820ef8dba6db909ccf95449f2d062d4b", size = 159438, upload-time = "2025-11-12T02:54:49.735Z" }, + { url = "https://files.pythonhosted.org/packages/e6/ad/3cc14f097111b4de0040c83a525973216457bbeeb63739ef1ed275c1c021/certifi-2026.1.4-py3-none-any.whl", hash = "sha256:9943707519e4add1115f44c2bc244f782c0249876bf51b6599fee1ffbedd685c", size = 152900, upload-time = "2026-01-04T02:42:40.15Z" }, ] [[package]] @@ -133,8 +133,8 @@ wheels = [ [[package]] name = "diffusers" -version = "0.36.0.dev0" -source = { git = "https://github.com/huggingface/diffusers#a1f36ee3ef4ae1bf98bd260e539197259aa981c1" } +version = "0.37.0.dev0" +source = { git = "https://github.com/huggingface/diffusers#5ffb65803d0ddc5e3298c35df638ceed5e580922" } dependencies = [ { name = "filelock" }, { name = "httpx" }, @@ -149,11 +149,11 @@ dependencies = [ [[package]] name = "filelock" -version = "3.20.0" +version = "3.20.2" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/58/46/0028a82567109b5ef6e4d2a1f04a583fb513e6cf9527fcdd09afd817deeb/filelock-3.20.0.tar.gz", hash = "sha256:711e943b4ec6be42e1d4e6690b48dc175c822967466bb31c0c293f34334c13f4", size = 18922, upload-time = "2025-10-08T18:03:50.056Z" } +sdist = { url = "https://files.pythonhosted.org/packages/c1/e0/a75dbe4bca1e7d41307323dad5ea2efdd95408f74ab2de8bd7dba9b51a1a/filelock-3.20.2.tar.gz", hash = "sha256:a2241ff4ddde2a7cebddf78e39832509cb045d18ec1a09d7248d6bfc6bfbbe64", size = 19510, upload-time = "2026-01-02T15:33:32.582Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/76/91/7216b27286936c16f5b4d0c530087e4a54eead683e6b0b73dd0c64844af6/filelock-3.20.0-py3-none-any.whl", hash = "sha256:339b4732ffda5cd79b13f4e2711a31b0365ce445d95d243bb996273d072546a2", size = 16054, upload-time = "2025-10-08T18:03:48.35Z" }, + { url = "https://files.pythonhosted.org/packages/9a/30/ab407e2ec752aa541704ed8f93c11e2a5d92c168b8a755d818b74a3c5c2d/filelock-3.20.2-py3-none-any.whl", hash = "sha256:fbba7237d6ea277175a32c54bb71ef814a8546d8601269e1bfc388de333974e8", size = 16697, upload-time = "2026-01-02T15:33:31.133Z" }, ] [[package]] @@ -165,6 +165,18 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/51/c7/b64cae5dba3a1b138d7123ec36bb5ccd39d39939f18454407e5468f4763f/fsspec-2025.12.0-py3-none-any.whl", hash = "sha256:8bf1fe301b7d8acfa6e8571e3b1c3d158f909666642431cc78a1b7b4dbc5ec5b", size = 201422, upload-time = "2025-12-03T15:23:41.434Z" }, ] +[[package]] +name = "ftfy" +version = "6.3.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "wcwidth" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/a5/d3/8650919bc3c7c6e90ee3fa7fd618bf373cbbe55dff043bd67353dbb20cd8/ftfy-6.3.1.tar.gz", hash = "sha256:9b3c3d90f84fb267fe64d375a07b7f8912d817cf86009ae134aa03e1819506ec", size = 308927, upload-time = "2024-10-26T00:50:35.149Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ab/6e/81d47999aebc1b155f81eca4477a616a70f238a2549848c38983f3c22a82/ftfy-6.3.1-py3-none-any.whl", hash = "sha256:7c70eb532015cd2f9adb53f101fb6c7945988d023a085d127d1573dc49dd0083", size = 44821, upload-time = "2024-10-26T00:50:33.425Z" }, +] + [[package]] name = "h11" version = "0.16.0" @@ -233,7 +245,7 @@ wheels = [ [[package]] name = "huggingface-hub" -version = "1.1.7" +version = "1.2.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "filelock" }, @@ -247,9 +259,9 @@ dependencies = [ { name = "typer-slim" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/6f/fa/a1a94c55637f2b7cfeb05263ac3881aa87c82df92d8b4b31c909079f4419/huggingface_hub-1.1.7.tar.gz", hash = "sha256:3c84b6283caca928595f08fd42e9a572f17ec3501dec508c3f2939d94bfbd9d2", size = 607537, upload-time = "2025-12-01T11:05:28.137Z" } +sdist = { url = "https://files.pythonhosted.org/packages/a7/c8/9cd2fcb670ba0e708bfdf95a1177b34ca62de2d3821df0773bc30559af80/huggingface_hub-1.2.3.tar.gz", hash = "sha256:4ba57f17004fd27bb176a6b7107df579865d4cde015112db59184c51f5602ba7", size = 614605, upload-time = "2025-12-12T15:31:42.161Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/dd/4f/82e5ab009089a2c48472bf4248391fe4091cf0b9c3e951dbb8afe3b23d76/huggingface_hub-1.1.7-py3-none-any.whl", hash = "sha256:f3efa4779f4890e44c957bbbb0f197e6028887ad09f0cf95a21659fa7753605d", size = 516239, upload-time = "2025-12-01T11:05:25.981Z" }, + { url = "https://files.pythonhosted.org/packages/df/8d/7ca723a884d55751b70479b8710f06a317296b1fa1c1dec01d0420d13e43/huggingface_hub-1.2.3-py3-none-any.whl", hash = "sha256:c9b7a91a9eedaa2149cdc12bdd8f5a11780e10de1f1024718becf9e41e5a4642", size = 520953, upload-time = "2025-12-12T15:31:40.339Z" }, ] [package.optional-dependencies] @@ -268,14 +280,14 @@ wheels = [ [[package]] name = "importlib-metadata" -version = "8.7.0" +version = "8.7.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "zipp" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/76/66/650a33bd90f786193e4de4b3ad86ea60b53c89b669a5c7be931fac31cdb0/importlib_metadata-8.7.0.tar.gz", hash = "sha256:d13b81ad223b890aa16c5471f2ac3056cf76c5f10f82d6f9292f0b415f389000", size = 56641, upload-time = "2025-04-27T15:29:01.736Z" } +sdist = { url = "https://files.pythonhosted.org/packages/f3/49/3b30cad09e7771a4982d9975a8cbf64f00d4a1ececb53297f1d9a7be1b10/importlib_metadata-8.7.1.tar.gz", hash = "sha256:49fef1ae6440c182052f407c8d34a68f72efc36db9ca90dc0113398f2fdde8bb", size = 57107, upload-time = "2025-12-21T10:00:19.278Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/20/b0/36bd937216ec521246249be3bf9855081de4c5e06a0c9b4219dbeda50373/importlib_metadata-8.7.0-py3-none-any.whl", hash = "sha256:e5dd1551894c77868a30651cef00984d50e1002d06942a7101d34870c5f02afd", size = 27656, upload-time = "2025-04-27T15:29:00.214Z" }, + { url = "https://files.pythonhosted.org/packages/fa/5e/f8e9a1d23b9c20a551a8a02ea3637b4642e22c2626e3a13a9a29cdea99eb/importlib_metadata-8.7.1-py3-none-any.whl", hash = "sha256:5a1f80bf1daa489495071efbb095d75a634cf28a8bc299581244063b53176151", size = 27865, upload-time = "2025-12-21T10:00:18.329Z" }, ] [[package]] @@ -388,8 +400,10 @@ version = "0.0.1" source = { editable = "." } dependencies = [ { name = "diffusers" }, + { name = "ftfy" }, { name = "huggingface-hub", extra = ["hf-xet"] }, { name = "pydantic" }, + { name = "sentencepiece" }, { name = "tokenizers" }, { name = "torch" }, { name = "torchvision" }, @@ -409,8 +423,10 @@ dev = [ [package.metadata] requires-dist = [ { name = "diffusers", git = "https://github.com/huggingface/diffusers" }, + { name = "ftfy", specifier = ">=6.3.1" }, { name = "huggingface-hub", extras = ["hf-xet"], specifier = ">=1.1.7" }, { name = "pydantic", specifier = ">=2.12.5" }, + { name = "sentencepiece", specifier = ">=0.2.1" }, { name = "tokenizers", specifier = ">=0.22.1" }, { name = "torch", specifier = ">=2.9.1" }, { name = "torchvision", specifier = ">=0.24.1" }, @@ -438,101 +454,99 @@ wheels = [ [[package]] name = "networkx" -version = "3.6" +version = "3.6.1" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/e8/fc/7b6fd4d22c8c4dc5704430140d8b3f520531d4fe7328b8f8d03f5a7950e8/networkx-3.6.tar.gz", hash = "sha256:285276002ad1f7f7da0f7b42f004bcba70d381e936559166363707fdad3d72ad", size = 2511464, upload-time = "2025-11-24T03:03:47.158Z" } +sdist = { url = "https://files.pythonhosted.org/packages/6a/51/63fe664f3908c97be9d2e4f1158eb633317598cfa6e1fc14af5383f17512/networkx-3.6.1.tar.gz", hash = "sha256:26b7c357accc0c8cde558ad486283728b65b6a95d85ee1cd66bafab4c8168509", size = 2517025, upload-time = "2025-12-08T17:02:39.908Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/07/c7/d64168da60332c17d24c0d2f08bdf3987e8d1ae9d84b5bbd0eec2eb26a55/networkx-3.6-py3-none-any.whl", hash = "sha256:cdb395b105806062473d3be36458d8f1459a4e4b98e236a66c3a48996e07684f", size = 2063713, upload-time = "2025-11-24T03:03:45.21Z" }, + { url = "https://files.pythonhosted.org/packages/9e/c9/b2622292ea83fbb4ec318f5b9ab867d0a28ab43c5717bb85b0a5f6b3b0a4/networkx-3.6.1-py3-none-any.whl", hash = "sha256:d47fbf302e7d9cbbb9e2555a0d267983d2aa476bac30e90dfbe5669bd57f3762", size = 2068504, upload-time = "2025-12-08T17:02:38.159Z" }, ] [[package]] name = "nodeenv" -version = "1.9.1" +version = "1.10.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/43/16/fc88b08840de0e0a72a2f9d8c6bae36be573e475a6326ae854bcc549fc45/nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f", size = 47437, upload-time = "2024-06-04T18:44:11.171Z" } +sdist = { url = "https://files.pythonhosted.org/packages/24/bf/d1bda4f6168e0b2e9e5958945e01910052158313224ada5ce1fb2e1113b8/nodeenv-1.10.0.tar.gz", hash = "sha256:996c191ad80897d076bdfba80a41994c2b47c68e224c542b48feba42ba00f8bb", size = 55611, upload-time = "2025-12-20T14:08:54.006Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/d2/1d/1b658dbd2b9fa9c4c9f32accbfc0205d532c8c6194dc0f2a4c0428e7128a/nodeenv-1.9.1-py2.py3-none-any.whl", hash = "sha256:ba11c9782d29c27c70ffbdda2d7415098754709be8a7056d79a737cd901155c9", size = 22314, upload-time = "2024-06-04T18:44:08.352Z" }, + { url = "https://files.pythonhosted.org/packages/88/b2/d0896bdcdc8d28a7fc5717c305f1a861c26e18c05047949fb371034d98bd/nodeenv-1.10.0-py2.py3-none-any.whl", hash = "sha256:5bb13e3eed2923615535339b3c620e76779af4cb4c6a90deccc9e36b274d3827", size = 23438, upload-time = "2025-12-20T14:08:52.782Z" }, ] [[package]] name = "numpy" -version = "2.3.5" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/76/65/21b3bc86aac7b8f2862db1e808f1ea22b028e30a225a34a5ede9bf8678f2/numpy-2.3.5.tar.gz", hash = "sha256:784db1dcdab56bf0517743e746dfb0f885fc68d948aba86eeec2cba234bdf1c0", size = 20584950, upload-time = "2025-11-16T22:52:42.067Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/43/77/84dd1d2e34d7e2792a236ba180b5e8fcc1e3e414e761ce0253f63d7f572e/numpy-2.3.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:de5672f4a7b200c15a4127042170a694d4df43c992948f5e1af57f0174beed10", size = 17034641, upload-time = "2025-11-16T22:49:19.336Z" }, - { url = "https://files.pythonhosted.org/packages/2a/ea/25e26fa5837106cde46ae7d0b667e20f69cbbc0efd64cba8221411ab26ae/numpy-2.3.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:acfd89508504a19ed06ef963ad544ec6664518c863436306153e13e94605c218", size = 12528324, upload-time = "2025-11-16T22:49:22.582Z" }, - { url = "https://files.pythonhosted.org/packages/4d/1a/e85f0eea4cf03d6a0228f5c0256b53f2df4bc794706e7df019fc622e47f1/numpy-2.3.5-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:ffe22d2b05504f786c867c8395de703937f934272eb67586817b46188b4ded6d", size = 5356872, upload-time = "2025-11-16T22:49:25.408Z" }, - { url = "https://files.pythonhosted.org/packages/5c/bb/35ef04afd567f4c989c2060cde39211e4ac5357155c1833bcd1166055c61/numpy-2.3.5-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:872a5cf366aec6bb1147336480fef14c9164b154aeb6542327de4970282cd2f5", size = 6893148, upload-time = "2025-11-16T22:49:27.549Z" }, - { url = "https://files.pythonhosted.org/packages/f2/2b/05bbeb06e2dff5eab512dfc678b1cc5ee94d8ac5956a0885c64b6b26252b/numpy-2.3.5-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3095bdb8dd297e5920b010e96134ed91d852d81d490e787beca7e35ae1d89cf7", size = 14557282, upload-time = "2025-11-16T22:49:30.964Z" }, - { url = "https://files.pythonhosted.org/packages/65/fb/2b23769462b34398d9326081fad5655198fcf18966fcb1f1e49db44fbf31/numpy-2.3.5-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8cba086a43d54ca804ce711b2a940b16e452807acebe7852ff327f1ecd49b0d4", size = 16897903, upload-time = "2025-11-16T22:49:34.191Z" }, - { url = "https://files.pythonhosted.org/packages/ac/14/085f4cf05fc3f1e8aa95e85404e984ffca9b2275a5dc2b1aae18a67538b8/numpy-2.3.5-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6cf9b429b21df6b99f4dee7a1218b8b7ffbbe7df8764dc0bd60ce8a0708fed1e", size = 16341672, upload-time = "2025-11-16T22:49:37.2Z" }, - { url = "https://files.pythonhosted.org/packages/6f/3b/1f73994904142b2aa290449b3bb99772477b5fd94d787093e4f24f5af763/numpy-2.3.5-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:396084a36abdb603546b119d96528c2f6263921c50df3c8fd7cb28873a237748", size = 18838896, upload-time = "2025-11-16T22:49:39.727Z" }, - { url = "https://files.pythonhosted.org/packages/cd/b9/cf6649b2124f288309ffc353070792caf42ad69047dcc60da85ee85fea58/numpy-2.3.5-cp311-cp311-win32.whl", hash = "sha256:b0c7088a73aef3d687c4deef8452a3ac7c1be4e29ed8bf3b366c8111128ac60c", size = 6563608, upload-time = "2025-11-16T22:49:42.079Z" }, - { url = "https://files.pythonhosted.org/packages/aa/44/9fe81ae1dcc29c531843852e2874080dc441338574ccc4306b39e2ff6e59/numpy-2.3.5-cp311-cp311-win_amd64.whl", hash = "sha256:a414504bef8945eae5f2d7cb7be2d4af77c5d1cb5e20b296c2c25b61dff2900c", size = 13078442, upload-time = "2025-11-16T22:49:43.99Z" }, - { url = "https://files.pythonhosted.org/packages/6d/a7/f99a41553d2da82a20a2f22e93c94f928e4490bb447c9ff3c4ff230581d3/numpy-2.3.5-cp311-cp311-win_arm64.whl", hash = "sha256:0cd00b7b36e35398fa2d16af7b907b65304ef8bb4817a550e06e5012929830fa", size = 10458555, upload-time = "2025-11-16T22:49:47.092Z" }, - { url = "https://files.pythonhosted.org/packages/44/37/e669fe6cbb2b96c62f6bbedc6a81c0f3b7362f6a59230b23caa673a85721/numpy-2.3.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:74ae7b798248fe62021dbf3c914245ad45d1a6b0cb4a29ecb4b31d0bfbc4cc3e", size = 16733873, upload-time = "2025-11-16T22:49:49.84Z" }, - { url = "https://files.pythonhosted.org/packages/c5/65/df0db6c097892c9380851ab9e44b52d4f7ba576b833996e0080181c0c439/numpy-2.3.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ee3888d9ff7c14604052b2ca5535a30216aa0a58e948cdd3eeb8d3415f638769", size = 12259838, upload-time = "2025-11-16T22:49:52.863Z" }, - { url = "https://files.pythonhosted.org/packages/5b/e1/1ee06e70eb2136797abe847d386e7c0e830b67ad1d43f364dd04fa50d338/numpy-2.3.5-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:612a95a17655e213502f60cfb9bf9408efdc9eb1d5f50535cc6eb365d11b42b5", size = 5088378, upload-time = "2025-11-16T22:49:55.055Z" }, - { url = "https://files.pythonhosted.org/packages/6d/9c/1ca85fb86708724275103b81ec4cf1ac1d08f465368acfc8da7ab545bdae/numpy-2.3.5-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:3101e5177d114a593d79dd79658650fe28b5a0d8abeb8ce6f437c0e6df5be1a4", size = 6628559, upload-time = "2025-11-16T22:49:57.371Z" }, - { url = "https://files.pythonhosted.org/packages/74/78/fcd41e5a0ce4f3f7b003da85825acddae6d7ecb60cf25194741b036ca7d6/numpy-2.3.5-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8b973c57ff8e184109db042c842423ff4f60446239bd585a5131cc47f06f789d", size = 14250702, upload-time = "2025-11-16T22:49:59.632Z" }, - { url = "https://files.pythonhosted.org/packages/b6/23/2a1b231b8ff672b4c450dac27164a8b2ca7d9b7144f9c02d2396518352eb/numpy-2.3.5-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0d8163f43acde9a73c2a33605353a4f1bc4798745a8b1d73183b28e5b435ae28", size = 16606086, upload-time = "2025-11-16T22:50:02.127Z" }, - { url = "https://files.pythonhosted.org/packages/a0/c5/5ad26fbfbe2012e190cc7d5003e4d874b88bb18861d0829edc140a713021/numpy-2.3.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:51c1e14eb1e154ebd80e860722f9e6ed6ec89714ad2db2d3aa33c31d7c12179b", size = 16025985, upload-time = "2025-11-16T22:50:04.536Z" }, - { url = "https://files.pythonhosted.org/packages/d2/fa/dd48e225c46c819288148d9d060b047fd2a6fb1eb37eae25112ee4cb4453/numpy-2.3.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b46b4ec24f7293f23adcd2d146960559aaf8020213de8ad1909dba6c013bf89c", size = 18542976, upload-time = "2025-11-16T22:50:07.557Z" }, - { url = "https://files.pythonhosted.org/packages/05/79/ccbd23a75862d95af03d28b5c6901a1b7da4803181513d52f3b86ed9446e/numpy-2.3.5-cp312-cp312-win32.whl", hash = "sha256:3997b5b3c9a771e157f9aae01dd579ee35ad7109be18db0e85dbdbe1de06e952", size = 6285274, upload-time = "2025-11-16T22:50:10.746Z" }, - { url = "https://files.pythonhosted.org/packages/2d/57/8aeaf160312f7f489dea47ab61e430b5cb051f59a98ae68b7133ce8fa06a/numpy-2.3.5-cp312-cp312-win_amd64.whl", hash = "sha256:86945f2ee6d10cdfd67bcb4069c1662dd711f7e2a4343db5cecec06b87cf31aa", size = 12782922, upload-time = "2025-11-16T22:50:12.811Z" }, - { url = "https://files.pythonhosted.org/packages/78/a6/aae5cc2ca78c45e64b9ef22f089141d661516856cf7c8a54ba434576900d/numpy-2.3.5-cp312-cp312-win_arm64.whl", hash = "sha256:f28620fe26bee16243be2b7b874da327312240a7cdc38b769a697578d2100013", size = 10194667, upload-time = "2025-11-16T22:50:16.16Z" }, - { url = "https://files.pythonhosted.org/packages/db/69/9cde09f36da4b5a505341180a3f2e6fadc352fd4d2b7096ce9778db83f1a/numpy-2.3.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d0f23b44f57077c1ede8c5f26b30f706498b4862d3ff0a7298b8411dd2f043ff", size = 16728251, upload-time = "2025-11-16T22:50:19.013Z" }, - { url = "https://files.pythonhosted.org/packages/79/fb/f505c95ceddd7027347b067689db71ca80bd5ecc926f913f1a23e65cf09b/numpy-2.3.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:aa5bc7c5d59d831d9773d1170acac7893ce3a5e130540605770ade83280e7188", size = 12254652, upload-time = "2025-11-16T22:50:21.487Z" }, - { url = "https://files.pythonhosted.org/packages/78/da/8c7738060ca9c31b30e9301ee0cf6c5ffdbf889d9593285a1cead337f9a5/numpy-2.3.5-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:ccc933afd4d20aad3c00bcef049cb40049f7f196e0397f1109dba6fed63267b0", size = 5083172, upload-time = "2025-11-16T22:50:24.562Z" }, - { url = "https://files.pythonhosted.org/packages/a4/b4/ee5bb2537fb9430fd2ef30a616c3672b991a4129bb1c7dcc42aa0abbe5d7/numpy-2.3.5-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:afaffc4393205524af9dfa400fa250143a6c3bc646c08c9f5e25a9f4b4d6a903", size = 6622990, upload-time = "2025-11-16T22:50:26.47Z" }, - { url = "https://files.pythonhosted.org/packages/95/03/dc0723a013c7d7c19de5ef29e932c3081df1c14ba582b8b86b5de9db7f0f/numpy-2.3.5-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c75442b2209b8470d6d5d8b1c25714270686f14c749028d2199c54e29f20b4d", size = 14248902, upload-time = "2025-11-16T22:50:28.861Z" }, - { url = "https://files.pythonhosted.org/packages/f5/10/ca162f45a102738958dcec8023062dad0cbc17d1ab99d68c4e4a6c45fb2b/numpy-2.3.5-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11e06aa0af8c0f05104d56450d6093ee639e15f24ecf62d417329d06e522e017", size = 16597430, upload-time = "2025-11-16T22:50:31.56Z" }, - { url = "https://files.pythonhosted.org/packages/2a/51/c1e29be863588db58175175f057286900b4b3327a1351e706d5e0f8dd679/numpy-2.3.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ed89927b86296067b4f81f108a2271d8926467a8868e554eaf370fc27fa3ccaf", size = 16024551, upload-time = "2025-11-16T22:50:34.242Z" }, - { url = "https://files.pythonhosted.org/packages/83/68/8236589d4dbb87253d28259d04d9b814ec0ecce7cb1c7fed29729f4c3a78/numpy-2.3.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:51c55fe3451421f3a6ef9a9c1439e82101c57a2c9eab9feb196a62b1a10b58ce", size = 18533275, upload-time = "2025-11-16T22:50:37.651Z" }, - { url = "https://files.pythonhosted.org/packages/40/56/2932d75b6f13465239e3b7b7e511be27f1b8161ca2510854f0b6e521c395/numpy-2.3.5-cp313-cp313-win32.whl", hash = "sha256:1978155dd49972084bd6ef388d66ab70f0c323ddee6f693d539376498720fb7e", size = 6277637, upload-time = "2025-11-16T22:50:40.11Z" }, - { url = "https://files.pythonhosted.org/packages/0c/88/e2eaa6cffb115b85ed7c7c87775cb8bcf0816816bc98ca8dbfa2ee33fe6e/numpy-2.3.5-cp313-cp313-win_amd64.whl", hash = "sha256:00dc4e846108a382c5869e77c6ed514394bdeb3403461d25a829711041217d5b", size = 12779090, upload-time = "2025-11-16T22:50:42.503Z" }, - { url = "https://files.pythonhosted.org/packages/8f/88/3f41e13a44ebd4034ee17baa384acac29ba6a4fcc2aca95f6f08ca0447d1/numpy-2.3.5-cp313-cp313-win_arm64.whl", hash = "sha256:0472f11f6ec23a74a906a00b48a4dcf3849209696dff7c189714511268d103ae", size = 10194710, upload-time = "2025-11-16T22:50:44.971Z" }, - { url = "https://files.pythonhosted.org/packages/13/cb/71744144e13389d577f867f745b7df2d8489463654a918eea2eeb166dfc9/numpy-2.3.5-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:414802f3b97f3c1eef41e530aaba3b3c1620649871d8cb38c6eaff034c2e16bd", size = 16827292, upload-time = "2025-11-16T22:50:47.715Z" }, - { url = "https://files.pythonhosted.org/packages/71/80/ba9dc6f2a4398e7f42b708a7fdc841bb638d353be255655498edbf9a15a8/numpy-2.3.5-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5ee6609ac3604fa7780e30a03e5e241a7956f8e2fcfe547d51e3afa5247ac47f", size = 12378897, upload-time = "2025-11-16T22:50:51.327Z" }, - { url = "https://files.pythonhosted.org/packages/2e/6d/db2151b9f64264bcceccd51741aa39b50150de9b602d98ecfe7e0c4bff39/numpy-2.3.5-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:86d835afea1eaa143012a2d7a3f45a3adce2d7adc8b4961f0b362214d800846a", size = 5207391, upload-time = "2025-11-16T22:50:54.542Z" }, - { url = "https://files.pythonhosted.org/packages/80/ae/429bacace5ccad48a14c4ae5332f6aa8ab9f69524193511d60ccdfdc65fa/numpy-2.3.5-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:30bc11310e8153ca664b14c5f1b73e94bd0503681fcf136a163de856f3a50139", size = 6721275, upload-time = "2025-11-16T22:50:56.794Z" }, - { url = "https://files.pythonhosted.org/packages/74/5b/1919abf32d8722646a38cd527bc3771eb229a32724ee6ba340ead9b92249/numpy-2.3.5-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1062fde1dcf469571705945b0f221b73928f34a20c904ffb45db101907c3454e", size = 14306855, upload-time = "2025-11-16T22:50:59.208Z" }, - { url = "https://files.pythonhosted.org/packages/a5/87/6831980559434973bebc30cd9c1f21e541a0f2b0c280d43d3afd909b66d0/numpy-2.3.5-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ce581db493ea1a96c0556360ede6607496e8bf9b3a8efa66e06477267bc831e9", size = 16657359, upload-time = "2025-11-16T22:51:01.991Z" }, - { url = "https://files.pythonhosted.org/packages/dd/91/c797f544491ee99fd00495f12ebb7802c440c1915811d72ac5b4479a3356/numpy-2.3.5-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:cc8920d2ec5fa99875b670bb86ddeb21e295cb07aa331810d9e486e0b969d946", size = 16093374, upload-time = "2025-11-16T22:51:05.291Z" }, - { url = "https://files.pythonhosted.org/packages/74/a6/54da03253afcbe7a72785ec4da9c69fb7a17710141ff9ac5fcb2e32dbe64/numpy-2.3.5-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:9ee2197ef8c4f0dfe405d835f3b6a14f5fee7782b5de51ba06fb65fc9b36e9f1", size = 18594587, upload-time = "2025-11-16T22:51:08.585Z" }, - { url = "https://files.pythonhosted.org/packages/80/e9/aff53abbdd41b0ecca94285f325aff42357c6b5abc482a3fcb4994290b18/numpy-2.3.5-cp313-cp313t-win32.whl", hash = "sha256:70b37199913c1bd300ff6e2693316c6f869c7ee16378faf10e4f5e3275b299c3", size = 6405940, upload-time = "2025-11-16T22:51:11.541Z" }, - { url = "https://files.pythonhosted.org/packages/d5/81/50613fec9d4de5480de18d4f8ef59ad7e344d497edbef3cfd80f24f98461/numpy-2.3.5-cp313-cp313t-win_amd64.whl", hash = "sha256:b501b5fa195cc9e24fe102f21ec0a44dffc231d2af79950b451e0d99cea02234", size = 12920341, upload-time = "2025-11-16T22:51:14.312Z" }, - { url = "https://files.pythonhosted.org/packages/bb/ab/08fd63b9a74303947f34f0bd7c5903b9c5532c2d287bead5bdf4c556c486/numpy-2.3.5-cp313-cp313t-win_arm64.whl", hash = "sha256:a80afd79f45f3c4a7d341f13acbe058d1ca8ac017c165d3fa0d3de6bc1a079d7", size = 10262507, upload-time = "2025-11-16T22:51:16.846Z" }, - { url = "https://files.pythonhosted.org/packages/ba/97/1a914559c19e32d6b2e233cf9a6a114e67c856d35b1d6babca571a3e880f/numpy-2.3.5-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:bf06bc2af43fa8d32d30fae16ad965663e966b1a3202ed407b84c989c3221e82", size = 16735706, upload-time = "2025-11-16T22:51:19.558Z" }, - { url = "https://files.pythonhosted.org/packages/57/d4/51233b1c1b13ecd796311216ae417796b88b0616cfd8a33ae4536330748a/numpy-2.3.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:052e8c42e0c49d2575621c158934920524f6c5da05a1d3b9bab5d8e259e045f0", size = 12264507, upload-time = "2025-11-16T22:51:22.492Z" }, - { url = "https://files.pythonhosted.org/packages/45/98/2fe46c5c2675b8306d0b4a3ec3494273e93e1226a490f766e84298576956/numpy-2.3.5-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:1ed1ec893cff7040a02c8aa1c8611b94d395590d553f6b53629a4461dc7f7b63", size = 5093049, upload-time = "2025-11-16T22:51:25.171Z" }, - { url = "https://files.pythonhosted.org/packages/ce/0e/0698378989bb0ac5f1660c81c78ab1fe5476c1a521ca9ee9d0710ce54099/numpy-2.3.5-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:2dcd0808a421a482a080f89859a18beb0b3d1e905b81e617a188bd80422d62e9", size = 6626603, upload-time = "2025-11-16T22:51:27Z" }, - { url = "https://files.pythonhosted.org/packages/5e/a6/9ca0eecc489640615642a6cbc0ca9e10df70df38c4d43f5a928ff18d8827/numpy-2.3.5-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:727fd05b57df37dc0bcf1a27767a3d9a78cbbc92822445f32cc3436ba797337b", size = 14262696, upload-time = "2025-11-16T22:51:29.402Z" }, - { url = "https://files.pythonhosted.org/packages/c8/f6/07ec185b90ec9d7217a00eeeed7383b73d7e709dae2a9a021b051542a708/numpy-2.3.5-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fffe29a1ef00883599d1dc2c51aa2e5d80afe49523c261a74933df395c15c520", size = 16597350, upload-time = "2025-11-16T22:51:32.167Z" }, - { url = "https://files.pythonhosted.org/packages/75/37/164071d1dde6a1a84c9b8e5b414fa127981bad47adf3a6b7e23917e52190/numpy-2.3.5-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f7f0e05112916223d3f438f293abf0727e1181b5983f413dfa2fefc4098245c", size = 16040190, upload-time = "2025-11-16T22:51:35.403Z" }, - { url = "https://files.pythonhosted.org/packages/08/3c/f18b82a406b04859eb026d204e4e1773eb41c5be58410f41ffa511d114ae/numpy-2.3.5-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2e2eb32ddb9ccb817d620ac1d8dae7c3f641c1e5f55f531a33e8ab97960a75b8", size = 18536749, upload-time = "2025-11-16T22:51:39.698Z" }, - { url = "https://files.pythonhosted.org/packages/40/79/f82f572bf44cf0023a2fe8588768e23e1592585020d638999f15158609e1/numpy-2.3.5-cp314-cp314-win32.whl", hash = "sha256:66f85ce62c70b843bab1fb14a05d5737741e74e28c7b8b5a064de10142fad248", size = 6335432, upload-time = "2025-11-16T22:51:42.476Z" }, - { url = "https://files.pythonhosted.org/packages/a3/2e/235b4d96619931192c91660805e5e49242389742a7a82c27665021db690c/numpy-2.3.5-cp314-cp314-win_amd64.whl", hash = "sha256:e6a0bc88393d65807d751a614207b7129a310ca4fe76a74e5c7da5fa5671417e", size = 12919388, upload-time = "2025-11-16T22:51:45.275Z" }, - { url = "https://files.pythonhosted.org/packages/07/2b/29fd75ce45d22a39c61aad74f3d718e7ab67ccf839ca8b60866054eb15f8/numpy-2.3.5-cp314-cp314-win_arm64.whl", hash = "sha256:aeffcab3d4b43712bb7a60b65f6044d444e75e563ff6180af8f98dd4b905dfd2", size = 10476651, upload-time = "2025-11-16T22:51:47.749Z" }, - { url = "https://files.pythonhosted.org/packages/17/e1/f6a721234ebd4d87084cfa68d081bcba2f5cfe1974f7de4e0e8b9b2a2ba1/numpy-2.3.5-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:17531366a2e3a9e30762c000f2c43a9aaa05728712e25c11ce1dbe700c53ad41", size = 16834503, upload-time = "2025-11-16T22:51:50.443Z" }, - { url = "https://files.pythonhosted.org/packages/5c/1c/baf7ffdc3af9c356e1c135e57ab7cf8d247931b9554f55c467efe2c69eff/numpy-2.3.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:d21644de1b609825ede2f48be98dfde4656aefc713654eeee280e37cadc4e0ad", size = 12381612, upload-time = "2025-11-16T22:51:53.609Z" }, - { url = "https://files.pythonhosted.org/packages/74/91/f7f0295151407ddc9ba34e699013c32c3c91944f9b35fcf9281163dc1468/numpy-2.3.5-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:c804e3a5aba5460c73955c955bdbd5c08c354954e9270a2c1565f62e866bdc39", size = 5210042, upload-time = "2025-11-16T22:51:56.213Z" }, - { url = "https://files.pythonhosted.org/packages/2e/3b/78aebf345104ec50dd50a4d06ddeb46a9ff5261c33bcc58b1c4f12f85ec2/numpy-2.3.5-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:cc0a57f895b96ec78969c34f682c602bf8da1a0270b09bc65673df2e7638ec20", size = 6724502, upload-time = "2025-11-16T22:51:58.584Z" }, - { url = "https://files.pythonhosted.org/packages/02/c6/7c34b528740512e57ef1b7c8337ab0b4f0bddf34c723b8996c675bc2bc91/numpy-2.3.5-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:900218e456384ea676e24ea6a0417f030a3b07306d29d7ad843957b40a9d8d52", size = 14308962, upload-time = "2025-11-16T22:52:01.698Z" }, - { url = "https://files.pythonhosted.org/packages/80/35/09d433c5262bc32d725bafc619e095b6a6651caf94027a03da624146f655/numpy-2.3.5-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:09a1bea522b25109bf8e6f3027bd810f7c1085c64a0c7ce050c1676ad0ba010b", size = 16655054, upload-time = "2025-11-16T22:52:04.267Z" }, - { url = "https://files.pythonhosted.org/packages/7a/ab/6a7b259703c09a88804fa2430b43d6457b692378f6b74b356155283566ac/numpy-2.3.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:04822c00b5fd0323c8166d66c701dc31b7fbd252c100acd708c48f763968d6a3", size = 16091613, upload-time = "2025-11-16T22:52:08.651Z" }, - { url = "https://files.pythonhosted.org/packages/c2/88/330da2071e8771e60d1038166ff9d73f29da37b01ec3eb43cb1427464e10/numpy-2.3.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:d6889ec4ec662a1a37eb4b4fb26b6100841804dac55bd9df579e326cdc146227", size = 18591147, upload-time = "2025-11-16T22:52:11.453Z" }, - { url = "https://files.pythonhosted.org/packages/51/41/851c4b4082402d9ea860c3626db5d5df47164a712cb23b54be028b184c1c/numpy-2.3.5-cp314-cp314t-win32.whl", hash = "sha256:93eebbcf1aafdf7e2ddd44c2923e2672e1010bddc014138b229e49725b4d6be5", size = 6479806, upload-time = "2025-11-16T22:52:14.641Z" }, - { url = "https://files.pythonhosted.org/packages/90/30/d48bde1dfd93332fa557cff1972fbc039e055a52021fbef4c2c4b1eefd17/numpy-2.3.5-cp314-cp314t-win_amd64.whl", hash = "sha256:c8a9958e88b65c3b27e22ca2a076311636850b612d6bbfb76e8d156aacde2aaf", size = 13105760, upload-time = "2025-11-16T22:52:17.975Z" }, - { url = "https://files.pythonhosted.org/packages/2d/fd/4b5eb0b3e888d86aee4d198c23acec7d214baaf17ea93c1adec94c9518b9/numpy-2.3.5-cp314-cp314t-win_arm64.whl", hash = "sha256:6203fdf9f3dc5bdaed7319ad8698e685c7a3be10819f41d32a0723e611733b42", size = 10545459, upload-time = "2025-11-16T22:52:20.55Z" }, - { url = "https://files.pythonhosted.org/packages/c6/65/f9dea8e109371ade9c782b4e4756a82edf9d3366bca495d84d79859a0b79/numpy-2.3.5-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:f0963b55cdd70fad460fa4c1341f12f976bb26cb66021a5580329bd498988310", size = 16910689, upload-time = "2025-11-16T22:52:23.247Z" }, - { url = "https://files.pythonhosted.org/packages/00/4f/edb00032a8fb92ec0a679d3830368355da91a69cab6f3e9c21b64d0bb986/numpy-2.3.5-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:f4255143f5160d0de972d28c8f9665d882b5f61309d8362fdd3e103cf7bf010c", size = 12457053, upload-time = "2025-11-16T22:52:26.367Z" }, - { url = "https://files.pythonhosted.org/packages/16/a4/e8a53b5abd500a63836a29ebe145fc1ab1f2eefe1cfe59276020373ae0aa/numpy-2.3.5-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:a4b9159734b326535f4dd01d947f919c6eefd2d9827466a696c44ced82dfbc18", size = 5285635, upload-time = "2025-11-16T22:52:29.266Z" }, - { url = "https://files.pythonhosted.org/packages/a3/2f/37eeb9014d9c8b3e9c55bc599c68263ca44fdbc12a93e45a21d1d56df737/numpy-2.3.5-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:2feae0d2c91d46e59fcd62784a3a83b3fb677fead592ce51b5a6fbb4f95965ff", size = 6801770, upload-time = "2025-11-16T22:52:31.421Z" }, - { url = "https://files.pythonhosted.org/packages/7d/e4/68d2f474df2cb671b2b6c2986a02e520671295647dad82484cde80ca427b/numpy-2.3.5-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ffac52f28a7849ad7576293c0cb7b9f08304e8f7d738a8cb8a90ec4c55a998eb", size = 14391768, upload-time = "2025-11-16T22:52:33.593Z" }, - { url = "https://files.pythonhosted.org/packages/b8/50/94ccd8a2b141cb50651fddd4f6a48874acb3c91c8f0842b08a6afc4b0b21/numpy-2.3.5-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:63c0e9e7eea69588479ebf4a8a270d5ac22763cc5854e9a7eae952a3908103f7", size = 16729263, upload-time = "2025-11-16T22:52:36.369Z" }, - { url = "https://files.pythonhosted.org/packages/2d/ee/346fa473e666fe14c52fcdd19ec2424157290a032d4c41f98127bfb31ac7/numpy-2.3.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:f16417ec91f12f814b10bafe79ef77e70113a2f5f7018640e7425ff979253425", size = 12967213, upload-time = "2025-11-16T22:52:39.38Z" }, +version = "2.4.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a4/7a/6a3d14e205d292b738db449d0de649b373a59edb0d0b4493821d0a3e8718/numpy-2.4.0.tar.gz", hash = "sha256:6e504f7b16118198f138ef31ba24d985b124c2c469fe8467007cf30fd992f934", size = 20685720, upload-time = "2025-12-20T16:18:19.023Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/26/7e/7bae7cbcc2f8132271967aa03e03954fc1e48aa1f3bf32b29ca95fbef352/numpy-2.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:316b2f2584682318539f0bcaca5a496ce9ca78c88066579ebd11fd06f8e4741e", size = 16940166, upload-time = "2025-12-20T16:15:43.434Z" }, + { url = "https://files.pythonhosted.org/packages/0f/27/6c13f5b46776d6246ec884ac5817452672156a506d08a1f2abb39961930a/numpy-2.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a2718c1de8504121714234b6f8241d0019450353276c88b9453c9c3d92e101db", size = 12641781, upload-time = "2025-12-20T16:15:45.701Z" }, + { url = "https://files.pythonhosted.org/packages/14/1c/83b4998d4860d15283241d9e5215f28b40ac31f497c04b12fa7f428ff370/numpy-2.4.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:21555da4ec4a0c942520ead42c3b0dc9477441e085c42b0fbdd6a084869a6f6b", size = 5470247, upload-time = "2025-12-20T16:15:47.943Z" }, + { url = "https://files.pythonhosted.org/packages/54/08/cbce72c835d937795571b0464b52069f869c9e78b0c076d416c5269d2718/numpy-2.4.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:413aa561266a4be2d06cd2b9665e89d9f54c543f418773076a76adcf2af08bc7", size = 6799807, upload-time = "2025-12-20T16:15:49.795Z" }, + { url = "https://files.pythonhosted.org/packages/ff/be/2e647961cd8c980591d75cdcd9e8f647d69fbe05e2a25613dc0a2ea5fb1a/numpy-2.4.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0feafc9e03128074689183031181fac0897ff169692d8492066e949041096548", size = 14701992, upload-time = "2025-12-20T16:15:51.615Z" }, + { url = "https://files.pythonhosted.org/packages/a2/fb/e1652fb8b6fd91ce6ed429143fe2e01ce714711e03e5b762615e7b36172c/numpy-2.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a8fdfed3deaf1928fb7667d96e0567cdf58c2b370ea2ee7e586aa383ec2cb346", size = 16646871, upload-time = "2025-12-20T16:15:54.129Z" }, + { url = "https://files.pythonhosted.org/packages/62/23/d841207e63c4322842f7cd042ae981cffe715c73376dcad8235fb31debf1/numpy-2.4.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:e06a922a469cae9a57100864caf4f8a97a1026513793969f8ba5b63137a35d25", size = 16487190, upload-time = "2025-12-20T16:15:56.147Z" }, + { url = "https://files.pythonhosted.org/packages/bc/a0/6a842c8421ebfdec0a230e65f61e0dabda6edbef443d999d79b87c273965/numpy-2.4.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:927ccf5cd17c48f801f4ed43a7e5673a2724bd2171460be3e3894e6e332ef83a", size = 18580762, upload-time = "2025-12-20T16:15:58.524Z" }, + { url = "https://files.pythonhosted.org/packages/0a/d1/c79e0046641186f2134dde05e6181825b911f8bdcef31b19ddd16e232847/numpy-2.4.0-cp311-cp311-win32.whl", hash = "sha256:882567b7ae57c1b1a0250208cc21a7976d8cbcc49d5a322e607e6f09c9e0bd53", size = 6233359, upload-time = "2025-12-20T16:16:00.938Z" }, + { url = "https://files.pythonhosted.org/packages/fc/f0/74965001d231f28184d6305b8cdc1b6fcd4bf23033f6cb039cfe76c9fca7/numpy-2.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:8b986403023c8f3bf8f487c2e6186afda156174d31c175f747d8934dfddf3479", size = 12601132, upload-time = "2025-12-20T16:16:02.484Z" }, + { url = "https://files.pythonhosted.org/packages/65/32/55408d0f46dfebce38017f5bd931affa7256ad6beac1a92a012e1fbc67a7/numpy-2.4.0-cp311-cp311-win_arm64.whl", hash = "sha256:3f3096405acc48887458bbf9f6814d43785ac7ba2a57ea6442b581dedbc60ce6", size = 10573977, upload-time = "2025-12-20T16:16:04.77Z" }, + { url = "https://files.pythonhosted.org/packages/8b/ff/f6400ffec95de41c74b8e73df32e3fff1830633193a7b1e409be7fb1bb8c/numpy-2.4.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2a8b6bb8369abefb8bd1801b054ad50e02b3275c8614dc6e5b0373c305291037", size = 16653117, upload-time = "2025-12-20T16:16:06.709Z" }, + { url = "https://files.pythonhosted.org/packages/fd/28/6c23e97450035072e8d830a3c411bf1abd1f42c611ff9d29e3d8f55c6252/numpy-2.4.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2e284ca13d5a8367e43734148622caf0b261b275673823593e3e3634a6490f83", size = 12369711, upload-time = "2025-12-20T16:16:08.758Z" }, + { url = "https://files.pythonhosted.org/packages/bc/af/acbef97b630ab1bb45e6a7d01d1452e4251aa88ce680ac36e56c272120ec/numpy-2.4.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:49ff32b09f5aa0cd30a20c2b39db3e669c845589f2b7fc910365210887e39344", size = 5198355, upload-time = "2025-12-20T16:16:10.902Z" }, + { url = "https://files.pythonhosted.org/packages/c1/c8/4e0d436b66b826f2e53330adaa6311f5cac9871a5b5c31ad773b27f25a74/numpy-2.4.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:36cbfb13c152b1c7c184ddac43765db8ad672567e7bafff2cc755a09917ed2e6", size = 6545298, upload-time = "2025-12-20T16:16:12.607Z" }, + { url = "https://files.pythonhosted.org/packages/ef/27/e1f5d144ab54eac34875e79037011d511ac57b21b220063310cb96c80fbc/numpy-2.4.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:35ddc8f4914466e6fc954c76527aa91aa763682a4f6d73249ef20b418fe6effb", size = 14398387, upload-time = "2025-12-20T16:16:14.257Z" }, + { url = "https://files.pythonhosted.org/packages/67/64/4cb909dd5ab09a9a5d086eff9586e69e827b88a5585517386879474f4cf7/numpy-2.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dc578891de1db95b2a35001b695451767b580bb45753717498213c5ff3c41d63", size = 16363091, upload-time = "2025-12-20T16:16:17.32Z" }, + { url = "https://files.pythonhosted.org/packages/9d/9c/8efe24577523ec6809261859737cf117b0eb6fdb655abdfdc81b2e468ce4/numpy-2.4.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:98e81648e0b36e325ab67e46b5400a7a6d4a22b8a7c8e8bbfe20e7db7906bf95", size = 16176394, upload-time = "2025-12-20T16:16:19.524Z" }, + { url = "https://files.pythonhosted.org/packages/61/f0/1687441ece7b47a62e45a1f82015352c240765c707928edd8aef875d5951/numpy-2.4.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d57b5046c120561ba8fa8e4030fbb8b822f3063910fa901ffadf16e2b7128ad6", size = 18287378, upload-time = "2025-12-20T16:16:22.866Z" }, + { url = "https://files.pythonhosted.org/packages/d3/6f/f868765d44e6fc466467ed810ba9d8d6db1add7d4a748abfa2a4c99a3194/numpy-2.4.0-cp312-cp312-win32.whl", hash = "sha256:92190db305a6f48734d3982f2c60fa30d6b5ee9bff10f2887b930d7b40119f4c", size = 5955432, upload-time = "2025-12-20T16:16:25.06Z" }, + { url = "https://files.pythonhosted.org/packages/d4/b5/94c1e79fcbab38d1ca15e13777477b2914dd2d559b410f96949d6637b085/numpy-2.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:680060061adb2d74ce352628cb798cfdec399068aa7f07ba9fb818b2b3305f98", size = 12306201, upload-time = "2025-12-20T16:16:26.979Z" }, + { url = "https://files.pythonhosted.org/packages/70/09/c39dadf0b13bb0768cd29d6a3aaff1fb7c6905ac40e9aaeca26b1c086e06/numpy-2.4.0-cp312-cp312-win_arm64.whl", hash = "sha256:39699233bc72dd482da1415dcb06076e32f60eddc796a796c5fb6c5efce94667", size = 10308234, upload-time = "2025-12-20T16:16:29.417Z" }, + { url = "https://files.pythonhosted.org/packages/a7/0d/853fd96372eda07c824d24adf02e8bc92bb3731b43a9b2a39161c3667cc4/numpy-2.4.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a152d86a3ae00ba5f47b3acf3b827509fd0b6cb7d3259665e63dafbad22a75ea", size = 16649088, upload-time = "2025-12-20T16:16:31.421Z" }, + { url = "https://files.pythonhosted.org/packages/e3/37/cc636f1f2a9f585434e20a3e6e63422f70bfe4f7f6698e941db52ea1ac9a/numpy-2.4.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:39b19251dec4de8ff8496cd0806cbe27bf0684f765abb1f4809554de93785f2d", size = 12364065, upload-time = "2025-12-20T16:16:33.491Z" }, + { url = "https://files.pythonhosted.org/packages/ed/69/0b78f37ca3690969beee54103ce5f6021709134e8020767e93ba691a72f1/numpy-2.4.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:009bd0ea12d3c784b6639a8457537016ce5172109e585338e11334f6a7bb88ee", size = 5192640, upload-time = "2025-12-20T16:16:35.636Z" }, + { url = "https://files.pythonhosted.org/packages/1d/2a/08569f8252abf590294dbb09a430543ec8f8cc710383abfb3e75cc73aeda/numpy-2.4.0-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:5fe44e277225fd3dff6882d86d3d447205d43532c3627313d17e754fb3905a0e", size = 6541556, upload-time = "2025-12-20T16:16:37.276Z" }, + { url = "https://files.pythonhosted.org/packages/93/e9/a949885a4e177493d61519377952186b6cbfdf1d6002764c664ba28349b5/numpy-2.4.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f935c4493eda9069851058fa0d9e39dbf6286be690066509305e52912714dbb2", size = 14396562, upload-time = "2025-12-20T16:16:38.953Z" }, + { url = "https://files.pythonhosted.org/packages/99/98/9d4ad53b0e9ef901c2ef1d550d2136f5ac42d3fd2988390a6def32e23e48/numpy-2.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8cfa5f29a695cb7438965e6c3e8d06e0416060cf0d709c1b1c1653a939bf5c2a", size = 16351719, upload-time = "2025-12-20T16:16:41.503Z" }, + { url = "https://files.pythonhosted.org/packages/28/de/5f3711a38341d6e8dd619f6353251a0cdd07f3d6d101a8fd46f4ef87f895/numpy-2.4.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ba0cb30acd3ef11c94dc27fbfba68940652492bc107075e7ffe23057f9425681", size = 16176053, upload-time = "2025-12-20T16:16:44.552Z" }, + { url = "https://files.pythonhosted.org/packages/2a/5b/2a3753dc43916501b4183532e7ace862e13211042bceafa253afb5c71272/numpy-2.4.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:60e8c196cd82cbbd4f130b5290007e13e6de3eca79f0d4d38014769d96a7c475", size = 18277859, upload-time = "2025-12-20T16:16:47.174Z" }, + { url = "https://files.pythonhosted.org/packages/2c/c5/a18bcdd07a941db3076ef489d036ab16d2bfc2eae0cf27e5a26e29189434/numpy-2.4.0-cp313-cp313-win32.whl", hash = "sha256:5f48cb3e88fbc294dc90e215d86fbaf1c852c63dbdb6c3a3e63f45c4b57f7344", size = 5953849, upload-time = "2025-12-20T16:16:49.554Z" }, + { url = "https://files.pythonhosted.org/packages/4f/f1/719010ff8061da6e8a26e1980cf090412d4f5f8060b31f0c45d77dd67a01/numpy-2.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:a899699294f28f7be8992853c0c60741f16ff199205e2e6cdca155762cbaa59d", size = 12302840, upload-time = "2025-12-20T16:16:51.227Z" }, + { url = "https://files.pythonhosted.org/packages/f5/5a/b3d259083ed8b4d335270c76966cb6cf14a5d1b69e1a608994ac57a659e6/numpy-2.4.0-cp313-cp313-win_arm64.whl", hash = "sha256:9198f447e1dc5647d07c9a6bbe2063cc0132728cc7175b39dbc796da5b54920d", size = 10308509, upload-time = "2025-12-20T16:16:53.313Z" }, + { url = "https://files.pythonhosted.org/packages/31/01/95edcffd1bb6c0633df4e808130545c4f07383ab629ac7e316fb44fff677/numpy-2.4.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:74623f2ab5cc3f7c886add4f735d1031a1d2be4a4ae63c0546cfd74e7a31ddf6", size = 12491815, upload-time = "2025-12-20T16:16:55.496Z" }, + { url = "https://files.pythonhosted.org/packages/59/ea/5644b8baa92cc1c7163b4b4458c8679852733fa74ca49c942cfa82ded4e0/numpy-2.4.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:0804a8e4ab070d1d35496e65ffd3cf8114c136a2b81f61dfab0de4b218aacfd5", size = 5320321, upload-time = "2025-12-20T16:16:57.468Z" }, + { url = "https://files.pythonhosted.org/packages/26/4e/e10938106d70bc21319bd6a86ae726da37edc802ce35a3a71ecdf1fdfe7f/numpy-2.4.0-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:02a2038eb27f9443a8b266a66911e926566b5a6ffd1a689b588f7f35b81e7dc3", size = 6641635, upload-time = "2025-12-20T16:16:59.379Z" }, + { url = "https://files.pythonhosted.org/packages/b3/8d/a8828e3eaf5c0b4ab116924df82f24ce3416fa38d0674d8f708ddc6c8aac/numpy-2.4.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1889b3a3f47a7b5bee16bc25a2145bd7cb91897f815ce3499db64c7458b6d91d", size = 14456053, upload-time = "2025-12-20T16:17:01.768Z" }, + { url = "https://files.pythonhosted.org/packages/68/a1/17d97609d87d4520aa5ae2dcfb32305654550ac6a35effb946d303e594ce/numpy-2.4.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:85eef4cb5625c47ee6425c58a3502555e10f45ee973da878ac8248ad58c136f3", size = 16401702, upload-time = "2025-12-20T16:17:04.235Z" }, + { url = "https://files.pythonhosted.org/packages/18/32/0f13c1b2d22bea1118356b8b963195446f3af124ed7a5adfa8fdecb1b6ca/numpy-2.4.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:6dc8b7e2f4eb184b37655195f421836cfae6f58197b67e3ffc501f1333d993fa", size = 16242493, upload-time = "2025-12-20T16:17:06.856Z" }, + { url = "https://files.pythonhosted.org/packages/ae/23/48f21e3d309fbc137c068a1475358cbd3a901b3987dcfc97a029ab3068e2/numpy-2.4.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:44aba2f0cafd287871a495fb3163408b0bd25bbce135c6f621534a07f4f7875c", size = 18324222, upload-time = "2025-12-20T16:17:09.392Z" }, + { url = "https://files.pythonhosted.org/packages/ac/52/41f3d71296a3dcaa4f456aaa3c6fc8e745b43d0552b6bde56571bb4b4a0f/numpy-2.4.0-cp313-cp313t-win32.whl", hash = "sha256:20c115517513831860c573996e395707aa9fb691eb179200125c250e895fcd93", size = 6076216, upload-time = "2025-12-20T16:17:11.437Z" }, + { url = "https://files.pythonhosted.org/packages/35/ff/46fbfe60ab0710d2a2b16995f708750307d30eccbb4c38371ea9e986866e/numpy-2.4.0-cp313-cp313t-win_amd64.whl", hash = "sha256:b48e35f4ab6f6a7597c46e301126ceba4c44cd3280e3750f85db48b082624fa4", size = 12444263, upload-time = "2025-12-20T16:17:13.182Z" }, + { url = "https://files.pythonhosted.org/packages/a3/e3/9189ab319c01d2ed556c932ccf55064c5d75bb5850d1df7a482ce0badead/numpy-2.4.0-cp313-cp313t-win_arm64.whl", hash = "sha256:4d1cfce39e511069b11e67cd0bd78ceff31443b7c9e5c04db73c7a19f572967c", size = 10378265, upload-time = "2025-12-20T16:17:15.211Z" }, + { url = "https://files.pythonhosted.org/packages/ab/ed/52eac27de39d5e5a6c9aadabe672bc06f55e24a3d9010cd1183948055d76/numpy-2.4.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c95eb6db2884917d86cde0b4d4cf31adf485c8ec36bf8696dd66fa70de96f36b", size = 16647476, upload-time = "2025-12-20T16:17:17.671Z" }, + { url = "https://files.pythonhosted.org/packages/77/c0/990ce1b7fcd4e09aeaa574e2a0a839589e4b08b2ca68070f1acb1fea6736/numpy-2.4.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:65167da969cd1ec3a1df31cb221ca3a19a8aaa25370ecb17d428415e93c1935e", size = 12374563, upload-time = "2025-12-20T16:17:20.216Z" }, + { url = "https://files.pythonhosted.org/packages/37/7c/8c5e389c6ae8f5fd2277a988600d79e9625db3fff011a2d87ac80b881a4c/numpy-2.4.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:3de19cfecd1465d0dcf8a5b5ea8b3155b42ed0b639dba4b71e323d74f2a3be5e", size = 5203107, upload-time = "2025-12-20T16:17:22.47Z" }, + { url = "https://files.pythonhosted.org/packages/e6/94/ca5b3bd6a8a70a5eec9a0b8dd7f980c1eff4b8a54970a9a7fef248ef564f/numpy-2.4.0-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:6c05483c3136ac4c91b4e81903cb53a8707d316f488124d0398499a4f8e8ef51", size = 6538067, upload-time = "2025-12-20T16:17:24.001Z" }, + { url = "https://files.pythonhosted.org/packages/79/43/993eb7bb5be6761dde2b3a3a594d689cec83398e3f58f4758010f3b85727/numpy-2.4.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:36667db4d6c1cea79c8930ab72fadfb4060feb4bfe724141cd4bd064d2e5f8ce", size = 14411926, upload-time = "2025-12-20T16:17:25.822Z" }, + { url = "https://files.pythonhosted.org/packages/03/75/d4c43b61de473912496317a854dac54f1efec3eeb158438da6884b70bb90/numpy-2.4.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9a818668b674047fd88c4cddada7ab8f1c298812783e8328e956b78dc4807f9f", size = 16354295, upload-time = "2025-12-20T16:17:28.308Z" }, + { url = "https://files.pythonhosted.org/packages/b8/0a/b54615b47ee8736a6461a4bb6749128dd3435c5a759d5663f11f0e9af4ac/numpy-2.4.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:1ee32359fb7543b7b7bd0b2f46294db27e29e7bbdf70541e81b190836cd83ded", size = 16190242, upload-time = "2025-12-20T16:17:30.993Z" }, + { url = "https://files.pythonhosted.org/packages/98/ce/ea207769aacad6246525ec6c6bbd66a2bf56c72443dc10e2f90feed29290/numpy-2.4.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:e493962256a38f58283de033d8af176c5c91c084ea30f15834f7545451c42059", size = 18280875, upload-time = "2025-12-20T16:17:33.327Z" }, + { url = "https://files.pythonhosted.org/packages/17/ef/ec409437aa962ea372ed601c519a2b141701683ff028f894b7466f0ab42b/numpy-2.4.0-cp314-cp314-win32.whl", hash = "sha256:6bbaebf0d11567fa8926215ae731e1d58e6ec28a8a25235b8a47405d301332db", size = 6002530, upload-time = "2025-12-20T16:17:35.729Z" }, + { url = "https://files.pythonhosted.org/packages/5f/4a/5cb94c787a3ed1ac65e1271b968686521169a7b3ec0b6544bb3ca32960b0/numpy-2.4.0-cp314-cp314-win_amd64.whl", hash = "sha256:3d857f55e7fdf7c38ab96c4558c95b97d1c685be6b05c249f5fdafcbd6f9899e", size = 12435890, upload-time = "2025-12-20T16:17:37.599Z" }, + { url = "https://files.pythonhosted.org/packages/48/a0/04b89db963af9de1104975e2544f30de89adbf75b9e75f7dd2599be12c79/numpy-2.4.0-cp314-cp314-win_arm64.whl", hash = "sha256:bb50ce5fb202a26fd5404620e7ef820ad1ab3558b444cb0b55beb7ef66cd2d63", size = 10591892, upload-time = "2025-12-20T16:17:39.649Z" }, + { url = "https://files.pythonhosted.org/packages/53/e5/d74b5ccf6712c06c7a545025a6a71bfa03bdc7e0568b405b0d655232fd92/numpy-2.4.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:355354388cba60f2132df297e2d53053d4063f79077b67b481d21276d61fc4df", size = 12494312, upload-time = "2025-12-20T16:17:41.714Z" }, + { url = "https://files.pythonhosted.org/packages/c2/08/3ca9cc2ddf54dfee7ae9a6479c071092a228c68aef08252aa08dac2af002/numpy-2.4.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:1d8f9fde5f6dc1b6fc34df8162f3b3079365468703fee7f31d4e0cc8c63baed9", size = 5322862, upload-time = "2025-12-20T16:17:44.145Z" }, + { url = "https://files.pythonhosted.org/packages/87/74/0bb63a68394c0c1e52670cfff2e309afa41edbe11b3327d9af29e4383f34/numpy-2.4.0-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:e0434aa22c821f44eeb4c650b81c7fbdd8c0122c6c4b5a576a76d5a35625ecd9", size = 6644986, upload-time = "2025-12-20T16:17:46.203Z" }, + { url = "https://files.pythonhosted.org/packages/06/8f/9264d9bdbcf8236af2823623fe2f3981d740fc3461e2787e231d97c38c28/numpy-2.4.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:40483b2f2d3ba7aad426443767ff5632ec3156ef09742b96913787d13c336471", size = 14457958, upload-time = "2025-12-20T16:17:48.017Z" }, + { url = "https://files.pythonhosted.org/packages/8c/d9/f9a69ae564bbc7236a35aa883319364ef5fd41f72aa320cc1cbe66148fe2/numpy-2.4.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d9e6a7664ddd9746e20b7325351fe1a8408d0a2bf9c63b5e898290ddc8f09544", size = 16398394, upload-time = "2025-12-20T16:17:50.409Z" }, + { url = "https://files.pythonhosted.org/packages/34/c7/39241501408dde7f885d241a98caba5421061a2c6d2b2197ac5e3aa842d8/numpy-2.4.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:ecb0019d44f4cdb50b676c5d0cb4b1eae8e15d1ed3d3e6639f986fc92b2ec52c", size = 16241044, upload-time = "2025-12-20T16:17:52.661Z" }, + { url = "https://files.pythonhosted.org/packages/7c/95/cae7effd90e065a95e59fe710eeee05d7328ed169776dfdd9f789e032125/numpy-2.4.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:d0ffd9e2e4441c96a9c91ec1783285d80bf835b677853fc2770a89d50c1e48ac", size = 18321772, upload-time = "2025-12-20T16:17:54.947Z" }, + { url = "https://files.pythonhosted.org/packages/96/df/3c6c279accd2bfb968a76298e5b276310bd55d243df4fa8ac5816d79347d/numpy-2.4.0-cp314-cp314t-win32.whl", hash = "sha256:77f0d13fa87036d7553bf81f0e1fe3ce68d14c9976c9851744e4d3e91127e95f", size = 6148320, upload-time = "2025-12-20T16:17:57.249Z" }, + { url = "https://files.pythonhosted.org/packages/92/8d/f23033cce252e7a75cae853d17f582e86534c46404dea1c8ee094a9d6d84/numpy-2.4.0-cp314-cp314t-win_amd64.whl", hash = "sha256:b1f5b45829ac1848893f0ddf5cb326110604d6df96cdc255b0bf9edd154104d4", size = 12623460, upload-time = "2025-12-20T16:17:58.963Z" }, + { url = "https://files.pythonhosted.org/packages/a4/4f/1f8475907d1a7c4ef9020edf7f39ea2422ec896849245f00688e4b268a71/numpy-2.4.0-cp314-cp314t-win_arm64.whl", hash = "sha256:23a3e9d1a6f360267e8fbb38ba5db355a6a7e9be71d7fce7ab3125e88bb646c8", size = 10661799, upload-time = "2025-12-20T16:18:01.078Z" }, + { url = "https://files.pythonhosted.org/packages/4b/ef/088e7c7342f300aaf3ee5f2c821c4b9996a1bef2aaf6a49cc8ab4883758e/numpy-2.4.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:b54c83f1c0c0f1d748dca0af516062b8829d53d1f0c402be24b4257a9c48ada6", size = 16819003, upload-time = "2025-12-20T16:18:03.41Z" }, + { url = "https://files.pythonhosted.org/packages/ff/ce/a53017b5443b4b84517182d463fc7bcc2adb4faa8b20813f8e5f5aeb5faa/numpy-2.4.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:aabb081ca0ec5d39591fc33018cd4b3f96e1a2dd6756282029986d00a785fba4", size = 12567105, upload-time = "2025-12-20T16:18:05.594Z" }, + { url = "https://files.pythonhosted.org/packages/77/58/5ff91b161f2ec650c88a626c3905d938c89aaadabd0431e6d9c1330c83e2/numpy-2.4.0-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:8eafe7c36c8430b7794edeab3087dec7bf31d634d92f2af9949434b9d1964cba", size = 5395590, upload-time = "2025-12-20T16:18:08.031Z" }, + { url = "https://files.pythonhosted.org/packages/1d/4e/f1a084106df8c2df8132fc437e56987308e0524836aa7733721c8429d4fe/numpy-2.4.0-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:2f585f52b2baf07ff3356158d9268ea095e221371f1074fadea2f42544d58b4d", size = 6709947, upload-time = "2025-12-20T16:18:09.836Z" }, + { url = "https://files.pythonhosted.org/packages/63/09/3d8aeb809c0332c3f642da812ac2e3d74fc9252b3021f8c30c82e99e3f3d/numpy-2.4.0-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:32ed06d0fe9cae27d8fb5f400c63ccee72370599c75e683a6358dd3a4fb50aaf", size = 14535119, upload-time = "2025-12-20T16:18:12.105Z" }, + { url = "https://files.pythonhosted.org/packages/fd/7f/68f0fc43a2cbdc6bb239160c754d87c922f60fbaa0fa3cd3d312b8a7f5ee/numpy-2.4.0-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:57c540ed8fb1f05cb997c6761cd56db72395b0d6985e90571ff660452ade4f98", size = 16475815, upload-time = "2025-12-20T16:18:14.433Z" }, + { url = "https://files.pythonhosted.org/packages/11/73/edeacba3167b1ca66d51b1a5a14697c2c40098b5ffa01811c67b1785a5ab/numpy-2.4.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:a39fb973a726e63223287adc6dafe444ce75af952d711e400f3bf2b36ef55a7b", size = 12489376, upload-time = "2025-12-20T16:18:16.524Z" }, ] [[package]] @@ -695,89 +709,89 @@ wheels = [ [[package]] name = "pillow" -version = "12.0.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/5a/b0/cace85a1b0c9775a9f8f5d5423c8261c858760e2466c79b2dd184638b056/pillow-12.0.0.tar.gz", hash = "sha256:87d4f8125c9988bfbed67af47dd7a953e2fc7b0cc1e7800ec6d2080d490bb353", size = 47008828, upload-time = "2025-10-15T18:24:14.008Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/0e/5a/a2f6773b64edb921a756eb0729068acad9fc5208a53f4a349396e9436721/pillow-12.0.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:0fd00cac9c03256c8b2ff58f162ebcd2587ad3e1f2e397eab718c47e24d231cc", size = 5289798, upload-time = "2025-10-15T18:21:47.763Z" }, - { url = "https://files.pythonhosted.org/packages/2e/05/069b1f8a2e4b5a37493da6c5868531c3f77b85e716ad7a590ef87d58730d/pillow-12.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a3475b96f5908b3b16c47533daaa87380c491357d197564e0ba34ae75c0f3257", size = 4650589, upload-time = "2025-10-15T18:21:49.515Z" }, - { url = "https://files.pythonhosted.org/packages/61/e3/2c820d6e9a36432503ead175ae294f96861b07600a7156154a086ba7111a/pillow-12.0.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:110486b79f2d112cf6add83b28b627e369219388f64ef2f960fef9ebaf54c642", size = 6230472, upload-time = "2025-10-15T18:21:51.052Z" }, - { url = "https://files.pythonhosted.org/packages/4f/89/63427f51c64209c5e23d4d52071c8d0f21024d3a8a487737caaf614a5795/pillow-12.0.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5269cc1caeedb67e6f7269a42014f381f45e2e7cd42d834ede3c703a1d915fe3", size = 8033887, upload-time = "2025-10-15T18:21:52.604Z" }, - { url = "https://files.pythonhosted.org/packages/f6/1b/c9711318d4901093c15840f268ad649459cd81984c9ec9887756cca049a5/pillow-12.0.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:aa5129de4e174daccbc59d0a3b6d20eaf24417d59851c07ebb37aeb02947987c", size = 6343964, upload-time = "2025-10-15T18:21:54.619Z" }, - { url = "https://files.pythonhosted.org/packages/41/1e/db9470f2d030b4995083044cd8738cdd1bf773106819f6d8ba12597d5352/pillow-12.0.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bee2a6db3a7242ea309aa7ee8e2780726fed67ff4e5b40169f2c940e7eb09227", size = 7034756, upload-time = "2025-10-15T18:21:56.151Z" }, - { url = "https://files.pythonhosted.org/packages/cc/b0/6177a8bdd5ee4ed87cba2de5a3cc1db55ffbbec6176784ce5bb75aa96798/pillow-12.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:90387104ee8400a7b4598253b4c406f8958f59fcf983a6cea2b50d59f7d63d0b", size = 6458075, upload-time = "2025-10-15T18:21:57.759Z" }, - { url = "https://files.pythonhosted.org/packages/bc/5e/61537aa6fa977922c6a03253a0e727e6e4a72381a80d63ad8eec350684f2/pillow-12.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:bc91a56697869546d1b8f0a3ff35224557ae7f881050e99f615e0119bf934b4e", size = 7125955, upload-time = "2025-10-15T18:21:59.372Z" }, - { url = "https://files.pythonhosted.org/packages/1f/3d/d5033539344ee3cbd9a4d69e12e63ca3a44a739eb2d4c8da350a3d38edd7/pillow-12.0.0-cp311-cp311-win32.whl", hash = "sha256:27f95b12453d165099c84f8a8bfdfd46b9e4bda9e0e4b65f0635430027f55739", size = 6298440, upload-time = "2025-10-15T18:22:00.982Z" }, - { url = "https://files.pythonhosted.org/packages/4d/42/aaca386de5cc8bd8a0254516957c1f265e3521c91515b16e286c662854c4/pillow-12.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:b583dc9070312190192631373c6c8ed277254aa6e6084b74bdd0a6d3b221608e", size = 6999256, upload-time = "2025-10-15T18:22:02.617Z" }, - { url = "https://files.pythonhosted.org/packages/ba/f1/9197c9c2d5708b785f631a6dfbfa8eb3fb9672837cb92ae9af812c13b4ed/pillow-12.0.0-cp311-cp311-win_arm64.whl", hash = "sha256:759de84a33be3b178a64c8ba28ad5c135900359e85fb662bc6e403ad4407791d", size = 2436025, upload-time = "2025-10-15T18:22:04.598Z" }, - { url = "https://files.pythonhosted.org/packages/2c/90/4fcce2c22caf044e660a198d740e7fbc14395619e3cb1abad12192c0826c/pillow-12.0.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:53561a4ddc36facb432fae7a9d8afbfaf94795414f5cdc5fc52f28c1dca90371", size = 5249377, upload-time = "2025-10-15T18:22:05.993Z" }, - { url = "https://files.pythonhosted.org/packages/fd/e0/ed960067543d080691d47d6938ebccbf3976a931c9567ab2fbfab983a5dd/pillow-12.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:71db6b4c1653045dacc1585c1b0d184004f0d7e694c7b34ac165ca70c0838082", size = 4650343, upload-time = "2025-10-15T18:22:07.718Z" }, - { url = "https://files.pythonhosted.org/packages/e7/a1/f81fdeddcb99c044bf7d6faa47e12850f13cee0849537a7d27eeab5534d4/pillow-12.0.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2fa5f0b6716fc88f11380b88b31fe591a06c6315e955c096c35715788b339e3f", size = 6232981, upload-time = "2025-10-15T18:22:09.287Z" }, - { url = "https://files.pythonhosted.org/packages/88/e1/9098d3ce341a8750b55b0e00c03f1630d6178f38ac191c81c97a3b047b44/pillow-12.0.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:82240051c6ca513c616f7f9da06e871f61bfd7805f566275841af15015b8f98d", size = 8041399, upload-time = "2025-10-15T18:22:10.872Z" }, - { url = "https://files.pythonhosted.org/packages/a7/62/a22e8d3b602ae8cc01446d0c57a54e982737f44b6f2e1e019a925143771d/pillow-12.0.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:55f818bd74fe2f11d4d7cbc65880a843c4075e0ac7226bc1a23261dbea531953", size = 6347740, upload-time = "2025-10-15T18:22:12.769Z" }, - { url = "https://files.pythonhosted.org/packages/4f/87/424511bdcd02c8d7acf9f65caa09f291a519b16bd83c3fb3374b3d4ae951/pillow-12.0.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b87843e225e74576437fd5b6a4c2205d422754f84a06942cfaf1dc32243e45a8", size = 7040201, upload-time = "2025-10-15T18:22:14.813Z" }, - { url = "https://files.pythonhosted.org/packages/dc/4d/435c8ac688c54d11755aedfdd9f29c9eeddf68d150fe42d1d3dbd2365149/pillow-12.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c607c90ba67533e1b2355b821fef6764d1dd2cbe26b8c1005ae84f7aea25ff79", size = 6462334, upload-time = "2025-10-15T18:22:16.375Z" }, - { url = "https://files.pythonhosted.org/packages/2b/f2/ad34167a8059a59b8ad10bc5c72d4d9b35acc6b7c0877af8ac885b5f2044/pillow-12.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:21f241bdd5080a15bc86d3466a9f6074a9c2c2b314100dd896ac81ee6db2f1ba", size = 7134162, upload-time = "2025-10-15T18:22:17.996Z" }, - { url = "https://files.pythonhosted.org/packages/0c/b1/a7391df6adacf0a5c2cf6ac1cf1fcc1369e7d439d28f637a847f8803beb3/pillow-12.0.0-cp312-cp312-win32.whl", hash = "sha256:dd333073e0cacdc3089525c7df7d39b211bcdf31fc2824e49d01c6b6187b07d0", size = 6298769, upload-time = "2025-10-15T18:22:19.923Z" }, - { url = "https://files.pythonhosted.org/packages/a2/0b/d87733741526541c909bbf159e338dcace4f982daac6e5a8d6be225ca32d/pillow-12.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:9fe611163f6303d1619bbcb653540a4d60f9e55e622d60a3108be0d5b441017a", size = 7001107, upload-time = "2025-10-15T18:22:21.644Z" }, - { url = "https://files.pythonhosted.org/packages/bc/96/aaa61ce33cc98421fb6088af2a03be4157b1e7e0e87087c888e2370a7f45/pillow-12.0.0-cp312-cp312-win_arm64.whl", hash = "sha256:7dfb439562f234f7d57b1ac6bc8fe7f838a4bd49c79230e0f6a1da93e82f1fad", size = 2436012, upload-time = "2025-10-15T18:22:23.621Z" }, - { url = "https://files.pythonhosted.org/packages/62/f2/de993bb2d21b33a98d031ecf6a978e4b61da207bef02f7b43093774c480d/pillow-12.0.0-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:0869154a2d0546545cde61d1789a6524319fc1897d9ee31218eae7a60ccc5643", size = 4045493, upload-time = "2025-10-15T18:22:25.758Z" }, - { url = "https://files.pythonhosted.org/packages/0e/b6/bc8d0c4c9f6f111a783d045310945deb769b806d7574764234ffd50bc5ea/pillow-12.0.0-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:a7921c5a6d31b3d756ec980f2f47c0cfdbce0fc48c22a39347a895f41f4a6ea4", size = 4120461, upload-time = "2025-10-15T18:22:27.286Z" }, - { url = "https://files.pythonhosted.org/packages/5d/57/d60d343709366a353dc56adb4ee1e7d8a2cc34e3fbc22905f4167cfec119/pillow-12.0.0-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:1ee80a59f6ce048ae13cda1abf7fbd2a34ab9ee7d401c46be3ca685d1999a399", size = 3576912, upload-time = "2025-10-15T18:22:28.751Z" }, - { url = "https://files.pythonhosted.org/packages/a4/a4/a0a31467e3f83b94d37568294b01d22b43ae3c5d85f2811769b9c66389dd/pillow-12.0.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:c50f36a62a22d350c96e49ad02d0da41dbd17ddc2e29750dbdba4323f85eb4a5", size = 5249132, upload-time = "2025-10-15T18:22:30.641Z" }, - { url = "https://files.pythonhosted.org/packages/83/06/48eab21dd561de2914242711434c0c0eb992ed08ff3f6107a5f44527f5e9/pillow-12.0.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:5193fde9a5f23c331ea26d0cf171fbf67e3f247585f50c08b3e205c7aeb4589b", size = 4650099, upload-time = "2025-10-15T18:22:32.73Z" }, - { url = "https://files.pythonhosted.org/packages/fc/bd/69ed99fd46a8dba7c1887156d3572fe4484e3f031405fcc5a92e31c04035/pillow-12.0.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:bde737cff1a975b70652b62d626f7785e0480918dece11e8fef3c0cf057351c3", size = 6230808, upload-time = "2025-10-15T18:22:34.337Z" }, - { url = "https://files.pythonhosted.org/packages/ea/94/8fad659bcdbf86ed70099cb60ae40be6acca434bbc8c4c0d4ef356d7e0de/pillow-12.0.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a6597ff2b61d121172f5844b53f21467f7082f5fb385a9a29c01414463f93b07", size = 8037804, upload-time = "2025-10-15T18:22:36.402Z" }, - { url = "https://files.pythonhosted.org/packages/20/39/c685d05c06deecfd4e2d1950e9a908aa2ca8bc4e6c3b12d93b9cafbd7837/pillow-12.0.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0b817e7035ea7f6b942c13aa03bb554fc44fea70838ea21f8eb31c638326584e", size = 6345553, upload-time = "2025-10-15T18:22:38.066Z" }, - { url = "https://files.pythonhosted.org/packages/38/57/755dbd06530a27a5ed74f8cb0a7a44a21722ebf318edbe67ddbd7fb28f88/pillow-12.0.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f4f1231b7dec408e8670264ce63e9c71409d9583dd21d32c163e25213ee2a344", size = 7037729, upload-time = "2025-10-15T18:22:39.769Z" }, - { url = "https://files.pythonhosted.org/packages/ca/b6/7e94f4c41d238615674d06ed677c14883103dce1c52e4af16f000338cfd7/pillow-12.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6e51b71417049ad6ab14c49608b4a24d8fb3fe605e5dfabfe523b58064dc3d27", size = 6459789, upload-time = "2025-10-15T18:22:41.437Z" }, - { url = "https://files.pythonhosted.org/packages/9c/14/4448bb0b5e0f22dd865290536d20ec8a23b64e2d04280b89139f09a36bb6/pillow-12.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:d120c38a42c234dc9a8c5de7ceaaf899cf33561956acb4941653f8bdc657aa79", size = 7130917, upload-time = "2025-10-15T18:22:43.152Z" }, - { url = "https://files.pythonhosted.org/packages/dd/ca/16c6926cc1c015845745d5c16c9358e24282f1e588237a4c36d2b30f182f/pillow-12.0.0-cp313-cp313-win32.whl", hash = "sha256:4cc6b3b2efff105c6a1656cfe59da4fdde2cda9af1c5e0b58529b24525d0a098", size = 6302391, upload-time = "2025-10-15T18:22:44.753Z" }, - { url = "https://files.pythonhosted.org/packages/6d/2a/dd43dcfd6dae9b6a49ee28a8eedb98c7d5ff2de94a5d834565164667b97b/pillow-12.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:4cf7fed4b4580601c4345ceb5d4cbf5a980d030fd5ad07c4d2ec589f95f09905", size = 7007477, upload-time = "2025-10-15T18:22:46.838Z" }, - { url = "https://files.pythonhosted.org/packages/77/f0/72ea067f4b5ae5ead653053212af05ce3705807906ba3f3e8f58ddf617e6/pillow-12.0.0-cp313-cp313-win_arm64.whl", hash = "sha256:9f0b04c6b8584c2c193babcccc908b38ed29524b29dd464bc8801bf10d746a3a", size = 2435918, upload-time = "2025-10-15T18:22:48.399Z" }, - { url = "https://files.pythonhosted.org/packages/f5/5e/9046b423735c21f0487ea6cb5b10f89ea8f8dfbe32576fe052b5ba9d4e5b/pillow-12.0.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:7fa22993bac7b77b78cae22bad1e2a987ddf0d9015c63358032f84a53f23cdc3", size = 5251406, upload-time = "2025-10-15T18:22:49.905Z" }, - { url = "https://files.pythonhosted.org/packages/12/66/982ceebcdb13c97270ef7a56c3969635b4ee7cd45227fa707c94719229c5/pillow-12.0.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:f135c702ac42262573fe9714dfe99c944b4ba307af5eb507abef1667e2cbbced", size = 4653218, upload-time = "2025-10-15T18:22:51.587Z" }, - { url = "https://files.pythonhosted.org/packages/16/b3/81e625524688c31859450119bf12674619429cab3119eec0e30a7a1029cb/pillow-12.0.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c85de1136429c524e55cfa4e033b4a7940ac5c8ee4d9401cc2d1bf48154bbc7b", size = 6266564, upload-time = "2025-10-15T18:22:53.215Z" }, - { url = "https://files.pythonhosted.org/packages/98/59/dfb38f2a41240d2408096e1a76c671d0a105a4a8471b1871c6902719450c/pillow-12.0.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:38df9b4bfd3db902c9c2bd369bcacaf9d935b2fff73709429d95cc41554f7b3d", size = 8069260, upload-time = "2025-10-15T18:22:54.933Z" }, - { url = "https://files.pythonhosted.org/packages/dc/3d/378dbea5cd1874b94c312425ca77b0f47776c78e0df2df751b820c8c1d6c/pillow-12.0.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7d87ef5795da03d742bf49439f9ca4d027cde49c82c5371ba52464aee266699a", size = 6379248, upload-time = "2025-10-15T18:22:56.605Z" }, - { url = "https://files.pythonhosted.org/packages/84/b0/d525ef47d71590f1621510327acec75ae58c721dc071b17d8d652ca494d8/pillow-12.0.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:aff9e4d82d082ff9513bdd6acd4f5bd359f5b2c870907d2b0a9c5e10d40c88fe", size = 7066043, upload-time = "2025-10-15T18:22:58.53Z" }, - { url = "https://files.pythonhosted.org/packages/61/2c/aced60e9cf9d0cde341d54bf7932c9ffc33ddb4a1595798b3a5150c7ec4e/pillow-12.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:8d8ca2b210ada074d57fcee40c30446c9562e542fc46aedc19baf758a93532ee", size = 6490915, upload-time = "2025-10-15T18:23:00.582Z" }, - { url = "https://files.pythonhosted.org/packages/ef/26/69dcb9b91f4e59f8f34b2332a4a0a951b44f547c4ed39d3e4dcfcff48f89/pillow-12.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:99a7f72fb6249302aa62245680754862a44179b545ded638cf1fef59befb57ef", size = 7157998, upload-time = "2025-10-15T18:23:02.627Z" }, - { url = "https://files.pythonhosted.org/packages/61/2b/726235842220ca95fa441ddf55dd2382b52ab5b8d9c0596fe6b3f23dafe8/pillow-12.0.0-cp313-cp313t-win32.whl", hash = "sha256:4078242472387600b2ce8d93ade8899c12bf33fa89e55ec89fe126e9d6d5d9e9", size = 6306201, upload-time = "2025-10-15T18:23:04.709Z" }, - { url = "https://files.pythonhosted.org/packages/c0/3d/2afaf4e840b2df71344ababf2f8edd75a705ce500e5dc1e7227808312ae1/pillow-12.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:2c54c1a783d6d60595d3514f0efe9b37c8808746a66920315bfd34a938d7994b", size = 7013165, upload-time = "2025-10-15T18:23:06.46Z" }, - { url = "https://files.pythonhosted.org/packages/6f/75/3fa09aa5cf6ed04bee3fa575798ddf1ce0bace8edb47249c798077a81f7f/pillow-12.0.0-cp313-cp313t-win_arm64.whl", hash = "sha256:26d9f7d2b604cd23aba3e9faf795787456ac25634d82cd060556998e39c6fa47", size = 2437834, upload-time = "2025-10-15T18:23:08.194Z" }, - { url = "https://files.pythonhosted.org/packages/54/2a/9a8c6ba2c2c07b71bec92cf63e03370ca5e5f5c5b119b742bcc0cde3f9c5/pillow-12.0.0-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:beeae3f27f62308f1ddbcfb0690bf44b10732f2ef43758f169d5e9303165d3f9", size = 4045531, upload-time = "2025-10-15T18:23:10.121Z" }, - { url = "https://files.pythonhosted.org/packages/84/54/836fdbf1bfb3d66a59f0189ff0b9f5f666cee09c6188309300df04ad71fa/pillow-12.0.0-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:d4827615da15cd59784ce39d3388275ec093ae3ee8d7f0c089b76fa87af756c2", size = 4120554, upload-time = "2025-10-15T18:23:12.14Z" }, - { url = "https://files.pythonhosted.org/packages/0d/cd/16aec9f0da4793e98e6b54778a5fbce4f375c6646fe662e80600b8797379/pillow-12.0.0-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:3e42edad50b6909089750e65c91aa09aaf1e0a71310d383f11321b27c224ed8a", size = 3576812, upload-time = "2025-10-15T18:23:13.962Z" }, - { url = "https://files.pythonhosted.org/packages/f6/b7/13957fda356dc46339298b351cae0d327704986337c3c69bb54628c88155/pillow-12.0.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:e5d8efac84c9afcb40914ab49ba063d94f5dbdf5066db4482c66a992f47a3a3b", size = 5252689, upload-time = "2025-10-15T18:23:15.562Z" }, - { url = "https://files.pythonhosted.org/packages/fc/f5/eae31a306341d8f331f43edb2e9122c7661b975433de5e447939ae61c5da/pillow-12.0.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:266cd5f2b63ff316d5a1bba46268e603c9caf5606d44f38c2873c380950576ad", size = 4650186, upload-time = "2025-10-15T18:23:17.379Z" }, - { url = "https://files.pythonhosted.org/packages/86/62/2a88339aa40c4c77e79108facbd307d6091e2c0eb5b8d3cf4977cfca2fe6/pillow-12.0.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:58eea5ebe51504057dd95c5b77d21700b77615ab0243d8152793dc00eb4faf01", size = 6230308, upload-time = "2025-10-15T18:23:18.971Z" }, - { url = "https://files.pythonhosted.org/packages/c7/33/5425a8992bcb32d1cb9fa3dd39a89e613d09a22f2c8083b7bf43c455f760/pillow-12.0.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f13711b1a5ba512d647a0e4ba79280d3a9a045aaf7e0cc6fbe96b91d4cdf6b0c", size = 8039222, upload-time = "2025-10-15T18:23:20.909Z" }, - { url = "https://files.pythonhosted.org/packages/d8/61/3f5d3b35c5728f37953d3eec5b5f3e77111949523bd2dd7f31a851e50690/pillow-12.0.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6846bd2d116ff42cba6b646edf5bf61d37e5cbd256425fa089fee4ff5c07a99e", size = 6346657, upload-time = "2025-10-15T18:23:23.077Z" }, - { url = "https://files.pythonhosted.org/packages/3a/be/ee90a3d79271227e0f0a33c453531efd6ed14b2e708596ba5dd9be948da3/pillow-12.0.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c98fa880d695de164b4135a52fd2e9cd7b7c90a9d8ac5e9e443a24a95ef9248e", size = 7038482, upload-time = "2025-10-15T18:23:25.005Z" }, - { url = "https://files.pythonhosted.org/packages/44/34/a16b6a4d1ad727de390e9bd9f19f5f669e079e5826ec0f329010ddea492f/pillow-12.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:fa3ed2a29a9e9d2d488b4da81dcb54720ac3104a20bf0bd273f1e4648aff5af9", size = 6461416, upload-time = "2025-10-15T18:23:27.009Z" }, - { url = "https://files.pythonhosted.org/packages/b6/39/1aa5850d2ade7d7ba9f54e4e4c17077244ff7a2d9e25998c38a29749eb3f/pillow-12.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:d034140032870024e6b9892c692fe2968493790dd57208b2c37e3fb35f6df3ab", size = 7131584, upload-time = "2025-10-15T18:23:29.752Z" }, - { url = "https://files.pythonhosted.org/packages/bf/db/4fae862f8fad0167073a7733973bfa955f47e2cac3dc3e3e6257d10fab4a/pillow-12.0.0-cp314-cp314-win32.whl", hash = "sha256:1b1b133e6e16105f524a8dec491e0586d072948ce15c9b914e41cdadd209052b", size = 6400621, upload-time = "2025-10-15T18:23:32.06Z" }, - { url = "https://files.pythonhosted.org/packages/2b/24/b350c31543fb0107ab2599464d7e28e6f856027aadda995022e695313d94/pillow-12.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:8dc232e39d409036af549c86f24aed8273a40ffa459981146829a324e0848b4b", size = 7142916, upload-time = "2025-10-15T18:23:34.71Z" }, - { url = "https://files.pythonhosted.org/packages/0f/9b/0ba5a6fd9351793996ef7487c4fdbde8d3f5f75dbedc093bb598648fddf0/pillow-12.0.0-cp314-cp314-win_arm64.whl", hash = "sha256:d52610d51e265a51518692045e372a4c363056130d922a7351429ac9f27e70b0", size = 2523836, upload-time = "2025-10-15T18:23:36.967Z" }, - { url = "https://files.pythonhosted.org/packages/f5/7a/ceee0840aebc579af529b523d530840338ecf63992395842e54edc805987/pillow-12.0.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:1979f4566bb96c1e50a62d9831e2ea2d1211761e5662afc545fa766f996632f6", size = 5255092, upload-time = "2025-10-15T18:23:38.573Z" }, - { url = "https://files.pythonhosted.org/packages/44/76/20776057b4bfd1aef4eeca992ebde0f53a4dce874f3ae693d0ec90a4f79b/pillow-12.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:b2e4b27a6e15b04832fe9bf292b94b5ca156016bbc1ea9c2c20098a0320d6cf6", size = 4653158, upload-time = "2025-10-15T18:23:40.238Z" }, - { url = "https://files.pythonhosted.org/packages/82/3f/d9ff92ace07be8836b4e7e87e6a4c7a8318d47c2f1463ffcf121fc57d9cb/pillow-12.0.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fb3096c30df99fd01c7bf8e544f392103d0795b9f98ba71a8054bcbf56b255f1", size = 6267882, upload-time = "2025-10-15T18:23:42.434Z" }, - { url = "https://files.pythonhosted.org/packages/9f/7a/4f7ff87f00d3ad33ba21af78bfcd2f032107710baf8280e3722ceec28cda/pillow-12.0.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7438839e9e053ef79f7112c881cef684013855016f928b168b81ed5835f3e75e", size = 8071001, upload-time = "2025-10-15T18:23:44.29Z" }, - { url = "https://files.pythonhosted.org/packages/75/87/fcea108944a52dad8cca0715ae6247e271eb80459364a98518f1e4f480c1/pillow-12.0.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d5c411a8eaa2299322b647cd932586b1427367fd3184ffbb8f7a219ea2041ca", size = 6380146, upload-time = "2025-10-15T18:23:46.065Z" }, - { url = "https://files.pythonhosted.org/packages/91/52/0d31b5e571ef5fd111d2978b84603fce26aba1b6092f28e941cb46570745/pillow-12.0.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d7e091d464ac59d2c7ad8e7e08105eaf9dafbc3883fd7265ffccc2baad6ac925", size = 7067344, upload-time = "2025-10-15T18:23:47.898Z" }, - { url = "https://files.pythonhosted.org/packages/7b/f4/2dd3d721f875f928d48e83bb30a434dee75a2531bca839bb996bb0aa5a91/pillow-12.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:792a2c0be4dcc18af9d4a2dfd8a11a17d5e25274a1062b0ec1c2d79c76f3e7f8", size = 6491864, upload-time = "2025-10-15T18:23:49.607Z" }, - { url = "https://files.pythonhosted.org/packages/30/4b/667dfcf3d61fc309ba5a15b141845cece5915e39b99c1ceab0f34bf1d124/pillow-12.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:afbefa430092f71a9593a99ab6a4e7538bc9eabbf7bf94f91510d3503943edc4", size = 7158911, upload-time = "2025-10-15T18:23:51.351Z" }, - { url = "https://files.pythonhosted.org/packages/a2/2f/16cabcc6426c32218ace36bf0d55955e813f2958afddbf1d391849fee9d1/pillow-12.0.0-cp314-cp314t-win32.whl", hash = "sha256:3830c769decf88f1289680a59d4f4c46c72573446352e2befec9a8512104fa52", size = 6408045, upload-time = "2025-10-15T18:23:53.177Z" }, - { url = "https://files.pythonhosted.org/packages/35/73/e29aa0c9c666cf787628d3f0dcf379f4791fba79f4936d02f8b37165bdf8/pillow-12.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:905b0365b210c73afb0ebe9101a32572152dfd1c144c7e28968a331b9217b94a", size = 7148282, upload-time = "2025-10-15T18:23:55.316Z" }, - { url = "https://files.pythonhosted.org/packages/c1/70/6b41bdcddf541b437bbb9f47f94d2db5d9ddef6c37ccab8c9107743748a4/pillow-12.0.0-cp314-cp314t-win_arm64.whl", hash = "sha256:99353a06902c2e43b43e8ff74ee65a7d90307d82370604746738a1e0661ccca7", size = 2525630, upload-time = "2025-10-15T18:23:57.149Z" }, - { url = "https://files.pythonhosted.org/packages/1d/b3/582327e6c9f86d037b63beebe981425d6811104cb443e8193824ef1a2f27/pillow-12.0.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:b22bd8c974942477156be55a768f7aa37c46904c175be4e158b6a86e3a6b7ca8", size = 5215068, upload-time = "2025-10-15T18:23:59.594Z" }, - { url = "https://files.pythonhosted.org/packages/fd/d6/67748211d119f3b6540baf90f92fae73ae51d5217b171b0e8b5f7e5d558f/pillow-12.0.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:805ebf596939e48dbb2e4922a1d3852cfc25c38160751ce02da93058b48d252a", size = 4614994, upload-time = "2025-10-15T18:24:01.669Z" }, - { url = "https://files.pythonhosted.org/packages/2d/e1/f8281e5d844c41872b273b9f2c34a4bf64ca08905668c8ae730eedc7c9fa/pillow-12.0.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cae81479f77420d217def5f54b5b9d279804d17e982e0f2fa19b1d1e14ab5197", size = 5246639, upload-time = "2025-10-15T18:24:03.403Z" }, - { url = "https://files.pythonhosted.org/packages/94/5a/0d8ab8ffe8a102ff5df60d0de5af309015163bf710c7bb3e8311dd3b3ad0/pillow-12.0.0-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:aeaefa96c768fc66818730b952a862235d68825c178f1b3ffd4efd7ad2edcb7c", size = 6986839, upload-time = "2025-10-15T18:24:05.344Z" }, - { url = "https://files.pythonhosted.org/packages/20/2e/3434380e8110b76cd9eb00a363c484b050f949b4bbe84ba770bb8508a02c/pillow-12.0.0-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:09f2d0abef9e4e2f349305a4f8cc784a8a6c2f58a8c4892eea13b10a943bd26e", size = 5313505, upload-time = "2025-10-15T18:24:07.137Z" }, - { url = "https://files.pythonhosted.org/packages/57/ca/5a9d38900d9d74785141d6580950fe705de68af735ff6e727cb911b64740/pillow-12.0.0-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bdee52571a343d721fb2eb3b090a82d959ff37fc631e3f70422e0c2e029f3e76", size = 5963654, upload-time = "2025-10-15T18:24:09.579Z" }, - { url = "https://files.pythonhosted.org/packages/95/7e/f896623c3c635a90537ac093c6a618ebe1a90d87206e42309cb5d98a1b9e/pillow-12.0.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:b290fd8aa38422444d4b50d579de197557f182ef1068b75f5aa8558638b8d0a5", size = 6997850, upload-time = "2025-10-15T18:24:11.495Z" }, +version = "12.1.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/d0/02/d52c733a2452ef1ffcc123b68e6606d07276b0e358db70eabad7e40042b7/pillow-12.1.0.tar.gz", hash = "sha256:5c5ae0a06e9ea030ab786b0251b32c7e4ce10e58d983c0d5c56029455180b5b9", size = 46977283, upload-time = "2026-01-02T09:13:29.892Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/43/c4/bf8328039de6cc22182c3ef007a2abfbbdab153661c0a9aa78af8d706391/pillow-12.1.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:a83e0850cb8f5ac975291ebfc4170ba481f41a28065277f7f735c202cd8e0af3", size = 5304057, upload-time = "2026-01-02T09:10:46.627Z" }, + { url = "https://files.pythonhosted.org/packages/43/06/7264c0597e676104cc22ca73ee48f752767cd4b1fe084662620b17e10120/pillow-12.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b6e53e82ec2db0717eabb276aa56cf4e500c9a7cec2c2e189b55c24f65a3e8c0", size = 4657811, upload-time = "2026-01-02T09:10:49.548Z" }, + { url = "https://files.pythonhosted.org/packages/72/64/f9189e44474610daf83da31145fa56710b627b5c4c0b9c235e34058f6b31/pillow-12.1.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:40a8e3b9e8773876d6e30daed22f016509e3987bab61b3b7fe309d7019a87451", size = 6232243, upload-time = "2026-01-02T09:10:51.62Z" }, + { url = "https://files.pythonhosted.org/packages/ef/30/0df458009be6a4caca4ca2c52975e6275c387d4e5c95544e34138b41dc86/pillow-12.1.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:800429ac32c9b72909c671aaf17ecd13110f823ddb7db4dfef412a5587c2c24e", size = 8037872, upload-time = "2026-01-02T09:10:53.446Z" }, + { url = "https://files.pythonhosted.org/packages/e4/86/95845d4eda4f4f9557e25381d70876aa213560243ac1a6d619c46caaedd9/pillow-12.1.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0b022eaaf709541b391ee069f0022ee5b36c709df71986e3f7be312e46f42c84", size = 6345398, upload-time = "2026-01-02T09:10:55.426Z" }, + { url = "https://files.pythonhosted.org/packages/5c/1f/8e66ab9be3aaf1435bc03edd1ebdf58ffcd17f7349c1d970cafe87af27d9/pillow-12.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1f345e7bc9d7f368887c712aa5054558bad44d2a301ddf9248599f4161abc7c0", size = 7034667, upload-time = "2026-01-02T09:10:57.11Z" }, + { url = "https://files.pythonhosted.org/packages/f9/f6/683b83cb9b1db1fb52b87951b1c0b99bdcfceaa75febf11406c19f82cb5e/pillow-12.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d70347c8a5b7ccd803ec0c85c8709f036e6348f1e6a5bf048ecd9c64d3550b8b", size = 6458743, upload-time = "2026-01-02T09:10:59.331Z" }, + { url = "https://files.pythonhosted.org/packages/9a/7d/de833d63622538c1d58ce5395e7c6cb7e7dce80decdd8bde4a484e095d9f/pillow-12.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1fcc52d86ce7a34fd17cb04e87cfdb164648a3662a6f20565910a99653d66c18", size = 7159342, upload-time = "2026-01-02T09:11:01.82Z" }, + { url = "https://files.pythonhosted.org/packages/8c/40/50d86571c9e5868c42b81fe7da0c76ca26373f3b95a8dd675425f4a92ec1/pillow-12.1.0-cp311-cp311-win32.whl", hash = "sha256:3ffaa2f0659e2f740473bcf03c702c39a8d4b2b7ffc629052028764324842c64", size = 6328655, upload-time = "2026-01-02T09:11:04.556Z" }, + { url = "https://files.pythonhosted.org/packages/6c/af/b1d7e301c4cd26cd45d4af884d9ee9b6fab893b0ad2450d4746d74a6968c/pillow-12.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:806f3987ffe10e867bab0ddad45df1148a2b98221798457fa097ad85d6e8bc75", size = 7031469, upload-time = "2026-01-02T09:11:06.538Z" }, + { url = "https://files.pythonhosted.org/packages/48/36/d5716586d887fb2a810a4a61518a327a1e21c8b7134c89283af272efe84b/pillow-12.1.0-cp311-cp311-win_arm64.whl", hash = "sha256:9f5fefaca968e700ad1a4a9de98bf0869a94e397fe3524c4c9450c1445252304", size = 2452515, upload-time = "2026-01-02T09:11:08.226Z" }, + { url = "https://files.pythonhosted.org/packages/20/31/dc53fe21a2f2996e1b7d92bf671cdb157079385183ef7c1ae08b485db510/pillow-12.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a332ac4ccb84b6dde65dbace8431f3af08874bf9770719d32a635c4ef411b18b", size = 5262642, upload-time = "2026-01-02T09:11:10.138Z" }, + { url = "https://files.pythonhosted.org/packages/ab/c1/10e45ac9cc79419cedf5121b42dcca5a50ad2b601fa080f58c22fb27626e/pillow-12.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:907bfa8a9cb790748a9aa4513e37c88c59660da3bcfffbd24a7d9e6abf224551", size = 4657464, upload-time = "2026-01-02T09:11:12.319Z" }, + { url = "https://files.pythonhosted.org/packages/ad/26/7b82c0ab7ef40ebede7a97c72d473bda5950f609f8e0c77b04af574a0ddb/pillow-12.1.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:efdc140e7b63b8f739d09a99033aa430accce485ff78e6d311973a67b6bf3208", size = 6234878, upload-time = "2026-01-02T09:11:14.096Z" }, + { url = "https://files.pythonhosted.org/packages/76/25/27abc9792615b5e886ca9411ba6637b675f1b77af3104710ac7353fe5605/pillow-12.1.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:bef9768cab184e7ae6e559c032e95ba8d07b3023c289f79a2bd36e8bf85605a5", size = 8044868, upload-time = "2026-01-02T09:11:15.903Z" }, + { url = "https://files.pythonhosted.org/packages/0a/ea/f200a4c36d836100e7bc738fc48cd963d3ba6372ebc8298a889e0cfc3359/pillow-12.1.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:742aea052cf5ab5034a53c3846165bc3ce88d7c38e954120db0ab867ca242661", size = 6349468, upload-time = "2026-01-02T09:11:17.631Z" }, + { url = "https://files.pythonhosted.org/packages/11/8f/48d0b77ab2200374c66d344459b8958c86693be99526450e7aee714e03e4/pillow-12.1.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a6dfc2af5b082b635af6e08e0d1f9f1c4e04d17d4e2ca0ef96131e85eda6eb17", size = 7041518, upload-time = "2026-01-02T09:11:19.389Z" }, + { url = "https://files.pythonhosted.org/packages/1d/23/c281182eb986b5d31f0a76d2a2c8cd41722d6fb8ed07521e802f9bba52de/pillow-12.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:609e89d9f90b581c8d16358c9087df76024cf058fa693dd3e1e1620823f39670", size = 6462829, upload-time = "2026-01-02T09:11:21.28Z" }, + { url = "https://files.pythonhosted.org/packages/25/ef/7018273e0faac099d7b00982abdcc39142ae6f3bd9ceb06de09779c4a9d6/pillow-12.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:43b4899cfd091a9693a1278c4982f3e50f7fb7cff5153b05174b4afc9593b616", size = 7166756, upload-time = "2026-01-02T09:11:23.559Z" }, + { url = "https://files.pythonhosted.org/packages/8f/c8/993d4b7ab2e341fe02ceef9576afcf5830cdec640be2ac5bee1820d693d4/pillow-12.1.0-cp312-cp312-win32.whl", hash = "sha256:aa0c9cc0b82b14766a99fbe6084409972266e82f459821cd26997a488a7261a7", size = 6328770, upload-time = "2026-01-02T09:11:25.661Z" }, + { url = "https://files.pythonhosted.org/packages/a7/87/90b358775a3f02765d87655237229ba64a997b87efa8ccaca7dd3e36e7a7/pillow-12.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:d70534cea9e7966169ad29a903b99fc507e932069a881d0965a1a84bb57f6c6d", size = 7033406, upload-time = "2026-01-02T09:11:27.474Z" }, + { url = "https://files.pythonhosted.org/packages/5d/cf/881b457eccacac9e5b2ddd97d5071fb6d668307c57cbf4e3b5278e06e536/pillow-12.1.0-cp312-cp312-win_arm64.whl", hash = "sha256:65b80c1ee7e14a87d6a068dd3b0aea268ffcabfe0498d38661b00c5b4b22e74c", size = 2452612, upload-time = "2026-01-02T09:11:29.309Z" }, + { url = "https://files.pythonhosted.org/packages/dd/c7/2530a4aa28248623e9d7f27316b42e27c32ec410f695929696f2e0e4a778/pillow-12.1.0-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:7b5dd7cbae20285cdb597b10eb5a2c13aa9de6cde9bb64a3c1317427b1db1ae1", size = 4062543, upload-time = "2026-01-02T09:11:31.566Z" }, + { url = "https://files.pythonhosted.org/packages/8f/1f/40b8eae823dc1519b87d53c30ed9ef085506b05281d313031755c1705f73/pillow-12.1.0-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:29a4cef9cb672363926f0470afc516dbf7305a14d8c54f7abbb5c199cd8f8179", size = 4138373, upload-time = "2026-01-02T09:11:33.367Z" }, + { url = "https://files.pythonhosted.org/packages/d4/77/6fa60634cf06e52139fd0e89e5bbf055e8166c691c42fb162818b7fda31d/pillow-12.1.0-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:681088909d7e8fa9e31b9799aaa59ba5234c58e5e4f1951b4c4d1082a2e980e0", size = 3601241, upload-time = "2026-01-02T09:11:35.011Z" }, + { url = "https://files.pythonhosted.org/packages/4f/bf/28ab865de622e14b747f0cd7877510848252d950e43002e224fb1c9ababf/pillow-12.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:983976c2ab753166dc66d36af6e8ec15bb511e4a25856e2227e5f7e00a160587", size = 5262410, upload-time = "2026-01-02T09:11:36.682Z" }, + { url = "https://files.pythonhosted.org/packages/1c/34/583420a1b55e715937a85bd48c5c0991598247a1fd2eb5423188e765ea02/pillow-12.1.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:db44d5c160a90df2d24a24760bbd37607d53da0b34fb546c4c232af7192298ac", size = 4657312, upload-time = "2026-01-02T09:11:38.535Z" }, + { url = "https://files.pythonhosted.org/packages/1d/fd/f5a0896839762885b3376ff04878f86ab2b097c2f9a9cdccf4eda8ba8dc0/pillow-12.1.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6b7a9d1db5dad90e2991645874f708e87d9a3c370c243c2d7684d28f7e133e6b", size = 6232605, upload-time = "2026-01-02T09:11:40.602Z" }, + { url = "https://files.pythonhosted.org/packages/98/aa/938a09d127ac1e70e6ed467bd03834350b33ef646b31edb7452d5de43792/pillow-12.1.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6258f3260986990ba2fa8a874f8b6e808cf5abb51a94015ca3dc3c68aa4f30ea", size = 8041617, upload-time = "2026-01-02T09:11:42.721Z" }, + { url = "https://files.pythonhosted.org/packages/17/e8/538b24cb426ac0186e03f80f78bc8dc7246c667f58b540bdd57c71c9f79d/pillow-12.1.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e115c15e3bc727b1ca3e641a909f77f8ca72a64fff150f666fcc85e57701c26c", size = 6346509, upload-time = "2026-01-02T09:11:44.955Z" }, + { url = "https://files.pythonhosted.org/packages/01/9a/632e58ec89a32738cabfd9ec418f0e9898a2b4719afc581f07c04a05e3c9/pillow-12.1.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6741e6f3074a35e47c77b23a4e4f2d90db3ed905cb1c5e6e0d49bff2045632bc", size = 7038117, upload-time = "2026-01-02T09:11:46.736Z" }, + { url = "https://files.pythonhosted.org/packages/c7/a2/d40308cf86eada842ca1f3ffa45d0ca0df7e4ab33c83f81e73f5eaed136d/pillow-12.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:935b9d1aed48fcfb3f838caac506f38e29621b44ccc4f8a64d575cb1b2a88644", size = 6460151, upload-time = "2026-01-02T09:11:48.625Z" }, + { url = "https://files.pythonhosted.org/packages/f1/88/f5b058ad6453a085c5266660a1417bdad590199da1b32fb4efcff9d33b05/pillow-12.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5fee4c04aad8932da9f8f710af2c1a15a83582cfb884152a9caa79d4efcdbf9c", size = 7164534, upload-time = "2026-01-02T09:11:50.445Z" }, + { url = "https://files.pythonhosted.org/packages/19/ce/c17334caea1db789163b5d855a5735e47995b0b5dc8745e9a3605d5f24c0/pillow-12.1.0-cp313-cp313-win32.whl", hash = "sha256:a786bf667724d84aa29b5db1c61b7bfdde380202aaca12c3461afd6b71743171", size = 6332551, upload-time = "2026-01-02T09:11:52.234Z" }, + { url = "https://files.pythonhosted.org/packages/e5/07/74a9d941fa45c90a0d9465098fe1ec85de3e2afbdc15cc4766622d516056/pillow-12.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:461f9dfdafa394c59cd6d818bdfdbab4028b83b02caadaff0ffd433faf4c9a7a", size = 7040087, upload-time = "2026-01-02T09:11:54.822Z" }, + { url = "https://files.pythonhosted.org/packages/88/09/c99950c075a0e9053d8e880595926302575bc742b1b47fe1bbcc8d388d50/pillow-12.1.0-cp313-cp313-win_arm64.whl", hash = "sha256:9212d6b86917a2300669511ed094a9406888362e085f2431a7da985a6b124f45", size = 2452470, upload-time = "2026-01-02T09:11:56.522Z" }, + { url = "https://files.pythonhosted.org/packages/b5/ba/970b7d85ba01f348dee4d65412476321d40ee04dcb51cd3735b9dc94eb58/pillow-12.1.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:00162e9ca6d22b7c3ee8e61faa3c3253cd19b6a37f126cad04f2f88b306f557d", size = 5264816, upload-time = "2026-01-02T09:11:58.227Z" }, + { url = "https://files.pythonhosted.org/packages/10/60/650f2fb55fdba7a510d836202aa52f0baac633e50ab1cf18415d332188fb/pillow-12.1.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:7d6daa89a00b58c37cb1747ec9fb7ac3bc5ffd5949f5888657dfddde6d1312e0", size = 4660472, upload-time = "2026-01-02T09:12:00.798Z" }, + { url = "https://files.pythonhosted.org/packages/2b/c0/5273a99478956a099d533c4f46cbaa19fd69d606624f4334b85e50987a08/pillow-12.1.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e2479c7f02f9d505682dc47df8c0ea1fc5e264c4d1629a5d63fe3e2334b89554", size = 6268974, upload-time = "2026-01-02T09:12:02.572Z" }, + { url = "https://files.pythonhosted.org/packages/b4/26/0bf714bc2e73d5267887d47931d53c4ceeceea6978148ed2ab2a4e6463c4/pillow-12.1.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f188d580bd870cda1e15183790d1cc2fa78f666e76077d103edf048eed9c356e", size = 8073070, upload-time = "2026-01-02T09:12:04.75Z" }, + { url = "https://files.pythonhosted.org/packages/43/cf/1ea826200de111a9d65724c54f927f3111dc5ae297f294b370a670c17786/pillow-12.1.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0fde7ec5538ab5095cc02df38ee99b0443ff0e1c847a045554cf5f9af1f4aa82", size = 6380176, upload-time = "2026-01-02T09:12:06.626Z" }, + { url = "https://files.pythonhosted.org/packages/03/e0/7938dd2b2013373fd85d96e0f38d62b7a5a262af21ac274250c7ca7847c9/pillow-12.1.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0ed07dca4a8464bada6139ab38f5382f83e5f111698caf3191cb8dbf27d908b4", size = 7067061, upload-time = "2026-01-02T09:12:08.624Z" }, + { url = "https://files.pythonhosted.org/packages/86/ad/a2aa97d37272a929a98437a8c0ac37b3cf012f4f8721e1bd5154699b2518/pillow-12.1.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:f45bd71d1fa5e5749587613037b172e0b3b23159d1c00ef2fc920da6f470e6f0", size = 6491824, upload-time = "2026-01-02T09:12:10.488Z" }, + { url = "https://files.pythonhosted.org/packages/a4/44/80e46611b288d51b115826f136fb3465653c28f491068a72d3da49b54cd4/pillow-12.1.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:277518bf4fe74aa91489e1b20577473b19ee70fb97c374aa50830b279f25841b", size = 7190911, upload-time = "2026-01-02T09:12:12.772Z" }, + { url = "https://files.pythonhosted.org/packages/86/77/eacc62356b4cf81abe99ff9dbc7402750044aed02cfd6a503f7c6fc11f3e/pillow-12.1.0-cp313-cp313t-win32.whl", hash = "sha256:7315f9137087c4e0ee73a761b163fc9aa3b19f5f606a7fc08d83fd3e4379af65", size = 6336445, upload-time = "2026-01-02T09:12:14.775Z" }, + { url = "https://files.pythonhosted.org/packages/e7/3c/57d81d0b74d218706dafccb87a87ea44262c43eef98eb3b164fd000e0491/pillow-12.1.0-cp313-cp313t-win_amd64.whl", hash = "sha256:0ddedfaa8b5f0b4ffbc2fa87b556dc59f6bb4ecb14a53b33f9189713ae8053c0", size = 7045354, upload-time = "2026-01-02T09:12:16.599Z" }, + { url = "https://files.pythonhosted.org/packages/ac/82/8b9b97bba2e3576a340f93b044a3a3a09841170ab4c1eb0d5c93469fd32f/pillow-12.1.0-cp313-cp313t-win_arm64.whl", hash = "sha256:80941e6d573197a0c28f394753de529bb436b1ca990ed6e765cf42426abc39f8", size = 2454547, upload-time = "2026-01-02T09:12:18.704Z" }, + { url = "https://files.pythonhosted.org/packages/8c/87/bdf971d8bbcf80a348cc3bacfcb239f5882100fe80534b0ce67a784181d8/pillow-12.1.0-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:5cb7bc1966d031aec37ddb9dcf15c2da5b2e9f7cc3ca7c54473a20a927e1eb91", size = 4062533, upload-time = "2026-01-02T09:12:20.791Z" }, + { url = "https://files.pythonhosted.org/packages/ff/4f/5eb37a681c68d605eb7034c004875c81f86ec9ef51f5be4a63eadd58859a/pillow-12.1.0-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:97e9993d5ed946aba26baf9c1e8cf18adbab584b99f452ee72f7ee8acb882796", size = 4138546, upload-time = "2026-01-02T09:12:23.664Z" }, + { url = "https://files.pythonhosted.org/packages/11/6d/19a95acb2edbace40dcd582d077b991646b7083c41b98da4ed7555b59733/pillow-12.1.0-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:414b9a78e14ffeb98128863314e62c3f24b8a86081066625700b7985b3f529bd", size = 3601163, upload-time = "2026-01-02T09:12:26.338Z" }, + { url = "https://files.pythonhosted.org/packages/fc/36/2b8138e51cb42e4cc39c3297713455548be855a50558c3ac2beebdc251dd/pillow-12.1.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:e6bdb408f7c9dd2a5ff2b14a3b0bb6d4deb29fb9961e6eb3ae2031ae9a5cec13", size = 5266086, upload-time = "2026-01-02T09:12:28.782Z" }, + { url = "https://files.pythonhosted.org/packages/53/4b/649056e4d22e1caa90816bf99cef0884aed607ed38075bd75f091a607a38/pillow-12.1.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3413c2ae377550f5487991d444428f1a8ae92784aac79caa8b1e3b89b175f77e", size = 4657344, upload-time = "2026-01-02T09:12:31.117Z" }, + { url = "https://files.pythonhosted.org/packages/6c/6b/c5742cea0f1ade0cd61485dc3d81f05261fc2276f537fbdc00802de56779/pillow-12.1.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e5dcbe95016e88437ecf33544ba5db21ef1b8dd6e1b434a2cb2a3d605299e643", size = 6232114, upload-time = "2026-01-02T09:12:32.936Z" }, + { url = "https://files.pythonhosted.org/packages/bf/8f/9f521268ce22d63991601aafd3d48d5ff7280a246a1ef62d626d67b44064/pillow-12.1.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d0a7735df32ccbcc98b98a1ac785cc4b19b580be1bdf0aeb5c03223220ea09d5", size = 8042708, upload-time = "2026-01-02T09:12:34.78Z" }, + { url = "https://files.pythonhosted.org/packages/1a/eb/257f38542893f021502a1bbe0c2e883c90b5cff26cc33b1584a841a06d30/pillow-12.1.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0c27407a2d1b96774cbc4a7594129cc027339fd800cd081e44497722ea1179de", size = 6347762, upload-time = "2026-01-02T09:12:36.748Z" }, + { url = "https://files.pythonhosted.org/packages/c4/5a/8ba375025701c09b309e8d5163c5a4ce0102fa86bbf8800eb0d7ac87bc51/pillow-12.1.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15c794d74303828eaa957ff8070846d0efe8c630901a1c753fdc63850e19ecd9", size = 7039265, upload-time = "2026-01-02T09:12:39.082Z" }, + { url = "https://files.pythonhosted.org/packages/cf/dc/cf5e4cdb3db533f539e88a7bbf9f190c64ab8a08a9bc7a4ccf55067872e4/pillow-12.1.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c990547452ee2800d8506c4150280757f88532f3de2a58e3022e9b179107862a", size = 6462341, upload-time = "2026-01-02T09:12:40.946Z" }, + { url = "https://files.pythonhosted.org/packages/d0/47/0291a25ac9550677e22eda48510cfc4fa4b2ef0396448b7fbdc0a6946309/pillow-12.1.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:b63e13dd27da389ed9475b3d28510f0f954bca0041e8e551b2a4eb1eab56a39a", size = 7165395, upload-time = "2026-01-02T09:12:42.706Z" }, + { url = "https://files.pythonhosted.org/packages/4f/4c/e005a59393ec4d9416be06e6b45820403bb946a778e39ecec62f5b2b991e/pillow-12.1.0-cp314-cp314-win32.whl", hash = "sha256:1a949604f73eb07a8adab38c4fe50791f9919344398bdc8ac6b307f755fc7030", size = 6431413, upload-time = "2026-01-02T09:12:44.944Z" }, + { url = "https://files.pythonhosted.org/packages/1c/af/f23697f587ac5f9095d67e31b81c95c0249cd461a9798a061ed6709b09b5/pillow-12.1.0-cp314-cp314-win_amd64.whl", hash = "sha256:4f9f6a650743f0ddee5593ac9e954ba1bdbc5e150bc066586d4f26127853ab94", size = 7176779, upload-time = "2026-01-02T09:12:46.727Z" }, + { url = "https://files.pythonhosted.org/packages/b3/36/6a51abf8599232f3e9afbd16d52829376a68909fe14efe29084445db4b73/pillow-12.1.0-cp314-cp314-win_arm64.whl", hash = "sha256:808b99604f7873c800c4840f55ff389936ef1948e4e87645eaf3fccbc8477ac4", size = 2543105, upload-time = "2026-01-02T09:12:49.243Z" }, + { url = "https://files.pythonhosted.org/packages/82/54/2e1dd20c8749ff225080d6ba465a0cab4387f5db0d1c5fb1439e2d99923f/pillow-12.1.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:bc11908616c8a283cf7d664f77411a5ed2a02009b0097ff8abbba5e79128ccf2", size = 5268571, upload-time = "2026-01-02T09:12:51.11Z" }, + { url = "https://files.pythonhosted.org/packages/57/61/571163a5ef86ec0cf30d265ac2a70ae6fc9e28413d1dc94fa37fae6bda89/pillow-12.1.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:896866d2d436563fa2a43a9d72f417874f16b5545955c54a64941e87c1376c61", size = 4660426, upload-time = "2026-01-02T09:12:52.865Z" }, + { url = "https://files.pythonhosted.org/packages/5e/e1/53ee5163f794aef1bf84243f755ee6897a92c708505350dd1923f4afec48/pillow-12.1.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8e178e3e99d3c0ea8fc64b88447f7cac8ccf058af422a6cedc690d0eadd98c51", size = 6269908, upload-time = "2026-01-02T09:12:54.884Z" }, + { url = "https://files.pythonhosted.org/packages/bc/0b/b4b4106ff0ee1afa1dc599fde6ab230417f800279745124f6c50bcffed8e/pillow-12.1.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:079af2fb0c599c2ec144ba2c02766d1b55498e373b3ac64687e43849fbbef5bc", size = 8074733, upload-time = "2026-01-02T09:12:56.802Z" }, + { url = "https://files.pythonhosted.org/packages/19/9f/80b411cbac4a732439e629a26ad3ef11907a8c7fc5377b7602f04f6fe4e7/pillow-12.1.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bdec5e43377761c5dbca620efb69a77f6855c5a379e32ac5b158f54c84212b14", size = 6381431, upload-time = "2026-01-02T09:12:58.823Z" }, + { url = "https://files.pythonhosted.org/packages/8f/b7/d65c45db463b66ecb6abc17c6ba6917a911202a07662247e1355ce1789e7/pillow-12.1.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:565c986f4b45c020f5421a4cea13ef294dde9509a8577f29b2fc5edc7587fff8", size = 7068529, upload-time = "2026-01-02T09:13:00.885Z" }, + { url = "https://files.pythonhosted.org/packages/50/96/dfd4cd726b4a45ae6e3c669fc9e49deb2241312605d33aba50499e9d9bd1/pillow-12.1.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:43aca0a55ce1eefc0aefa6253661cb54571857b1a7b2964bd8a1e3ef4b729924", size = 6492981, upload-time = "2026-01-02T09:13:03.314Z" }, + { url = "https://files.pythonhosted.org/packages/4d/1c/b5dc52cf713ae46033359c5ca920444f18a6359ce1020dd3e9c553ea5bc6/pillow-12.1.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:0deedf2ea233722476b3a81e8cdfbad786f7adbed5d848469fa59fe52396e4ef", size = 7191878, upload-time = "2026-01-02T09:13:05.276Z" }, + { url = "https://files.pythonhosted.org/packages/53/26/c4188248bd5edaf543864fe4834aebe9c9cb4968b6f573ce014cc42d0720/pillow-12.1.0-cp314-cp314t-win32.whl", hash = "sha256:b17fbdbe01c196e7e159aacb889e091f28e61020a8abeac07b68079b6e626988", size = 6438703, upload-time = "2026-01-02T09:13:07.491Z" }, + { url = "https://files.pythonhosted.org/packages/b8/0e/69ed296de8ea05cb03ee139cee600f424ca166e632567b2d66727f08c7ed/pillow-12.1.0-cp314-cp314t-win_amd64.whl", hash = "sha256:27b9baecb428899db6c0de572d6d305cfaf38ca1596b5c0542a5182e3e74e8c6", size = 7182927, upload-time = "2026-01-02T09:13:09.841Z" }, + { url = "https://files.pythonhosted.org/packages/fc/f5/68334c015eed9b5cff77814258717dec591ded209ab5b6fb70e2ae873d1d/pillow-12.1.0-cp314-cp314t-win_arm64.whl", hash = "sha256:f61333d817698bdcdd0f9d7793e365ac3d2a21c1f1eb02b32ad6aefb8d8ea831", size = 2545104, upload-time = "2026-01-02T09:13:12.068Z" }, + { url = "https://files.pythonhosted.org/packages/8b/bc/224b1d98cffd7164b14707c91aac83c07b047fbd8f58eba4066a3e53746a/pillow-12.1.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ca94b6aac0d7af2a10ba08c0f888b3d5114439b6b3ef39968378723622fed377", size = 5228605, upload-time = "2026-01-02T09:13:14.084Z" }, + { url = "https://files.pythonhosted.org/packages/0c/ca/49ca7769c4550107de049ed85208240ba0f330b3f2e316f24534795702ce/pillow-12.1.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:351889afef0f485b84078ea40fe33727a0492b9af3904661b0abbafee0355b72", size = 4622245, upload-time = "2026-01-02T09:13:15.964Z" }, + { url = "https://files.pythonhosted.org/packages/73/48/fac807ce82e5955bcc2718642b94b1bd22a82a6d452aea31cbb678cddf12/pillow-12.1.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:bb0984b30e973f7e2884362b7d23d0a348c7143ee559f38ef3eaab640144204c", size = 5247593, upload-time = "2026-01-02T09:13:17.913Z" }, + { url = "https://files.pythonhosted.org/packages/d2/95/3e0742fe358c4664aed4fd05d5f5373dcdad0b27af52aa0972568541e3f4/pillow-12.1.0-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:84cabc7095dd535ca934d57e9ce2a72ffd216e435a84acb06b2277b1de2689bd", size = 6989008, upload-time = "2026-01-02T09:13:20.083Z" }, + { url = "https://files.pythonhosted.org/packages/5a/74/fe2ac378e4e202e56d50540d92e1ef4ff34ed687f3c60f6a121bcf99437e/pillow-12.1.0-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:53d8b764726d3af1a138dd353116f774e3862ec7e3794e0c8781e30db0f35dfc", size = 5313824, upload-time = "2026-01-02T09:13:22.405Z" }, + { url = "https://files.pythonhosted.org/packages/f3/77/2a60dee1adee4e2655ac328dd05c02a955c1cd683b9f1b82ec3feb44727c/pillow-12.1.0-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5da841d81b1a05ef940a8567da92decaa15bc4d7dedb540a8c219ad83d91808a", size = 5963278, upload-time = "2026-01-02T09:13:24.706Z" }, + { url = "https://files.pythonhosted.org/packages/2d/71/64e9b1c7f04ae0027f788a248e6297d7fcc29571371fe7d45495a78172c0/pillow-12.1.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:75af0b4c229ac519b155028fa1be632d812a519abba9b46b20e50c6caa184f19", size = 7029809, upload-time = "2026-01-02T09:13:26.541Z" }, ] [[package]] @@ -925,7 +939,7 @@ wheels = [ [[package]] name = "pytest" -version = "9.0.1" +version = "9.0.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "colorama", marker = "sys_platform == 'win32'" }, @@ -934,9 +948,9 @@ dependencies = [ { name = "pluggy" }, { name = "pygments" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/07/56/f013048ac4bc4c1d9be45afd4ab209ea62822fb1598f40687e6bf45dcea4/pytest-9.0.1.tar.gz", hash = "sha256:3e9c069ea73583e255c3b21cf46b8d3c56f6e3a1a8f6da94ccb0fcf57b9d73c8", size = 1564125, upload-time = "2025-11-12T13:05:09.333Z" } +sdist = { url = "https://files.pythonhosted.org/packages/d1/db/7ef3487e0fb0049ddb5ce41d3a49c235bf9ad299b6a25d5780a89f19230f/pytest-9.0.2.tar.gz", hash = "sha256:75186651a92bd89611d1d9fc20f0b4345fd827c41ccd5c299a868a05d70edf11", size = 1568901, upload-time = "2025-12-06T21:30:51.014Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/0b/8b/6300fb80f858cda1c51ffa17075df5d846757081d11ab4aa35cef9e6258b/pytest-9.0.1-py3-none-any.whl", hash = "sha256:67be0030d194df2dfa7b556f2e56fb3c3315bd5c8822c6951162b92b32ce7dad", size = 373668, upload-time = "2025-11-12T13:05:07.379Z" }, + { url = "https://files.pythonhosted.org/packages/3b/ab/b3226f0bd7cdcf710fbede2b3548584366da3b19b5021e74f5bde2a8fa3f/pytest-9.0.2-py3-none-any.whl", hash = "sha256:711ffd45bf766d5264d487b917733b453d917afd2b0ad65223959f59089f875b", size = 374801, upload-time = "2025-12-06T21:30:49.154Z" }, ] [[package]] @@ -1128,28 +1142,28 @@ wheels = [ [[package]] name = "ruff" -version = "0.14.7" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/b7/5b/dd7406afa6c95e3d8fa9d652b6d6dd17dd4a6bf63cb477014e8ccd3dcd46/ruff-0.14.7.tar.gz", hash = "sha256:3417deb75d23bd14a722b57b0a1435561db65f0ad97435b4cf9f85ffcef34ae5", size = 5727324, upload-time = "2025-11-28T20:55:10.525Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/8c/b1/7ea5647aaf90106f6d102230e5df874613da43d1089864da1553b899ba5e/ruff-0.14.7-py3-none-linux_armv6l.whl", hash = "sha256:b9d5cb5a176c7236892ad7224bc1e63902e4842c460a0b5210701b13e3de4fca", size = 13414475, upload-time = "2025-11-28T20:54:54.569Z" }, - { url = "https://files.pythonhosted.org/packages/af/19/fddb4cd532299db9cdaf0efdc20f5c573ce9952a11cb532d3b859d6d9871/ruff-0.14.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:3f64fe375aefaf36ca7d7250292141e39b4cea8250427482ae779a2aa5d90015", size = 13634613, upload-time = "2025-11-28T20:55:17.54Z" }, - { url = "https://files.pythonhosted.org/packages/40/2b/469a66e821d4f3de0440676ed3e04b8e2a1dc7575cf6fa3ba6d55e3c8557/ruff-0.14.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:93e83bd3a9e1a3bda64cb771c0d47cda0e0d148165013ae2d3554d718632d554", size = 12765458, upload-time = "2025-11-28T20:55:26.128Z" }, - { url = "https://files.pythonhosted.org/packages/f1/05/0b001f734fe550bcfde4ce845948ac620ff908ab7241a39a1b39bb3c5f49/ruff-0.14.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3838948e3facc59a6070795de2ae16e5786861850f78d5914a03f12659e88f94", size = 13236412, upload-time = "2025-11-28T20:55:28.602Z" }, - { url = "https://files.pythonhosted.org/packages/11/36/8ed15d243f011b4e5da75cd56d6131c6766f55334d14ba31cce5461f28aa/ruff-0.14.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:24c8487194d38b6d71cd0fd17a5b6715cda29f59baca1defe1e3a03240f851d1", size = 13182949, upload-time = "2025-11-28T20:55:33.265Z" }, - { url = "https://files.pythonhosted.org/packages/3b/cf/fcb0b5a195455729834f2a6eadfe2e4519d8ca08c74f6d2b564a4f18f553/ruff-0.14.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:79c73db6833f058a4be8ffe4a0913b6d4ad41f6324745179bd2aa09275b01d0b", size = 13816470, upload-time = "2025-11-28T20:55:08.203Z" }, - { url = "https://files.pythonhosted.org/packages/7f/5d/34a4748577ff7a5ed2f2471456740f02e86d1568a18c9faccfc73bd9ca3f/ruff-0.14.7-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:12eb7014fccff10fc62d15c79d8a6be4d0c2d60fe3f8e4d169a0d2def75f5dad", size = 15289621, upload-time = "2025-11-28T20:55:30.837Z" }, - { url = "https://files.pythonhosted.org/packages/53/53/0a9385f047a858ba133d96f3f8e3c9c66a31cc7c4b445368ef88ebeac209/ruff-0.14.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6c623bbdc902de7ff715a93fa3bb377a4e42dd696937bf95669118773dbf0c50", size = 14975817, upload-time = "2025-11-28T20:55:24.107Z" }, - { url = "https://files.pythonhosted.org/packages/a8/d7/2f1c32af54c3b46e7fadbf8006d8b9bcfbea535c316b0bd8813d6fb25e5d/ruff-0.14.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f53accc02ed2d200fa621593cdb3c1ae06aa9b2c3cae70bc96f72f0000ae97a9", size = 14284549, upload-time = "2025-11-28T20:55:06.08Z" }, - { url = "https://files.pythonhosted.org/packages/92/05/434ddd86becd64629c25fb6b4ce7637dd52a45cc4a4415a3008fe61c27b9/ruff-0.14.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:281f0e61a23fcdcffca210591f0f53aafaa15f9025b5b3f9706879aaa8683bc4", size = 14071389, upload-time = "2025-11-28T20:55:35.617Z" }, - { url = "https://files.pythonhosted.org/packages/ff/50/fdf89d4d80f7f9d4f420d26089a79b3bb1538fe44586b148451bc2ba8d9c/ruff-0.14.7-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:dbbaa5e14148965b91cb090236931182ee522a5fac9bc5575bafc5c07b9f9682", size = 14202679, upload-time = "2025-11-28T20:55:01.472Z" }, - { url = "https://files.pythonhosted.org/packages/77/54/87b34988984555425ce967f08a36df0ebd339bb5d9d0e92a47e41151eafc/ruff-0.14.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:1464b6e54880c0fe2f2d6eaefb6db15373331414eddf89d6b903767ae2458143", size = 13147677, upload-time = "2025-11-28T20:55:19.933Z" }, - { url = "https://files.pythonhosted.org/packages/67/29/f55e4d44edfe053918a16a3299e758e1c18eef216b7a7092550d7a9ec51c/ruff-0.14.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:f217ed871e4621ea6128460df57b19ce0580606c23aeab50f5de425d05226784", size = 13151392, upload-time = "2025-11-28T20:55:21.967Z" }, - { url = "https://files.pythonhosted.org/packages/36/69/47aae6dbd4f1d9b4f7085f4d9dcc84e04561ee7ad067bf52e0f9b02e3209/ruff-0.14.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:6be02e849440ed3602d2eb478ff7ff07d53e3758f7948a2a598829660988619e", size = 13412230, upload-time = "2025-11-28T20:55:12.749Z" }, - { url = "https://files.pythonhosted.org/packages/b7/4b/6e96cb6ba297f2ba502a231cd732ed7c3de98b1a896671b932a5eefa3804/ruff-0.14.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:19a0f116ee5e2b468dfe80c41c84e2bbd6b74f7b719bee86c2ecde0a34563bcc", size = 14195397, upload-time = "2025-11-28T20:54:56.896Z" }, - { url = "https://files.pythonhosted.org/packages/69/82/251d5f1aa4dcad30aed491b4657cecd9fb4274214da6960ffec144c260f7/ruff-0.14.7-py3-none-win32.whl", hash = "sha256:e33052c9199b347c8937937163b9b149ef6ab2e4bb37b042e593da2e6f6cccfa", size = 13126751, upload-time = "2025-11-28T20:55:03.47Z" }, - { url = "https://files.pythonhosted.org/packages/a8/b5/d0b7d145963136b564806f6584647af45ab98946660d399ec4da79cae036/ruff-0.14.7-py3-none-win_amd64.whl", hash = "sha256:e17a20ad0d3fad47a326d773a042b924d3ac31c6ca6deb6c72e9e6b5f661a7c6", size = 14531726, upload-time = "2025-11-28T20:54:59.121Z" }, - { url = "https://files.pythonhosted.org/packages/1d/d2/1637f4360ada6a368d3265bf39f2cf737a0aaab15ab520fc005903e883f8/ruff-0.14.7-py3-none-win_arm64.whl", hash = "sha256:be4d653d3bea1b19742fcc6502354e32f65cd61ff2fbdb365803ef2c2aec6228", size = 13609215, upload-time = "2025-11-28T20:55:15.375Z" }, +version = "0.14.10" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/57/08/52232a877978dd8f9cf2aeddce3e611b40a63287dfca29b6b8da791f5e8d/ruff-0.14.10.tar.gz", hash = "sha256:9a2e830f075d1a42cd28420d7809ace390832a490ed0966fe373ba288e77aaf4", size = 5859763, upload-time = "2025-12-18T19:28:57.98Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/60/01/933704d69f3f05ee16ef11406b78881733c186fe14b6a46b05cfcaf6d3b2/ruff-0.14.10-py3-none-linux_armv6l.whl", hash = "sha256:7a3ce585f2ade3e1f29ec1b92df13e3da262178df8c8bdf876f48fa0e8316c49", size = 13527080, upload-time = "2025-12-18T19:29:25.642Z" }, + { url = "https://files.pythonhosted.org/packages/df/58/a0349197a7dfa603ffb7f5b0470391efa79ddc327c1e29c4851e85b09cc5/ruff-0.14.10-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:674f9be9372907f7257c51f1d4fc902cb7cf014b9980152b802794317941f08f", size = 13797320, upload-time = "2025-12-18T19:29:02.571Z" }, + { url = "https://files.pythonhosted.org/packages/7b/82/36be59f00a6082e38c23536df4e71cdbc6af8d7c707eade97fcad5c98235/ruff-0.14.10-py3-none-macosx_11_0_arm64.whl", hash = "sha256:d85713d522348837ef9df8efca33ccb8bd6fcfc86a2cde3ccb4bc9d28a18003d", size = 12918434, upload-time = "2025-12-18T19:28:51.202Z" }, + { url = "https://files.pythonhosted.org/packages/a6/00/45c62a7f7e34da92a25804f813ebe05c88aa9e0c25e5cb5a7d23dd7450e3/ruff-0.14.10-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6987ebe0501ae4f4308d7d24e2d0fe3d7a98430f5adfd0f1fead050a740a3a77", size = 13371961, upload-time = "2025-12-18T19:29:04.991Z" }, + { url = "https://files.pythonhosted.org/packages/40/31/a5906d60f0405f7e57045a70f2d57084a93ca7425f22e1d66904769d1628/ruff-0.14.10-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:16a01dfb7b9e4eee556fbfd5392806b1b8550c9b4a9f6acd3dbe6812b193c70a", size = 13275629, upload-time = "2025-12-18T19:29:21.381Z" }, + { url = "https://files.pythonhosted.org/packages/3e/60/61c0087df21894cf9d928dc04bcd4fb10e8b2e8dca7b1a276ba2155b2002/ruff-0.14.10-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7165d31a925b7a294465fa81be8c12a0e9b60fb02bf177e79067c867e71f8b1f", size = 14029234, upload-time = "2025-12-18T19:29:00.132Z" }, + { url = "https://files.pythonhosted.org/packages/44/84/77d911bee3b92348b6e5dab5a0c898d87084ea03ac5dc708f46d88407def/ruff-0.14.10-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:c561695675b972effb0c0a45db233f2c816ff3da8dcfbe7dfc7eed625f218935", size = 15449890, upload-time = "2025-12-18T19:28:53.573Z" }, + { url = "https://files.pythonhosted.org/packages/e9/36/480206eaefa24a7ec321582dda580443a8f0671fdbf6b1c80e9c3e93a16a/ruff-0.14.10-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4bb98fcbbc61725968893682fd4df8966a34611239c9fd07a1f6a07e7103d08e", size = 15123172, upload-time = "2025-12-18T19:29:23.453Z" }, + { url = "https://files.pythonhosted.org/packages/5c/38/68e414156015ba80cef5473d57919d27dfb62ec804b96180bafdeaf0e090/ruff-0.14.10-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f24b47993a9d8cb858429e97bdf8544c78029f09b520af615c1d261bf827001d", size = 14460260, upload-time = "2025-12-18T19:29:27.808Z" }, + { url = "https://files.pythonhosted.org/packages/b3/19/9e050c0dca8aba824d67cc0db69fb459c28d8cd3f6855b1405b3f29cc91d/ruff-0.14.10-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59aabd2e2c4fd614d2862e7939c34a532c04f1084476d6833dddef4afab87e9f", size = 14229978, upload-time = "2025-12-18T19:29:11.32Z" }, + { url = "https://files.pythonhosted.org/packages/51/eb/e8dd1dd6e05b9e695aa9dd420f4577debdd0f87a5ff2fedda33c09e9be8c/ruff-0.14.10-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:213db2b2e44be8625002dbea33bb9c60c66ea2c07c084a00d55732689d697a7f", size = 14338036, upload-time = "2025-12-18T19:29:09.184Z" }, + { url = "https://files.pythonhosted.org/packages/6a/12/f3e3a505db7c19303b70af370d137795fcfec136d670d5de5391e295c134/ruff-0.14.10-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b914c40ab64865a17a9a5b67911d14df72346a634527240039eb3bd650e5979d", size = 13264051, upload-time = "2025-12-18T19:29:13.431Z" }, + { url = "https://files.pythonhosted.org/packages/08/64/8c3a47eaccfef8ac20e0484e68e0772013eb85802f8a9f7603ca751eb166/ruff-0.14.10-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:1484983559f026788e3a5c07c81ef7d1e97c1c78ed03041a18f75df104c45405", size = 13283998, upload-time = "2025-12-18T19:29:06.994Z" }, + { url = "https://files.pythonhosted.org/packages/12/84/534a5506f4074e5cc0529e5cd96cfc01bb480e460c7edf5af70d2bcae55e/ruff-0.14.10-py3-none-musllinux_1_2_i686.whl", hash = "sha256:c70427132db492d25f982fffc8d6c7535cc2fd2c83fc8888f05caaa248521e60", size = 13601891, upload-time = "2025-12-18T19:28:55.811Z" }, + { url = "https://files.pythonhosted.org/packages/0d/1e/14c916087d8598917dbad9b2921d340f7884824ad6e9c55de948a93b106d/ruff-0.14.10-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5bcf45b681e9f1ee6445d317ce1fa9d6cba9a6049542d1c3d5b5958986be8830", size = 14336660, upload-time = "2025-12-18T19:29:16.531Z" }, + { url = "https://files.pythonhosted.org/packages/f2/1c/d7b67ab43f30013b47c12b42d1acd354c195351a3f7a1d67f59e54227ede/ruff-0.14.10-py3-none-win32.whl", hash = "sha256:104c49fc7ab73f3f3a758039adea978869a918f31b73280db175b43a2d9b51d6", size = 13196187, upload-time = "2025-12-18T19:29:19.006Z" }, + { url = "https://files.pythonhosted.org/packages/fb/9c/896c862e13886fae2af961bef3e6312db9ebc6adc2b156fe95e615dee8c1/ruff-0.14.10-py3-none-win_amd64.whl", hash = "sha256:466297bd73638c6bdf06485683e812db1c00c7ac96d4ddd0294a338c62fdc154", size = 14661283, upload-time = "2025-12-18T19:29:30.16Z" }, + { url = "https://files.pythonhosted.org/packages/74/31/b0e29d572670dca3674eeee78e418f20bdf97fa8aa9ea71380885e175ca0/ruff-0.14.10-py3-none-win_arm64.whl", hash = "sha256:e51d046cf6dda98a4633b8a8a771451107413b0f07183b2bef03f075599e44e6", size = 13729839, upload-time = "2025-12-18T19:28:48.636Z" }, ] [[package]] @@ -1174,6 +1188,62 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/5d/e6/ec8471c8072382cb91233ba7267fd931219753bb43814cbc71757bfd4dab/safetensors-0.7.0-cp38-abi3-win_amd64.whl", hash = "sha256:d1239932053f56f3456f32eb9625590cc7582e905021f94636202a864d470755", size = 341380, upload-time = "2025-11-19T15:18:44.427Z" }, ] +[[package]] +name = "sentencepiece" +version = "0.2.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/15/15/2e7a025fc62d764b151ae6d0f2a92f8081755ebe8d4a64099accc6f77ba6/sentencepiece-0.2.1.tar.gz", hash = "sha256:8138cec27c2f2282f4a34d9a016e3374cd40e5c6e9cb335063db66a0a3b71fad", size = 3228515, upload-time = "2025-08-12T07:00:51.718Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d8/15/46afbab00733d81788b64be430ca1b93011bb9388527958e26cc31832de5/sentencepiece-0.2.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6356d0986b8b8dc351b943150fcd81a1c6e6e4d439772e8584c64230e58ca987", size = 1942560, upload-time = "2025-08-12T06:59:25.82Z" }, + { url = "https://files.pythonhosted.org/packages/fa/79/7c01b8ef98a0567e9d84a4e7a910f8e7074fcbf398a5cd76f93f4b9316f9/sentencepiece-0.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8f8ba89a3acb3dc1ae90f65ec1894b0b9596fdb98ab003ff38e058f898b39bc7", size = 1325385, upload-time = "2025-08-12T06:59:27.722Z" }, + { url = "https://files.pythonhosted.org/packages/bb/88/2b41e07bd24f33dcf2f18ec3b74247aa4af3526bad8907b8727ea3caba03/sentencepiece-0.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:02593eca45440ef39247cee8c47322a34bdcc1d8ae83ad28ba5a899a2cf8d79a", size = 1253319, upload-time = "2025-08-12T06:59:29.306Z" }, + { url = "https://files.pythonhosted.org/packages/a0/54/38a1af0c6210a3c6f95aa46d23d6640636d020fba7135cd0d9a84ada05a7/sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0a0d15781a171d188b661ae4bde1d998c303f6bd8621498c50c671bd45a4798e", size = 1316162, upload-time = "2025-08-12T06:59:30.914Z" }, + { url = "https://files.pythonhosted.org/packages/ef/66/fb191403ade791ad2c3c1e72fe8413e63781b08cfa3aa4c9dfc536d6e795/sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4f5a3e0d9f445ed9d66c0fec47d4b23d12cfc858b407a03c194c1b26c2ac2a63", size = 1387785, upload-time = "2025-08-12T06:59:32.491Z" }, + { url = "https://files.pythonhosted.org/packages/a9/2d/3bd9b08e70067b2124518b308db6a84a4f8901cc8a4317e2e4288cdd9b4d/sentencepiece-0.2.1-cp311-cp311-win32.whl", hash = "sha256:6d297a1748d429ba8534eebe5535448d78b8acc32d00a29b49acf28102eeb094", size = 999555, upload-time = "2025-08-12T06:59:34.475Z" }, + { url = "https://files.pythonhosted.org/packages/32/b8/f709977f5fda195ae1ea24f24e7c581163b6f142b1005bc3d0bbfe4d7082/sentencepiece-0.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:82d9ead6591015f009cb1be1cb1c015d5e6f04046dbb8c9588b931e869a29728", size = 1054617, upload-time = "2025-08-12T06:59:36.461Z" }, + { url = "https://files.pythonhosted.org/packages/7a/40/a1fc23be23067da0f703709797b464e8a30a1c78cc8a687120cd58d4d509/sentencepiece-0.2.1-cp311-cp311-win_arm64.whl", hash = "sha256:39f8651bd10974eafb9834ce30d9bcf5b73e1fc798a7f7d2528f9820ca86e119", size = 1033877, upload-time = "2025-08-12T06:59:38.391Z" }, + { url = "https://files.pythonhosted.org/packages/4a/be/32ce495aa1d0e0c323dcb1ba87096037358edee539cac5baf8755a6bd396/sentencepiece-0.2.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:57cae326c8727de58c85977b175af132a7138d84c764635d7e71bbee7e774133", size = 1943152, upload-time = "2025-08-12T06:59:40.048Z" }, + { url = "https://files.pythonhosted.org/packages/88/7e/ff23008899a58678e98c6ff592bf4d368eee5a71af96d0df6b38a039dd4f/sentencepiece-0.2.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:56dd39a3c4d6493db3cdca7e8cc68c6b633f0d4195495cbadfcf5af8a22d05a6", size = 1325651, upload-time = "2025-08-12T06:59:41.536Z" }, + { url = "https://files.pythonhosted.org/packages/19/84/42eb3ce4796777a1b5d3699dfd4dca85113e68b637f194a6c8d786f16a04/sentencepiece-0.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d9381351182ff9888cc80e41c632e7e274b106f450de33d67a9e8f6043da6f76", size = 1253645, upload-time = "2025-08-12T06:59:42.903Z" }, + { url = "https://files.pythonhosted.org/packages/89/fa/d3d5ebcba3cb9e6d3775a096251860c41a6bc53a1b9461151df83fe93255/sentencepiece-0.2.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:99f955df238021bf11f0fc37cdb54fd5e5b5f7fd30ecc3d93fb48b6815437167", size = 1316273, upload-time = "2025-08-12T06:59:44.476Z" }, + { url = "https://files.pythonhosted.org/packages/04/88/14f2f4a2b922d8b39be45bf63d79e6cd3a9b2f248b2fcb98a69b12af12f5/sentencepiece-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0cdfecef430d985f1c2bcbfff3defd1d95dae876fbd0173376012d2d7d24044b", size = 1387881, upload-time = "2025-08-12T06:59:46.09Z" }, + { url = "https://files.pythonhosted.org/packages/fd/b8/903e5ccb77b4ef140605d5d71b4f9e0ad95d456d6184688073ed11712809/sentencepiece-0.2.1-cp312-cp312-win32.whl", hash = "sha256:a483fd29a34c3e34c39ac5556b0a90942bec253d260235729e50976f5dba1068", size = 999540, upload-time = "2025-08-12T06:59:48.023Z" }, + { url = "https://files.pythonhosted.org/packages/2d/81/92df5673c067148c2545b1bfe49adfd775bcc3a169a047f5a0e6575ddaca/sentencepiece-0.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:4cdc7c36234fda305e85c32949c5211faaf8dd886096c7cea289ddc12a2d02de", size = 1054671, upload-time = "2025-08-12T06:59:49.895Z" }, + { url = "https://files.pythonhosted.org/packages/fe/02/c5e3bc518655d714622bec87d83db9cdba1cd0619a4a04e2109751c4f47f/sentencepiece-0.2.1-cp312-cp312-win_arm64.whl", hash = "sha256:daeb5e9e9fcad012324807856113708614d534f596d5008638eb9b40112cd9e4", size = 1033923, upload-time = "2025-08-12T06:59:51.952Z" }, + { url = "https://files.pythonhosted.org/packages/ba/4a/85fbe1706d4d04a7e826b53f327c4b80f849cf1c7b7c5e31a20a97d8f28b/sentencepiece-0.2.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:dcd8161eee7b41aae57ded06272905dbd680a0a04b91edd0f64790c796b2f706", size = 1943150, upload-time = "2025-08-12T06:59:53.588Z" }, + { url = "https://files.pythonhosted.org/packages/c2/83/4cfb393e287509fc2155480b9d184706ef8d9fa8cbf5505d02a5792bf220/sentencepiece-0.2.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:c6c8f42949f419ff8c7e9960dbadcfbc982d7b5efc2f6748210d3dd53a7de062", size = 1325651, upload-time = "2025-08-12T06:59:55.073Z" }, + { url = "https://files.pythonhosted.org/packages/8d/de/5a007fb53b1ab0aafc69d11a5a3dd72a289d5a3e78dcf2c3a3d9b14ffe93/sentencepiece-0.2.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:097f3394e99456e9e4efba1737c3749d7e23563dd1588ce71a3d007f25475fff", size = 1253641, upload-time = "2025-08-12T06:59:56.562Z" }, + { url = "https://files.pythonhosted.org/packages/2c/d2/f552be5928105588f4f4d66ee37dd4c61460d8097e62d0e2e0eec41bc61d/sentencepiece-0.2.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d7b670879c370d350557edabadbad1f6561a9e6968126e6debca4029e5547820", size = 1316271, upload-time = "2025-08-12T06:59:58.109Z" }, + { url = "https://files.pythonhosted.org/packages/96/df/0cfe748ace5485be740fed9476dee7877f109da32ed0d280312c94ec259f/sentencepiece-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c7f0fd2f2693309e6628aeeb2e2faf6edd221134dfccac3308ca0de01f8dab47", size = 1387882, upload-time = "2025-08-12T07:00:00.701Z" }, + { url = "https://files.pythonhosted.org/packages/ac/dd/f7774d42a881ced8e1739f393ab1e82ece39fc9abd4779e28050c2e975b5/sentencepiece-0.2.1-cp313-cp313-win32.whl", hash = "sha256:92b3816aa2339355fda2c8c4e021a5de92180b00aaccaf5e2808972e77a4b22f", size = 999541, upload-time = "2025-08-12T07:00:02.709Z" }, + { url = "https://files.pythonhosted.org/packages/dd/e9/932b9eae6fd7019548321eee1ab8d5e3b3d1294df9d9a0c9ac517c7b636d/sentencepiece-0.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:10ed3dab2044c47f7a2e7b4969b0c430420cdd45735d78c8f853191fa0e3148b", size = 1054669, upload-time = "2025-08-12T07:00:04.915Z" }, + { url = "https://files.pythonhosted.org/packages/c9/3a/76488a00ea7d6931689cda28726a1447d66bf1a4837943489314593d5596/sentencepiece-0.2.1-cp313-cp313-win_arm64.whl", hash = "sha256:ac650534e2251083c5f75dde4ff28896ce7c8904133dc8fef42780f4d5588fcd", size = 1033922, upload-time = "2025-08-12T07:00:06.496Z" }, + { url = "https://files.pythonhosted.org/packages/4a/b6/08fe2ce819e02ccb0296f4843e3f195764ce9829cbda61b7513f29b95718/sentencepiece-0.2.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:8dd4b477a7b069648d19363aad0cab9bad2f4e83b2d179be668efa672500dc94", size = 1946052, upload-time = "2025-08-12T07:00:08.136Z" }, + { url = "https://files.pythonhosted.org/packages/ab/d9/1ea0e740591ff4c6fc2b6eb1d7510d02f3fb885093f19b2f3abd1363b402/sentencepiece-0.2.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0c0f672da370cc490e4c59d89e12289778310a0e71d176c541e4834759e1ae07", size = 1327408, upload-time = "2025-08-12T07:00:09.572Z" }, + { url = "https://files.pythonhosted.org/packages/99/7e/1fb26e8a21613f6200e1ab88824d5d203714162cf2883248b517deb500b7/sentencepiece-0.2.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:ad8493bea8432dae8d6830365352350f3b4144415a1d09c4c8cb8d30cf3b6c3c", size = 1254857, upload-time = "2025-08-12T07:00:11.021Z" }, + { url = "https://files.pythonhosted.org/packages/bc/85/c72fd1f3c7a6010544d6ae07f8ddb38b5e2a7e33bd4318f87266c0bbafbf/sentencepiece-0.2.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b81a24733726e3678d2db63619acc5a8dccd074f7aa7a54ecd5ca33ca6d2d596", size = 1315722, upload-time = "2025-08-12T07:00:12.989Z" }, + { url = "https://files.pythonhosted.org/packages/4a/e8/661e5bd82a8aa641fd6c1020bd0e890ef73230a2b7215ddf9c8cd8e941c2/sentencepiece-0.2.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0a81799d0a68d618e89063fb423c3001a034c893069135ffe51fee439ae474d6", size = 1387452, upload-time = "2025-08-12T07:00:15.088Z" }, + { url = "https://files.pythonhosted.org/packages/99/5e/ae66c361023a470afcbc1fbb8da722c72ea678a2fcd9a18f1a12598c7501/sentencepiece-0.2.1-cp313-cp313t-win32.whl", hash = "sha256:89a3ea015517c42c0341d0d962f3e6aaf2cf10d71b1932d475c44ba48d00aa2b", size = 1002501, upload-time = "2025-08-12T07:00:16.966Z" }, + { url = "https://files.pythonhosted.org/packages/c1/03/d332828c4ff764e16c1b56c2c8f9a33488bbe796b53fb6b9c4205ddbf167/sentencepiece-0.2.1-cp313-cp313t-win_amd64.whl", hash = "sha256:33f068c9382dc2e7c228eedfd8163b52baa86bb92f50d0488bf2b7da7032e484", size = 1057555, upload-time = "2025-08-12T07:00:18.573Z" }, + { url = "https://files.pythonhosted.org/packages/88/14/5aee0bf0864df9bd82bd59e7711362908e4935e3f9cdc1f57246b5d5c9b9/sentencepiece-0.2.1-cp313-cp313t-win_arm64.whl", hash = "sha256:b3616ad246f360e52c85781e47682d31abfb6554c779e42b65333d4b5f44ecc0", size = 1036042, upload-time = "2025-08-12T07:00:20.209Z" }, + { url = "https://files.pythonhosted.org/packages/24/9c/89eb8b2052f720a612478baf11c8227dcf1dc28cd4ea4c0c19506b5af2a2/sentencepiece-0.2.1-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:5d0350b686c320068702116276cfb26c066dc7e65cfef173980b11bb4d606719", size = 1943147, upload-time = "2025-08-12T07:00:21.809Z" }, + { url = "https://files.pythonhosted.org/packages/82/0b/a1432bc87f97c2ace36386ca23e8bd3b91fb40581b5e6148d24b24186419/sentencepiece-0.2.1-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:c7f54a31cde6fa5cb030370566f68152a742f433f8d2be458463d06c208aef33", size = 1325624, upload-time = "2025-08-12T07:00:23.289Z" }, + { url = "https://files.pythonhosted.org/packages/ea/99/bbe054ebb5a5039457c590e0a4156ed073fb0fe9ce4f7523404dd5b37463/sentencepiece-0.2.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c83b85ab2d6576607f31df77ff86f28182be4a8de6d175d2c33ca609925f5da1", size = 1253670, upload-time = "2025-08-12T07:00:24.69Z" }, + { url = "https://files.pythonhosted.org/packages/19/ad/d5c7075f701bd97971d7c2ac2904f227566f51ef0838dfbdfdccb58cd212/sentencepiece-0.2.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1855f57db07b51fb51ed6c9c452f570624d2b169b36f0f79ef71a6e6c618cd8b", size = 1316247, upload-time = "2025-08-12T07:00:26.435Z" }, + { url = "https://files.pythonhosted.org/packages/fb/03/35fbe5f3d9a7435eebd0b473e09584bd3cc354ce118b960445b060d33781/sentencepiece-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:01e6912125cb45d3792f530a4d38f8e21bf884d6b4d4ade1b2de5cf7a8d2a52b", size = 1387894, upload-time = "2025-08-12T07:00:28.339Z" }, + { url = "https://files.pythonhosted.org/packages/dc/aa/956ef729aafb6c8f9c443104c9636489093bb5c61d6b90fc27aa1a865574/sentencepiece-0.2.1-cp314-cp314-win32.whl", hash = "sha256:c415c9de1447e0a74ae3fdb2e52f967cb544113a3a5ce3a194df185cbc1f962f", size = 1096698, upload-time = "2025-08-12T07:00:29.764Z" }, + { url = "https://files.pythonhosted.org/packages/b8/cb/fe400d8836952cc535c81a0ce47dc6875160e5fedb71d2d9ff0e9894c2a6/sentencepiece-0.2.1-cp314-cp314-win_amd64.whl", hash = "sha256:881b2e44b14fc19feade3cbed314be37de639fc415375cefaa5bc81a4be137fd", size = 1155115, upload-time = "2025-08-12T07:00:32.865Z" }, + { url = "https://files.pythonhosted.org/packages/32/89/047921cf70f36c7b6b6390876b2399b3633ab73b8d0cb857e5a964238941/sentencepiece-0.2.1-cp314-cp314-win_arm64.whl", hash = "sha256:2005242a16d2dc3ac5fe18aa7667549134d37854823df4c4db244752453b78a8", size = 1133890, upload-time = "2025-08-12T07:00:34.763Z" }, + { url = "https://files.pythonhosted.org/packages/a1/11/5b414b9fae6255b5fb1e22e2ed3dc3a72d3a694e5703910e640ac78346bb/sentencepiece-0.2.1-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:a19adcec27c524cb7069a1c741060add95f942d1cbf7ad0d104dffa0a7d28a2b", size = 1946081, upload-time = "2025-08-12T07:00:36.97Z" }, + { url = "https://files.pythonhosted.org/packages/77/eb/7a5682bb25824db8545f8e5662e7f3e32d72a508fdce086029d89695106b/sentencepiece-0.2.1-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:e37e4b4c4a11662b5db521def4e44d4d30ae69a1743241412a93ae40fdcab4bb", size = 1327406, upload-time = "2025-08-12T07:00:38.669Z" }, + { url = "https://files.pythonhosted.org/packages/03/b0/811dae8fb9f2784e138785d481469788f2e0d0c109c5737372454415f55f/sentencepiece-0.2.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:477c81505db072b3ab627e7eab972ea1025331bd3a92bacbf798df2b75ea86ec", size = 1254846, upload-time = "2025-08-12T07:00:40.611Z" }, + { url = "https://files.pythonhosted.org/packages/ef/23/195b2e7ec85ebb6a547969f60b723c7aca5a75800ece6cc3f41da872d14e/sentencepiece-0.2.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:010f025a544ef770bb395091d57cb94deb9652d8972e0d09f71d85d5a0816c8c", size = 1315721, upload-time = "2025-08-12T07:00:42.914Z" }, + { url = "https://files.pythonhosted.org/packages/7e/aa/553dbe4178b5f23eb28e59393dddd64186178b56b81d9b8d5c3ff1c28395/sentencepiece-0.2.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:733e59ff1794d26db706cd41fc2d7ca5f6c64a820709cb801dc0ea31780d64ab", size = 1387458, upload-time = "2025-08-12T07:00:44.56Z" }, + { url = "https://files.pythonhosted.org/packages/66/7c/08ff0012507297a4dd74a5420fdc0eb9e3e80f4e88cab1538d7f28db303d/sentencepiece-0.2.1-cp314-cp314t-win32.whl", hash = "sha256:d3233770f78e637dc8b1fda2cd7c3b99ec77e7505041934188a4e7fe751de3b0", size = 1099765, upload-time = "2025-08-12T07:00:46.058Z" }, + { url = "https://files.pythonhosted.org/packages/91/d5/2a69e1ce15881beb9ddfc7e3f998322f5cedcd5e4d244cb74dade9441663/sentencepiece-0.2.1-cp314-cp314t-win_amd64.whl", hash = "sha256:5e4366c97b68218fd30ea72d70c525e6e78a6c0a88650f57ac4c43c63b234a9d", size = 1157807, upload-time = "2025-08-12T07:00:47.673Z" }, + { url = "https://files.pythonhosted.org/packages/f3/16/54f611fcfc2d1c46cbe3ec4169780b2cfa7cf63708ef2b71611136db7513/sentencepiece-0.2.1-cp314-cp314t-win_arm64.whl", hash = "sha256:105e36e75cbac1292642045458e8da677b2342dcd33df503e640f0b457cb6751", size = 1136264, upload-time = "2025-08-12T07:00:49.485Z" }, +] + [[package]] name = "setuptools" version = "80.9.0" @@ -1206,27 +1276,28 @@ wheels = [ [[package]] name = "tokenizers" -version = "0.22.1" +version = "0.22.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "huggingface-hub" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/1c/46/fb6854cec3278fbfa4a75b50232c77622bc517ac886156e6afbfa4d8fc6e/tokenizers-0.22.1.tar.gz", hash = "sha256:61de6522785310a309b3407bac22d99c4db5dba349935e99e4d15ea2226af2d9", size = 363123, upload-time = "2025-09-19T09:49:23.424Z" } +sdist = { url = "https://files.pythonhosted.org/packages/73/6f/f80cfef4a312e1fb34baf7d85c72d4411afde10978d4657f8cdd811d3ccc/tokenizers-0.22.2.tar.gz", hash = "sha256:473b83b915e547aa366d1eee11806deaf419e17be16310ac0a14077f1e28f917", size = 372115, upload-time = "2026-01-05T10:45:15.988Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/bf/33/f4b2d94ada7ab297328fc671fed209368ddb82f965ec2224eb1892674c3a/tokenizers-0.22.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:59fdb013df17455e5f950b4b834a7b3ee2e0271e6378ccb33aa74d178b513c73", size = 3069318, upload-time = "2025-09-19T09:49:11.848Z" }, - { url = "https://files.pythonhosted.org/packages/1c/58/2aa8c874d02b974990e89ff95826a4852a8b2a273c7d1b4411cdd45a4565/tokenizers-0.22.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:8d4e484f7b0827021ac5f9f71d4794aaef62b979ab7608593da22b1d2e3c4edc", size = 2926478, upload-time = "2025-09-19T09:49:09.759Z" }, - { url = "https://files.pythonhosted.org/packages/1e/3b/55e64befa1e7bfea963cf4b787b2cea1011362c4193f5477047532ce127e/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19d2962dd28bc67c1f205ab180578a78eef89ac60ca7ef7cbe9635a46a56422a", size = 3256994, upload-time = "2025-09-19T09:48:56.701Z" }, - { url = "https://files.pythonhosted.org/packages/71/0b/fbfecf42f67d9b7b80fde4aabb2b3110a97fac6585c9470b5bff103a80cb/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38201f15cdb1f8a6843e6563e6e79f4abd053394992b9bbdf5213ea3469b4ae7", size = 3153141, upload-time = "2025-09-19T09:48:59.749Z" }, - { url = "https://files.pythonhosted.org/packages/17/a9/b38f4e74e0817af8f8ef925507c63c6ae8171e3c4cb2d5d4624bf58fca69/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1cbe5454c9a15df1b3443c726063d930c16f047a3cc724b9e6e1a91140e5a21", size = 3508049, upload-time = "2025-09-19T09:49:05.868Z" }, - { url = "https://files.pythonhosted.org/packages/d2/48/dd2b3dac46bb9134a88e35d72e1aa4869579eacc1a27238f1577270773ff/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7d094ae6312d69cc2a872b54b91b309f4f6fbce871ef28eb27b52a98e4d0214", size = 3710730, upload-time = "2025-09-19T09:49:01.832Z" }, - { url = "https://files.pythonhosted.org/packages/93/0e/ccabc8d16ae4ba84a55d41345207c1e2ea88784651a5a487547d80851398/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afd7594a56656ace95cdd6df4cca2e4059d294c5cfb1679c57824b605556cb2f", size = 3412560, upload-time = "2025-09-19T09:49:03.867Z" }, - { url = "https://files.pythonhosted.org/packages/d0/c6/dc3a0db5a6766416c32c034286d7c2d406da1f498e4de04ab1b8959edd00/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2ef6063d7a84994129732b47e7915e8710f27f99f3a3260b8a38fc7ccd083f4", size = 3250221, upload-time = "2025-09-19T09:49:07.664Z" }, - { url = "https://files.pythonhosted.org/packages/d7/a6/2c8486eef79671601ff57b093889a345dd3d576713ef047776015dc66de7/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ba0a64f450b9ef412c98f6bcd2a50c6df6e2443b560024a09fa6a03189726879", size = 9345569, upload-time = "2025-09-19T09:49:14.214Z" }, - { url = "https://files.pythonhosted.org/packages/6b/16/32ce667f14c35537f5f605fe9bea3e415ea1b0a646389d2295ec348d5657/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:331d6d149fa9c7d632cde4490fb8bbb12337fa3a0232e77892be656464f4b446", size = 9271599, upload-time = "2025-09-19T09:49:16.639Z" }, - { url = "https://files.pythonhosted.org/packages/51/7c/a5f7898a3f6baa3fc2685c705e04c98c1094c523051c805cdd9306b8f87e/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:607989f2ea68a46cb1dfbaf3e3aabdf3f21d8748312dbeb6263d1b3b66c5010a", size = 9533862, upload-time = "2025-09-19T09:49:19.146Z" }, - { url = "https://files.pythonhosted.org/packages/36/65/7e75caea90bc73c1dd8d40438adf1a7bc26af3b8d0a6705ea190462506e1/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a0f307d490295717726598ef6fa4f24af9d484809223bbc253b201c740a06390", size = 9681250, upload-time = "2025-09-19T09:49:21.501Z" }, - { url = "https://files.pythonhosted.org/packages/30/2c/959dddef581b46e6209da82df3b78471e96260e2bc463f89d23b1bf0e52a/tokenizers-0.22.1-cp39-abi3-win32.whl", hash = "sha256:b5120eed1442765cd90b903bb6cfef781fd8fe64e34ccaecbae4c619b7b12a82", size = 2472003, upload-time = "2025-09-19T09:49:27.089Z" }, - { url = "https://files.pythonhosted.org/packages/b3/46/e33a8c93907b631a99377ef4c5f817ab453d0b34f93529421f42ff559671/tokenizers-0.22.1-cp39-abi3-win_amd64.whl", hash = "sha256:65fd6e3fb11ca1e78a6a93602490f134d1fdeb13bcef99389d5102ea318ed138", size = 2674684, upload-time = "2025-09-19T09:49:24.953Z" }, + { url = "https://files.pythonhosted.org/packages/92/97/5dbfabf04c7e348e655e907ed27913e03db0923abb5dfdd120d7b25630e1/tokenizers-0.22.2-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:544dd704ae7238755d790de45ba8da072e9af3eea688f698b137915ae959281c", size = 3100275, upload-time = "2026-01-05T10:41:02.158Z" }, + { url = "https://files.pythonhosted.org/packages/2e/47/174dca0502ef88b28f1c9e06b73ce33500eedfac7a7692108aec220464e7/tokenizers-0.22.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1e418a55456beedca4621dbab65a318981467a2b188e982a23e117f115ce5001", size = 2981472, upload-time = "2026-01-05T10:41:00.276Z" }, + { url = "https://files.pythonhosted.org/packages/d6/84/7990e799f1309a8b87af6b948f31edaa12a3ed22d11b352eaf4f4b2e5753/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2249487018adec45d6e3554c71d46eb39fa8ea67156c640f7513eb26f318cec7", size = 3290736, upload-time = "2026-01-05T10:40:32.165Z" }, + { url = "https://files.pythonhosted.org/packages/78/59/09d0d9ba94dcd5f4f1368d4858d24546b4bdc0231c2354aa31d6199f0399/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:25b85325d0815e86e0bac263506dd114578953b7b53d7de09a6485e4a160a7dd", size = 3168835, upload-time = "2026-01-05T10:40:38.847Z" }, + { url = "https://files.pythonhosted.org/packages/47/50/b3ebb4243e7160bda8d34b731e54dd8ab8b133e50775872e7a434e524c28/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bfb88f22a209ff7b40a576d5324bf8286b519d7358663db21d6246fb17eea2d5", size = 3521673, upload-time = "2026-01-05T10:40:56.614Z" }, + { url = "https://files.pythonhosted.org/packages/e0/fa/89f4cb9e08df770b57adb96f8cbb7e22695a4cb6c2bd5f0c4f0ebcf33b66/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1c774b1276f71e1ef716e5486f21e76333464f47bece56bbd554485982a9e03e", size = 3724818, upload-time = "2026-01-05T10:40:44.507Z" }, + { url = "https://files.pythonhosted.org/packages/64/04/ca2363f0bfbe3b3d36e95bf67e56a4c88c8e3362b658e616d1ac185d47f2/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:df6c4265b289083bf710dff49bc51ef252f9d5be33a45ee2bed151114a56207b", size = 3379195, upload-time = "2026-01-05T10:40:51.139Z" }, + { url = "https://files.pythonhosted.org/packages/2e/76/932be4b50ef6ccedf9d3c6639b056a967a86258c6d9200643f01269211ca/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:369cc9fc8cc10cb24143873a0d95438bb8ee257bb80c71989e3ee290e8d72c67", size = 3274982, upload-time = "2026-01-05T10:40:58.331Z" }, + { url = "https://files.pythonhosted.org/packages/1d/28/5f9f5a4cc211b69e89420980e483831bcc29dade307955cc9dc858a40f01/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:29c30b83d8dcd061078b05ae0cb94d3c710555fbb44861139f9f83dcca3dc3e4", size = 9478245, upload-time = "2026-01-05T10:41:04.053Z" }, + { url = "https://files.pythonhosted.org/packages/6c/fb/66e2da4704d6aadebf8cb39f1d6d1957df667ab24cff2326b77cda0dcb85/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:37ae80a28c1d3265bb1f22464c856bd23c02a05bb211e56d0c5301a435be6c1a", size = 9560069, upload-time = "2026-01-05T10:45:10.673Z" }, + { url = "https://files.pythonhosted.org/packages/16/04/fed398b05caa87ce9b1a1bb5166645e38196081b225059a6edaff6440fac/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:791135ee325f2336f498590eb2f11dc5c295232f288e75c99a36c5dbce63088a", size = 9899263, upload-time = "2026-01-05T10:45:12.559Z" }, + { url = "https://files.pythonhosted.org/packages/05/a1/d62dfe7376beaaf1394917e0f8e93ee5f67fea8fcf4107501db35996586b/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:38337540fbbddff8e999d59970f3c6f35a82de10053206a7562f1ea02d046fa5", size = 10033429, upload-time = "2026-01-05T10:45:14.333Z" }, + { url = "https://files.pythonhosted.org/packages/fd/18/a545c4ea42af3df6effd7d13d250ba77a0a86fb20393143bbb9a92e434d4/tokenizers-0.22.2-cp39-abi3-win32.whl", hash = "sha256:a6bf3f88c554a2b653af81f3204491c818ae2ac6fbc09e76ef4773351292bc92", size = 2502363, upload-time = "2026-01-05T10:45:20.593Z" }, + { url = "https://files.pythonhosted.org/packages/65/71/0670843133a43d43070abeb1949abfdef12a86d490bea9cd9e18e37c5ff7/tokenizers-0.22.2-cp39-abi3-win_amd64.whl", hash = "sha256:c9ea31edff2968b44a88f97d784c2f16dc0729b8b143ed004699ebca91f05c48", size = 2747786, upload-time = "2026-01-05T10:45:18.411Z" }, + { url = "https://files.pythonhosted.org/packages/72/f4/0de46cfa12cdcbcd464cc59fde36912af405696f687e53a091fb432f694c/tokenizers-0.22.2-cp39-abi3-win_arm64.whl", hash = "sha256:9ce725d22864a1e965217204946f830c37876eee3b2ba6fc6255e8e903d5fcbc", size = 2612133, upload-time = "2026-01-05T10:45:17.232Z" }, ] [[package]] @@ -1336,7 +1407,7 @@ wheels = [ [[package]] name = "transformers" version = "5.0.0.dev0" -source = { git = "https://github.com/huggingface/transformers#a48d68c6b06172938948eef457ebb7bcd5dcb77c" } +source = { git = "https://github.com/huggingface/transformers#e8c51d1848187b9e58d00bf7d638811686ab2a4b" } dependencies = [ { name = "filelock" }, { name = "huggingface-hub" }, @@ -1366,15 +1437,15 @@ wheels = [ [[package]] name = "typer-slim" -version = "0.20.0" +version = "0.21.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/8e/45/81b94a52caed434b94da65729c03ad0fb7665fab0f7db9ee54c94e541403/typer_slim-0.20.0.tar.gz", hash = "sha256:9fc6607b3c6c20f5c33ea9590cbeb17848667c51feee27d9e314a579ab07d1a3", size = 106561, upload-time = "2025-10-20T17:03:46.642Z" } +sdist = { url = "https://files.pythonhosted.org/packages/f9/3b/2f60ce16f578b1db5b8816d37d6a4d9786b33b76407fc8c13b0b86312c31/typer_slim-0.21.0.tar.gz", hash = "sha256:f2dbd150cfa0fead2242e21fa9f654dfc64773763ddf07c6be9a49ad34f79557", size = 106841, upload-time = "2025-12-25T09:54:55.998Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/5e/dd/5cbf31f402f1cc0ab087c94d4669cfa55bd1e818688b910631e131d74e75/typer_slim-0.20.0-py3-none-any.whl", hash = "sha256:f42a9b7571a12b97dddf364745d29f12221865acef7a2680065f9bb29c7dc89d", size = 47087, upload-time = "2025-10-20T17:03:44.546Z" }, + { url = "https://files.pythonhosted.org/packages/b4/84/e97abf10e4a699194ff07fd586ec7f4cf867d9d04bead559a65f9e7aff84/typer_slim-0.21.0-py3-none-any.whl", hash = "sha256:92aee2188ac6fc2b2924bd75bb61a340b78bd8cd51fd9735533ce5a856812c8e", size = 47174, upload-time = "2025-12-25T09:54:54.609Z" }, ] [[package]] @@ -1400,11 +1471,20 @@ wheels = [ [[package]] name = "urllib3" -version = "2.5.0" +version = "2.6.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/1e/24/a2a2ed9addd907787d7aa0355ba36a6cadf1768b934c652ea78acbd59dcd/urllib3-2.6.2.tar.gz", hash = "sha256:016f9c98bb7e98085cb2b4b17b87d2c702975664e4f060c6532e64d1c1a5e797", size = 432930, upload-time = "2025-12-11T15:56:40.252Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/6d/b9/4095b668ea3678bf6a0af005527f39de12fb026516fb3df17495a733b7f8/urllib3-2.6.2-py3-none-any.whl", hash = "sha256:ec21cddfe7724fc7cb4ba4bea7aa8e2ef36f607a4bab81aa6ce42a13dc3f03dd", size = 131182, upload-time = "2025-12-11T15:56:38.584Z" }, +] + +[[package]] +name = "wcwidth" +version = "0.2.14" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185, upload-time = "2025-06-18T14:07:41.644Z" } +sdist = { url = "https://files.pythonhosted.org/packages/24/30/6b0809f4510673dc723187aeaf24c7f5459922d01e2f794277a3dfb90345/wcwidth-0.2.14.tar.gz", hash = "sha256:4d478375d31bc5395a3c55c40ccdf3354688364cd61c4f6adacaa9215d0b3605", size = 102293, upload-time = "2025-09-22T16:29:53.023Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" }, + { url = "https://files.pythonhosted.org/packages/af/b5/123f13c975e9f27ab9c0770f514345bd406d0e8d3b7a0723af9d43f710af/wcwidth-0.2.14-py2.py3-none-any.whl", hash = "sha256:a7bb560c8aee30f9957e5f9895805edd20602f2d7f720186dfd906e82b4982e1", size = 37286, upload-time = "2025-09-22T16:29:51.641Z" }, ] [[package]] From 492a7dfa8cc45f891b34cd8ac537f3492dceaf7e Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sun, 11 Jan 2026 14:59:55 -0500 Subject: [PATCH 03/16] ~patched diffusers and transformers generation --- mir/config/constants.py | 16 +- mir/doc_parser.py | 11 +- mir/indexers.py | 44 +- mir/mir.json | 4634 ++++++++++++++++++++++++++++++--------- mir/spec/template.json | 1 + mir/tag.py | 7 +- 6 files changed, 3643 insertions(+), 1070 deletions(-) diff --git a/mir/config/constants.py b/mir/config/constants.py index 5736e52..23632fd 100644 --- a/mir/config/constants.py +++ b/mir/config/constants.py @@ -9,6 +9,7 @@ from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES from mir.config.json_io import read_json_file +from mir.config.console import nfo def mapped_cls(model_identifier: str): @@ -50,9 +51,15 @@ def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable: module = module_name.strip() library = pkg_name_or_abs_path.strip() - base_library = import_module(library, module) - module = getattr(base_library, module) - return module + try: + base_library = import_module(library, module) + except SyntaxError: + base_library = None + nfo(f"Syntax error attempting to import {module_name}") + if module := getattr(base_library, module, None): + return module + else: + nfo("failed to find module {module}") def extract_init_params(module: Callable | str, package_name: str | None = None) -> dict[str, list[str]]: @@ -137,12 +144,15 @@ class DocStringParserConstants: ">>> motion_adapter = ", ">>> adapter = ", # if this moves, also change motion_adapter check ">>> controlnet = ", + ">>> super_res_1_pipe = ", ">>> pipe_prior = ", + ">>> pipe_prior_redux = ", ">>> pipe = ", ">>> pipeline = ", ">>> blip_diffusion_pipe = ", ">>> prior_pipe = ", ">>> gen_pipe = ", + "pipe = ", ] repo_variables: List[str] = [ "controlnet_model", diff --git a/mir/doc_parser.py b/mir/doc_parser.py index 9bf6181..505149c 100644 --- a/mir/doc_parser.py +++ b/mir/doc_parser.py @@ -4,7 +4,7 @@ from typing import List, Optional, Tuple from pydantic import BaseModel, field_validator -from mir.config.console import dbuq, nfo +from mir.config.console import nfo from mir.config.constants import DocParseData, DocStringParserConstants @@ -80,6 +80,7 @@ def parse(self) -> DocParseData: motion_adapter = "motion_adapter" in candidate or "adapter" in candidate if motion_adapter and pipe_repo: staged, prior_candidate, _ = self.doc_match(DocStringParserConstants.pipe_prefixes[2:]) # skip the adapter statements + staged_class, staged_repo = ( self._extract_class_and_repo( segment=staged, @@ -90,13 +91,13 @@ def parse(self) -> DocParseData: if staged else (None, None) ) - if motion_adapter and pipe_class: + if motion_adapter and pipe_class and staged_class is not None: pipe_class = staged_class staged_repo = None staged_class = None if DocStringValidator.validate_pipe_class(pipe_class): - dbuq(f"class :{pipe_class}, repo : {pipe_repo}, staged_class: {staged_class}, staged_repo:{staged_repo} \n") + # dbuq(f"class :{pipe_class}, repo : {pipe_repo}, staged_class: {staged_class}, staged_repo:{staged_repo} \n") return DocParseData(pipe_class=pipe_class, pipe_repo=pipe_repo, staged_class=staged_class, staged_repo=staged_repo) def _extract_class_and_repo( @@ -110,8 +111,8 @@ def _extract_class_and_repo( pipe_repo = None for call_type in call_types: if call_type in segment: - pipe_class = segment.partition(call_type)[0].strip().split("= ")[-1] - if prior_class == pipe_class: + pipe_class = segment.partition(call_type)[0].strip().split("= ")[-1].split(".")[-1] + if prior_class == pipe_class and prior_text.split(call_type)[-1].strip().replace(")", ""): pipe_class = prior_text.partition(call_type)[0].strip().split("= ")[-1] repo_segment = segment.partition(call_type)[2].partition(")")[0] else: diff --git a/mir/indexers.py b/mir/indexers.py index 7d78c6a..0c155ce 100644 --- a/mir/indexers.py +++ b/mir/indexers.py @@ -10,7 +10,7 @@ from mir.config.console import nfo from mir.config.constants import ClassMapEntry, extract_init_params from mir.config.conversion import get_repo_from_class_map, import_submodules -from mir.doc_parser import parse_docs +from mir.doc_parser import parse_docs, DocParseData from mir.tag import mir_prefix_from_forward_pass, mir_tag_from_config, tag_model_from_repo if "pytest" in sys.modules: @@ -101,44 +101,42 @@ def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: from mir.inspect.metadata import find_diffusers_docstrings extracted_docstrings = find_diffusers_docstrings() - model_info = [ - extract # - for pipeline in extracted_docstrings - for extract in pipeline - ] + model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] pipe_data = {} # pipeline_stable_diffusion_xl_inpaint - for extract in model_info: - pipe = parse_docs(extract.doc_string) - if not pipe: - nfo(f"Doc string not found in '{extract.package_name}' in {extract.file_name}") + for extracted in model_info: + parsed_data: DocParseData = parse_docs(extracted.doc_string) + if parsed_data is None: + print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") continue for class_name, swap_repo in special_classes.items(): - if pipe.pipe_class == class_name: - pipe.pipe_repo = swap_repo + if parsed_data.pipe_class == class_name: + parsed_data.pipe_repo = swap_repo break - model_class_obj = import_submodules(pipe.pipe_class, f"diffusers.pipelines.{extract.package_name}.{extract.file_name}") + model_class_obj = import_submodules(parsed_data.pipe_class, f"diffusers.pipelines.{extracted.package_name}.{extracted.file_name}") + if not model_class_obj: + continue extract_init_params(model_class_obj) try: - series, comp_data = create_pipe_entry(pipe.pipe_repo, pipe.pipe_class) + series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) except TypeError: pass # Attempt 1 if pipe_data.get(series): - if "img2img" in pipe.pipe_class.lower(): + if "img2img" in parsed_data.pipe_class.lower(): continue pipe_data.setdefault(series, {}).update(comp_data) special_conditions = special_repos | special_classes - if pipe.staged_class or pipe.pipe_repo in list(special_conditions): - test = special_conditions.get(pipe.pipe_repo) + if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): + test = special_conditions.get(parsed_data.pipe_repo) if test: staged_repo = test - pipe.staged_class = pipe.pipe_class + parsed_data.staged_class = parsed_data.pipe_class try: series, comp_data = create_pipe_entry( - staged_repo if pipe.staged_repo else pipe.pipe_repo, - pipe.staged_class # - if pipe.staged_class - else pipe.pipe_class, + staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, + parsed_data.staged_class # + if parsed_data.staged_class + else parsed_data.pipe_class, ) except TypeError as error_log: nfo(series, comp_data) @@ -166,7 +164,6 @@ def transformers_index(): mir_data = {} transformers_data: list[ClassMapEntry] = map_transformers_classes() for entry in transformers_data: - print(entry) repo_path = get_repo_from_class_map(entry) if config := missing_config_params.get(entry.name, {}): entry.config_params = config.get("params", entry.config_params) @@ -182,7 +179,6 @@ def transformers_index(): tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) if isinstance(tokenizer_classes, str): tokenizer_classes = [tokenizer_classes] - print(type(tokenizer_classes)) # mode = modalities.get("mode") if tokenizer_classes: index = 0 diff --git a/mir/mir.json b/mir/mir.json index 78868b2..4c9d44d 100644 --- a/mir/mir.json +++ b/mir/mir.json @@ -49,6 +49,16 @@ } } }, + "info.controlnet.stable-diffusion-xl-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-base-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLControlNetUnionInpaintPipeline" + } + } + } + }, "info.controlnet.controlnet-union-sdxl-1": { "*": { "repo": "xinsir/controlnet-union-sdxl-1.0", @@ -99,6 +109,36 @@ } } }, + "info.unet.marigold-depth-v1-1": { + "*": { + "repo": "prs-eth/marigold-depth-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldDepthPipeline" + } + } + } + }, + "info.unet.marigold-iid-appearance-v1-1": { + "*": { + "repo": "prs-eth/marigold-iid-appearance-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldIntrinsicsPipeline" + } + } + } + }, + "info.unet.marigold-normals-v1-1": { + "*": { + "repo": "prs-eth/marigold-normals-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldNormalsPipeline" + } + } + } + }, "info.unet.stable-diffusion-v1-5": { "*": { "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", @@ -337,6 +377,16 @@ } } }, + "info.lora.animatelcm": { + "*": { + "repo": "wangfuyun/AnimateLCM", + "pkg": { + "0": { + "diffusers": "MotionAdapter" + } + } + } + }, "info.lora.animatediff-motion-adapter-sdxl": { "*": { "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", @@ -479,6 +529,16 @@ } } }, + "info.controlnet.flux1-depth-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Depth-dev", + "pkg": { + "0": { + "diffusers": "FluxControlInpaintPipeline" + } + } + } + }, "info.controlnet.flux1-dev-controlnet-canny": { "*": { "repo": "InstantX/FLUX.1-dev-controlnet-canny", @@ -519,119 +579,6 @@ } } }, - "info.dit.flux1-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-dev", - "pkg": { - "0": { - "diffusers": "FluxPipeline" - } - } - }, - "mystic": { - "repo": "enhanceaiteam/Mystic", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 16, - "guidance_scale": 7.5, - "width": 768, - "height": 1024 - } - } - }, - "file_256": [ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" - ], - "layer_256": [ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" - ], - "layer_b3": [ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" - ] - }, - "flux1-lite": { - "repo": "freepik/flux.1-lite-8b", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 28 - } - } - }, - "file_256": [ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" - ], - "layer_256": [ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" - ], - "layer_b3": [ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" - ] - }, - "f-lite": { - "repo": "freepik/f-lite", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "f-lite-texture": { - "repo": "freepik/f-lite-texture", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "flux": { - "repo": "TencentARC/flux-mini", - "file_256": [ - "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" - ], - "layer_256": [ - "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" - ], - "layer_b3": [ - "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" - ] - }, - "flex2": { - "repo": "ostris/Flex.2-preview", - "file_256": [ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" - ], - "layer_256": [ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" - ], - "layer_b3": [ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" - ] - }, - "flex1-alpha": { - "repo": "ostris/Flex.1-alpha", - "file_256": [ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" - ], - "layer_256": [ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" - ], - "layer_b3": [ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" - ] - } - }, "info.dit.prx-512-t2i-sft": { "*": { "repo": "Photoroom/prx-512-t2i-sft", @@ -835,12 +782,12 @@ } } }, - "info.unet.if-i-xl-v1": { + "info.unet.if-ii-l-v1": { "*": { - "repo": "DeepFloyd/IF-I-XL-v1.0", + "repo": "DeepFloyd/IF-II-L-v1.0", "pkg": { "0": { - "diffusers": "IFPipeline" + "diffusers": "IFSuperResolutionPipeline" } } } @@ -970,7 +917,7 @@ "repo": "kandinsky-community/kandinsky-2-2-prior", "pkg": { "0": { - "diffusers": "KandinskyPriorPipeline" + "diffusers": "KandinskyV22PriorPipeline" } } } @@ -1200,16 +1147,6 @@ } } }, - "info.unet.flux1-dev": { - "decoder": { - "repo": "black-forest-labs/FLUX.1-dev", - "pkg": { - "0": { - "diffusers": "WuerstchenDecoderPipeline" - } - } - } - }, "info.dit.auraflow": { "*": { "repo": "fal/AuraFlow", @@ -1543,1149 +1480,3669 @@ } }, "info.encoder.tokenizer": { - "funnel": { + "aimv2-patch14-224-lit": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" } } }, - "nllb-moe": { + "albert-xx-v2": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" } } }, - "deberta-v2-x": { + "align": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "xlm-roberta": { + "aria": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "gpt2": { + "audio-flamingo-3-hf": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" } } }, - "megatron-bert-uncased": { + "aya-vision": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" } } }, - "blenderbot": { + "bark": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "20": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "21": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "22": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "23": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "omdet-turbo-swin-hf": { + "bart": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" } } }, - "mgp-str": { + "bert-uncased": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "bert-for-seq-generation-l-24-bbc-encoder": { + "pkg": { + "0": { + "transformers": "transformers.models.bert_generation.tokenization_bert_generation.BertGenerationTokenizer" + } + } + }, + "bigbird-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.big_bird.tokenization_big_bird.BigBirdTokenizer" + } + } + }, + "bigbird-pegasus-arxiv": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "biogpt": { + "pkg": { + "0": { + "transformers": "transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer" + } + } + }, + "blenderbot": { + "pkg": { + "0": { + "transformers": "transformers.models.blenderbot_small.tokenization_blenderbot_small.BlenderbotSmallTokenizer" + } + } + }, + "blip-vqa": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, "blip2-opt": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" } } }, - "efficient-mlm-m0-0": { + "bloom": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" } } }, - "wav2vec2-conformer-rel-pos": { + "bridgetower": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" } } }, - "wav2vec2-bert-rel-pos": { + "bros-uncased": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "mm-grounding-dino-o365v1-goldg-v3det": { + "camembert": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.camembert.tokenization_camembert.CamembertTokenizer" + } + } + }, + "canine-s": { + "pkg": { + "0": { + "transformers": "transformers.models.canine.tokenization_canine.CanineTokenizer" + } + } + }, + "chinese-clip-vit-patch16": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "clap-htsat-fused": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "clip-vit-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "clipseg-rd64": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "clvp-dev": { + "pkg": { + "0": { + "transformers": "transformers.models.clvp.tokenization_clvp.ClvpTokenizer" + } + } + }, + "codegen-mono": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "conv-bert": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "ctrl": { + "pkg": { + "0": { + "transformers": "transformers.models.ctrl.tokenization_ctrl.CTRLTokenizer" + } + } + }, + "data2vec-audio-960h": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "data2vec-text": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "deberta": { + "pkg": { + "0": { + "transformers": "transformers.models.deberta.tokenization_deberta.DebertaTokenizer" + } + } + }, + "deberta-v2-x": { + "pkg": { + "0": { + "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2.DebertaV2Tokenizer" + } + } + }, + "distilbert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "dpr-ctx-encoder-single-nq": { + "pkg": { + "0": { + "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" + } + } + }, + "electra-discriminator": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "ernie-3-zh": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "ernie-4-vl-a-pt": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "esm": { + "pkg": { + "0": { + "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" + } + } + }, + "falcon-mamba": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "flaubert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" + } + } + }, + "florence-2": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "fnet": { + "pkg": { + "0": { + "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" + } + } + }, + "wmt19-en-ru": { + "pkg": { + "0": { + "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" + } + } + }, + "funnel": { + "pkg": { + "0": { + "transformers": "transformers.models.funnel.tokenization_funnel.FunnelTokenizer" + } + } + }, + "git": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "glm-4v-thinking": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4v": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-asr-nano-2512": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "gpt2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-bigcode-santacoder": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-neo": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-j": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "grounding-dino": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "groupvit-gcc-yfcc": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "hubert-ls960": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "ibert-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "idefics": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "idefics2": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "idefics3-llama3": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "blip-flan-t5": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "internvl3-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "jamba-v0": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "janus": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "kosmos-2-patch14-224": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "kosmos-2": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "todo": { + "pkg": { + "0": { + "transformers": "transformers.models.parakeet.tokenization_parakeet_fast.ParakeetTokenizerFast" + } + } + }, + "layoutlm-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "layoutlmv2-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2.LayoutLMv2Tokenizer" + } + } + }, + "layoutlmv3": { + "pkg": { + "0": { + "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" + } + } + }, + "led-16384": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "lfm2-vl": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "lilt-roberta-en": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "llama-4-scout-16e": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-v1-mistral-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-next-video-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-onevision-qwen2-ov-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "long-t5-local": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "luke": { + "pkg": { + "0": { + "transformers": "transformers.models.luke.tokenization_luke.LukeTokenizer" + } + } + }, + "lxmert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "m": { + "pkg": { + "0": { + "transformers": "transformers.models.m2m_100.tokenization_m2m_100.M2M100Tokenizer" + } + } + }, + "mamba": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "mamba2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "opus-mt-en-de": { + "pkg": { + "0": { + "transformers": "transformers.models.marian.tokenization_marian.MarianTokenizer" + } + } + }, + "mbart-cc25": { + "pkg": { + "0": { + "transformers": "transformers.models.mbart.tokenization_mbart.MBartTokenizer" + } + } + }, + "megatron-bert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "metaclip-2-worldwide-huge-quickgelu": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "mgp-str": { + "pkg": { + "0": { + "transformers": "transformers.models.mgp_str.tokenization_mgp_str.MgpstrTokenizer" + } + } + }, + "mistral-3-2503": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llama-3-vision": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mm-grounding-dino-o365v1-goldg-v3det": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "mobilebert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "modernbert": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "mpnet": { + "pkg": { + "0": { + "transformers": "transformers.models.mpnet.tokenization_mpnet.MPNetTokenizer" + } + } + }, + "mpt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "mra-512-4": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "mt5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "musicgen": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "musicgen-melody": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "mvp": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "nllb-moe": { + "pkg": { + "0": { + "transformers": "transformers.models.nllb.tokenization_nllb.NllbTokenizer" + } + } + }, + "nystromformer-512": { + "pkg": { + "0": { + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" + } + } + }, + "omdet-turbo-swin-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "openai-gpt": { + "pkg": { + "0": { + "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" + } + } + }, + "opt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "ovis2-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "owlv2-patch16": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "owlvit-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "paligemma": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "pegasus": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "pegasus-x": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "language-perceiver": { + "pkg": { + "0": { + "transformers": "transformers.models.perceiver.tokenization_perceiver.PerceiverTokenizer" + } + } + }, + "plbart": { + "pkg": { + "0": { + "transformers": "transformers.models.plbart.tokenization_plbart.PLBartTokenizer" + } + } + }, + "qwen2-vl": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-vl": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-vl-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "reformer-crime-and-punishment": { + "pkg": { + "0": { + "transformers": "transformers.models.reformer.tokenization_reformer.ReformerTokenizer" + } + } + }, + "rembert": { + "pkg": { + "0": { + "transformers": "transformers.models.rembert.tokenization_rembert.RemBertTokenizer" + } + } + }, + "roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "efficient-mlm-m0-0": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "roc-bert-zh": { + "pkg": { + "0": { + "transformers": "transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer" + } + } + }, + "roformer-chinese": { + "pkg": { + "0": { + "transformers": "transformers.models.roformer.tokenization_roformer.RoFormerTokenizer" + } + } + }, + "rwkv-4-pile": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "hf-seamless-m4t": { + "pkg": { + "0": { + "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" + } + } + }, + "seamless-m4t-v2": { + "pkg": { + "0": { + "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" + } + } + }, + "siglip-patch16-224": { + "pkg": { + "0": { + "transformers": "transformers.models.siglip.tokenization_siglip.SiglipTokenizer" + } + } + }, + "siglip2-patch16-224": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "s2t-librispeech-asr": { + "pkg": { + "0": { + "transformers": "transformers.models.speech_to_text.tokenization_speech_to_text.Speech2TextTokenizer" + } + } + }, + "speecht5-asr": { + "pkg": { + "0": { + "transformers": "transformers.models.speecht5.tokenization_speecht5.SpeechT5Tokenizer" + } + } + }, + "splinter": { + "pkg": { + "0": { + "transformers": "transformers.models.splinter.tokenization_splinter.SplinterTokenizer" + } + } + }, + "squeezebert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "switch-8": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "t5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "tapas-finetuned-sqa": { + "pkg": { + "0": { + "transformers": "transformers.models.tapas.tokenization_tapas.TapasTokenizer" + } + } + }, + "tvp": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "udop": { + "pkg": { + "0": { + "transformers": "transformers.models.udop.tokenization_udop.UdopTokenizer" + } + } + }, + "umt5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "video-llava-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "vilt-b32-mlm": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "vip-llava-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "visualbert-vqa-coco-pre": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "mms-tts-eng": { + "pkg": { + "0": { + "transformers": "transformers.models.vits.tokenization_vits.VitsTokenizer" + } + } + }, + "voxtral-2507": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "wav2vec2-960h": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "wav2vec2-bert-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "wav2vec2-conformer-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "whisper": { + "pkg": { + "0": { + "transformers": "transformers.models.whisper.tokenization_whisper.WhisperTokenizer" + } + } + }, + "xclip-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "xglm": { + "pkg": { + "0": { + "transformers": "transformers.models.xglm.tokenization_xglm.XGLMTokenizer" + } + } + }, + "xlm-mlm-en-2048": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm.tokenization_xlm.XLMTokenizer" + } + } + }, + "xlm-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "xlm-roberta-xl": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "xlnet-cased": { + "pkg": { + "0": { + "transformers": "transformers.models.xlnet.tokenization_xlnet.XLNetTokenizer" + } + } + }, + "xlstm": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "xmod": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "yoso-4096": { + "pkg": { + "0": { + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" + } + } + }, + "zamba-v1": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + } + }, + "info.vit.aimv2-patch14-224-lit": { + "*": { + "repo": "apple/aimv2-large-patch14-224-lit", + "pkg": { + "0": { + "transformers": "Aimv2Model" + } + } + } + }, + "info.art.albert-xx-v2": { + "*": { + "repo": "albert/albert-xxlarge-v2", + "pkg": { + "0": { + "transformers": "AlbertModel" + } + } + } + }, + "info.vit.align": { + "*": { + "repo": "kakaobrain/align-base", + "pkg": { + "0": { + "transformers": "AlignModel" + } + } + } + }, + "info.vit.altclip": { + "*": { + "repo": "BAAI/AltCLIP", + "pkg": { + "0": { + "transformers": "AltCLIPModel" + } + } + } + }, + "info.vit.aria": { + "*": { + "repo": "rhymes-ai/Aria", + "pkg": { + "0": { + "transformers": "AriaModel" + } + } + } + }, + "info.vit.ast-finetuned-audioset-10-10-0593": { + "*": { + "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "pkg": { + "0": { + "transformers": "ASTModel" + } + } + } + }, + "info.stst.audio-flamingo-3-hf": { + "*": { + "repo": "nvidia/audio-flamingo-3-hf", + "pkg": { + "0": { + "transformers": "AudioFlamingo3ForConditionalGeneration" + } + } + } + }, + "info.aet.audio-flamingo-3-hf": { + "*": { + "repo": "nvidia/audio-flamingo-3-hf", + "pkg": { + "0": { + "transformers": "AudioFlamingo3Encoder" + } + } + } + }, + "info.stst.autoformer-tourism-monthly": { + "*": { + "repo": "huggingface/autoformer-tourism-monthly", + "pkg": { + "0": { + "transformers": "AutoformerModel" + } + } + } + }, + "info.vit.aya-vision": { + "*": { + "repo": "CohereForAI/aya-vision-8b", + "pkg": { + "0": { + "transformers": "AyaVisionModel" + } + } + } + }, + "info.art.bark": { + "*": { + "repo": "suno/bark", + "pkg": { + "0": { + "transformers": "BarkModel" + } + } + } + }, + "info.stst.bart": { + "*": { + "repo": "facebook/bart-large", + "pkg": { + "0": { + "transformers": "BartModel" + } + } + } + }, + "info.vit.beit-patch16-224-pt": { + "*": { + "repo": "microsoft/beit-base-patch16-224-pt22k", + "pkg": { + "0": { + "transformers": "BeitModel" + } + } + } + }, + "info.art.bert-uncased": { + "*": { + "repo": "google-bert/bert-base-uncased", + "pkg": { + "0": { + "transformers": "BertModel" + } + } + } + }, + "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "*": { + "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "pkg": { + "0": { + "transformers": "BertGenerationEncoder" + } + } + } + }, + "info.art.bigbird-roberta": { + "*": { + "repo": "google/bigbird-roberta-base", + "pkg": { + "0": { + "transformers": "BigBirdModel" + } + } + } + }, + "info.stst.bigbird-pegasus-arxiv": { + "*": { + "repo": "google/bigbird-pegasus-large-arxiv", + "pkg": { + "0": { + "transformers": "BigBirdPegasusModel" + } + } + } + }, + "info.art.biogpt": { + "*": { + "repo": "microsoft/biogpt", + "pkg": { + "0": { + "transformers": "BioGptModel" + } + } + } + }, + "info.vit.bit-50": { + "*": { + "repo": "google/bit-50", + "pkg": { + "0": { + "transformers": "BitModel" + } + } + } + }, + "info.stst.blenderbot": { + "*": { + "repo": "facebook/blenderbot-3B", + "pkg": { + "0": { + "transformers": "BlenderbotModel" + } + } + } + }, + "info.vit.blip-vqa": { + "*": { + "repo": "Salesforce/blip-vqa-base", + "pkg": { + "0": { + "transformers": "BlipModel" + } + } + } + }, + "info.vit.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2Model" + } + } + } + }, + "info.stst.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2QFormerModel" + } + } + } + }, + "info.art.bloom": { + "*": { + "repo": "bigscience/bloom", + "pkg": { + "0": { + "transformers": "BloomModel" + } + } + } + }, + "info.vit.bridgetower": { + "*": { + "repo": "BridgeTower/bridgetower-base", + "pkg": { + "0": { + "transformers": "BridgeTowerModel" + } + } + } + }, + "info.art.bros-uncased": { + "*": { + "repo": "jinho8345/bros-base-uncased", + "pkg": { + "0": { + "transformers": "BrosModel" + } + } + } + }, + "info.art.camembert": { + "*": { + "repo": "almanach/camembert-base", + "pkg": { + "0": { + "transformers": "CamembertModel" + } + } + } + }, + "info.art.canine-s": { + "*": { + "repo": "google/canine-s", + "pkg": { + "0": { + "transformers": "CanineModel" + } + } + } + }, + "info.vit.chinese-clip-vit-patch16": { + "*": { + "repo": "OFA-Sys/chinese-clip-vit-base-patch16", + "pkg": { + "0": { + "transformers": "ChineseCLIPModel" + } + } + } + }, + "info.vit.clap-htsat-fused": { + "*": { + "repo": "laion/clap-htsat-fused", + "pkg": { + "0": { + "transformers": "ClapModel" + } + } + } + }, + "info.vit.clip-vit-patch32": { + "*": { + "repo": "openai/clip-vit-base-patch32", + "pkg": { + "0": { + "transformers": "CLIPModel" + } + } + } + }, + "info.vit.clipseg-rd64": { + "*": { + "repo": "CIDAS/clipseg-rd64", + "pkg": { + "0": { + "transformers": "CLIPSegModel" + } + } + } + }, + "info.vit.clvp-dev": { + "*": { + "repo": "susnato/clvp_dev", + "pkg": { + "0": { + "transformers": "ClvpModelForConditionalGeneration" + } + } + } + }, + "info.art.codegen-mono": { + "*": { + "repo": "Salesforce/codegen-2B-mono", + "pkg": { + "0": { + "transformers": "CodeGenModel" + } + } + } + }, + "info.vit.command-a-vision-07-2025": { + "*": { + "repo": "CohereLabs/command-a-vision-07-2025", + "pkg": { + "0": { + "transformers": "Cohere2VisionModel" + } + } + } + }, + "info.detr.conditional-detr-resnet-50": { + "*": { + "repo": "microsoft/conditional-detr-resnet-50", + "pkg": { + "0": { + "transformers": "ConditionalDetrModel" + } + } + } + }, + "info.art.conv-bert": { + "*": { + "repo": "YituTech/conv-bert-base", + "pkg": { + "0": { + "transformers": "ConvBertModel" + } + } + } + }, + "info.vit.convnext-224": { + "*": { + "repo": "facebook/convnext-tiny-224", + "pkg": { + "0": { + "transformers": "ConvNextModel" + } + } + } + }, + "info.vit.convnextv2-224": { + "*": { + "repo": "facebook/convnextv2-tiny-1k-224", + "pkg": { + "0": { + "transformers": "ConvNextV2Model" + } + } + } + }, + "info.art.ctrl": { + "*": { + "repo": "Salesforce/ctrl", + "pkg": { + "0": { + "transformers": "CTRLModel" + } + } + } + }, + "info.vit.cvt-13": { + "*": { + "repo": "microsoft/cvt-13", + "pkg": { + "0": { + "transformers": "CvtModel" + } + } + } + }, + "info.art.cwm": { + "*": { + "repo": "facebook/cwm", + "pkg": { + "0": { + "transformers": "CwmModel" + } + } + } + }, + "info.detr.dfine-x-coco": { + "*": { + "repo": "ustc-community/dfine-xlarge-coco", + "pkg": { + "0": { + "transformers": "DFineModel" + } + } + } + }, + "info.detr.dab-detr": { + "*": { + "repo": "IDEA-Research/dab-detr-resnet-50", + "pkg": { + "0": { + "transformers": "DabDetrModel" + } + } + } + }, + "info.gan.dac": { + "*": { + "repo": "descript/dac_16khz", + "pkg": { + "0": { + "transformers": "DacModel" + } + } + } + }, + "info.aet.data2vec-audio-960h": { + "*": { + "repo": "facebook/data2vec-audio-base-960h", + "pkg": { + "0": { + "transformers": "Data2VecAudioModel" + } + } + } + }, + "info.art.data2vec-text": { + "*": { + "repo": "facebook/data2vec-text-base", + "pkg": { + "0": { + "transformers": "Data2VecTextModel" + } + } + } + }, + "info.vit.data2vec-vision": { + "*": { + "repo": "facebook/data2vec-vision-base", + "pkg": { + "0": { + "transformers": "Data2VecVisionModel" + } + } + } + }, + "info.art.deberta": { + "*": { + "repo": "microsoft/deberta-base", + "pkg": { + "0": { + "transformers": "DebertaModel" + } + } + } + }, + "info.art.deberta-v2-x": { + "*": { + "repo": "microsoft/deberta-v2-xlarge", + "pkg": { + "0": { + "transformers": "DebertaV2Model" + } + } + } + }, + "info.art.decision-transformer-gym-hopper": { + "*": { + "repo": "edbeeching/decision-transformer-gym-hopper-medium", + "pkg": { + "0": { + "transformers": "DecisionTransformerModel" + } + } + } + }, + "info.detr.deformable-detr": { + "*": { + "repo": "SenseTime/deformable-detr", + "pkg": { + "0": { + "transformers": "DeformableDetrModel" + } + } + } + }, + "info.vit.deit-distilled-patch16-224": { + "*": { + "repo": "facebook/deit-base-distilled-patch16-224", + "pkg": { + "0": { + "transformers": "DeiTModel" + } + } + } + }, + "info.vit.depth": { + "*": { + "repo": "apple/DepthPro", + "pkg": { + "0": { + "transformers": "DepthProModel" + } + } + } + }, + "info.detr.detr-resnet-50": { + "*": { + "repo": "facebook/detr-resnet-50", + "pkg": { + "0": { + "transformers": "DetrModel" + } + } + } + }, + "info.gan.dinat-in-224": { + "*": { + "repo": "shi-labs/dinat-mini-in1k-224", + "pkg": { + "0": { + "transformers": "DinatModel" + } + } + } + }, + "info.vit.dinov2-patch16-224": { + "*": { + "repo": "google/dinov2-base-patch16-224", + "pkg": { + "0": { + "transformers": "Dinov2Model" + } + } + } + }, + "info.vit.dinov2-with-registers": { + "*": { + "repo": "facebook/dinov2-with-registers-base", + "pkg": { + "0": { + "transformers": "Dinov2WithRegistersModel" + } + } + } + }, + "info.art.distilbert-uncased": { + "*": { + "repo": "distilbert-base-uncased", + "pkg": { + "0": { + "transformers": "DistilBertModel" + } + } + } + }, + "info.vit.donut": { + "*": { + "repo": "naver-clova-ix/donut-base", + "pkg": { + "0": { + "transformers": "DonutSwinModel" + } + } + } + }, + "info.art.dpr-ctx-encoder-single-nq": { + "*": { + "repo": "facebook/dpr-ctx_encoder-single-nq-base", + "pkg": { + "0": { + "transformers": "DPRQuestionEncoder" + } + } + } + }, + "info.detr.dpt": { + "*": { + "repo": "Intel/dpt-large", + "pkg": { + "0": { + "transformers": "DPTModel" + } + } + } + }, + "info.vit.edgetam1-hiera": { + "*": { + "repo": "facebook/edgetam.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "EdgeTamModel" + } + } + } + }, + "info.vit.edgetam": { + "*": { + "repo": "facebook/EdgeTAM", + "pkg": { + "0": { + "transformers": "EdgeTamVideoModel" + } + } + } + }, + "info.art.electra-discriminator": { + "*": { + "repo": "google/electra-small-discriminator", + "pkg": { + "0": { + "transformers": "ElectraModel" + } + } + } + }, + "info.gan.encodec": { + "*": { + "repo": "facebook/encodec_24khz", + "pkg": { + "0": { + "transformers": "EncodecModel" + } + } + } + }, + "info.art.ernie-3-zh": { + "*": { + "repo": "nghuyong/ernie-3.0-base-zh", + "pkg": { + "0": { + "transformers": "ErnieModel" + } + } + } + }, + "info.vit.ernie-4-vl-a-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-VL-28B-A3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5_VL_MoeModel" + } + } + } + }, + "info.aet.esm": { + "*": { + "repo": "facebook/esm-1b", + "pkg": { + "0": { + "transformers": "EsmModel" + } + } + } + }, + "info.ssm.falcon-mamba": { + "*": { + "repo": "tiiuae/falcon-mamba-7b", + "pkg": { + "0": { + "transformers": "FalconMambaModel" + } + } + } + }, + "info.vit.fastvlm": { + "*": { + "repo": "KamilaMila/FastVLM-7B", + "pkg": { + "0": { + "transformers": "FastVlmModel" + } + } + } + }, + "info.aet.fastspeech2-conformer": { + "*": { + "repo": "espnet/fastspeech2_conformer", + "pkg": { + "0": { + "transformers": "FastSpeech2ConformerModel" + } + } + } + }, + "info.art.flaubert-uncased": { + "*": { + "repo": "flaubert/flaubert_base_uncased", + "pkg": { + "0": { + "transformers": "FlaubertModel" + } + } + } + }, + "info.vit.florence-2": { + "*": { + "repo": "florence-community/Florence-2-base", + "pkg": { + "0": { + "transformers": "Florence2Model" + } + } + } + }, + "info.art.fnet": { + "*": { + "repo": "google/fnet-base", + "pkg": { + "0": { + "transformers": "FNetModel" + } + } + } + }, + "info.vit.focalnet": { + "*": { + "repo": "microsoft/focalnet-tiny", + "pkg": { + "0": { + "transformers": "FocalNetModel" + } + } + } + }, + "info.stst.wmt19-en-ru": { + "*": { + "repo": "facebook/wmt19-en-ru", + "pkg": { + "0": { + "transformers": "FSMTModel" + } + } + } + }, + "info.aet.funnel": { + "*": { + "repo": "funnel-transformer/small", + "pkg": { + "0": { + "transformers": "FunnelModel" + } + } + } + }, + "info.vit.git": { + "*": { + "repo": "microsoft/git-base", + "pkg": { + "0": { + "transformers": "GitModel" + } + } + } + }, + "info.vit.glm-4v-thinking": { + "*": { + "repo": "zai-org/GLM-4.1V-9B-Thinking", + "pkg": { + "0": { + "transformers": "Glm46VModel" + } + } + } + }, + "info.vit.glm-4v": { + "*": { + "repo": "zai-org/GLM-4.5V", + "pkg": { + "0": { + "transformers": "Glm4vMoeModel" + } + } + } + }, + "info.stst.glm-asr-nano-2512": { + "*": { + "repo": "zai-org/GLM-ASR-Nano-2512", + "pkg": { + "0": { + "transformers": "GlmAsrForConditionalGeneration" + } + } + } + }, + "info.vit.glpn-kitti": { + "*": { + "repo": "vinvino02/glpn-kitti", + "pkg": { + "0": { + "transformers": "GLPNModel" + } + } + } + }, + "info.art.gpt2": { + "*": { + "repo": "openai-community/gpt2", + "pkg": { + "0": { + "transformers": "GPT2Model" + } + } + } + }, + "info.art.gpt-bigcode-santacoder": { + "*": { + "repo": "bigcode/gpt_bigcode-santacoder", + "pkg": { + "0": { + "transformers": "GPTBigCodeModel" + } + } + } + }, + "info.art.gpt-neo": { + "*": { + "repo": "EleutherAI/gpt-neo-1.3B", + "pkg": { + "0": { + "transformers": "GPTNeoModel" + } + } + } + }, + "info.art.gpt-j": { + "*": { + "repo": "EleutherAI/gpt-j-6B", + "pkg": { + "0": { + "transformers": "GPTJModel" + } + } + } + }, + "info.vit.llava-v1-mistral-hf": { + "*": { + "repo": "llava-hf/llava-v1.6-mistral-7b-hf", + "pkg": { + "0": { + "transformers": "LlavaNextModel" + } + } + } + }, + "info.detr.grounding-dino": { + "*": { + "repo": "IDEA-Research/grounding-dino-tiny", + "pkg": { + "0": { + "transformers": "GroundingDinoModel" + } + } + } + }, + "info.vit.groupvit-gcc-yfcc": { + "*": { + "repo": "nvidia/groupvit-gcc-yfcc", + "pkg": { + "0": { + "transformers": "GroupViTModel" + } + } + } + }, + "info.vit.dfine-x-coco": { + "*": { + "repo": "ustc-community/dfine_x_coco", + "pkg": { + "0": { + "transformers": "HGNetV2Backbone" + } + } + } + }, + "info.vit.hiera-224": { + "*": { + "repo": "facebook/hiera-base-224-hf", + "pkg": { + "0": { + "transformers": "HieraModel" + } + } + } + }, + "info.aet.hubert-ls960": { + "*": { + "repo": "facebook/hubert-base-ls960", + "pkg": { + "0": { + "transformers": "HubertModel" + } + } + } + }, + "info.art.ibert-roberta": { + "*": { + "repo": "kssteven/ibert-roberta-base", + "pkg": { + "0": { + "transformers": "IBertModel" + } + } + } + }, + "info.vit.idefics": { + "*": { + "repo": "HuggingFaceM4/idefics-9b", + "pkg": { + "0": { + "transformers": "IdeficsModel" + } + } + } + }, + "info.vit.idefics2": { + "*": { + "repo": "HuggingFaceM4/idefics2-8b", + "pkg": { + "0": { + "transformers": "Idefics2Model" + } + } + } + }, + "info.vit.idefics3-llama3": { + "*": { + "repo": "HuggingFaceM4/Idefics3-8B-Llama3", + "pkg": { + "0": { + "transformers": "Idefics3Model" + } + } + } + }, + "info.vit.siglip-patch16-224": { + "*": { + "repo": "google/siglip-base-patch16-224", + "pkg": { + "0": { + "transformers": "Idefics3VisionTransformer" + } + } + } + }, + "info.vit.ijepa-vith14": { + "*": { + "repo": "facebook/ijepa_vith14_1k", + "pkg": { + "0": { + "transformers": "IJepaModel" + } + } + } + }, + "info.art.imagegpt": { + "*": { + "repo": "openai/imagegpt-small", + "pkg": { + "0": { + "transformers": "ImageGPTModel" + } + } + } + }, + "info.vit.blip-flan-t5": { + "*": { + "repo": "Salesforce/instructblip-flan-t5-xl", + "pkg": { + "0": { + "transformers": "InstructBlipModel" + } + } + } + }, + "info.vit.internvl3-hf": { + "*": { + "repo": "OpenGVLab/InternVL3-1B-hf", + "pkg": { + "0": { + "transformers": "InternVLModel" + } + } + } + }, + "info.ssm.jamba-v0": { + "*": { + "repo": "ai21labs/Jamba-v0.1", + "pkg": { + "0": { + "transformers": "JambaModel" + } + } + } + }, + "info.vit.janus": { + "*": { + "repo": "deepseek-community/Janus-Pro-1B", + "pkg": { + "0": { + "transformers": "JanusModel" + } + } + } + }, + "info.vit.kosmos-2-patch14-224": { + "*": { + "repo": "microsoft/kosmos-2-patch14-224", + "pkg": { + "0": { + "transformers": "Kosmos2Model" + } + } + } + }, + "info.vit.kosmos-2": { + "*": { + "repo": "microsoft/kosmos-2.5", + "pkg": { + "0": { + "transformers": "Kosmos2_5Model" + } + } + } + }, + "info.aet.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrForCTC" + } + } + } + }, + "info.stst.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrEncoder" + } + } + } + }, + "info.art.layoutlm-uncased": { + "*": { + "repo": "microsoft/layoutlm-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMModel" + } + } + } + }, + "info.art.layoutlmv2-uncased": { + "*": { + "repo": "microsoft/layoutlmv2-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMv2Model" + } + } + } + }, + "info.vit.layoutlmv3": { + "*": { + "repo": "microsoft/layoutlmv3-base", + "pkg": { + "0": { + "transformers": "LayoutLMv3Model" + } + } + } + }, + "info.stst.led-16384": { + "*": { + "repo": "allenai/led-base-16384", + "pkg": { + "0": { + "transformers": "LEDModel" + } + } + } + }, + "info.gan.levit-128s": { + "*": { + "repo": "facebook/levit-128S", + "pkg": { + "0": { + "transformers": "LevitModel" + } + } + } + }, + "info.stst.lfm2-a": { + "*": { + "repo": "LiquidAI/LFM2-8B-A1B", + "pkg": { + "0": { + "transformers": "Lfm2MoeModel" + } + } + } + }, + "info.vit.lfm2-vl": { + "*": { + "repo": "LiquidAI/LFM2-VL-1.6B", + "pkg": { + "0": { + "transformers": "Lfm2VlModel" + } + } + } + }, + "info.aet.lightglue-superpoint": { + "*": { + "repo": "ETH-CVG/lightglue_superpoint", + "pkg": { + "0": { + "transformers": "LightGlueForKeypointMatching" + } + } + } + }, + "info.art.lilt-roberta-en": { + "*": { + "repo": "SCUT-DLVCLab/lilt-roberta-en-base", + "pkg": { + "0": { + "transformers": "LiltModel" + } + } + } + }, + "info.vit.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4ForConditionalGeneration" + } + } + } + }, + "info.moe.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4TextModel" + } + } + } + }, + "info.vit.llava": { + "*": { + "repo": "llava-hf/llava-9b", + "pkg": { + "0": { + "transformers": "LlavaModel" + } + } + } + }, + "info.vit.llava-next-video-hf": { + "*": { + "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", + "pkg": { + "0": { + "transformers": "LlavaNextVideoModel" + } + } + } + }, + "info.vit.llava-onevision-qwen2-ov-hf": { + "*": { + "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", + "pkg": { + "0": { + "transformers": "LlavaOnevisionModel" + } + } + } + }, + "info.stst.long-t5-local": { + "*": { + "repo": "google/long-t5-local-base", + "pkg": { + "0": { + "transformers": "LongT5Model" + } + } + } + }, + "info.art.luke": { + "*": { + "repo": "studio-ousia/luke-base", + "pkg": { + "0": { + "transformers": "LukeModel" + } + } + } + }, + "info.art.lxmert-uncased": { + "*": { + "repo": "unc-nlp/lxmert-base-uncased", + "pkg": { + "0": { + "transformers": "LxmertModel" + } + } + } + }, + "info.stst.m": { + "*": { + "repo": "facebook/m2m100_418M", + "pkg": { + "0": { + "transformers": "M2M100Model" + } + } + } + }, + "info.ssm.mamba": { + "*": { + "repo": "state-spaces/mamba-2.8b", + "pkg": { + "0": { + "transformers": "MambaModel" + } + } + } + }, + "info.ssm.mamba2": { + "*": { + "repo": "AntonV/mamba2-2.7b-hf", + "pkg": { + "0": { + "transformers": "Mamba2Model" + } + } + } + }, + "info.stst.opus-mt-en-de": { + "*": { + "repo": "Helsinki-NLP/opus-mt-en-de", + "pkg": { + "0": { + "transformers": "MarianModel" + } + } + } + }, + "info.art.markuplm": { + "*": { + "repo": "microsoft/markuplm-base", + "pkg": { + "0": { + "transformers": "MarkupLMModel" + } + } + } + }, + "info.vit.swin-patch4-window7-224": { + "*": { + "repo": "microsoft/swin-tiny-patch4-window7-224", + "pkg": { + "0": { + "transformers": "MaskFormerSwinModel" + } + } + } + }, + "info.stst.mbart-cc25": { + "*": { + "repo": "facebook/mbart-large-cc25", + "pkg": { + "0": { + "transformers": "MBartModel" + } + } + } + }, + "info.art.megatron-bert-uncased": { + "*": { + "repo": "nvidia/megatron-bert-uncased-345m", + "pkg": { + "0": { + "transformers": "MegatronBertModel" + } + } + } + }, + "info.vit.metaclip-2-worldwide-huge-quickgelu": { + "*": { + "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", + "pkg": { + "0": { + "transformers": "MetaClip2Model" + } + } + } + }, + "info.vit.mgp-str": { + "*": { + "repo": "alibaba-damo/mgp-str-base", + "pkg": { + "0": { + "transformers": "MgpstrForSceneTextRecognition" + } + } + } + }, + "info.vit.mistral-3-2503": { + "*": { + "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", + "pkg": { + "0": { + "transformers": "Mistral3Model" + } + } + } + }, + "info.vit.mlcd-vit-bigg-patch14-336": { + "*": { + "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", + "pkg": { + "0": { + "transformers": "MLCDVisionModel" + } + } + } + }, + "info.vit.llama-3-vision": { + "*": { + "repo": "meta-llama/Llama-3.2-11B-Vision", + "pkg": { + "0": { + "transformers": "MllamaModel" + } + } + } + }, + "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "*": { + "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "pkg": { + "0": { + "transformers": "MMGroundingDinoModel" + } + } + } + }, + "info.art.mobilebert-uncased": { + "*": { + "repo": "google/mobilebert-uncased", + "pkg": { + "0": { + "transformers": "MobileBertModel" + } + } + } + }, + "info.vit.mobilenet-v1-1--224": { + "*": { + "repo": "google/mobilenet_v1_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV1Model" + } + } + } + }, + "info.vit.mobilenet-v2-1--224": { + "*": { + "repo": "google/mobilenet_v2_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV2Model" + } + } + } + }, + "info.vit.mobilevit": { + "*": { + "repo": "apple/mobilevit-small", + "pkg": { + "0": { + "transformers": "MobileViTModel" + } + } + } + }, + "info.vit.mobilevitv2-1": { + "*": { + "repo": "apple/mobilevitv2-1.0-imagenet1k-256", + "pkg": { + "0": { + "transformers": "MobileViTV2Model" + } + } + } + }, + "info.aet.modernbert": { + "*": { + "repo": "answerdotai/ModernBERT-base", + "pkg": { + "0": { + "transformers": "ModernBertModel" + } + } + } + }, + "info.art.mpnet": { + "*": { + "repo": "microsoft/mpnet-base", + "pkg": { + "0": { + "transformers": "MPNetModel" + } + } + } + }, + "info.art.mpt": { + "*": { + "repo": "mosaicml/mpt-7b", + "pkg": { + "0": { + "transformers": "MptModel" + } + } + } + }, + "info.art.mra-512-4": { + "*": { + "repo": "uw-madison/mra-base-512-4", + "pkg": { + "0": { + "transformers": "MraModel" + } + } + } + }, + "info.stst.mt5": { + "*": { + "repo": "google/mt5-small", + "pkg": { + "0": { + "transformers": "MT5Model" + } + } + } + }, + "info.art.musicgen": { + "*": { + "repo": "facebook/musicgen-small", + "pkg": { + "0": { + "transformers": "MusicgenModel" + } + } + } + }, + "info.art.musicgen-melody": { + "*": { + "repo": "facebook/musicgen-melody", + "pkg": { + "0": { + "transformers": "MusicgenMelodyModel" + } + } + } + }, + "info.stst.mvp": { + "*": { + "repo": "RUCAIBox/mvp", + "pkg": { + "0": { + "transformers": "MvpModel" + } + } + } + }, + "info.stst.nllb-moe": { + "*": { + "repo": "facebook/nllb-moe-54b", + "pkg": { + "0": { + "transformers": "NllbMoeModel" + } + } + } + }, + "info.art.nystromformer-512": { + "*": { + "repo": "uw-madison/nystromformer-512", + "pkg": { + "0": { + "transformers": "NystromformerModel" + } + } + } + }, + "info.detr.omdet-turbo-swin-hf": { + "*": { + "repo": "omlab/omdet-turbo-swin-tiny-hf", + "pkg": { + "0": { + "transformers": "OmDetTurboForObjectDetection" + } + } + } + }, + "info.art.openai-gpt": { + "*": { + "repo": "openai-community/openai-gpt", + "pkg": { + "0": { + "transformers": "OpenAIGPTModel" + } + } + } + }, + "info.art.opt": { + "*": { + "repo": "facebook/opt-350m", + "pkg": { + "0": { + "transformers": "OPTModel" + } + } + } + }, + "info.vit.ovis2-hf": { + "*": { + "repo": "thisisiron/Ovis2-1B-hf", + "pkg": { + "0": { + "transformers": "Ovis2Model" + } + } + } + }, + "info.vit.owlv2-patch16": { + "*": { + "repo": "google/owlv2-base-patch16", + "pkg": { + "0": { + "transformers": "Owlv2Model" + } + } + } + }, + "info.vit.owlvit-patch32": { + "*": { + "repo": "google/owlvit-base-patch32", + "pkg": { + "0": { + "transformers": "OwlViTModel" + } + } + } + }, + "info.vit.paligemma": { + "*": { + "repo": "google/paligemma2-3b-mix-224", + "pkg": { + "0": { + "transformers": "PaliGemmaModel" + } + } + } + }, + "info.aet.parakeet-ctc-b": { + "*": { + "repo": "nvidia/parakeet-ctc-1.1b", + "pkg": { + "0": { + "transformers": "ParakeetForCTC" + } + } + } + }, + "info.stst.parakeet-ctc-b": { + "*": { + "repo": "nvidia/parakeet-ctc-1.1b", + "pkg": { + "0": { + "transformers": "ParakeetEncoder" + } + } + } + }, + "info.stst.pe-av": { + "*": { + "repo": "facebook/pe-av-large", + "pkg": { + "0": { + "transformers": "PeAudioModel" + } + } + } + }, + "info.aet.pe-av": { + "*": { + "repo": "facebook/pe-av-large", + "pkg": { + "0": { + "transformers": "PeAudioVideoModel" + } + } + } + }, + "info.stst.pegasus": { + "*": { + "repo": "google/pegasus-large", + "pkg": { + "0": { + "transformers": "PegasusModel" + } + } + } + }, + "info.stst.pegasus-x": { + "*": { + "repo": "google/pegasus-x-large", + "pkg": { + "0": { + "transformers": "PegasusXModel" + } + } + } + }, + "info.vit.language-perceiver": { + "*": { + "repo": "deepmind/language-perceiver", + "pkg": { + "0": { + "transformers": "PerceiverModel" + } + } + } + }, + "info.vit.perception-lm": { + "*": { + "repo": "facebook/Perception-LM-1B", + "pkg": { + "0": { + "transformers": "PerceptionLMModel" + } + } + } + }, + "info.vit.pixio-huge": { + "*": { + "repo": "facebook/pixio-huge", + "pkg": { + "0": { + "transformers": "PixioModel" + } + } + } + }, + "info.stst.plbart": { + "*": { + "repo": "uclanlp/plbart-base", + "pkg": { + "0": { + "transformers": "PLBartModel" + } + } + } + }, + "info.vit.poolformer-s12": { + "*": { + "repo": "sail/poolformer_s12", + "pkg": { + "0": { + "transformers": "PoolFormerModel" + } + } + } + }, + "info.vit.pvt-v2-b0": { + "*": { + "repo": "OpenGVLab/pvt_v2_b0", + "pkg": { + "0": { + "transformers": "PvtV2Model" + } + } + } + }, + "info.vit.qwen2-vl": { + "*": { + "repo": "Qwen/Qwen2-VL-7B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen2_5_VLModel" + } + } + } + }, + "info.aet.qwen2-audio": { + "*": { + "repo": "Qwen/Qwen2-Audio-7B", + "pkg": { + "0": { + "transformers": "Qwen2AudioEncoder" + } + } + } + }, + "info.vit.qwen3-vl": { + "*": { + "repo": "Qwen/Qwen3-VL-4B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLModel" + } + } + } + }, + "info.vit.qwen3-vl-a": { + "*": { + "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLMoeModel" + } + } + } + }, + "info.art.reformer-crime-and-punishment": { + "*": { + "repo": "google/reformer-crime-and-punishment", + "pkg": { + "0": { + "transformers": "ReformerModel" + } + } + } + }, + "info.vit.regnet-y-040": { + "*": { + "repo": "facebook/regnet-y-040", + "pkg": { + "0": { + "transformers": "RegNetModel" + } + } + } + }, + "info.art.rembert": { + "*": { + "repo": "google/rembert", + "pkg": { + "0": { + "transformers": "RemBertModel" + } + } + } + }, + "info.vit.resnet-50": { + "*": { + "repo": "microsoft/resnet-50", + "pkg": { + "0": { + "transformers": "ResNetModel" + } + } + } + }, + "info.art.roberta": { + "*": { + "repo": "FacebookAI/roberta-base", + "pkg": { + "0": { + "transformers": "RobertaModel" + } + } + } + }, + "info.art.efficient-mlm-m0-0": { + "*": { + "repo": "andreasmadsen/efficient_mlm_m0.40", + "pkg": { + "0": { + "transformers": "RobertaPreLayerNormModel" + } + } + } + }, + "info.art.roc-bert-zh": { + "*": { + "repo": "weiweishi/roc-bert-base-zh", + "pkg": { + "0": { + "transformers": "RoCBertModel" + } + } + } + }, + "info.art.roformer-chinese": { + "*": { + "repo": "junnyu/roformer_chinese_base", + "pkg": { + "0": { + "transformers": "RoFormerModel" + } + } + } + }, + "info.detr.rtdetr-r50vd": { + "*": { + "repo": "PekingU/rtdetr_r50vd", + "pkg": { + "0": { + "transformers": "RTDetrModel" + } + } + } + }, + "info.detr.rtdetr-r18vd": { + "*": { + "repo": "PekingU/rtdetr_r18vd", + "pkg": { + "0": { + "transformers": "RTDetrV2Model" + } + } + } + }, + "info.rnn.rwkv-4-pile": { + "*": { + "repo": "RWKV/rwkv-4-169m-pile", + "pkg": { + "0": { + "transformers": "RwkvModel" + } + } + } + }, + "info.vit.sam-vit-huge": { + "*": { + "repo": "facebook/sam-vit-huge", + "pkg": { + "0": { + "transformers": "SamModel" + } + } + } + }, + "info.vit.sam2-hiera": { + "*": { + "repo": "facebook/sam2.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "Sam2Model" + } + } + } + }, + "info.vit.sam3": { + "*": { + "repo": "facebook/sam3", + "pkg": { + "0": { + "transformers": "Sam3Model" + } + } + } + }, + "info.vit.sam3-tracker1-hiera": { + "*": { + "repo": "facebook/sam3_tracker.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "Sam3TrackerModel" + } + } + } + }, + "info.stst.sam3": { + "*": { + "repo": "facebook/sam3", + "pkg": { + "0": { + "transformers": "Sam3VideoModel" + } + } + } + }, + "info.vit.sam-hq-vit-h": { + "*": { + "repo": "sushmanth/sam_hq_vit_h", + "pkg": { + "0": { + "transformers": "SamHQModel" + } + } + } + }, + "info.vit.sam-hq-vit-huge": { + "*": { + "repo": "syscv-community/sam-hq-vit-huge", + "pkg": { + "0": { + "transformers": "SamHQVisionModel" + } + } + } + }, + "info.aet.hf-seamless-m4t": { + "*": { + "repo": "facebook/hf-seamless-m4t-medium", + "pkg": { + "0": { + "transformers": "SeamlessM4TModel" + } + } + } + }, + "info.stst.seamless-m4t-v2": { + "*": { + "repo": "facebook/seamless-m4t-v2-large", + "pkg": { + "0": { + "transformers": "SeamlessM4Tv2Model" + } + } + } + }, + "info.vit.segformer-b0-finetuned-ade-512-512": { + "*": { + "repo": "nvidia/segformer-b0-finetuned-ade-512-512", + "pkg": { + "0": { + "transformers": "SegformerModel" + } + } + } + }, + "info.vit.seggpt-vit": { + "*": { + "repo": "BAAI/seggpt-vit-large", + "pkg": { + "0": { + "transformers": "SegGptModel" + } + } + } + }, + "info.aet.sew": { + "*": { + "repo": "asapp/sew-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWModel" + } + } + } + }, + "info.aet.sew-d": { + "*": { + "repo": "asapp/sew-d-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWDModel" + } + } + } + }, + "info.vit.siglip2-patch16-224": { + "*": { + "repo": "google/siglip2-base-patch16-224", + "pkg": { + "0": { + "transformers": "Siglip2Model" + } + } + } + }, + "info.vit.siglip2-patch16-naflex": { + "*": { + "repo": "google/siglip2-base-patch16-naflex", + "pkg": { + "0": { + "transformers": "Siglip2VisionModel" + } + } + } + }, + "info.vit.smolvlm": { + "*": { + "repo": "HuggingFaceTB/SmolVLM2-2.2B-Instruct", + "pkg": { + "0": { + "transformers": "SmolVLMModel" + } + } + } + }, + "info.vit.siglip-so-patch14-384": { + "*": { + "repo": "google/siglip-so400m-patch14-384", + "pkg": { + "0": { + "transformers": "SmolVLMVisionTransformer" + } + } + } + }, + "info.aet.s2t-librispeech-asr": { + "*": { + "repo": "facebook/s2t-small-librispeech-asr", + "pkg": { + "0": { + "transformers": "Speech2TextModel" + } + } + } + }, + "info.stst.speecht5-asr": { + "*": { + "repo": "microsoft/speecht5_asr", + "pkg": { + "0": { + "transformers": "SpeechT5Model" + } + } + } + }, + "info.art.splinter": { + "*": { + "repo": "tau/splinter-base", + "pkg": { + "0": { + "transformers": "SplinterModel" + } + } + } + }, + "info.art.squeezebert-uncased": { + "*": { + "repo": "squeezebert/squeezebert-uncased", + "pkg": { + "0": { + "transformers": "SqueezeBertModel" + } + } + } + }, + "info.vit.swiftformer-xs": { + "*": { + "repo": "MBZUAI/swiftformer-xs", + "pkg": { + "0": { + "transformers": "SwiftFormerModel" + } + } + } + }, + "info.vit.swin2sr-classicalsr-x2-64": { + "*": { + "repo": "caidas/swin2sr-classicalsr-x2-64", + "pkg": { + "0": { + "transformers": "Swin2SRModel" + } + } + } + }, + "info.vit.swinv2-patch4-window8-256": { + "*": { + "repo": "microsoft/swinv2-tiny-patch4-window8-256", + "pkg": { + "0": { + "transformers": "Swinv2Model" + } + } + } + }, + "info.stst.switch-8": { + "*": { + "repo": "google/switch-base-8", + "pkg": { + "0": { + "transformers": "SwitchTransformersModel" + } + } + } + }, + "info.stst.t5": { + "*": { + "repo": "google-t5/t5-small", + "pkg": { + "0": { + "transformers": "T5Model" + } + } + } + }, + "info.detr.table-transformer-detection": { + "*": { + "repo": "microsoft/table-transformer-detection", + "pkg": { + "0": { + "transformers": "TableTransformerModel" + } + } + } + }, + "info.art.tapas-finetuned-sqa": { + "*": { + "repo": "google/tapas-base-finetuned-sqa", + "pkg": { + "0": { + "transformers": "TapasModel" + } + } + } + }, + "info.vit.textnet": { + "*": { + "repo": "czczup/textnet-base", + "pkg": { + "0": { + "transformers": "TextNetModel" + } + } + } + }, + "info.vit.timesformer-finetuned-k600": { + "*": { + "repo": "facebook/timesformer-base-finetuned-k600", + "pkg": { + "0": { + "transformers": "TimesformerModel" + } + } + } + }, + "info.detr.tvp": { + "*": { + "repo": "Intel/tvp-base", + "pkg": { + "0": { + "transformers": "TvpModel" + } + } + } + }, + "info.vit.udop": { + "*": { + "repo": "microsoft/udop-large", + "pkg": { + "0": { + "transformers": "UdopModel" + } + } + } + }, + "info.stst.umt5": { + "*": { + "repo": "google/umt5-small", + "pkg": { + "0": { + "transformers": "UMT5Model" + } + } + } + }, + "info.aet.unispeech-1500h-cv": { + "*": { + "repo": "microsoft/unispeech-large-1500h-cv", + "pkg": { + "0": { + "transformers": "UniSpeechModel" + } + } + } + }, + "info.aet.unispeech-sat-100h-libri-ft": { + "*": { + "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "pkg": { + "0": { + "transformers": "UniSpeechSatModel" + } + } + } + }, + "info.gan.univnet-dev": { + "*": { + "repo": "dg845/univnet-dev", + "pkg": { + "0": { + "transformers": "UnivNetModel" + } + } + } + }, + "info.vit.videollama3-image-hf": { + "*": { + "repo": "lkhl/VideoLLaMA3-2B-Image-HF", + "pkg": { + "0": { + "transformers": "VideoLlama3Model" + } + } + } + }, + "info.vit.video-llava-hf": { + "*": { + "repo": "LanguageBind/Video-LLaVA-7B-hf", + "pkg": { + "0": { + "transformers": "VideoLlavaModel" + } + } + } + }, + "info.vit.videomae": { + "*": { + "repo": "MCG-NJU/videomae-base", + "pkg": { + "0": { + "transformers": "VideoMAEModel" + } + } + } + }, + "info.vit.vilt-b32-mlm": { + "*": { + "repo": "dandelin/vilt-b32-mlm", + "pkg": { + "0": { + "transformers": "ViltModel" + } + } + } + }, + "info.vit.vip-llava-hf": { + "*": { + "repo": "ybelkada/vip-llava-7b-hf", + "pkg": { + "0": { + "transformers": "VipLlavaModel" + } + } + } + }, + "info.vit.japanese-clip-vit-h-14-bert-wider": { + "*": { + "repo": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", + "pkg": { + "0": { + "transformers": "VisionTextDualEncoderModel" + } + } + } + }, + "info.art.visualbert-vqa-coco-pre": { + "*": { + "repo": "uclanlp/visualbert-vqa-coco-pre", + "pkg": { + "0": { + "transformers": "VisualBertModel" } } - }, - "bert-for-seq-generation-l-24-bbc-encoder": { + } + }, + "info.vit.vit-patch16-224": { + "*": { + "repo": "google/vit-base-patch16-224", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "20": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "21": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "22": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViTModel" } } - }, - "grounding-dino": { + } + }, + "info.vit.vit-mae": { + "*": { + "repo": "facebook/vit-mae-base", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViTMAEModel" } } - }, - "xlm-roberta-xl": { + } + }, + "info.vit.vit-msn": { + "*": { + "repo": "facebook/vit-msn-base", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViTMSNModel" } } } }, - "info.aet.funnel": { + "info.vit.vitdet-patch16-224": { "*": { - "repo": "funnel-transformer/small", + "repo": "google/vitdet-base-patch16-224", "pkg": { "0": { - "transformers": "FunnelModel" + "transformers": "VitDetModel" } } } }, - "info.stst.nllb-moe": { + "info.art.mms-tts-eng": { "*": { - "repo": "facebook/nllb-moe-54b", + "repo": "facebook/mms-tts-eng", "pkg": { "0": { - "transformers": "NllbMoeModel" + "transformers": "VitsModel" } } } }, - "info.art.deberta-v2-x": { + "info.vit.vivit16x2-kinetics400": { "*": { - "repo": "microsoft/deberta-v2-xlarge", + "repo": "google/vivit-b-16x2-kinetics400", "pkg": { "0": { - "transformers": "DebertaV2Model" + "transformers": "VivitModel" } } } }, - "info.art.xlm-roberta": { + "info.vit.vjepa2-vitl-fpc64-256": { "*": { - "repo": "FacebookAI/xlm-roberta-base", + "repo": "facebook/vjepa2-vitl-fpc64-256", "pkg": { "0": { - "transformers": "XLMRobertaModel" + "transformers": "VJEPA2Model" } } } }, - "info.art.gpt2": { + "info.stst.voxtral-2507": { "*": { - "repo": "openai-community/gpt2", + "repo": "mistralai/Voxtral-Mini-3B-2507", "pkg": { "0": { - "transformers": "GPT2Model" + "transformers": "VoxtralForConditionalGeneration" } } } }, - "info.art.megatron-bert-uncased": { + "info.aet.voxtral-2507": { "*": { - "repo": "nvidia/megatron-bert-uncased-345m", + "repo": "mistralai/Voxtral-Mini-3B-2507", "pkg": { "0": { - "transformers": "MegatronBertModel" + "transformers": "VoxtralEncoder" } } } }, - "info.stst.blenderbot": { + "info.aet.wav2vec2-960h": { "*": { - "repo": "facebook/blenderbot_small-90M", + "repo": "facebook/wav2vec2-base-960h", "pkg": { "0": { - "transformers": "BlenderbotSmallModel" + "transformers": "Wav2Vec2Model" } } } }, - "info.detr.omdet-turbo-swin-hf": { + "info.aet.wav2vec2-bert-rel-pos": { "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", + "repo": "facebook/w2v-bert-2.0", "pkg": { "0": { - "transformers": "OmDetTurboForObjectDetection" + "transformers": "Wav2Vec2BertModel" } } } }, - "info.vit.ast-finetuned-audioset-10-10-0593": { + "info.aet.wav2vec2-conformer-rel-pos": { "*": { - "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "repo": "facebook/wav2vec2-conformer-rel-pos-large", "pkg": { "0": { - "transformers": "ASTModel" + "transformers": "Wav2Vec2ConformerModel" } } } }, - "info.vit.mgp-str": { + "info.aet.wavlm": { "*": { - "repo": "alibaba-damo/mgp-str-base", + "repo": "microsoft/wavlm-base", "pkg": { "0": { - "transformers": "MgpstrForSceneTextRecognition" + "transformers": "WavLMModel" } } } }, - "info.vit.blip2-opt": { + "info.aet.whisper": { "*": { - "repo": "Salesforce/blip2-opt-2.7b", + "repo": "openai/whisper-tiny", "pkg": { "0": { - "transformers": "Blip2Model" + "transformers": "WhisperModel" } } } }, - "info.art.efficient-mlm-m0-0": { + "info.vit.xclip-patch32": { "*": { - "repo": "andreasmadsen/efficient_mlm_m0.40", + "repo": "microsoft/xclip-base-patch32", "pkg": { "0": { - "transformers": "RobertaPreLayerNormModel" + "transformers": "XCLIPModel" } } } }, - "info.aet.wav2vec2-conformer-rel-pos": { + "info.art.xglm": { "*": { - "repo": "facebook/wav2vec2-conformer-rel-pos-large", + "repo": "facebook/xglm-564M", "pkg": { "0": { - "transformers": "Wav2Vec2ConformerModel" + "transformers": "XGLMModel" } } } }, - "info.aet.unispeech-sat-100h-libri-ft": { + "info.art.xlm-mlm-en-2048": { "*": { - "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "repo": "FacebookAI/xlm-mlm-en-2048", "pkg": { "0": { - "transformers": "UniSpeechSatModel" + "transformers": "XLMModel" } } } }, - "info.detr.table-transformer-detection": { + "info.art.xlm-roberta": { "*": { - "repo": "microsoft/table-transformer-detection", + "repo": "FacebookAI/xlm-roberta-base", "pkg": { "0": { - "transformers": "TableTransformerModel" + "transformers": "XLMRobertaModel" } } } }, - "info.detr.dab-detr": { + "info.art.xlm-roberta-xl": { "*": { - "repo": "IDEA-Research/dab-detr-resnet-50", + "repo": "facebook/xlm-roberta-xl", "pkg": { "0": { - "transformers": "DabDetrModel" + "transformers": "XLMRobertaXLModel" } } } }, - "info.aet.wav2vec2-bert-rel-pos": { + "info.art.xlnet-cased": { "*": { - "repo": "facebook/w2v-bert-2.0", + "repo": "xlnet/xlnet-large-cased", "pkg": { "0": { - "transformers": "Wav2Vec2BertModel" + "transformers": "XLNetModel" } } } }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "info.lstm.xlstm": { "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "repo": "NX-AI/xLSTM-7b", "pkg": { "0": { - "transformers": "MMGroundingDinoModel" + "transformers": "xLSTMModel" } } } }, - "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "info.art.xmod": { "*": { - "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "repo": "facebook/xmod-base", "pkg": { "0": { - "transformers": "BertGenerationEncoder" + "transformers": "XmodModel" } } } }, - "info.detr.grounding-dino": { + "info.cnn.yolos": { "*": { - "repo": "IDEA-Research/grounding-dino-tiny", + "repo": "hustvl/yolos-base", "pkg": { "0": { - "transformers": "GroundingDinoModel" + "transformers": "YolosModel" } } } }, - "info.art.xlm-roberta-xl": { + "info.art.yoso-4096": { "*": { - "repo": "facebook/xlm-roberta-xl", + "repo": "uw-madison/yoso-4096", "pkg": { "0": { - "transformers": "XLMRobertaXLModel" + "transformers": "YosoModel" } } } }, - "info.aet.sew-d": { + "info.ssm.zamba-v1": { "*": { - "repo": "asapp/sew-d-tiny-100k", + "repo": "Zyphra/Zamba-7B-v1", "pkg": { "0": { - "transformers": "SEWDModel" + "transformers": "ZambaModel" } } } @@ -4389,6 +6846,111 @@ ] } }, + "info.dit.flux1-dev": { + "mystic": { + "repo": "enhanceaiteam/Mystic", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 16, + "guidance_scale": 7.5, + "width": 768, + "height": 1024 + } + } + }, + "file_256": [ + "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", + "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" + ], + "layer_256": [ + "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" + ], + "layer_b3": [ + "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" + ] + }, + "flux1-lite": { + "repo": "freepik/flux.1-lite-8b", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 28 + } + } + }, + "file_256": [ + "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", + "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" + ], + "layer_256": [ + "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" + ], + "layer_b3": [ + "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" + ] + }, + "f-lite": { + "repo": "freepik/f-lite", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "f-lite-texture": { + "repo": "freepik/f-lite-texture", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "flux": { + "repo": "TencentARC/flux-mini", + "file_256": [ + "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" + ], + "layer_256": [ + "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" + ], + "layer_b3": [ + "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" + ] + }, + "flex2": { + "repo": "ostris/Flex.2-preview", + "file_256": [ + "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", + "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" + ], + "layer_256": [ + "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" + ], + "layer_b3": [ + "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" + ] + }, + "flex1-alpha": { + "repo": "ostris/Flex.1-alpha", + "file_256": [ + "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", + "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" + ], + "layer_256": [ + "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" + ], + "layer_b3": [ + "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" + ] + } + }, "info.dit.wan2-flf2v-720p": { "diffusers": { "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", diff --git a/mir/spec/template.json b/mir/spec/template.json index 1381e19..8479db5 100644 --- a/mir/spec/template.json +++ b/mir/spec/template.json @@ -80,6 +80,7 @@ "act_dropout", "max_source_positions", "classifier_pooling", + "ctc_loss_reduction", "audio_video_config", "video_config" ], diff --git a/mir/tag.py b/mir/tag.py index 7b272fe..fc95b7a 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -94,9 +94,12 @@ def tag_base_model(repo_path: str, class_name: str, addendum: dict | None = None :param class_name: The HF transformers class for the model :return: A segmented MIR tag useful for appending index entries""" - from mir.inspect.classes import extract_init_params + from mir.config.constants import extract_init_params - annotations = extract_init_params(class_name.replace("Model", "Config"), "transformers") # remove default annotations from python + annotations = extract_init_params(class_name.replace("Model", "Config"), "transformers") + if not annotations: + class_name = class_name.replace("Config", "Model") + annotations = extract_init_params(class_name, "transformers") if not annotations: raise TypeError("No mode type returned") mir_prefix = mir_prefix_from_forward_pass(True, **annotations) From fb8eebe9b6a8ea979b81cf093de00631a0458acf Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sun, 11 Jan 2026 23:06:29 -0500 Subject: [PATCH 04/16] ~mir gen complete --- mir.json | 10880 +++++++++++++++++++++++++++------ mir/config/constants.py | 31 +- mir/indexers.py | 11 +- mir/inspect/metadata.py | 2 +- mir/inspect/pipes.py | 4 +- mir/mir.json | 8600 ++++++++++++++++++++++++-- mir/spec/missing_params.json | 13 +- mir/spec/template.json | 9 +- mir/tag.py | 6 +- 9 files changed, 17019 insertions(+), 2537 deletions(-) diff --git a/mir.json b/mir.json index c73a611..c897555 100644 --- a/mir.json +++ b/mir.json @@ -49,6 +49,16 @@ } } }, + "info.controlnet.stable-diffusion-xl-1": { + "*": { + "repo": "stabilityai/stable-diffusion-xl-base-1.0", + "pkg": { + "0": { + "diffusers": "StableDiffusionXLControlNetUnionInpaintPipeline" + } + } + } + }, "info.controlnet.controlnet-union-sdxl-1": { "*": { "repo": "xinsir/controlnet-union-sdxl-1.0", @@ -99,6 +109,105 @@ } } }, + "info.unet.marigold-depth-v1-1": { + "*": { + "repo": "prs-eth/marigold-depth-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldDepthPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-depth-v1-1" + ] + } + } + }, + "info.unet.marigold-iid-appearance-v1-1": { + "*": { + "repo": "prs-eth/marigold-iid-appearance-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldIntrinsicsPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-iid-appearance-v1-1" + ] + } + } + }, + "info.unet.marigold-normals-v1-1": { + "*": { + "repo": "prs-eth/marigold-normals-v1-1", + "pkg": { + "0": { + "diffusers": "MarigoldNormalsPipeline" + } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-normals-v1-1" + ] + } + } + }, "info.unet.stable-diffusion-v1-5": { "*": { "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", @@ -107,6 +216,32 @@ "diffusers": "StableDiffusionPipeline" } }, + "identifiers": [ + "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" + ], + "file_256": [ + "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", + "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", + "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", + "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", + "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", + "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", + "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" + ], + "layer_b3": [ + "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", + "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", + "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", + "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" + ], + "layer_256": [ + "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", + "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", + "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" + ], "tasks": [ "StableDiffusion3ControlNetInpaintingPipeline", "StableDiffusion3ControlNetPipeline", @@ -146,7 +281,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -161,10 +296,11 @@ "StableDiffusionSafetyChecker" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ] } @@ -218,7 +354,7 @@ "stable-unclip-2-1-l" ], "prior_text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "prior": [ @@ -229,7 +365,8 @@ "schedulers" ], "image_normalizer": [ - "StableUnCLIPImageNormalizer" + "info.dit.flux1-schnell", + "*" ], "image_noising_scheduler": [ "ops.scheduler.karrasdiffusion", @@ -240,7 +377,7 @@ "stable-unclip-2-1-l" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "scheduler": [ @@ -297,14 +434,16 @@ ], "pipe_names": { "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "image_normalizer": [ - "StableUnCLIPImageNormalizer" + "info.dit.flux1-schnell", + "*" ], "image_noising_scheduler": [ "ops.scheduler.karrasdiffusion", @@ -315,7 +454,7 @@ "stable-diffusion-2-1-unclip" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "scheduler": [ @@ -333,59 +472,42 @@ "repo": "stabilityai/stable-diffusion-xl-base-1.0", "pkg": { "0": { - "diffusers": "StableDiffusionXLPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "denoising_end": 0.8, + "num_inference_steps": 40, + "output_type": "latent", + "safety_checker": false, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" } }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" + "file_256": [ + "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", + "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", + "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", + "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" ], - "pipe_names": { - "vae": [ - "info.vae.eq", - "info.vae.ms-lc-eq", - "stable-diffusion-xl-1" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-1" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-1" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - } + "layer_256": [ + "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", + "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", + "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" + ], + "layer_b3": [ + "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", + "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", + "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" + ], + "identifiers": [ + "logit_scale", + "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", + "add_embedding.linear_2.bias" + ], + "pipe_names": {} }, "pony-diffusion": { "file_256": [ @@ -543,8 +665,33 @@ "pkg": { "0": { "diffusers": "StableDiffusionXLImg2ImgPipeline" + }, + "1": { + "diffusers": "DiffusionPipeline", + "generation": { + "num_inference_steps": 40, + "denoising_end": 0.8 + } } }, + "identifiers": [ + "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" + ], + "file_256": [ + "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", + "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", + "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" + ], + "layer_b3": [ + "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", + "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", + "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" + ], + "layer_256": [ + "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", + "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", + "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" + ], "tasks": [ "StableDiffusionXLControlNetImg2ImgPipeline", "StableDiffusionXLControlNetInpaintPipeline", @@ -566,11 +713,11 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -586,11 +733,12 @@ "schedulers" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -624,11 +772,11 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -651,29 +799,23 @@ "repo": "rhymes-ai/Allegro", "pkg": { "0": { - "diffusers": "AllegroPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "guidance_scale": 7.5, + "max_sequence_length": 512, + "num_inference_steps": 100 + } } }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "allegro" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "allegro" - ], - "transformer": [ - "AllegroTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } + "file_256": [ + "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" + ], + "layer_b3": [ + "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" + ], + "layer_256": [ + "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" + ] } }, "info.dit.amused-512": { @@ -693,7 +835,7 @@ "amused-512" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "transformer": [ @@ -716,6 +858,16 @@ } } }, + "info.lora.animatelcm": { + "*": { + "repo": "wangfuyun/AnimateLCM", + "pkg": { + "0": { + "diffusers": "MotionAdapter" + } + } + } + }, "info.lora.animatediff-motion-adapter-sdxl": { "*": { "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", @@ -772,18 +924,20 @@ "AutoencoderKL" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "bria-3" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -806,7 +960,8 @@ "audioldm-s-v2" ], "text_encoder": [ - "Mistral3ForConditionalGeneration" + "info.vit.mistral-3-2503", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -823,70 +978,69 @@ "repo": "black-forest-labs/FLUX.1-schnell", "pkg": { "0": { - "diffusers": "FluxInpaintPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 0.0, + "num_inference_steps": 4, + "max_sequence_length": 256 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "num_inference_steps": 4 + } } }, + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ], + "file_256": [ + "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", + "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" + ], + "layer_b3": [ + "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", + "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", + "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" + ], + "layer_256": [ + "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", + "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", + "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" + ], "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-schnell" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-schnell" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - } - }, - "shuttle-3-aesthetic": { - "repo": "shuttleai/shuttle-3.1-aesthetic", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", - "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" + "Image", + "Redux", + "Kontext", + "Depth", + "Fill", + "ConceptAttention", + "ControlNet", + "CavTon", + "IC-Edit" + ] + }, + "shuttle-3-aesthetic": { + "repo": "shuttleai/shuttle-3.1-aesthetic", + "pkg": { + "2": { + "diffusers": "DiffusionPipeline", + "generation": { + "guidance_scale": 3.5, + "num_inference_steps": 4 + } + } + }, + "file_256": [ + "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", + "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" ], "layer_256": [ "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", @@ -956,6 +1110,16 @@ } } }, + "info.controlnet.flux1-depth-dev": { + "*": { + "repo": "black-forest-labs/FLUX.1-Depth-dev", + "pkg": { + "0": { + "diffusers": "FluxControlInpaintPipeline" + } + } + } + }, "info.controlnet.flux1-dev-controlnet-canny": { "*": { "repo": "InstantX/FLUX.1-dev-controlnet-canny", @@ -1005,7 +1169,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -1013,7 +1177,8 @@ "flux1-fill-dev" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", @@ -1054,7 +1219,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -1062,7 +1227,8 @@ "flux1-kontext-dev" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", @@ -1072,172 +1238,14 @@ "FluxTransformer2DModel" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" - ] - } - } - }, - "info.dit.flux1-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-dev", - "pkg": { - "0": { - "diffusers": "FluxPipeline" - } - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-dev" - ], - "text_encoder_2": [ - "T5EncoderModel" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.dit.flux1-schnell", "*" - ], - "feature_extractor": [ - "CLIPImageProcessor" ] } - }, - "mystic": { - "repo": "enhanceaiteam/Mystic", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 16, - "guidance_scale": 7.5, - "width": 768, - "height": 1024 - } - } - }, - "file_256": [ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" - ], - "layer_256": [ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" - ], - "layer_b3": [ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" - ] - }, - "flux1-lite": { - "repo": "freepik/flux.1-lite-8b", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 28 - } - } - }, - "file_256": [ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" - ], - "layer_256": [ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" - ], - "layer_b3": [ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" - ] - }, - "f-lite": { - "repo": "freepik/f-lite", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "f-lite-texture": { - "repo": "freepik/f-lite-texture", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "flux": { - "repo": "TencentARC/flux-mini", - "file_256": [ - "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" - ], - "layer_256": [ - "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" - ], - "layer_b3": [ - "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" - ] - }, - "flex2": { - "repo": "ostris/Flex.2-preview", - "file_256": [ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" - ], - "layer_256": [ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" - ], - "layer_b3": [ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" - ] - }, - "flex1-alpha": { - "repo": "ostris/Flex.1-alpha", - "file_256": [ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" - ], - "layer_256": [ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" - ], - "layer_b3": [ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" - ] } }, "info.dit.prx-512-t2i-sft": { @@ -1257,7 +1265,8 @@ "discrete" ], "text_encoder": [ - "T5GemmaEncoder" + "info.stst.t5gemma-prefixlm", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1282,12 +1291,22 @@ "diffusers": "AudioLDMPipeline" } }, + "file_256": [ + "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ], "pipe_names": { "vae": [ "AutoencoderKL" ], "text_encoder": [ - "ClapTextModelWithProjection" + "info.vit.clap-htsat-fused", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1298,7 +1317,8 @@ "schedulers" ], "vocoder": [ - "SpeechT5HifiGan" + "info.stst.speecht5-asr", + "*" ] } } @@ -1308,49 +1328,22 @@ "repo": "cvssp/audioldm2", "pkg": { "0": { - "diffusers": "AudioLDM2Pipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } } }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ClapModel" - ], - "text_encoder_2": [ - "T5EncoderModel", - "VitsModel" - ], - "projection_model": [ - "AudioLDM2ProjectionModel" - ], - "language_model": [ - "info.art.gpt2", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "audioldm2" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "audioldm2" - ], - "feature_extractor": [ - "ClapFeatureExtractor" - ], - "unet": [ - "AudioLDM2UNet2DConditionModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "SpeechT5HifiGan" - ] - } + "file_256": [ + "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" + ], + "layer_b3": [ + "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" + ], + "layer_256": [ + "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" + ] } }, "info.unet.blipdiffusion": { @@ -1367,7 +1360,7 @@ "blipdiffusion" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "vae": [ @@ -1382,7 +1375,8 @@ "*" ], "image_processor": [ - "BlipImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -1393,8 +1387,30 @@ "pkg": { "0": { "diffusers": "ChromaPipeline" + }, + "1": { + "generation": { + "neg_text": "", + "num_steps": "28", + "latent_size": [ + 64, + 64 + ] + } } }, + "file_256": [ + "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", + "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", + "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", + "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" + ], + "layer_b3": [ + "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" + ], + "layer_256": [ + "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" + ], "tasks": [ "ChromaPipeline" ], @@ -1407,7 +1423,8 @@ "AutoencoderKL" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1417,11 +1434,12 @@ "ChromaTransformer2DModel" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } }, @@ -1469,7 +1487,8 @@ "AutoencoderKL" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1479,11 +1498,12 @@ "ChromaTransformer2DModel" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -1508,7 +1528,8 @@ "AutoencoderKL" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1518,11 +1539,12 @@ "ChromaTransformer2DModel" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -1532,35 +1554,24 @@ "repo": "zai-org/CogVideoX-2b", "pkg": { "0": { - "diffusers": "CogVideoXPipeline" - } + "precision": "ops.precision.float.F16", + "generation": { + "num_videos_per_prompt": 1, + "num_inference_steps": 50, + "num_frames": 49, + "guidance_scale": 6 + } + } }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogvideox" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "transformer": [ - "CogVideoXTransformer3DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - } + "file_256": [ + "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" + ], + "layer_b3": [ + "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" + ], + "layer_256": [ + "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" + ] } }, "info.controlnet.cogvideox-fun-v-pose": { @@ -1587,7 +1598,8 @@ "cogvideox-i2v" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "vae": [ "info.vae.cogvideox", @@ -1614,36 +1626,15 @@ "repo": "zai-org/CogView3-Plus-3B", "pkg": { "0": { - "diffusers": "CogView3PlusPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "guidance_scale": 7.0, + "num_images_per_prompt": 1, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } } - }, - "tasks": [ - "CogView3PlusPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogview3" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "CogView3PlusTransformer2DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] } } }, @@ -1665,7 +1656,8 @@ "cogview4" ], "text_encoder": [ - "GlmModel" + "info.stst.glm-4-chat", + "*" ], "vae": [ "AutoencoderKL" @@ -1700,7 +1692,8 @@ }, "pipe_names": { "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1731,9 +1724,55 @@ "diffusers": "Cosmos2TextToImagePipeline" } }, + "file_256": [ + "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", + "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", + "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", + "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", + "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", + "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", + "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", + "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", + "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", + "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", + "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", + "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", + "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" + ], + "layer_b3": [ + "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", + "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", + "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", + "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", + "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", + "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", + "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", + "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", + "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", + "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", + "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", + "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", + "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" + ], + "layer_256": [ + "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", + "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", + "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", + "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", + "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", + "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", + "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", + "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", + "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", + "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", + "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", + "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", + "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" + ], "pipe_names": { "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1766,7 +1805,8 @@ }, "pipe_names": { "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1799,7 +1839,8 @@ }, "pipe_names": { "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1832,7 +1873,8 @@ }, "pipe_names": { "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -1855,30 +1897,30 @@ } } }, - "info.unet.if-i-xl-v1": { + "info.unet.if-ii-l-v1": { "*": { - "repo": "DeepFloyd/IF-I-XL-v1.0", + "repo": "DeepFloyd/IF-II-L-v1.0", "pkg": { "0": { - "diffusers": "IFPipeline" + "diffusers": "IFSuperResolutionPipeline" } }, - "tasks": [ - "IFImg2ImgPipeline", - "IFInpaintingPipeline", - "IFPipeline" - ], "pipe_names": { "tokenizer": [ "info.encoder.tokenizer", - "if-i-xl-v1" + "if-ii-l-v1" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "scheduler": [ "ops.scheduler.ddpm", "scheduler" + ], + "image_noising_scheduler": [ + "ops.scheduler.ddpm", + "scheduler" ] } } @@ -1898,7 +1940,10 @@ ], "text_encoder": [ "Qwen2VLForConditionalGeneration", - "BertModel" + [ + "info.art.bert-uncased", + "*" + ] ], "tokenizer": [ "info.encoder.tokenizer", @@ -1939,7 +1984,10 @@ ], "text_encoder": [ "Qwen2VLForConditionalGeneration", - "BertModel" + [ + "info.art.bert-uncased", + "*" + ] ], "tokenizer": [ "info.encoder.tokenizer", @@ -1963,6 +2011,15 @@ "diffusers": "HiDreamImagePipeline" } }, + "file_256": [ + "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" + ], + "layer_b3": [ + "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" + ], + "layer_256": [ + "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" + ], "pipe_names": { "scheduler": [ "ops.scheduler.euler", @@ -1972,7 +2029,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -1980,7 +2037,7 @@ "hidream-i1" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -1988,21 +2045,24 @@ "hidream-i1" ], "text_encoder_3": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_3": [ "info.encoder.tokenizer", "hidream-i1" ], "text_encoder_4": [ - "LlamaForCausalLM" + "info.stst.llama-2-hf", + "*" ], "tokenizer_4": [ "info.encoder.tokenizer", "hidream-i1" ], "transformer": [ - "HiDreamImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2012,41 +2072,29 @@ "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", "pkg": { "0": { - "diffusers": "HunyuanDiTPipeline" + "precision": "ops.precision.float.F16" } }, - "tasks": [ - "HunyuanDiTPipeline" + "identifiers": [ + "extra_embedder", + "model.blocks", + "skip_norm.weight" ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "BertModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuandit-v1" - ], - "transformer": [ - "HunyuanDiT2DModel" - ], - "scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuandit-v1" - ] - } + "file_256": [ + "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", + "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", + "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" + ], + "layer_b3": [ + "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", + "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", + "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" + ], + "layer_256": [ + "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", + "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", + "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" + ] } }, "info.dit.hunyuanvideo": { @@ -2057,9 +2105,19 @@ "diffusers": "HunyuanVideoPipeline" } }, + "file_256": [ + "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" + ], + "layer_b3": [ + "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" + ], + "layer_256": [ + "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" + ], "pipe_names": { "text_encoder": [ - "LlamaModel" + "info.stst.llama-2-hf", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2077,7 +2135,7 @@ "discrete" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -2097,7 +2155,8 @@ }, "pipe_names": { "text_encoder": [ - "LlavaForConditionalGeneration" + "info.vit.llava", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2115,7 +2174,7 @@ "discrete" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -2123,7 +2182,8 @@ "hunyuanvideo-i2v" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -2138,7 +2198,8 @@ }, "pipe_names": { "text_encoder": [ - "Qwen2_5_VLTextModel" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2156,7 +2217,8 @@ "discrete" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", @@ -2178,7 +2240,8 @@ }, "pipe_names": { "text_encoder": [ - "Qwen2_5_VLTextModel" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2196,7 +2259,8 @@ "discrete" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", @@ -2209,7 +2273,8 @@ "SiglipVisionModel" ], "feature_extractor": [ - "SiglipImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -2232,21 +2297,24 @@ "audioldm-s-v2" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "hunyuanimage-2" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", "hunyuanimage-2" ], "transformer": [ - "HunyuanImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2269,14 +2337,16 @@ "audioldm-s-v2" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "hunyuanimage-2-refiner" ], "transformer": [ - "HunyuanImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2310,11 +2380,11 @@ "PriorTransformer" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -2326,7 +2396,8 @@ "scheduler" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -2336,35 +2407,19 @@ "repo": "kandinsky-community/kandinsky-2-2-prior", "pkg": { "0": { - "diffusers": "KandinskyPriorPipeline" + "diffusers": "KandinskyV22PriorPipeline" } }, - "tasks": [ - "Kandinsky3Img2ImgPipeline", - "Kandinsky3Pipeline", - "KandinskyCombinedPipeline", - "KandinskyImg2ImgCombinedPipeline", - "KandinskyImg2ImgPipeline", - "KandinskyInpaintCombinedPipeline", - "KandinskyInpaintPipeline", - "KandinskyPipeline", - "KandinskyV22CombinedPipeline", - "KandinskyV22Img2ImgCombinedPipeline", - "KandinskyV22Img2ImgPipeline", - "KandinskyV22InpaintCombinedPipeline", - "KandinskyV22InpaintPipeline", - "KandinskyV22Pipeline" - ], "pipe_names": { "prior": [ "PriorTransformer" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -2376,7 +2431,8 @@ "scheduler" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -2395,7 +2451,8 @@ "latte-1" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "vae": [ "AutoencoderKL" @@ -2428,7 +2485,8 @@ "ltx-video" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2458,7 +2516,8 @@ "ltx-video" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2475,32 +2534,24 @@ "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", "pkg": { "0": { - "diffusers": "LuminaPipeline" + "precision": " ops.precision.bfloat.B16" } }, - "tasks": [ - "Lumina2Pipeline", - "LuminaPipeline" + "identifiers": [ + "time_caption", + "feed_forward" ], - "pipe_names": { - "transformer": [ - "LuminaNextDiT2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "GemmaPreTrainedModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "lumina-next-sft" - ] - } + "file_256": [ + "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" + ], + "layer_b3": [ + "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", + "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" + ], + "layer_256": [ + "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", + "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" + ] } }, "info.dit.lumina-image-2": { @@ -2511,6 +2562,18 @@ "diffusers": "Lumina2Pipeline" } }, + "file_256": [ + "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", + "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" + ], + "layer_b3": [ + "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" + ], + "layer_256": [ + "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" + ], "tasks": [ "Lumina2Pipeline" ], @@ -2526,7 +2589,8 @@ "AutoencoderKL" ], "text_encoder": [ - "Gemma2PreTrainedModel" + "info.stst.gemma2", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2550,6 +2614,34 @@ ] } }, + "info.dit.lucy-edit-dev": { + "*": { + "repo": "decart-ai/Lucy-Edit-Dev", + "pkg": { + "0": { + "diffusers": "LucyEditPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "lucy-edit-dev" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, "info.dit.longcat-image": { "*": { "repo": "meituan-longcat/LongCat-Image", @@ -2567,7 +2659,8 @@ "AutoencoderKL" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2577,7 +2670,8 @@ "Qwen2VLProcessor" ], "transformer": [ - "LongCatImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2599,7 +2693,8 @@ "AutoencoderKL" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2609,7 +2704,8 @@ "Qwen2VLProcessor" ], "transformer": [ - "LongCatImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2632,7 +2728,8 @@ "mochi-1" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -2649,29 +2746,21 @@ "repo": "ucsd-reach/musicldm", "pkg": { "0": { - "diffusers": "MusicLDMPipeline" + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } } }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ClapTextModelWithProjection", - "ClapModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "musicldm" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "SpeechT5HifiGan" - ] - } + "file_256": [ + "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ] } }, "info.dit.omnigen-v1": { @@ -2720,14 +2809,16 @@ "AutoencoderKL" ], "text_encoder": [ - "Qwen3Model" + "info.stst.qwen3", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "ovis-image" ], "transformer": [ - "OvisImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -2749,7 +2840,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -2757,7 +2848,8 @@ "visualclozepipeline-384" ], "text_encoder_2": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "tokenizer_2": [ "info.encoder.tokenizer", @@ -2769,14 +2861,39 @@ } } }, - "info.dit.pixart-xl-2-1024-ms": { + "info.lora.pia-condition-adapter": { "*": { - "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", + "repo": "openmmlab/PIA-condition-adapter", + "pkg": { + "0": { + "diffusers": "PIAPipeline" + } + } + } + }, + "info.dit.pixart-xl-2-1024-ms": { + "*": { + "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", "pkg": { "0": { "diffusers": "PixArtAlphaPipeline" } }, + "identifiers": [ + "aspect_ratio", + "y_embedding", + "emb.resolution", + "caption_projection" + ], + "file_256": [ + "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" + ], + "layer_b3": [ + "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" + ], + "layer_256": [ + "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" + ], "tasks": [ "PixArtAlphaPipeline" ], @@ -2786,7 +2903,8 @@ "pixart-xl-2-1024-ms" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "vae": [ "AutoencoderKL" @@ -2809,6 +2927,22 @@ "diffusers": "PixArtSigmaPipeline" } }, + "identifiers": [ + "adaln_single", + "scale_shift_table" + ], + "file_256": [ + "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", + "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" + ], + "layer_b3": [ + "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", + "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" + ], + "layer_256": [ + "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", + "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" + ], "tasks": [ "PixArtAlphaPipeline", "PixArtSigmaPipeline" @@ -2819,7 +2953,8 @@ "pixart-sigma-xl-2-1024-ms" ], "text_encoder": [ - "T5EncoderModel" + "info.stst.t5", + "*" ], "vae": [ "AutoencoderKL" @@ -2839,33 +2974,24 @@ "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", "pkg": { "0": { - "diffusers": "SanaPipeline" + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 4.5, + "num_inference_steps": 20 + }, + "precision": "ops.precision.bfloat.B16" } }, - "tasks": [ - "SanaPAGPipeline", - "SanaPipeline" + "file_256": [ + "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-1024px-bf16" - ], - "text_encoder": [ - "Gemma2PreTrainedModel" - ], - "vae": [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "transformer": [ - "SanaTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } + "layer_b3": [ + "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" + ], + "layer_256": [ + "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" + ] } }, "info.controlnet.sana-1024px-controlnet": { @@ -2896,7 +3022,8 @@ "sana-sprint-1024px" ], "text_encoder": [ - "Gemma2PreTrainedModel" + "info.stst.gemma2", + "*" ], "vae": [ "info.vae.dc", @@ -2926,7 +3053,8 @@ "sana-video" ], "text_encoder": [ - "Gemma2PreTrainedModel" + "info.stst.gemma2", + "*" ], "vae": [ [ @@ -2953,28 +3081,13 @@ "repo": "openai/shap-e", "pkg": { "0": { - "diffusers": "ShapEPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 64, + "size": 256, + "guidance_scale": 15 + } } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "shap-e" - ], - "scheduler": [ - "ops.scheduler.heun", - "discrete" - ], - "shap_e_renderer": [ - "ShapERenderer" - ] } } }, @@ -2983,31 +3096,13 @@ "repo": "stabilityai/stable-audio-open-1.0", "pkg": { "0": { - "diffusers": "StableAudioPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_end_in_s": 10, + "num_waveforms_per_prompt": 3 + } } - }, - "pipe_names": { - "vae": [ - "info.vae.oobleck", - "stable-audio-open-1" - ], - "text_encoder": [ - "T5EncoderModel" - ], - "projection_model": [ - "StableAudioProjectionModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-audio-open-1" - ], - "transformer": [ - "StableAudioDiTModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] } } }, @@ -3016,60 +3111,85 @@ "repo": "stabilityai/stable-cascade-prior", "pkg": { "0": { - "diffusers": "StableCascadePriorPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "negative_prompt": "", + "num_images_per_prompt": 1, + "num_inference_steps": 20, + "guidance_scale": 4.0, + "width": 1024, + "height": 1024 + } } }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "stable-cascade" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "prior": [ - "StableCascadeUNet" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ] - } - } - }, - "info.unet.flux1-dev": { + "file_256": [ + "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", + "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", + "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", + "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", + "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", + "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" + ], + "layer_b3": [ + "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", + "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", + "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", + "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", + "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", + "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" + ], + "layer_256": [ + "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", + "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", + "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", + "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", + "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", + "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" + ], + "identifiers": [ + "down_blocks.0.2.kv_mapper", + "previewer", + "backbone" + ] + }, "decoder": { - "repo": "black-forest-labs/FLUX.1-dev", "pkg": { "0": { - "diffusers": "WuerstchenDecoderPipeline" + "generation": { + "negative_prompt": "", + "guidance_scale": 0.0, + "output_type": "pil", + "num_inference_steps": 10 + }, + "precision": "ops.precision.bfloat.B16" } }, - "tasks": [ - "WuerstchenCombinedPipeline", - "WuerstchenDecoderPipeline" + "file_256": [ + "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", + "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", + "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", + "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", + "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-dev" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "decoder": [ - "WuerstchenDiffNeXt" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ], - "vqgan": [ - "PaellaVQModel" - ] - } + "layer_b3": [ + "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", + "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", + "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", + "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", + "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" + ], + "layer_256": [ + "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", + "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", + "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", + "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", + "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" + ], + "identifiers": [ + "0.2.channelwise", + "clip_mapper.bias", + ".12.self_attn.k_proj.weight" + ] } }, "info.dit.auraflow": { @@ -3080,6 +3200,32 @@ "diffusers": "AuraFlowPipeline" } }, + "identifiers": [ + [ + 8192, + 3072 + ], + "mlpX.c_fc2.weight", + "joint_transformer_blocks.2.ff_context.linear_2.weight" + ], + "file_256": [ + "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", + "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", + "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", + "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" + ], + "layer_b3": [ + "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", + "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", + "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", + "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" + ], + "layer_256": [ + "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", + "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", + "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", + "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" + ], "tasks": [ "AuraFlowPipeline" ], @@ -3089,7 +3235,8 @@ "auraflow" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "vae": [ "AutoencoderKL" @@ -3109,60 +3256,27 @@ "repo": "stabilityai/stable-diffusion-3.5-medium", "pkg": { "0": { - "diffusers": "StableDiffusion3Pipeline" + "precision": "ops.precision.float.F16" } }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline" + "identifiers": [ + "model.diffusion_model.joint_blocks.", + "transformer_blocks.21.norm1_context.linear.weight", + "transformer_blocks.31.norm1_context.linear.weight", + "blocks.11.ff.net.2.weight" ], - "pipe_names": { - "transformer": [ - "SD3Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.tae", - "stable-diffusion-3" - ], - "text_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch14", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "text_encoder_3": [ - "T5EncoderModel" - ], - "tokenizer_3": [ - "info.encoder.tokenizer", - "stable-diffusion-3" - ], - "image_encoder": [ - "SiglipVisionModel" - ], - "feature_extractor": [ - "SiglipImageProcessor" - ] - } + "file_256": [ + "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", + "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" + ], + "layer_b3": [ + "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", + "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" + ], + "layer_256": [ + "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", + "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" + ] }, "stable-diffusion-3-turbo": { "repo": "tensorart/stable-diffusion-3.5-medium-turbo", @@ -3231,7 +3345,7 @@ "audioldm-s-v2" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "unet": [ @@ -3242,7 +3356,8 @@ "discrete" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -3294,7 +3409,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -3309,7 +3424,8 @@ "StableDiffusionSafetyChecker" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ] } } @@ -3327,7 +3443,7 @@ "AutoencoderKL" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer": [ @@ -3335,11 +3451,12 @@ "i2vgen-xl" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "feature_extractor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "unet": [ "I2VGenXLUNet" @@ -3369,7 +3486,7 @@ "wuerstchen" ], "text_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "prior": [ @@ -3387,31 +3504,43 @@ "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", "pkg": { "0": { - "diffusers": "WanPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } } }, - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" + "file_256": [ + "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", + "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", + "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", + "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", + "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", + "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", + "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", + "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan2-t2v" - ], - "text_encoder": [ - "UMT5EncoderModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } + "layer_b3": [ + "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", + "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", + "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", + "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", + "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", + "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", + "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" + ], + "layer_256": [ + "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", + "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", + "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", + "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", + "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", + "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", + "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" + ] } }, "info.dit.wan-animate": { @@ -3433,7 +3562,8 @@ "wan-animate" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "vae": [ "info.vae.kl", @@ -3444,10 +3574,11 @@ "multistep" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "transformer": [ @@ -3464,6 +3595,31 @@ "diffusers": "WanImageToVideoPipeline" } }, + "file_256": [ + "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", + "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", + "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", + "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", + "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", + "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", + "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", + "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", + "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" + ], + "layer_b3": [ + "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", + "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", + "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", + "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", + "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" + ], + "layer_256": [ + "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", + "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", + "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", + "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", + "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" + ], "tasks": [ "WanImageToVideoPipeline", "WanPipeline", @@ -3475,7 +3631,8 @@ "wan2-i2v-480p" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "vae": [ "info.vae.wan", @@ -3486,10 +3643,11 @@ "discrete" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "transformer": [ @@ -3509,6 +3667,25 @@ "diffusers": "WanVACEPipeline" } }, + "file_256": [ + "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", + "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", + "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", + "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", + "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" + ], + "layer_b3": [ + "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", + "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", + "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", + "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" + ], + "layer_256": [ + "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", + "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", + "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", + "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" + ], "tasks": [ "WanImageToVideoPipeline", "WanPipeline", @@ -3520,7 +3697,8 @@ "wan21-vace" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "vae": [ "info.vae.kl", @@ -3544,7 +3722,14 @@ "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", "pkg": { "0": { - "diffusers": "WanVideoToVideoPipeline" + "diffusers": "WanPipeline", + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } } }, "tasks": [ @@ -3558,10 +3743,8 @@ "wan21-t2v" ], "text_encoder": [ - "UMT5EncoderModel" - ], - "transformer": [ - "WanTransformer3DModel" + "info.stst.mt5", + "*" ], "vae": [ "info.vae.kl", @@ -3591,14 +3774,15 @@ "hunyuanvideo-i2v" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "kandinsky-5-t2v-lite-sft-5s" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -3628,14 +3812,15 @@ "AutoencoderKL" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "kandinsky-5-i2i-lite-sft" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -3666,14 +3851,15 @@ "hunyuanvideo-i2v" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "kandinsky-5-i2v-sft-5s" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -3703,14 +3889,15 @@ "AutoencoderKL" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "kandinsky-5-t2i-lite-sft" ], "text_encoder_2": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "tokenizer_2": [ @@ -3755,13 +3942,16 @@ "z-image-turbo" ], "transformer": [ - "ZImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ], "siglip": [ - "Siglip2VisionModel" + "info.vit.siglip2-patch16-224", + "*" ], "siglip_processor": [ - "Siglip2ImageProcessorFast" + "info.dit.flux1-schnell", + "*" ] } } @@ -3790,7 +3980,8 @@ "skyreels-v2-t2v-720p" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "transformer": [ "SkyReelsV2Transformer3DModel" @@ -3820,7 +4011,8 @@ "skyreels-v2-df-720p" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "transformer": [ "SkyReelsV2Transformer3DModel" @@ -3850,10 +4042,11 @@ "skyreels-v2-i2v-720p" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "image_processor": [ @@ -3881,6 +4074,15 @@ "diffusers": "QwenImageInpaintPipeline" } }, + "file_256": [ + "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" + ], + "layer_b3": [ + "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" + ], + "layer_256": [ + "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" + ], "tasks": [ "QwenImageControlNetPipeline", "QwenImageEditInpaintPipeline", @@ -3900,14 +4102,16 @@ "qwen-image" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", "qwen-image" ], "transformer": [ - "QwenImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -3959,7 +4163,8 @@ "qwen-image" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -3969,7 +4174,8 @@ "Qwen2VLProcessor" ], "transformer": [ - "QwenImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -4001,7 +4207,8 @@ "qwen-image" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -4011,7 +4218,8 @@ "Qwen2VLProcessor" ], "transformer": [ - "QwenImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -4043,7 +4251,8 @@ "qwen-image" ], "text_encoder": [ - "Qwen2_5_VLForConditionalGeneration" + "info.vit.qwen2-vl", + "*" ], "tokenizer": [ "info.encoder.tokenizer", @@ -4053,7 +4262,8 @@ "Qwen2VLProcessor" ], "transformer": [ - "QwenImageTransformer2DModel" + "info.dit.flux1-schnell", + "*" ] } } @@ -4072,14 +4282,16 @@ "chronoedit" ], "text_encoder": [ - "UMT5EncoderModel" + "info.stst.mt5", + "*" ], "image_encoder": [ - "info.vit.clip-vit-patch14", + "info.vit.clip-vit-patch32", "*" ], "image_processor": [ - "CLIPImageProcessor" + "info.dit.flux1-schnell", + "*" ], "transformer": [ "ChronoEditTransformer3DModel" @@ -4100,1078 +4312,7799 @@ "repo": "Kwai-Kolors/Kolors-diffusers", "pkg": { "0": { - "diffusers": "KolorsPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "negative_prompt": "", + "guidance_scale": 5.0, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" } }, - "tasks": [ - "KolorsImg2ImgPipeline", - "KolorsPAGPipeline", - "KolorsPipeline" + "file_256": [ + "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "ChatGLMModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kolors" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "info.vit.clip-vit-patch14", - "*" - ], - "feature_extractor": [ - "CLIPImageProcessor" - ] - } + "layer_b3": [ + "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" + ], + "layer_256": [ + "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" + ], + "identifiers": [ + ".DenseReluDense.wi.weight", + "encoder_hid_proj.weight" + ], + "pipe_names": {} + } + }, + "info.moe.trinity": { + "*": { + "repo": "arcee-ai/Trinity-Mini", + "pkg": { + "0": { + "transformers": "AfmoeModel" + } + }, + "tasks": [ + "AfmoeForCausalLM", + "AfmoeModel", + "AfmoePreTrainedModel" + ] } }, "info.encoder.tokenizer": { - "omdet-turbo-swin-hf": { + "aimv2-patch14-224-lit": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" } } }, - "blip2-opt": { + "albert-xx-v2": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" } } }, - "deberta-v2-x": { + "align": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "bert-for-seq-generation-l-24-bbc-encoder": { + "afm": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "20": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "21": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "22": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "wav2vec2-bert-rel-pos": { + "aria": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "nllb-moe": { + "audio-flamingo-3-hf": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" } } }, - "efficient-mlm-m0-0": { + "aya-vision": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" } } }, - "xlm-roberta": { + "bark": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "mgp-str": { + "bart": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" } } }, - "blenderbot": { + "bert-uncased": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "20": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "21": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "22": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "23": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "xlm-roberta-xl": { + "bert-for-seq-generation-l-24-bbc-encoder": { "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "transformers.models.bert_generation.tokenization_bert_generation.BertGenerationTokenizer" + } + } + }, + "bigbird-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.big_bird.tokenization_big_bird.BigBirdTokenizer" + } + } + }, + "bigbird-pegasus-arxiv": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "biogpt": { + "pkg": { + "0": { + "transformers": "transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer" + } + } + }, + "bitnet-b18-4t": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "blenderbot": { + "pkg": { + "0": { + "transformers": "transformers.models.blenderbot_small.tokenization_blenderbot_small.BlenderbotSmallTokenizer" + } + } + }, + "blip-vqa": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "blip2-opt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "bloom": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "blt": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "bridgetower": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "bros-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "camembert": { + "pkg": { + "0": { + "transformers": "transformers.models.camembert.tokenization_camembert.CamembertTokenizer" + } + } + }, + "canine-s": { + "pkg": { + "0": { + "transformers": "transformers.models.canine.tokenization_canine.CanineTokenizer" + } + } + }, + "chameleon": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "chinese-clip-vit-patch16": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "clap-htsat-fused": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "clip-vit-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "clipseg-rd64": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "clvp-dev": { + "pkg": { + "0": { + "transformers": "transformers.models.clvp.tokenization_clvp.ClvpTokenizer" + } + } + }, + "llama-2-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "codegen-mono": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "c4ai-command-r-v01": { + "pkg": { + "0": { + "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" + } + } + }, + "conv-bert": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "cpm-ant": { + "pkg": { + "0": { + "transformers": "transformers.models.cpmant.tokenization_cpmant.CpmAntTokenizer" + } + } + }, + "csm": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "ctrl": { + "pkg": { + "0": { + "transformers": "transformers.models.ctrl.tokenization_ctrl.CTRLTokenizer" + } + } + }, + "data2vec-audio-960h": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "data2vec-text": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "dbrx": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "deberta": { + "pkg": { + "0": { + "transformers": "transformers.models.deberta.tokenization_deberta.DebertaTokenizer" + } + } + }, + "deberta-v2-x": { + "pkg": { + "0": { + "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2.DebertaV2Tokenizer" + } + } + }, + "deepseek-v2-lite": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "deepseek-v3": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "deepseek-vl-chat": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "dia": { + "pkg": { + "0": { + "transformers": "transformers.models.dia.tokenization_dia.DiaTokenizer" + } + } + }, + "diffllama-handcut": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "distilbert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "dpr-ctx-encoder-single-nq": { + "pkg": { + "0": { + "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" + } + } + }, + "electra-discriminator": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "emu3-chat-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "ernie-3-zh": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "ernie-45-pt": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "ernie-4-a-pt": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "ernie-4-vl-a-pt": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "esm": { + "pkg": { + "0": { + "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" + } + } + }, + "exaone-4": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "falcon": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "falcon-mamba": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "flaubert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" + } + } + }, + "flava": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "flexolmo-7x-1t": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "florence-2": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "fnet": { + "pkg": { + "0": { + "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" + } + } + }, + "wmt19-en-ru": { + "pkg": { + "0": { + "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" + } + } + }, + "funnel": { + "pkg": { + "0": { + "transformers": "transformers.models.funnel.tokenization_funnel.FunnelTokenizer" + } + } + }, + "fuyu": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "gemma": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma2": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma-3": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma3-text": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma-3n-e": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "git": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "glm-4-chat": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4-0414": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4-a": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4v-thinking": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4v": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-asr-nano-2512": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "got-ocr-2-hf": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "gpt2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-bigcode-santacoder": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-neo": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "gpt-neox": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "gpt-neox-japanese": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox_japanese.tokenization_gpt_neox_japanese.GPTNeoXJapaneseTokenizer" + } + } + }, + "gpt-oss": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "gpt-j": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "granite": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "powermoe": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "granite-4-h": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "moe-active-shared-experts": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "grounding-dino": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "groupvit-gcc-yfcc": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "helium": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "hubert-ls960": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "ibert-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "idefics": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "idefics2": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "idefics3-llama3": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "blip-flan-t5": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "internvl3-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "jais-2-chat": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "jamba-v0": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "janus": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "jetmoe": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "kosmos-2-patch14-224": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "kosmos-2": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "todo": { + "pkg": { + "0": { + "transformers": "transformers.models.parakeet.tokenization_parakeet_fast.ParakeetTokenizerFast" + } + } + }, + "layoutlm-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "layoutlmv2-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2.LayoutLMv2Tokenizer" + } + } + }, + "layoutlmv3": { + "pkg": { + "0": { + "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" + } + } + }, + "led-16384": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "lfm2-vl": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "lilt-roberta-en": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "llama-4-scout-16e": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-v1-mistral-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-next-video-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llava-onevision-qwen2-ov-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "longformer-4096": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "long-t5-local": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "luke": { + "pkg": { + "0": { + "transformers": "transformers.models.luke.tokenization_luke.LukeTokenizer" + } + } + }, + "lxmert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "m": { + "pkg": { + "0": { + "transformers": "transformers.models.m2m_100.tokenization_m2m_100.M2M100Tokenizer" + } + } + }, + "mamba": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "mamba2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "opus-mt-en-de": { + "pkg": { + "0": { + "transformers": "transformers.models.marian.tokenization_marian.MarianTokenizer" + } + } + }, + "mbart-cc25": { + "pkg": { + "0": { + "transformers": "transformers.models.mbart.tokenization_mbart.MBartTokenizer" + } + } + }, + "megatron-bert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "metaclip-2-worldwide-huge-quickgelu": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "mgp-str": { + "pkg": { + "0": { + "transformers": "transformers.models.mgp_str.tokenization_mgp_str.MgpstrTokenizer" + } + } + }, + "max-text-01-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "stral-3-2512": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mistral-v0": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mistral-3-2503": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mixtral-8x": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "llama-3-vision": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mm-grounding-dino-o365v1-goldg-v3det": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "mobilebert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "modernbert": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "moonshine": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "hf-moshiko": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "mpnet": { + "pkg": { + "0": { + "transformers": "transformers.models.mpnet.tokenization_mpnet.MPNetTokenizer" + } + } + }, + "mpt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "mra-512-4": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "mt5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "musicgen": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "musicgen-melody": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "mvp": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "nemotron-3-hf": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "nllb-moe": { + "pkg": { + "0": { + "transformers": "transformers.models.nllb.tokenization_nllb.NllbTokenizer" + } + } + }, + "nystromformer-512": { + "pkg": { + "0": { + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" + } + } + }, + "olmo-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "olmo2-1124-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "olmo-3-0725": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "olmoe-0924": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "omdet-turbo-swin-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "oneformer-ade-swin": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "openai-gpt": { + "pkg": { + "0": { + "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" + } + } + }, + "opt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "ovis2-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "owlv2-patch16": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "owlvit-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "paligemma": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "pegasus": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "pegasus-x": { + "pkg": { + "0": { + "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" + } + } + }, + "language-perceiver": { + "pkg": { + "0": { + "transformers": "transformers.models.perceiver.tokenization_perceiver.PerceiverTokenizer" + } + } + }, + "persimmon": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "phi-1": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "phi-3": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "phi-3-moe": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "pixtral": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "plbart": { + "pkg": { + "0": { + "transformers": "transformers.models.plbart.tokenization_plbart.PLBartTokenizer" + } + } + }, + "phetnet-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.prophetnet.tokenization_prophetnet.ProphetNetTokenizer" + } + } + }, + "qwen2": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen2-vl": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen15-moe-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-next-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-vl": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-vl-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "recurrentgemma": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "reformer-crime-and-punishment": { + "pkg": { + "0": { + "transformers": "transformers.models.reformer.tokenization_reformer.ReformerTokenizer" + } + } + }, + "rembert": { + "pkg": { + "0": { + "transformers": "transformers.models.rembert.tokenization_rembert.RemBertTokenizer" + } + } + }, + "roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "efficient-mlm-m0-0": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "roc-bert-zh": { + "pkg": { + "0": { + "transformers": "transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer" + } + } + }, + "roformer-chinese": { + "pkg": { + "0": { + "transformers": "transformers.models.roformer.tokenization_roformer.RoFormerTokenizer" + } + } + }, + "rwkv-4-pile": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "hf-seamless-m4t": { + "pkg": { + "0": { + "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" + } + } + }, + "seamless-m4t-v2": { + "pkg": { + "0": { + "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" + } + } + }, + "siglip-patch16-224": { + "pkg": { + "0": { + "transformers": "transformers.models.siglip.tokenization_siglip.SiglipTokenizer" + } + } + }, + "siglip2-patch16-224": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "smollm3": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "s2t-librispeech-asr": { + "pkg": { + "0": { + "transformers": "transformers.models.speech_to_text.tokenization_speech_to_text.Speech2TextTokenizer" + } + } + }, + "speecht5-asr": { + "pkg": { + "0": { + "transformers": "transformers.models.speecht5.tokenization_speecht5.SpeechT5Tokenizer" + } + } + }, + "splinter": { + "pkg": { + "0": { + "transformers": "transformers.models.splinter.tokenization_splinter.SplinterTokenizer" + } + } + }, + "squeezebert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "stablelm-4e1t": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "starcoder2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "switch-8": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "t5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "t5gemma-prefixlm": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "tapas-finetuned-sqa": { + "pkg": { + "0": { + "transformers": "transformers.models.tapas.tokenization_tapas.TapasTokenizer" + } + } + }, + "tvp": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "udop": { + "pkg": { + "0": { + "transformers": "transformers.models.udop.tokenization_udop.UdopTokenizer" + } + } + }, + "umt5": { + "pkg": { + "0": { + "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" + } + } + }, + "video-llava-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "vilt-b32-mlm": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "vip-llava-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "visualbert-vqa-coco-pre": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "mms-tts-eng": { + "pkg": { + "0": { + "transformers": "transformers.models.vits.tokenization_vits.VitsTokenizer" + } + } + }, + "voxtral-2507": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "wav2vec2-960h": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "wav2vec2-bert-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "wav2vec2-conformer-rel-pos": { + "pkg": { + "0": { + "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" + } + } + }, + "whisper": { + "pkg": { + "0": { + "transformers": "transformers.models.whisper.tokenization_whisper.WhisperTokenizer" + } + } + }, + "xclip-patch32": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "xglm": { + "pkg": { + "0": { + "transformers": "transformers.models.xglm.tokenization_xglm.XGLMTokenizer" + } + } + }, + "xlm-mlm-en-2048": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm.tokenization_xlm.XLMTokenizer" + } + } + }, + "xlm-roberta": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "xlm-roberta-xl": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "xlnet-cased": { + "pkg": { + "0": { + "transformers": "transformers.models.xlnet.tokenization_xlnet.XLNetTokenizer" + } + } + }, + "xlstm": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "xmod": { + "pkg": { + "0": { + "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" + } + } + }, + "yoso-4096": { + "pkg": { + "0": { + "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" + } + } + }, + "zamba-v1": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "zamba2": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + } + }, + "info.vit.aimv2-patch14-224-lit": { + "*": { + "repo": "apple/aimv2-large-patch14-224-lit", + "pkg": { + "0": { + "transformers": "Aimv2Model" + } + }, + "tasks": [ + "Aimv2VisionModel", + "Aimv2Model", + "Aimv2PreTrainedModel", + "Aimv2TextModel" + ] + } + }, + "info.vit.aimv2-patch14-224": { + "*": { + "repo": "apple/aimv2-large-patch14-224", + "pkg": { + "0": { + "transformers": "Aimv2VisionModel" + } + }, + "tasks": [ + "Aimv2VisionModel", + "Aimv2Model", + "Aimv2PreTrainedModel", + "Aimv2TextModel" + ] + } + }, + "info.art.albert-xx-v2": { + "*": { + "repo": "albert/albert-xxlarge-v2", + "pkg": { + "0": { + "transformers": "AlbertModel" + } + }, + "tasks": [ + "AlbertPreTrainedModel", + "AlbertModel", + "AlbertForPreTraining", + "AlbertForMaskedLM", + "AlbertForSequenceClassification", + "AlbertForTokenClassification", + "AlbertForQuestionAnswering", + "AlbertForMultipleChoice" + ] + } + }, + "info.vit.align": { + "*": { + "repo": "kakaobrain/align-base", + "pkg": { + "0": { + "transformers": "AlignModel" + } + }, + "tasks": [ + "AlignPreTrainedModel", + "AlignTextModel", + "AlignVisionModel", + "AlignModel" + ] + } + }, + "info.vit.altclip": { + "*": { + "repo": "BAAI/AltCLIP", + "pkg": { + "0": { + "transformers": "AltCLIPModel" + } + }, + "tasks": [ + "AltCLIPPreTrainedModel", + "AltCLIPVisionModel", + "AltCLIPTextModel", + "AltCLIPModel" + ] + } + }, + "info.stst.apertus": { + "*": { + "repo": "swiss-ai/Apertus-8B", + "pkg": { + "0": { + "transformers": "ApertusModel" + } + }, + "tasks": [ + "ApertusModel", + "ApertusForCausalLM", + "ApertusForTokenClassification", + "ApertusPreTrainedModel" + ] + } + }, + "info.stst.afm": { + "*": { + "repo": "arcee-ai/AFM-4.5B", + "pkg": { + "0": { + "transformers": "ArceeModel" + } + }, + "tasks": [ + "ArceeForCausalLM", + "ArceeForQuestionAnswering", + "ArceeForSequenceClassification", + "ArceeForTokenClassification", + "ArceeModel", + "ArceePreTrainedModel" + ] + } + }, + "info.vit.aria": { + "*": { + "repo": "rhymes-ai/Aria", + "pkg": { + "0": { + "transformers": "AriaModel" + } + }, + "tasks": [ + "AriaForConditionalGeneration", + "AriaPreTrainedModel", + "AriaTextPreTrainedModel", + "AriaTextModel", + "AriaModel", + "AriaTextForCausalLM" + ] + } + }, + "info.vit.ast-finetuned-audioset-10-10-0593": { + "*": { + "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "pkg": { + "0": { + "transformers": "ASTModel" + } + }, + "tasks": [ + "ASTForAudioClassification", + "ASTModel", + "ASTPreTrainedModel" + ] + } + }, + "info.stst.audio-flamingo-3-hf": { + "*": { + "repo": "nvidia/audio-flamingo-3-hf", + "pkg": { + "0": { + "transformers": "AudioFlamingo3ForConditionalGeneration" + } + }, + "tasks": [ + "AudioFlamingo3ForConditionalGeneration", + "AudioFlamingo3PreTrainedModel", + "AudioFlamingo3Encoder" + ] + } + }, + "info.aet.audio-flamingo-3-hf": { + "*": { + "repo": "nvidia/audio-flamingo-3-hf", + "pkg": { + "0": { + "transformers": "AudioFlamingo3Encoder" + } + }, + "tasks": [ + "AudioFlamingo3ForConditionalGeneration", + "AudioFlamingo3PreTrainedModel", + "AudioFlamingo3Encoder" + ] + } + }, + "info.stst.autoformer-tourism-monthly": { + "*": { + "repo": "huggingface/autoformer-tourism-monthly", + "pkg": { + "0": { + "transformers": "AutoformerModel" + } + }, + "tasks": [ + "AutoformerForPrediction", + "AutoformerModel", + "AutoformerPreTrainedModel" + ] + } + }, + "info.vit.aya-vision": { + "*": { + "repo": "CohereForAI/aya-vision-8b", + "pkg": { + "0": { + "transformers": "AyaVisionModel" + } + }, + "tasks": [ + "AyaVisionForConditionalGeneration", + "AyaVisionPreTrainedModel", + "AyaVisionModel" + ] + } + }, + "info.ssm.bamba-t-hf": { + "*": { + "repo": "ibm-fms/Bamba-9.8b-2.2T-hf", + "pkg": { + "0": { + "transformers": "BambaModel" + } + }, + "tasks": [ + "BambaModel", + "BambaForCausalLM", + "BambaPreTrainedModel" + ] + } + }, + "info.art.bark": { + "*": { + "repo": "suno/bark", + "pkg": { + "0": { + "transformers": "BarkModel" + } + }, + "tasks": [ + "BarkFineModel", + "BarkSemanticModel", + "BarkCoarseModel", + "BarkModel", + "BarkPreTrainedModel", + "BarkCausalModel" + ] + } + }, + "info.stst.bart": { + "*": { + "repo": "facebook/bart-large", + "pkg": { + "0": { + "transformers": "BartModel" + } + }, + "tasks": [ + "BartForCausalLM", + "BartForConditionalGeneration", + "BartForQuestionAnswering", + "BartForSequenceClassification", + "BartModel", + "BartPreTrainedModel", + "BartPretrainedModel", + "PretrainedBartModel" + ] + } + }, + "info.vit.beit-patch16-224-pt": { + "*": { + "repo": "microsoft/beit-base-patch16-224-pt22k", + "pkg": { + "0": { + "transformers": "BeitModel" + } + }, + "tasks": [ + "BeitForImageClassification", + "BeitForMaskedImageModeling", + "BeitForSemanticSegmentation", + "BeitModel", + "BeitPreTrainedModel", + "BeitBackbone" + ] + } + }, + "info.art.bert-uncased": { + "*": { + "repo": "google-bert/bert-base-uncased", + "pkg": { + "0": { + "transformers": "BertModel" + } + }, + "file_256": [ + "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" + ], + "layer_b3": [ + "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" + ], + "layer_256": [ + "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" + ], + "tasks": [ + "BertForMaskedLM", + "BertForMultipleChoice", + "BertForNextSentencePrediction", + "BertForPreTraining", + "BertForQuestionAnswering", + "BertForSequenceClassification", + "BertForTokenClassification", + "BertLayer", + "BertLMHeadModel", + "BertModel", + "BertPreTrainedModel" + ] + } + }, + "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "*": { + "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "pkg": { + "0": { + "transformers": "BertGenerationEncoder" + } + }, + "tasks": [ + "BertGenerationDecoder", + "BertGenerationEncoder", + "BertGenerationPreTrainedModel" + ] + } + }, + "info.art.bigbird-roberta": { + "*": { + "repo": "google/bigbird-roberta-base", + "pkg": { + "0": { + "transformers": "BigBirdModel" + } + }, + "tasks": [ + "BigBirdForCausalLM", + "BigBirdForMaskedLM", + "BigBirdForMultipleChoice", + "BigBirdForPreTraining", + "BigBirdForQuestionAnswering", + "BigBirdForSequenceClassification", + "BigBirdForTokenClassification", + "BigBirdLayer", + "BigBirdModel", + "BigBirdPreTrainedModel" + ] + } + }, + "info.stst.bigbird-pegasus-arxiv": { + "*": { + "repo": "google/bigbird-pegasus-large-arxiv", + "pkg": { + "0": { + "transformers": "BigBirdPegasusModel" + } + }, + "tasks": [ + "BigBirdPegasusForCausalLM", + "BigBirdPegasusForConditionalGeneration", + "BigBirdPegasusForQuestionAnswering", + "BigBirdPegasusForSequenceClassification", + "BigBirdPegasusModel", + "BigBirdPegasusPreTrainedModel" + ] + } + }, + "info.art.biogpt": { + "*": { + "repo": "microsoft/biogpt", + "pkg": { + "0": { + "transformers": "BioGptModel" + } + }, + "tasks": [ + "BioGptForCausalLM", + "BioGptForTokenClassification", + "BioGptForSequenceClassification", + "BioGptModel", + "BioGptPreTrainedModel" + ] + } + }, + "info.vit.bit-50": { + "*": { + "repo": "google/bit-50", + "pkg": { + "0": { + "transformers": "BitModel" + } + }, + "tasks": [ + "BitForImageClassification", + "BitModel", + "BitPreTrainedModel", + "BitBackbone" + ] + } + }, + "info.stst.bitnet-b18-4t": { + "*": { + "repo": "microsoft/bitnet-b1.58-2B-4T", + "pkg": { + "0": { + "transformers": "BitNetModel" + } + }, + "tasks": [ + "BitNetForCausalLM", + "BitNetModel", + "BitNetPreTrainedModel" + ] + } + }, + "info.stst.blenderbot": { + "*": { + "repo": "facebook/blenderbot-3B", + "pkg": { + "0": { + "transformers": "BlenderbotModel" + } + }, + "tasks": [ + "BlenderbotForCausalLM", + "BlenderbotForConditionalGeneration", + "BlenderbotModel", + "BlenderbotPreTrainedModel" + ] + } + }, + "info.vit.blip-vqa": { + "*": { + "repo": "Salesforce/blip-vqa-base", + "pkg": { + "0": { + "transformers": "BlipModel" + } + }, + "tasks": [ + "BlipModel", + "BlipPreTrainedModel", + "BlipForConditionalGeneration", + "BlipForQuestionAnswering", + "BlipVisionModel", + "BlipTextModel", + "BlipForImageTextRetrieval" + ] + } + }, + "info.vit.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2Model" + } + }, + "tasks": [ + "Blip2Model", + "Blip2VisionModelWithProjection", + "Blip2QFormerModel", + "Blip2PreTrainedModel", + "Blip2ForConditionalGeneration", + "Blip2ForImageTextRetrieval", + "Blip2VisionModel", + "Blip2TextModelWithProjection" + ] + } + }, + "info.stst.blip2-opt": { + "*": { + "repo": "Salesforce/blip2-opt-2.7b", + "pkg": { + "0": { + "transformers": "Blip2QFormerModel" + } + }, + "tasks": [ + "Blip2Model", + "Blip2VisionModelWithProjection", + "Blip2QFormerModel", + "Blip2PreTrainedModel", + "Blip2ForConditionalGeneration", + "Blip2ForImageTextRetrieval", + "Blip2VisionModel", + "Blip2TextModelWithProjection" + ] + } + }, + "info.art.bloom": { + "*": { + "repo": "bigscience/bloom", + "pkg": { + "0": { + "transformers": "BloomModel" + } + }, + "tasks": [ + "BloomForCausalLM", + "BloomModel", + "BloomPreTrainedModel", + "BloomForSequenceClassification", + "BloomForTokenClassification", + "BloomForQuestionAnswering" + ] + } + }, + "info.vit.blt": { + "*": { + "repo": "facebook/blt", + "pkg": { + "0": { + "transformers": "BltModel" + } + }, + "tasks": [ + "BltPreTrainedModel", + "BltModel", + "BltPatcher", + "BltForCausalLM" + ] + } + }, + "info.vit.bridgetower": { + "*": { + "repo": "BridgeTower/bridgetower-base", + "pkg": { + "0": { + "transformers": "BridgeTowerModel" + } + }, + "tasks": [ + "BridgeTowerForContrastiveLearning", + "BridgeTowerForImageAndTextRetrieval", + "BridgeTowerForMaskedLM", + "BridgeTowerModel", + "BridgeTowerPreTrainedModel" + ] + } + }, + "info.art.bros-uncased": { + "*": { + "repo": "jinho8345/bros-base-uncased", + "pkg": { + "0": { + "transformers": "BrosModel" + } + }, + "tasks": [ + "BrosPreTrainedModel", + "BrosModel", + "BrosForTokenClassification", + "BrosSpadeEEForTokenClassification", + "BrosSpadeELForTokenClassification" + ] + } + }, + "info.art.camembert": { + "*": { + "repo": "almanach/camembert-base", + "pkg": { + "0": { + "transformers": "CamembertModel" + } + }, + "tasks": [ + "CamembertForCausalLM", + "CamembertForMaskedLM", + "CamembertForMultipleChoice", + "CamembertForQuestionAnswering", + "CamembertForSequenceClassification", + "CamembertForTokenClassification", + "CamembertModel", + "CamembertPreTrainedModel" + ] + } + }, + "info.art.canine-s": { + "*": { + "repo": "google/canine-s", + "pkg": { + "0": { + "transformers": "CanineModel" + } + }, + "tasks": [ + "CanineForMultipleChoice", + "CanineForQuestionAnswering", + "CanineForSequenceClassification", + "CanineForTokenClassification", + "CanineLayer", + "CanineModel", + "CaninePreTrainedModel" + ] + } + }, + "info.stst.chameleon": { + "*": { + "repo": "meta/chameleon-7B", + "pkg": { + "0": { + "transformers": "ChameleonModel" + } + }, + "tasks": [ + "ChameleonForConditionalGeneration", + "ChameleonModel", + "ChameleonPreTrainedModel", + "ChameleonVQVAE" + ] + } + }, + "info.vit.chinese-clip-vit-patch16": { + "*": { + "repo": "OFA-Sys/chinese-clip-vit-base-patch16", + "pkg": { + "0": { + "transformers": "ChineseCLIPModel" + } + }, + "tasks": [ + "ChineseCLIPModel", + "ChineseCLIPPreTrainedModel", + "ChineseCLIPTextModel", + "ChineseCLIPVisionModel" + ] + } + }, + "info.vit.clap-htsat-fused": { + "*": { + "repo": "laion/clap-htsat-fused", + "pkg": { + "0": { + "transformers": "ClapModel" + } + }, + "file_256": [ + "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", + "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" + ], + "layer_b3": [ + "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", + "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" + ], + "layer_256": [ + "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", + "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" + ], + "tasks": [ + "ClapModel", + "ClapPreTrainedModel", + "ClapTextModel", + "ClapTextModelWithProjection", + "ClapAudioModel", + "ClapAudioModelWithProjection" + ] + } + }, + "info.vit.clip-vit-patch32": { + "*": { + "repo": "openai/clip-vit-base-patch32", + "pkg": { + "0": { + "transformers": "CLIPModel" + } + }, + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" + ] + } + }, + "info.vit.clipseg-rd64": { + "*": { + "repo": "CIDAS/clipseg-rd64", + "pkg": { + "0": { + "transformers": "CLIPSegModel" + } + }, + "tasks": [ + "CLIPSegModel", + "CLIPSegPreTrainedModel", + "CLIPSegTextModel", + "CLIPSegVisionModel", + "CLIPSegForImageSegmentation" + ] + } + }, + "info.vit.clvp-dev": { + "*": { + "repo": "susnato/clvp_dev", + "pkg": { + "0": { + "transformers": "ClvpModelForConditionalGeneration" + } + }, + "tasks": [ + "ClvpModelForConditionalGeneration", + "ClvpForCausalLM", + "ClvpModel", + "ClvpPreTrainedModel", + "ClvpEncoder", + "ClvpDecoder" + ] + } + }, + "info.stst.llama-2-hf": { + "*": { + "repo": "meta-llama/Llama-2-7b-hf", + "pkg": { + "0": { + "transformers": "LlamaModel" + } + }, + "tasks": [ + "LlamaForCausalLM", + "LlamaModel", + "LlamaPreTrainedModel", + "LlamaForSequenceClassification", + "LlamaForQuestionAnswering", + "LlamaForTokenClassification" + ] + } + }, + "info.art.codegen-mono": { + "*": { + "repo": "Salesforce/codegen-2B-mono", + "pkg": { + "0": { + "transformers": "CodeGenModel" + } + }, + "tasks": [ + "CodeGenForCausalLM", + "CodeGenModel", + "CodeGenPreTrainedModel" + ] + } + }, + "info.stst.c4ai-command-r-v01": { + "*": { + "repo": "CohereForAI/c4ai-command-r-v01", + "pkg": { + "0": { + "transformers": "CohereModel" + } + }, + "tasks": [ + "CohereForCausalLM", + "CohereModel", + "CoherePreTrainedModel" + ] + } + }, + "info.vit.command-a-vision-07-2025": { + "*": { + "repo": "CohereLabs/command-a-vision-07-2025", + "pkg": { + "0": { + "transformers": "Cohere2VisionModel" + } + }, + "tasks": [ + "Cohere2VisionForConditionalGeneration", + "Cohere2VisionPreTrainedModel", + "Cohere2VisionModel" + ] + } + }, + "info.detr.conditional-detr-resnet-50": { + "*": { + "repo": "microsoft/conditional-detr-resnet-50", + "pkg": { + "0": { + "transformers": "ConditionalDetrModel" + } + }, + "tasks": [ + "ConditionalDetrForObjectDetection", + "ConditionalDetrForSegmentation", + "ConditionalDetrModel", + "ConditionalDetrPreTrainedModel" + ] + } + }, + "info.art.conv-bert": { + "*": { + "repo": "YituTech/conv-bert-base", + "pkg": { + "0": { + "transformers": "ConvBertModel" + } + }, + "tasks": [ + "ConvBertForMaskedLM", + "ConvBertForMultipleChoice", + "ConvBertForQuestionAnswering", + "ConvBertForSequenceClassification", + "ConvBertForTokenClassification", + "ConvBertLayer", + "ConvBertModel", + "ConvBertPreTrainedModel" + ] + } + }, + "info.vit.convnext-224": { + "*": { + "repo": "facebook/convnext-tiny-224", + "pkg": { + "0": { + "transformers": "ConvNextModel" + } + }, + "tasks": [ + "ConvNextForImageClassification", + "ConvNextModel", + "ConvNextPreTrainedModel", + "ConvNextBackbone" + ] + } + }, + "info.vit.convnextv2-224": { + "*": { + "repo": "facebook/convnextv2-tiny-1k-224", + "pkg": { + "0": { + "transformers": "ConvNextV2Model" + } + }, + "tasks": [ + "ConvNextV2ForImageClassification", + "ConvNextV2Model", + "ConvNextV2PreTrainedModel", + "ConvNextV2Backbone" + ] + } + }, + "info.stst.cpm-ant": { + "*": { + "repo": "openbmb/cpm-ant-10b", + "pkg": { + "0": { + "transformers": "CpmAntModel" + } + }, + "tasks": [ + "CpmAntForCausalLM", + "CpmAntModel", + "CpmAntPreTrainedModel" + ] + } + }, + "info.stst.csm": { + "*": { + "repo": "sesame/csm-1b", + "pkg": { + "0": { + "transformers": "CsmForConditionalGeneration" + } + }, + "tasks": [ + "CsmPreTrainedModel", + "CsmBackboneModel", + "CsmDepthDecoderModel", + "CsmDepthDecoderForCausalLM", + "CsmForConditionalGeneration" + ] + } + }, + "info.art.ctrl": { + "*": { + "repo": "Salesforce/ctrl", + "pkg": { + "0": { + "transformers": "CTRLModel" + } + }, + "tasks": [ + "CTRLForSequenceClassification", + "CTRLLMHeadModel", + "CTRLModel", + "CTRLPreTrainedModel" + ] + } + }, + "info.vit.cvt-13": { + "*": { + "repo": "microsoft/cvt-13", + "pkg": { + "0": { + "transformers": "CvtModel" + } + }, + "tasks": [ + "CvtForImageClassification", + "CvtModel", + "CvtPreTrainedModel" + ] + } + }, + "info.art.cwm": { + "*": { + "repo": "facebook/cwm", + "pkg": { + "0": { + "transformers": "CwmModel" + } + }, + "tasks": [ + "CwmPreTrainedModel", + "CwmModel", + "CwmForCausalLM" + ] + } + }, + "info.detr.dfine-x-coco": { + "*": { + "repo": "ustc-community/dfine-xlarge-coco", + "pkg": { + "0": { + "transformers": "DFineModel" + } + }, + "tasks": [ + "DFineModel", + "DFinePreTrainedModel", + "DFineForObjectDetection" + ] + } + }, + "info.detr.dab-detr": { + "*": { + "repo": "IDEA-Research/dab-detr-resnet-50", + "pkg": { + "0": { + "transformers": "DabDetrModel" + } + }, + "tasks": [ + "DabDetrForObjectDetection", + "DabDetrModel", + "DabDetrPreTrainedModel" + ] + } + }, + "info.gan.dac": { + "*": { + "repo": "descript/dac_16khz", + "pkg": { + "0": { + "transformers": "DacModel" + } + }, + "tasks": [ + "DacModel", + "DacPreTrainedModel" + ] + } + }, + "info.aet.data2vec-audio-960h": { + "*": { + "repo": "facebook/data2vec-audio-base-960h", + "pkg": { + "0": { + "transformers": "Data2VecAudioModel" + } + }, + "tasks": [ + "Data2VecAudioForAudioFrameClassification", + "Data2VecAudioForCTC", + "Data2VecAudioForSequenceClassification", + "Data2VecAudioForXVector", + "Data2VecAudioModel", + "Data2VecAudioPreTrainedModel" + ] + } + }, + "info.art.data2vec-text": { + "*": { + "repo": "facebook/data2vec-text-base", + "pkg": { + "0": { + "transformers": "Data2VecTextModel" + } + }, + "tasks": [ + "Data2VecTextForCausalLM", + "Data2VecTextForMaskedLM", + "Data2VecTextForMultipleChoice", + "Data2VecTextForQuestionAnswering", + "Data2VecTextForSequenceClassification", + "Data2VecTextForTokenClassification", + "Data2VecTextModel", + "Data2VecTextPreTrainedModel" + ] + } + }, + "info.vit.data2vec-vision": { + "*": { + "repo": "facebook/data2vec-vision-base", + "pkg": { + "0": { + "transformers": "Data2VecVisionModel" + } + }, + "tasks": [ + "Data2VecVisionForImageClassification", + "Data2VecVisionForSemanticSegmentation", + "Data2VecVisionModel", + "Data2VecVisionPreTrainedModel" + ] + } + }, + "info.stst.dbrx": { + "*": { + "repo": "databricks/dbrx-instruct", + "pkg": { + "0": { + "transformers": "DbrxModel" + } + }, + "tasks": [ + "DbrxForCausalLM", + "DbrxModel", + "DbrxPreTrainedModel" + ] + } + }, + "info.art.deberta": { + "*": { + "repo": "microsoft/deberta-base", + "pkg": { + "0": { + "transformers": "DebertaModel" + } + }, + "tasks": [ + "DebertaForMaskedLM", + "DebertaForQuestionAnswering", + "DebertaForSequenceClassification", + "DebertaForTokenClassification", + "DebertaModel", + "DebertaPreTrainedModel" + ] + } + }, + "info.art.deberta-v2-x": { + "*": { + "repo": "microsoft/deberta-v2-xlarge", + "pkg": { + "0": { + "transformers": "DebertaV2Model" + } + }, + "tasks": [ + "DebertaV2ForMaskedLM", + "DebertaV2ForMultipleChoice", + "DebertaV2ForQuestionAnswering", + "DebertaV2ForSequenceClassification", + "DebertaV2ForTokenClassification", + "DebertaV2Model", + "DebertaV2PreTrainedModel" + ] + } + }, + "info.art.decision-transformer-gym-hopper": { + "*": { + "repo": "edbeeching/decision-transformer-gym-hopper-medium", + "pkg": { + "0": { + "transformers": "DecisionTransformerModel" + } + }, + "tasks": [ + "DecisionTransformerGPT2Model", + "DecisionTransformerGPT2PreTrainedModel", + "DecisionTransformerModel", + "DecisionTransformerPreTrainedModel" + ] + } + }, + "info.moe.deepseek-v2-lite": { + "*": { + "repo": "deepseek-ai/DeepSeek-V2-Lite", + "pkg": { + "0": { + "transformers": "DeepseekV2Model" + } + }, + "tasks": [ + "DeepseekV2PreTrainedModel", + "DeepseekV2Model", + "DeepseekV2ForCausalLM", + "DeepseekV2ForSequenceClassification" + ] + } + }, + "info.moe.deepseek-v3": { + "*": { + "repo": "bzantium/tiny-deepseek-v3", + "pkg": { + "0": { + "transformers": "DeepseekV3Model" + } + }, + "tasks": [ + "DeepseekV3PreTrainedModel", + "DeepseekV3Model", + "DeepseekV3ForCausalLM", + "DeepseekV3ForSequenceClassification", + "DeepseekV3ForTokenClassification" + ] + } + }, + "info.vit.deepseek-vl-chat": { + "*": { + "repo": "deepseek-community/deepseek-vl-1.3b-chat", + "pkg": { + "0": { + "transformers": "DeepseekVLModel" + } + }, + "tasks": [ + "DeepseekVLPreTrainedModel", + "DeepseekVLModel", + "DeepseekVLForConditionalGeneration" + ] + } + }, + "info.detr.deformable-detr": { + "*": { + "repo": "SenseTime/deformable-detr", + "pkg": { + "0": { + "transformers": "DeformableDetrModel" + } + }, + "tasks": [ + "DeformableDetrForObjectDetection", + "DeformableDetrModel", + "DeformableDetrPreTrainedModel" + ] + } + }, + "info.vit.deit-distilled-patch16-224": { + "*": { + "repo": "facebook/deit-base-distilled-patch16-224", + "pkg": { + "0": { + "transformers": "DeiTModel" + } + }, + "tasks": [ + "DeiTForImageClassification", + "DeiTForImageClassificationWithTeacher", + "DeiTForMaskedImageModeling", + "DeiTModel", + "DeiTPreTrainedModel" + ] + } + }, + "info.vit.depth": { + "*": { + "repo": "apple/DepthPro", + "pkg": { + "0": { + "transformers": "DepthProModel" + } + }, + "tasks": [ + "DepthProPreTrainedModel", + "DepthProModel", + "DepthProForDepthEstimation" + ] + } + }, + "info.detr.detr-resnet-50": { + "*": { + "repo": "facebook/detr-resnet-50", + "pkg": { + "0": { + "transformers": "DetrModel" + } + }, + "tasks": [ + "DetrForObjectDetection", + "DetrForSegmentation", + "DetrModel", + "DetrPreTrainedModel" + ] + } + }, + "info.stst.dia": { + "*": { + "repo": "nari-labs/Dia-1.6B", + "pkg": { + "0": { + "transformers": "DiaModel" + } + }, + "tasks": [ + "DiaModel", + "DiaPreTrainedModel", + "DiaForConditionalGeneration" + ] + } + }, + "info.stst.diffllama-handcut": { + "*": { + "repo": "kajuma/DiffLlama-0.3B-handcut", + "pkg": { + "0": { + "transformers": "DiffLlamaModel" + } + }, + "tasks": [ + "DiffLlamaPreTrainedModel", + "DiffLlamaModel", + "DiffLlamaForCausalLM", + "DiffLlamaForSequenceClassification", + "DiffLlamaForQuestionAnswering", + "DiffLlamaForTokenClassification" + ] + } + }, + "info.gan.dinat-in-224": { + "*": { + "repo": "shi-labs/dinat-mini-in1k-224", + "pkg": { + "0": { + "transformers": "DinatModel" + } + }, + "tasks": [ + "DinatForImageClassification", + "DinatModel", + "DinatPreTrainedModel", + "DinatBackbone" + ] + } + }, + "info.vit.dinov2-patch16-224": { + "*": { + "repo": "google/dinov2-base-patch16-224", + "pkg": { + "0": { + "transformers": "Dinov2Model" + } + }, + "tasks": [ + "Dinov2ForImageClassification", + "Dinov2Model", + "Dinov2PreTrainedModel", + "Dinov2Backbone" + ] + } + }, + "info.vit.dinov2-with-registers": { + "*": { + "repo": "facebook/dinov2-with-registers-base", + "pkg": { + "0": { + "transformers": "Dinov2WithRegistersModel" + } + }, + "tasks": [ + "Dinov2WithRegistersPreTrainedModel", + "Dinov2WithRegistersModel", + "Dinov2WithRegistersForImageClassification", + "Dinov2WithRegistersBackbone" + ] + } + }, + "info.vit.dinov3-convnext-pretrain-lvd": { + "*": { + "repo": "facebook/dinov3-convnext-tiny-pretrain-lvd1689m", + "pkg": { + "0": { + "transformers": "DINOv3ConvNextModel" + } + }, + "tasks": [ + "DINOv3ConvNextModel", + "DINOv3ConvNextPreTrainedModel", + "DINOv3ConvNextBackbone" + ] + } + }, + "info.vit.dinov3-vits16-pretrain-lvd": { + "*": { + "repo": "facebook/dinov3-vits16-pretrain-lvd1689m", + "pkg": { + "0": { + "transformers": "DINOv3ViTModel" + } + }, + "tasks": [ + "DINOv3ViTModel", + "DINOv3ViTPreTrainedModel", + "DINOv3ViTBackbone" + ] + } + }, + "info.art.distilbert-uncased": { + "*": { + "repo": "distilbert-base-uncased", + "pkg": { + "0": { + "transformers": "DistilBertModel" + } + }, + "tasks": [ + "DistilBertForMaskedLM", + "DistilBertForMultipleChoice", + "DistilBertForQuestionAnswering", + "DistilBertForSequenceClassification", + "DistilBertForTokenClassification", + "DistilBertModel", + "DistilBertPreTrainedModel" + ] + } + }, + "info.moe.doge": { + "*": { + "repo": "SmallDoge/Doge-320M", + "pkg": { + "0": { + "transformers": "DogeModel" + } + }, + "tasks": [ + "DogeForCausalLM", + "DogeModel", + "DogePreTrainedModel", + "DogeForSequenceClassification" + ] + } + }, + "info.vit.donut": { + "*": { + "repo": "naver-clova-ix/donut-base", + "pkg": { + "0": { + "transformers": "DonutSwinModel" + } + }, + "tasks": [ + "DonutSwinModel", + "DonutSwinPreTrainedModel", + "DonutSwinForImageClassification" + ] + } + }, + "info.moe.dots-llm1": { + "*": { + "repo": "rednote-hilab/dots.llm1.base", + "pkg": { + "0": { + "transformers": "Dots1Model" + } + }, + "tasks": [ + "Dots1PreTrainedModel", + "Dots1Model", + "Dots1ForCausalLM" + ] + } + }, + "info.vit.dpr-ctx-encoder-single-nq": { + "*": { + "repo": "facebook/dpr-ctx_encoder-single-nq-base", + "pkg": { + "0": { + "transformers": "DPRQuestionEncoder" + } + }, + "tasks": [ + "DPRContextEncoder", + "DPRPretrainedContextEncoder", + "DPRPreTrainedModel", + "DPRPretrainedQuestionEncoder", + "DPRPretrainedReader", + "DPRQuestionEncoder", + "DPRReader" + ] + } + }, + "info.detr.dpt": { + "*": { + "repo": "Intel/dpt-large", + "pkg": { + "0": { + "transformers": "DPTModel" + } + }, + "tasks": [ + "DPTForDepthEstimation", + "DPTForSemanticSegmentation", + "DPTModel", + "DPTPreTrainedModel" + ] + } + }, + "info.vit.edgetam1-hiera": { + "*": { + "repo": "facebook/edgetam.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "EdgeTamModel" + } + }, + "tasks": [ + "EdgeTamModel", + "EdgeTamVisionModel", + "EdgeTamPreTrainedModel" + ] + } + }, + "info.vit.edgetam": { + "*": { + "repo": "facebook/EdgeTAM", + "pkg": { + "0": { + "transformers": "EdgeTamVideoModel" + } + }, + "tasks": [ + "EdgeTamVideoModel", + "EdgeTamVideoInferenceSession", + "EdgeTamVideoPreTrainedModel" + ] + } + }, + "info.vit.efficientloftr": { + "*": { + "repo": "zju-community/efficientloftr", + "pkg": { + "0": { + "transformers": "EfficientLoFTRModel" + } + }, + "tasks": [ + "EfficientLoFTRPreTrainedModel", + "EfficientLoFTRModel", + "EfficientLoFTRForKeypointMatching" + ] + } + }, + "info.vit.efficientnet-b7": { + "*": { + "repo": "google/efficientnet-b7", + "pkg": { + "0": { + "transformers": "EfficientNetModel" + } + }, + "tasks": [ + "EfficientNetForImageClassification", + "EfficientNetModel", + "EfficientNetPreTrainedModel" + ] + } + }, + "info.art.electra-discriminator": { + "*": { + "repo": "google/electra-small-discriminator", + "pkg": { + "0": { + "transformers": "ElectraModel" + } + }, + "tasks": [ + "ElectraForCausalLM", + "ElectraForMaskedLM", + "ElectraForMultipleChoice", + "ElectraForPreTraining", + "ElectraForQuestionAnswering", + "ElectraForSequenceClassification", + "ElectraForTokenClassification", + "ElectraModel", + "ElectraPreTrainedModel" + ] + } + }, + "info.art.emu3-chat-hf": { + "*": { + "repo": "Emu3-community/Emu3-Chat-hf", + "pkg": { + "0": { + "transformers": "Emu3Model" + } + }, + "tasks": [ + "Emu3ForConditionalGeneration", + "Emu3ForCausalLM", + "Emu3TextModel", + "Emu3PreTrainedModel", + "Emu3VQVAE", + "Emu3Model" + ] + } + }, + "info.gan.encodec": { + "*": { + "repo": "facebook/encodec_24khz", + "pkg": { + "0": { + "transformers": "EncodecModel" + } + }, + "tasks": [ + "EncodecModel", + "EncodecPreTrainedModel" + ] + } + }, + "info.art.ernie-3-zh": { + "*": { + "repo": "nghuyong/ernie-3.0-base-zh", + "pkg": { + "0": { + "transformers": "ErnieModel" + } + }, + "tasks": [ + "ErnieForCausalLM", + "ErnieForMaskedLM", + "ErnieForMultipleChoice", + "ErnieForNextSentencePrediction", + "ErnieForPreTraining", + "ErnieForQuestionAnswering", + "ErnieForSequenceClassification", + "ErnieForTokenClassification", + "ErnieModel", + "ErniePreTrainedModel" + ] + } + }, + "info.stst.ernie-45-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-0.3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5Model" + } + }, + "tasks": [ + "Ernie4_5ForCausalLM", + "Ernie4_5Model", + "Ernie4_5PreTrainedModel" + ] + } + }, + "info.moe.ernie-4-a-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-21B-A3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5_MoeModel" + } + }, + "tasks": [ + "Ernie4_5_MoeForCausalLM", + "Ernie4_5_MoeModel", + "Ernie4_5_MoePreTrainedModel" + ] + } + }, + "info.vit.ernie-4-vl-a-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-VL-28B-A3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5_VL_MoeModel" + } + }, + "tasks": [ + "Ernie4_5_VL_MoePreTrainedModel", + "Ernie4_5_VL_MoeForConditionalGeneration", + "Ernie4_5_VL_MoeModel", + "Ernie4_5_VL_MoeTextModel", + "Ernie4_5_VL_MoeVisionTransformerPretrainedModel", + "Ernie4_5_VL_MoeVariableResolutionResamplerModel" + ] + } + }, + "info.aet.esm": { + "*": { + "repo": "facebook/esm-1b", + "pkg": { + "0": { + "transformers": "EsmModel" + } + }, + "tasks": [ + "EsmForMaskedLM", + "EsmForSequenceClassification", + "EsmForTokenClassification", + "EsmModel", + "EsmPreTrainedModel" + ] + } + }, + "info.stst.evolla-hf": { + "*": { + "repo": "westlake-repl/Evolla-10B-hf", + "pkg": { + "0": { + "transformers": "EvollaModel" + } + }, + "tasks": [ + "EvollaForProteinText2Text", + "EvollaModel", + "EvollaPreTrainedModel" + ] + } + }, + "info.stst.exaone-4": { + "*": { + "repo": "LGAI-EXAONE/EXAONE-4.0-32B", + "pkg": { + "0": { + "transformers": "Exaone4Model" + } + }, + "tasks": [ + "Exaone4PreTrainedModel", + "Exaone4Model", + "Exaone4ForCausalLM", + "Exaone4ForSequenceClassification", + "Exaone4ForTokenClassification", + "Exaone4ForQuestionAnswering" + ] + } + }, + "info.ssm.falcon": { + "*": { + "repo": "tiiuae/falcon-7b", + "pkg": { + "0": { + "transformers": "FalconModel" + } + }, + "tasks": [ + "FalconForCausalLM", + "FalconModel", + "FalconPreTrainedModel", + "FalconForSequenceClassification", + "FalconForTokenClassification", + "FalconForQuestionAnswering" + ] + } + }, + "info.ssm.falconh1-t-hf": { + "*": { + "repo": "tiiuae/Falcon-H1-34B-Instruct", + "pkg": { + "0": { + "transformers": "FalconH1Model" + } + }, + "tasks": [ + "FalconH1Model", + "FalconH1ForCausalLM", + "FalconH1PreTrainedModel" + ] + } + }, + "info.ssm.falcon-mamba": { + "*": { + "repo": "tiiuae/falcon-mamba-7b", + "pkg": { + "0": { + "transformers": "FalconMambaModel" + } + }, + "tasks": [ + "FalconMambaForCausalLM", + "FalconMambaModel", + "FalconMambaPreTrainedModel", + "FalconMambaCache" + ] + } + }, + "info.vit.fastvlm": { + "*": { + "repo": "KamilaMila/FastVLM-7B", + "pkg": { + "0": { + "transformers": "FastVlmModel" + } + }, + "tasks": [ + "FastVlmForConditionalGeneration", + "FastVlmModel", + "FastVlmPreTrainedModel" + ] + } + }, + "info.aet.fastspeech2-conformer": { + "*": { + "repo": "espnet/fastspeech2_conformer", + "pkg": { + "0": { + "transformers": "FastSpeech2ConformerModel" + } + }, + "tasks": [ + "FastSpeech2ConformerWithHifiGan", + "FastSpeech2ConformerHifiGan", + "FastSpeech2ConformerModel", + "FastSpeech2ConformerPreTrainedModel" + ] + } + }, + "info.stst.fastspeech2-conformer": { + "*": { + "repo": "espnet/fastspeech2_conformer", + "pkg": { + "0": { + "transformers": "FastSpeech2ConformerWithHifiGan" + } + }, + "tasks": [ + "FastSpeech2ConformerWithHifiGan", + "FastSpeech2ConformerHifiGan", + "FastSpeech2ConformerModel", + "FastSpeech2ConformerPreTrainedModel" + ] + } + }, + "info.art.flaubert-uncased": { + "*": { + "repo": "flaubert/flaubert_base_uncased", + "pkg": { + "0": { + "transformers": "FlaubertModel" + } + }, + "tasks": [ + "FlaubertForMultipleChoice", + "FlaubertForQuestionAnswering", + "FlaubertForQuestionAnsweringSimple", + "FlaubertForSequenceClassification", + "FlaubertForTokenClassification", + "FlaubertModel", + "FlaubertWithLMHeadModel", + "FlaubertPreTrainedModel" + ] + } + }, + "info.vit.flava": { + "*": { + "repo": "facebook/flava-full", + "pkg": { + "0": { + "transformers": "FlavaModel" + } + }, + "tasks": [ + "FlavaForPreTraining", + "FlavaImageCodebook", + "FlavaImageModel", + "FlavaModel", + "FlavaMultimodalModel", + "FlavaPreTrainedModel", + "FlavaTextModel" + ] + } + }, + "info.moe.flexolmo-7x-1t": { + "*": { + "repo": "allenai/FlexOlmo-7x7B-1T", + "pkg": { + "0": { + "transformers": "FlexOlmoModel" + } + }, + "tasks": [ + "FlexOlmoForCausalLM", + "FlexOlmoModel", + "FlexOlmoPreTrainedModel" + ] + } + }, + "info.vit.florence-2": { + "*": { + "repo": "florence-community/Florence-2-base", + "pkg": { + "0": { + "transformers": "Florence2Model" + } + }, + "tasks": [ + "Florence2Model", + "Florence2ForConditionalGeneration", + "Florence2PreTrainedModel", + "Florence2VisionBackbone", + "Florence2VisionPreTrainedModel" + ] + } + }, + "info.art.fnet": { + "*": { + "repo": "google/fnet-base", + "pkg": { + "0": { + "transformers": "FNetModel" + } + }, + "tasks": [ + "FNetForMaskedLM", + "FNetForMultipleChoice", + "FNetForNextSentencePrediction", + "FNetForPreTraining", + "FNetForQuestionAnswering", + "FNetForSequenceClassification", + "FNetForTokenClassification", + "FNetLayer", + "FNetModel", + "FNetPreTrainedModel" + ] + } + }, + "info.vit.focalnet": { + "*": { + "repo": "microsoft/focalnet-tiny", + "pkg": { + "0": { + "transformers": "FocalNetModel" + } + }, + "tasks": [ + "FocalNetForImageClassification", + "FocalNetForMaskedImageModeling", + "FocalNetBackbone", + "FocalNetModel", + "FocalNetPreTrainedModel" + ] + } + }, + "info.stst.wmt19-en-ru": { + "*": { + "repo": "facebook/wmt19-en-ru", + "pkg": { + "0": { + "transformers": "FSMTModel" + } + }, + "tasks": [ + "FSMTForConditionalGeneration", + "FSMTModel", + "PretrainedFSMTModel" + ] + } + }, + "info.aet.funnel": { + "*": { + "repo": "funnel-transformer/small", + "pkg": { + "0": { + "transformers": "FunnelModel" + } + }, + "tasks": [ + "FunnelBaseModel", + "FunnelForMaskedLM", + "FunnelForMultipleChoice", + "FunnelForPreTraining", + "FunnelForQuestionAnswering", + "FunnelForSequenceClassification", + "FunnelForTokenClassification", + "FunnelModel", + "FunnelPreTrainedModel" + ] + } + }, + "info.vit.fuyu": { + "*": { + "repo": "adept/fuyu-8b", + "pkg": { + "0": { + "transformers": "FuyuModel" + } + }, + "tasks": [ + "FuyuForCausalLM", + "FuyuPreTrainedModel", + "FuyuModel" + ] + } + }, + "info.stst.gemma": { + "*": { + "repo": "google/gemma-7b", + "pkg": { + "0": { + "transformers": "GemmaModel" + } + }, + "file_256": [ + "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" + ], + "layer_b3": [ + "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", + "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" + ], + "layer_256": [ + "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", + "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" + ], + "tasks": [ + "GemmaModel", + "GemmaForCausalLM", + "GemmaForSequenceClassification", + "GemmaForTokenClassification", + "GemmaPreTrainedModel" + ] + } + }, + "info.stst.gemma2": { + "*": { + "repo": "google/gemma-2-9b", + "pkg": { + "0": { + "transformers": "Gemma2Model" + } + }, + "file_256": [ + "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", + "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" + ], + "layer_b3": [ + "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", + "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" + ], + "layer_256": [ + "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", + "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" + ], + "tasks": [ + "Gemma2ForCausalLM", + "Gemma2Model", + "Gemma2PreTrainedModel", + "Gemma2ForSequenceClassification", + "Gemma2ForTokenClassification" + ] + } + }, + "info.vit.gemma-3": { + "*": { + "repo": "google/gemma-3-4b-it", + "pkg": { + "0": { + "transformers": "Gemma3Model" + } + }, + "tasks": [ + "Gemma3PreTrainedModel", + "Gemma3TextModel", + "Gemma3ForCausalLM", + "Gemma3ForConditionalGeneration", + "Gemma3Model", + "Gemma3ForSequenceClassification", + "Gemma3TextForSequenceClassification" + ] + } + }, + "info.stst.gemma3-text": { + "*": { + "repo": "google/gemma-3-12b-it", + "pkg": { + "0": { + "transformers": "Gemma3TextModel" + } + }, + "tasks": [ + "Gemma3PreTrainedModel", + "Gemma3TextModel", + "Gemma3ForCausalLM", + "Gemma3ForConditionalGeneration", + "Gemma3Model", + "Gemma3ForSequenceClassification", + "Gemma3TextForSequenceClassification" + ] + } + }, + "info.vit.gemma-3n-e": { + "*": { + "repo": "google/gemma-3n-E4B", + "pkg": { + "0": { + "transformers": "Gemma3nModel" + } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] + } + }, + "info.art.gemma-3n-e": { + "*": { + "repo": "google/gemma-3n-E4B", + "pkg": { + "0": { + "transformers": "Gemma3nAudioEncoder" + } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] + } + }, + "info.stst.gemma-3n-e": { + "*": { + "repo": "google/gemma-3n-E4B", + "pkg": { + "0": { + "transformers": "Gemma3nTextModel" + } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] + } + }, + "info.vit.git": { + "*": { + "repo": "microsoft/git-base", + "pkg": { + "0": { + "transformers": "GitModel" + } + }, + "tasks": [ + "GitForCausalLM", + "GitModel", + "GitPreTrainedModel", + "GitVisionModel" + ] + } + }, + "info.stst.glm-4-chat": { + "*": { + "repo": "zai-org/glm-4-9b-chat", + "pkg": { + "0": { + "transformers": "GlmModel" + } + }, + "tasks": [ + "GlmPreTrainedModel", + "GlmModel", + "GlmForCausalLM", + "GlmForSequenceClassification", + "GlmForTokenClassification" + ] + } + }, + "info.stst.glm-4-0414": { + "*": { + "repo": "zai-org/GLM-4-9B-0414", + "pkg": { + "0": { + "transformers": "Glm4Model" + } + }, + "tasks": [ + "Glm4PreTrainedModel", + "Glm4Model", + "Glm4ForCausalLM", + "Glm4ForSequenceClassification", + "Glm4ForTokenClassification" + ] + } + }, + "info.vit.glm-4v-thinking": { + "*": { + "repo": "zai-org/GLM-4.1V-9B-Thinking", + "pkg": { + "0": { + "transformers": "Glm46VModel" + } + }, + "tasks": [ + "Glm46VModel", + "Glm46VPreTrainedModel", + "Glm46VForConditionalGeneration" + ] + } + }, + "info.moe.glm-4-a": { + "*": { + "repo": "zai-org/GLM-4.5-Air", + "pkg": { + "0": { + "transformers": "Glm4MoeModel" + } + }, + "tasks": [ + "Glm4MoePreTrainedModel", + "Glm4MoeModel", + "Glm4MoeForCausalLM" + ] + } + }, + "info.vit.glm-4v": { + "*": { + "repo": "zai-org/GLM-4.5V", + "pkg": { + "0": { + "transformers": "Glm4vMoeModel" + } + }, + "tasks": [ + "Glm4vMoeForConditionalGeneration", + "Glm4vMoeModel", + "Glm4vMoePreTrainedModel", + "Glm4vMoeTextModel", + "Glm4vMoeVisionModel" + ] + } + }, + "info.moe.glm-4v": { + "*": { + "repo": "zai-org/GLM-4.5V", + "pkg": { + "0": { + "transformers": "Glm4vMoeTextModel" + } + }, + "tasks": [ + "Glm4vMoeForConditionalGeneration", + "Glm4vMoeModel", + "Glm4vMoePreTrainedModel", + "Glm4vMoeTextModel", + "Glm4vMoeVisionModel" + ] + } + }, + "info.stst.glm-4v-thinking": { + "*": { + "repo": "zai-org/GLM-4.1V-9B-Thinking", + "pkg": { + "0": { + "transformers": "Glm4vTextModel" + } + }, + "tasks": [ + "Glm4vForConditionalGeneration", + "Glm4vModel", + "Glm4vPreTrainedModel", + "Glm4vTextModel", + "Glm4vVisionModel" + ] + } + }, + "info.stst.glm-asr-nano-2512": { + "*": { + "repo": "zai-org/GLM-ASR-Nano-2512", + "pkg": { + "0": { + "transformers": "GlmAsrForConditionalGeneration" + } + }, + "tasks": [ + "GlmAsrEncoder", + "GlmAsrForConditionalGeneration", + "GlmAsrPreTrainedModel" + ] + } + }, + "info.vit.glpn-kitti": { + "*": { + "repo": "vinvino02/glpn-kitti", + "pkg": { + "0": { + "transformers": "GLPNModel" + } + }, + "tasks": [ + "GLPNForDepthEstimation", + "GLPNLayer", + "GLPNModel", + "GLPNPreTrainedModel" + ] + } + }, + "info.vit.got-ocr-2-hf": { + "*": { + "repo": "stepfun-ai/GOT-OCR-2.0-hf", + "pkg": { + "0": { + "transformers": "GotOcr2Model" + } + }, + "tasks": [ + "GotOcr2PreTrainedModel", + "GotOcr2Model", + "GotOcr2ForConditionalGeneration" + ] + } + }, + "info.art.gpt2": { + "*": { + "repo": "openai-community/gpt2", + "pkg": { + "0": { + "transformers": "GPT2Model" + } + }, + "tasks": [ + "GPT2DoubleHeadsModel", + "GPT2ForQuestionAnswering", + "GPT2ForSequenceClassification", + "GPT2ForTokenClassification", + "GPT2LMHeadModel", + "GPT2Model", + "GPT2PreTrainedModel" + ] + } + }, + "info.art.gpt-bigcode-santacoder": { + "*": { + "repo": "bigcode/gpt_bigcode-santacoder", + "pkg": { + "0": { + "transformers": "GPTBigCodeModel" + } + }, + "tasks": [ + "GPTBigCodeForSequenceClassification", + "GPTBigCodeForTokenClassification", + "GPTBigCodeForCausalLM", + "GPTBigCodeModel", + "GPTBigCodePreTrainedModel" + ] + } + }, + "info.art.gpt-neo": { + "*": { + "repo": "EleutherAI/gpt-neo-1.3B", + "pkg": { + "0": { + "transformers": "GPTNeoModel" + } + }, + "tasks": [ + "GPTNeoForCausalLM", + "GPTNeoForQuestionAnswering", + "GPTNeoForSequenceClassification", + "GPTNeoForTokenClassification", + "GPTNeoModel", + "GPTNeoPreTrainedModel" + ] + } + }, + "info.stst.gpt-neox": { + "*": { + "repo": "EleutherAI/gpt-neox-20b", + "pkg": { + "0": { + "transformers": "GPTNeoXModel" + } + }, + "tasks": [ + "GPTNeoXForCausalLM", + "GPTNeoXForQuestionAnswering", + "GPTNeoXForSequenceClassification", + "GPTNeoXForTokenClassification", + "GPTNeoXLayer", + "GPTNeoXModel", + "GPTNeoXPreTrainedModel" + ] + } + }, + "info.stst.gpt-neox-japanese": { + "*": { + "repo": "abeja/gpt-neox-japanese-2.7b", + "pkg": { + "0": { + "transformers": "GPTNeoXJapaneseModel" + } + }, + "tasks": [ + "GPTNeoXJapaneseForCausalLM", + "GPTNeoXJapaneseLayer", + "GPTNeoXJapaneseModel", + "GPTNeoXJapanesePreTrainedModel" + ] + } + }, + "info.moe.gpt-oss": { + "*": { + "repo": "openai/gpt-oss-120b", + "pkg": { + "0": { + "transformers": "GptOssModel" + } + }, + "file_256": [ + "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", + "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" + ], + "layer_b3": [ + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", + "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" + ], + "layer_256": [ + "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", + "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" + ], + "tasks": [ + "GptOssForCausalLM", + "GptOssForSequenceClassification", + "GptOssForTokenClassification", + "GptOssModel", + "GptOssPreTrainedModel" + ] + } + }, + "info.art.gpt-j": { + "*": { + "repo": "EleutherAI/gpt-j-6B", + "pkg": { + "0": { + "transformers": "GPTJModel" + } + }, + "tasks": [ + "GPTJForCausalLM", + "GPTJForQuestionAnswering", + "GPTJForSequenceClassification", + "GPTJModel", + "GPTJPreTrainedModel" + ] + } + }, + "info.stst.granite": { + "*": { + "repo": "ibm-granite/granite-3.3-2b-base", + "pkg": { + "0": { + "transformers": "GraniteModel" + } + }, + "tasks": [ + "GraniteForCausalLM", + "GraniteModel", + "GranitePreTrainedModel" + ] + } + }, + "info.moe.powermoe": { + "*": { + "repo": "ibm-research/PowerMoE-3b", + "pkg": { + "0": { + "transformers": "GraniteMoeModel" + } + }, + "tasks": [ + "GraniteMoeForCausalLM", + "GraniteMoeModel", + "GraniteMoePreTrainedModel" + ] + } + }, + "info.ssm.granite-4-h": { + "*": { + "repo": "ibm-granite/granite-4.0-h-small", + "pkg": { + "0": { + "transformers": "GraniteMoeHybridModel" + } + }, + "tasks": [ + "GraniteMoeHybridForCausalLM", + "GraniteMoeHybridModel", + "GraniteMoeHybridPreTrainedModel" + ] + } + }, + "info.moe.moe-active-shared-experts": { + "*": { + "repo": "ibm-research/moe-7b-1b-active-shared-experts", + "pkg": { + "0": { + "transformers": "GraniteMoeSharedModel" + } + }, + "tasks": [ + "GraniteMoeSharedForCausalLM", + "GraniteMoeSharedModel", + "GraniteMoeSharedPreTrainedModel" + ] + } + }, + "info.vit.llava-v1-mistral-hf": { + "*": { + "repo": "llava-hf/llava-v1.6-mistral-7b-hf", + "pkg": { + "0": { + "transformers": "LlavaNextModel" + } + }, + "tasks": [ + "LlavaNextForConditionalGeneration", + "LlavaNextPreTrainedModel", + "LlavaNextModel" + ] + } + }, + "info.detr.grounding-dino": { + "*": { + "repo": "IDEA-Research/grounding-dino-tiny", + "pkg": { + "0": { + "transformers": "GroundingDinoModel" + } + }, + "tasks": [ + "GroundingDinoForObjectDetection", + "GroundingDinoModel", + "GroundingDinoPreTrainedModel" + ] + } + }, + "info.vit.groupvit-gcc-yfcc": { + "*": { + "repo": "nvidia/groupvit-gcc-yfcc", + "pkg": { + "0": { + "transformers": "GroupViTModel" + } + }, + "tasks": [ + "GroupViTModel", + "GroupViTPreTrainedModel", + "GroupViTTextModel", + "GroupViTVisionModel" + ] + } + }, + "info.stst.helium": { + "*": { + "repo": "kyutai/helium-1-2b", + "pkg": { + "0": { + "transformers": "HeliumModel" + } + }, + "tasks": [ + "HeliumPreTrainedModel", + "HeliumModel", + "HeliumForCausalLM", + "HeliumForSequenceClassification", + "HeliumForTokenClassification" + ] + } + }, + "info.vit.dfine-x-coco": { + "*": { + "repo": "ustc-community/dfine_x_coco", + "pkg": { + "0": { + "transformers": "HGNetV2Backbone" + } + }, + "tasks": [ + "HGNetV2Backbone", + "HGNetV2PreTrainedModel", + "HGNetV2ForImageClassification" + ] + } + }, + "info.vit.hiera-224": { + "*": { + "repo": "facebook/hiera-base-224-hf", + "pkg": { + "0": { + "transformers": "HieraModel" + } + }, + "tasks": [ + "HieraForImageClassification", + "HieraForPreTraining", + "HieraBackbone", + "HieraModel", + "HieraPreTrainedModel" + ] + } + }, + "info.aet.hubert-ls960": { + "*": { + "repo": "facebook/hubert-base-ls960", + "pkg": { + "0": { + "transformers": "HubertModel" + } + }, + "tasks": [ + "HubertForCTC", + "HubertForSequenceClassification", + "HubertModel", + "HubertPreTrainedModel" + ] + } + }, + "info.stst.hunyuan": { + "*": { + "repo": "tencent/Hunyuan-7B-Instruct", + "pkg": { + "0": { + "transformers": "HunYuanDenseV1Model" + } + }, + "tasks": [ + "HunYuanDenseV1ForCausalLM", + "HunYuanDenseV1Model", + "HunYuanDenseV1PreTrainedModel", + "HunYuanDenseV1ForSequenceClassification" + ] + } + }, + "info.moe.hunyuan-a": { + "*": { + "repo": "tencent/Hunyuan-A13B-Instruct", + "pkg": { + "0": { + "transformers": "HunYuanMoEV1Model" + } + }, + "tasks": [ + "HunYuanMoEV1ForCausalLM", + "HunYuanMoEV1Model", + "HunYuanMoEV1PreTrainedModel", + "HunYuanMoEV1ForSequenceClassification" + ] + } + }, + "info.art.ibert-roberta": { + "*": { + "repo": "kssteven/ibert-roberta-base", + "pkg": { + "0": { + "transformers": "IBertModel" + } + }, + "tasks": [ + "IBertForMaskedLM", + "IBertForMultipleChoice", + "IBertForQuestionAnswering", + "IBertForSequenceClassification", + "IBertForTokenClassification", + "IBertModel", + "IBertPreTrainedModel" + ] + } + }, + "info.vit.idefics": { + "*": { + "repo": "HuggingFaceM4/idefics-9b", + "pkg": { + "0": { + "transformers": "IdeficsModel" + } + }, + "tasks": [ + "IdeficsForVisionText2Text", + "IdeficsModel", + "IdeficsPreTrainedModel" + ] + } + }, + "info.vit.idefics2": { + "*": { + "repo": "HuggingFaceM4/idefics2-8b", + "pkg": { + "0": { + "transformers": "Idefics2Model" + } + }, + "tasks": [ + "Idefics2ForConditionalGeneration", + "Idefics2PreTrainedModel", + "Idefics2Model" + ] + } + }, + "info.vit.idefics3-llama3": { + "*": { + "repo": "HuggingFaceM4/Idefics3-8B-Llama3", + "pkg": { + "0": { + "transformers": "Idefics3Model" + } + }, + "tasks": [ + "Idefics3ForConditionalGeneration", + "Idefics3PreTrainedModel", + "Idefics3Model", + "Idefics3VisionTransformer" + ] + } + }, + "info.vit.siglip-patch16-224": { + "*": { + "repo": "google/siglip-base-patch16-224", + "pkg": { + "0": { + "transformers": "Idefics3VisionTransformer" + } + }, + "tasks": [ + "Idefics3ForConditionalGeneration", + "Idefics3PreTrainedModel", + "Idefics3Model", + "Idefics3VisionTransformer" + ] + } + }, + "info.vit.ijepa-vith14": { + "*": { + "repo": "facebook/ijepa_vith14_1k", + "pkg": { + "0": { + "transformers": "IJepaModel" + } + }, + "tasks": [ + "IJepaPreTrainedModel", + "IJepaModel", + "IJepaForImageClassification" + ] + } + }, + "info.art.imagegpt": { + "*": { + "repo": "openai/imagegpt-small", + "pkg": { + "0": { + "transformers": "ImageGPTModel" + } + }, + "tasks": [ + "ImageGPTForCausalImageModeling", + "ImageGPTForImageClassification", + "ImageGPTModel", + "ImageGPTPreTrainedModel" + ] + } + }, + "info.stst.informer-tourism-monthly": { + "*": { + "repo": "huggingface/informer-tourism-monthly", + "pkg": { + "0": { + "transformers": "InformerModel" + } + }, + "tasks": [ + "InformerForPrediction", + "InformerModel", + "InformerPreTrainedModel" + ] + } + }, + "info.vit.blip-flan-t5": { + "*": { + "repo": "Salesforce/instructblip-flan-t5-xl", + "pkg": { + "0": { + "transformers": "InstructBlipModel" + } + }, + "tasks": [ + "InstructBlipQFormerModel", + "InstructBlipPreTrainedModel", + "InstructBlipModel", + "InstructBlipForConditionalGeneration", + "InstructBlipVisionModel" + ] + } + }, + "info.vit.internvl3-hf": { + "*": { + "repo": "OpenGVLab/InternVL3-1B-hf", + "pkg": { + "0": { + "transformers": "InternVLModel" + } + }, + "tasks": [ + "InternVLVisionPreTrainedModel", + "InternVLVisionModel", + "InternVLPreTrainedModel", + "InternVLModel", + "InternVLForConditionalGeneration" + ] + } + }, + "info.stst.jais-2-chat": { + "*": { + "repo": "inceptionai/Jais-2-8B-Chat", + "pkg": { + "0": { + "transformers": "Jais2Model" + } + }, + "tasks": [ + "Jais2Model", + "Jais2ForCausalLM", + "Jais2PreTrainedModel" + ] + } + }, + "info.ssm.jamba-v0": { + "*": { + "repo": "ai21labs/Jamba-v0.1", + "pkg": { + "0": { + "transformers": "JambaModel" + } + }, + "tasks": [ + "JambaForCausalLM", + "JambaForSequenceClassification", + "JambaModel", + "JambaPreTrainedModel" + ] + } + }, + "info.vit.janus": { + "*": { + "repo": "deepseek-community/Janus-Pro-1B", + "pkg": { + "0": { + "transformers": "JanusModel" + } + }, + "tasks": [ + "JanusPreTrainedModel", + "JanusForConditionalGeneration", + "JanusModel", + "JanusVQVAE", + "JanusVisionModel" + ] + } + }, + "info.moe.jetmoe": { + "*": { + "repo": "jetmoe/jetmoe-8b", + "pkg": { + "0": { + "transformers": "JetMoeModel" + } + }, + "tasks": [ + "JetMoeForCausalLM", + "JetMoeModel", + "JetMoePreTrainedModel", + "JetMoeForSequenceClassification" + ] + } + }, + "info.vit.kosmos-2-patch14-224": { + "*": { + "repo": "microsoft/kosmos-2-patch14-224", + "pkg": { + "0": { + "transformers": "Kosmos2Model" + } + }, + "tasks": [ + "Kosmos2ForConditionalGeneration", + "Kosmos2Model", + "Kosmos2PreTrainedModel" + ] + } + }, + "info.vit.kosmos-2": { + "*": { + "repo": "microsoft/kosmos-2.5", + "pkg": { + "0": { + "transformers": "Kosmos2_5Model" + } + }, + "tasks": [ + "Kosmos2_5ForConditionalGeneration", + "Kosmos2_5Model", + "Kosmos2_5PreTrainedModel" + ] + } + }, + "info.stst.stt-en-trfs": { + "*": { + "repo": "kyutai/stt-2.6b-en-trfs", + "pkg": { + "0": { + "transformers": "KyutaiSpeechToTextModel" + } + }, + "tasks": [ + "KyutaiSpeechToTextPreTrainedModel", + "KyutaiSpeechToTextModel", + "KyutaiSpeechToTextForConditionalGeneration" + ] + } + }, + "info.aet.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrForCTC" + } + }, + "tasks": [ + "LasrForCTC", + "LasrEncoder", + "LasrPreTrainedModel" + ] + } + }, + "info.stst.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrEncoder" + } + }, + "tasks": [ + "LasrForCTC", + "LasrEncoder", + "LasrPreTrainedModel" + ] + } + }, + "info.art.layoutlm-uncased": { + "*": { + "repo": "microsoft/layoutlm-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMModel" + } + }, + "tasks": [ + "LayoutLMForMaskedLM", + "LayoutLMForSequenceClassification", + "LayoutLMForTokenClassification", + "LayoutLMForQuestionAnswering", + "LayoutLMModel", + "LayoutLMPreTrainedModel" + ] + } + }, + "info.art.layoutlmv2-uncased": { + "*": { + "repo": "microsoft/layoutlmv2-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMv2Model" + } + }, + "tasks": [ + "LayoutLMv2ForQuestionAnswering", + "LayoutLMv2ForSequenceClassification", + "LayoutLMv2ForTokenClassification", + "LayoutLMv2Layer", + "LayoutLMv2Model", + "LayoutLMv2PreTrainedModel" + ] + } + }, + "info.vit.layoutlmv3": { + "*": { + "repo": "microsoft/layoutlmv3-base", + "pkg": { + "0": { + "transformers": "LayoutLMv3Model" + } + }, + "tasks": [ + "LayoutLMv3ForQuestionAnswering", + "LayoutLMv3ForSequenceClassification", + "LayoutLMv3ForTokenClassification", + "LayoutLMv3Model", + "LayoutLMv3PreTrainedModel" + ] + } + }, + "info.stst.led-16384": { + "*": { + "repo": "allenai/led-base-16384", + "pkg": { + "0": { + "transformers": "LEDModel" + } + }, + "tasks": [ + "LEDForConditionalGeneration", + "LEDForQuestionAnswering", + "LEDForSequenceClassification", + "LEDModel", + "LEDPreTrainedModel" + ] + } + }, + "info.gan.levit-128s": { + "*": { + "repo": "facebook/levit-128S", + "pkg": { + "0": { + "transformers": "LevitModel" + } + }, + "tasks": [ + "LevitForImageClassification", + "LevitForImageClassificationWithTeacher", + "LevitModel", + "LevitPreTrainedModel" + ] + } + }, + "info.stst.lfm": { + "*": { + "repo": "LiquidAI/LFM2-1.2B", + "pkg": { + "0": { + "transformers": "Lfm2Model" + } + }, + "tasks": [ + "Lfm2ForCausalLM", + "Lfm2Model", + "Lfm2PreTrainedModel" + ] + } + }, + "info.moe.lfm2-a": { + "*": { + "repo": "LiquidAI/LFM2-8B-A1B", + "pkg": { + "0": { + "transformers": "Lfm2MoeModel" + } + }, + "tasks": [ + "Lfm2MoeForCausalLM", + "Lfm2MoeModel", + "Lfm2MoePreTrainedModel" + ] + } + }, + "info.vit.lfm2-vl": { + "*": { + "repo": "LiquidAI/LFM2-VL-1.6B", + "pkg": { + "0": { + "transformers": "Lfm2VlModel" + } + }, + "tasks": [ + "Lfm2VlForConditionalGeneration", + "Lfm2VlPreTrainedModel", + "Lfm2VlModel" + ] + } + }, + "info.aet.lightglue-superpoint": { + "*": { + "repo": "ETH-CVG/lightglue_superpoint", + "pkg": { + "0": { + "transformers": "LightGlueForKeypointMatching" + } + }, + "tasks": [ + "LightGluePreTrainedModel", + "LightGlueForKeypointMatching" + ] + } + }, + "info.art.lilt-roberta-en": { + "*": { + "repo": "SCUT-DLVCLab/lilt-roberta-en-base", + "pkg": { + "0": { + "transformers": "LiltModel" + } + }, + "tasks": [ + "LiltForQuestionAnswering", + "LiltForSequenceClassification", + "LiltForTokenClassification", + "LiltModel", + "LiltPreTrainedModel" + ] + } + }, + "info.vit.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4ForConditionalGeneration" + } + }, + "tasks": [ + "Llama4PreTrainedModel", + "Llama4TextModel", + "Llama4VisionModel", + "Llama4ForCausalLM", + "Llama4ForConditionalGeneration" + ] + } + }, + "info.moe.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4TextModel" + } + }, + "tasks": [ + "Llama4PreTrainedModel", + "Llama4TextModel", + "Llama4VisionModel", + "Llama4ForCausalLM", + "Llama4ForConditionalGeneration" + ] + } + }, + "info.vit.llava": { + "*": { + "repo": "llava-hf/llava-9b", + "pkg": { + "0": { + "transformers": "LlavaModel" + } + }, + "file_256": [ + "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" + ], + "layer_b3": [ + "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" + ], + "layer_256": [ + "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" + ], + "tasks": [ + "LlavaForConditionalGeneration", + "LlavaPreTrainedModel", + "LlavaModel" + ] + } + }, + "info.vit.llava-next-video-hf": { + "*": { + "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", + "pkg": { + "0": { + "transformers": "LlavaNextVideoModel" + } + }, + "tasks": [ + "LlavaNextVideoForConditionalGeneration", + "LlavaNextVideoModel", + "LlavaNextVideoPreTrainedModel" + ] + } + }, + "info.vit.llava-onevision-qwen2-ov-hf": { + "*": { + "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", + "pkg": { + "0": { + "transformers": "LlavaOnevisionModel" + } + }, + "tasks": [ + "LlavaOnevisionModel", + "LlavaOnevisionForConditionalGeneration", + "LlavaOnevisionPreTrainedModel" + ] + } + }, + "info.stst.longcat-flash-chat": { + "*": { + "repo": "meituan-longcat/LongCat-Flash-Chat", + "pkg": { + "0": { + "transformers": "LongcatFlashModel" + } + }, + "tasks": [ + "LongcatFlashPreTrainedModel", + "LongcatFlashModel", + "LongcatFlashForCausalLM" + ] + } + }, + "info.art.longformer-4096": { + "*": { + "repo": "allenai/longformer-base-4096", + "pkg": { + "0": { + "transformers": "LongformerModel" + } + }, + "tasks": [ + "LongformerForMaskedLM", + "LongformerForMultipleChoice", + "LongformerForQuestionAnswering", + "LongformerForSequenceClassification", + "LongformerForTokenClassification", + "LongformerModel", + "LongformerPreTrainedModel", + "LongformerSelfAttention" + ] + } + }, + "info.stst.long-t5-local": { + "*": { + "repo": "google/long-t5-local-base", + "pkg": { + "0": { + "transformers": "LongT5Model" + } + }, + "tasks": [ + "LongT5EncoderModel", + "LongT5ForConditionalGeneration", + "LongT5Model", + "LongT5PreTrainedModel" + ] + } + }, + "info.art.luke": { + "*": { + "repo": "studio-ousia/luke-base", + "pkg": { + "0": { + "transformers": "LukeModel" + } + }, + "tasks": [ + "LukeForEntityClassification", + "LukeForEntityPairClassification", + "LukeForEntitySpanClassification", + "LukeForMultipleChoice", + "LukeForQuestionAnswering", + "LukeForSequenceClassification", + "LukeForTokenClassification", + "LukeForMaskedLM", + "LukeModel", + "LukePreTrainedModel" + ] + } + }, + "info.art.lxmert-uncased": { + "*": { + "repo": "unc-nlp/lxmert-base-uncased", + "pkg": { + "0": { + "transformers": "LxmertModel" + } + }, + "tasks": [ + "LxmertEncoder", + "LxmertForPreTraining", + "LxmertForQuestionAnswering", + "LxmertModel", + "LxmertPreTrainedModel", + "LxmertVisualFeatureEncoder", + "LxmertXLayer" + ] + } + }, + "info.stst.m": { + "*": { + "repo": "facebook/m2m100_418M", + "pkg": { + "0": { + "transformers": "M2M100Model" + } + }, + "tasks": [ + "M2M100ForConditionalGeneration", + "M2M100Model", + "M2M100PreTrainedModel" + ] + } + }, + "info.ssm.mamba": { + "*": { + "repo": "state-spaces/mamba-2.8b", + "pkg": { + "0": { + "transformers": "MambaModel" + } + }, + "tasks": [ + "MambaForCausalLM", + "MambaModel", + "MambaPreTrainedModel", + "MambaCache" + ] + } + }, + "info.ssm.mamba2": { + "*": { + "repo": "AntonV/mamba2-2.7b-hf", + "pkg": { + "0": { + "transformers": "Mamba2Model" + } + }, + "tasks": [ + "Mamba2ForCausalLM", + "Mamba2Model", + "Mamba2PreTrainedModel" + ] + } + }, + "info.stst.opus-mt-en-de": { + "*": { + "repo": "Helsinki-NLP/opus-mt-en-de", + "pkg": { + "0": { + "transformers": "MarianModel" + } + }, + "tasks": [ + "MarianForCausalLM", + "MarianModel", + "MarianMTModel", + "MarianPreTrainedModel" + ] + } + }, + "info.art.markuplm": { + "*": { + "repo": "microsoft/markuplm-base", + "pkg": { + "0": { + "transformers": "MarkupLMModel" + } + }, + "tasks": [ + "MarkupLMForQuestionAnswering", + "MarkupLMForSequenceClassification", + "MarkupLMForTokenClassification", + "MarkupLMModel", + "MarkupLMPreTrainedModel" + ] + } + }, + "info.detr.mask2former-swin-coco-instance": { + "*": { + "repo": "facebook/mask2former-swin-small-coco-instance", + "pkg": { + "0": { + "transformers": "Mask2FormerModel" + } + }, + "tasks": [ + "Mask2FormerForUniversalSegmentation", + "Mask2FormerModel", + "Mask2FormerPreTrainedModel" + ] + } + }, + "info.detr.maskformer-swin-ade": { + "*": { + "repo": "facebook/maskformer-swin-base-ade", + "pkg": { + "0": { + "transformers": "MaskFormerModel" + } + }, + "tasks": [ + "MaskFormerForInstanceSegmentation", + "MaskFormerModel", + "MaskFormerPreTrainedModel" + ] + } + }, + "info.vit.swin-patch4-window7-224": { + "*": { + "repo": "microsoft/swin-tiny-patch4-window7-224", + "pkg": { + "0": { + "transformers": "MaskFormerSwinModel" + } + }, + "tasks": [ + "MaskFormerSwinBackbone", + "MaskFormerSwinModel", + "MaskFormerSwinPreTrainedModel" + ] + } + }, + "info.stst.mbart-cc25": { + "*": { + "repo": "facebook/mbart-large-cc25", + "pkg": { + "0": { + "transformers": "MBartModel" + } + }, + "tasks": [ + "MBartForCausalLM", + "MBartForConditionalGeneration", + "MBartForQuestionAnswering", + "MBartForSequenceClassification", + "MBartModel", + "MBartPreTrainedModel" + ] + } + }, + "info.art.megatron-bert-uncased": { + "*": { + "repo": "nvidia/megatron-bert-uncased-345m", + "pkg": { + "0": { + "transformers": "MegatronBertModel" + } + }, + "tasks": [ + "MegatronBertForCausalLM", + "MegatronBertForMaskedLM", + "MegatronBertForMultipleChoice", + "MegatronBertForNextSentencePrediction", + "MegatronBertForPreTraining", + "MegatronBertForQuestionAnswering", + "MegatronBertForSequenceClassification", + "MegatronBertForTokenClassification", + "MegatronBertModel", + "MegatronBertPreTrainedModel" + ] + } + }, + "info.vit.metaclip-2-worldwide-huge-quickgelu": { + "*": { + "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", + "pkg": { + "0": { + "transformers": "MetaClip2Model" + } + }, + "tasks": [ + "MetaClip2Model", + "MetaClip2PreTrainedModel", + "MetaClip2TextModel", + "MetaClip2TextModelWithProjection", + "MetaClip2VisionModel", + "MetaClip2VisionModelWithProjection", + "MetaClip2ForImageClassification" + ] + } + }, + "info.vit.mgp-str": { + "*": { + "repo": "alibaba-damo/mgp-str-base", + "pkg": { + "0": { + "transformers": "MgpstrForSceneTextRecognition" + } + }, + "tasks": [ + "MgpstrModel", + "MgpstrPreTrainedModel", + "MgpstrForSceneTextRecognition" + ] + } + }, + "info.gan.mimi": { + "*": { + "repo": "kyutai/mimi", + "pkg": { + "0": { + "transformers": "MimiModel" + } + }, + "tasks": [ + "MimiModel", + "MimiPreTrainedModel" + ] + } + }, + "info.moe.max-text-01-hf": { + "*": { + "repo": "MiniMaxAI/MiniMax-Text-01-hf", + "pkg": { + "0": { + "transformers": "MiniMaxModel" + } + }, + "tasks": [ + "MiniMaxPreTrainedModel", + "MiniMaxModel", + "MiniMaxForCausalLM", + "MiniMaxForSequenceClassification", + "MiniMaxForTokenClassification", + "MiniMaxForQuestionAnswering" + ] + } + }, + "info.stst.stral-2410": { + "*": { + "repo": "mistralai/Ministral-8B-Instruct-2410", + "pkg": { + "0": { + "transformers": "MinistralModel" + } + }, + "tasks": [ + "MinistralPreTrainedModel", + "MinistralModel", + "MinistralForCausalLM", + "MinistralForSequenceClassification", + "MinistralForTokenClassification", + "MinistralForQuestionAnswering" + ] + } + }, + "info.stst.stral-3-2512": { + "*": { + "repo": "mistralai/Ministral-3-8B-Base-2512", + "pkg": { + "0": { + "transformers": "Ministral3Model" + } + }, + "tasks": [ + "Ministral3ForCausalLM", + "Ministral3ForQuestionAnswering", + "Ministral3Model", + "Ministral3PreTrainedModel", + "Ministral3ForSequenceClassification", + "Ministral3ForTokenClassification" + ] + } + }, + "info.stst.mistral-v0": { + "*": { + "repo": "mistralai/Mistral-7B-v0.1", + "pkg": { + "0": { + "transformers": "MistralModel" + } + }, + "tasks": [ + "MistralForCausalLM", + "MistralForQuestionAnswering", + "MistralModel", + "MistralPreTrainedModel", + "MistralForSequenceClassification", + "MistralForTokenClassification" + ] + } + }, + "info.vit.mistral-3-2503": { + "*": { + "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", + "pkg": { + "0": { + "transformers": "Mistral3Model" + } + }, + "tasks": [ + "Mistral3Model", + "Mistral3PreTrainedModel", + "Mistral3ForConditionalGeneration" + ] + } + }, + "info.moe.mixtral-8x": { + "*": { + "repo": "mistralai/Mixtral-8x7B-v0.1", + "pkg": { + "0": { + "transformers": "MixtralModel" + } + }, + "tasks": [ + "MixtralForCausalLM", + "MixtralForQuestionAnswering", + "MixtralModel", + "MixtralPreTrainedModel", + "MixtralForSequenceClassification", + "MixtralForTokenClassification" + ] + } + }, + "info.vit.mlcd-vit-bigg-patch14-336": { + "*": { + "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", + "pkg": { + "0": { + "transformers": "MLCDVisionModel" + } + }, + "tasks": [ + "MLCDPreTrainedModel", + "MLCDVisionModel" + ] + } + }, + "info.vit.llama-3-vision": { + "*": { + "repo": "meta-llama/Llama-3.2-11B-Vision", + "pkg": { + "0": { + "transformers": "MllamaModel" + } + }, + "tasks": [ + "MllamaForConditionalGeneration", + "MllamaForCausalLM", + "MllamaTextModel", + "MllamaVisionModel", + "MllamaPreTrainedModel", + "MllamaModel" + ] + } + }, + "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "*": { + "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "pkg": { + "0": { + "transformers": "MMGroundingDinoModel" + } + }, + "tasks": [ + "MMGroundingDinoForObjectDetection", + "MMGroundingDinoModel", + "MMGroundingDinoPreTrainedModel" + ] + } + }, + "info.art.mobilebert-uncased": { + "*": { + "repo": "google/mobilebert-uncased", + "pkg": { + "0": { + "transformers": "MobileBertModel" + } + }, + "tasks": [ + "MobileBertForMaskedLM", + "MobileBertForMultipleChoice", + "MobileBertForNextSentencePrediction", + "MobileBertForPreTraining", + "MobileBertForQuestionAnswering", + "MobileBertForSequenceClassification", + "MobileBertForTokenClassification", + "MobileBertLayer", + "MobileBertModel", + "MobileBertPreTrainedModel" + ] + } + }, + "info.vit.mobilenet-v1-1--224": { + "*": { + "repo": "google/mobilenet_v1_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV1Model" + } + }, + "tasks": [ + "MobileNetV1ForImageClassification", + "MobileNetV1Model", + "MobileNetV1PreTrainedModel" + ] + } + }, + "info.vit.mobilenet-v2-1--224": { + "*": { + "repo": "google/mobilenet_v2_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV2Model" + } + }, + "tasks": [ + "MobileNetV2ForImageClassification", + "MobileNetV2ForSemanticSegmentation", + "MobileNetV2Model", + "MobileNetV2PreTrainedModel" + ] + } + }, + "info.vit.mobilevit": { + "*": { + "repo": "apple/mobilevit-small", + "pkg": { + "0": { + "transformers": "MobileViTModel" + } + }, + "tasks": [ + "MobileViTForImageClassification", + "MobileViTForSemanticSegmentation", + "MobileViTModel", + "MobileViTPreTrainedModel" + ] + } + }, + "info.vit.mobilevitv2-1": { + "*": { + "repo": "apple/mobilevitv2-1.0-imagenet1k-256", + "pkg": { + "0": { + "transformers": "MobileViTV2Model" + } + }, + "tasks": [ + "MobileViTV2ForImageClassification", + "MobileViTV2ForSemanticSegmentation", + "MobileViTV2Model", + "MobileViTV2PreTrainedModel" + ] + } + }, + "info.aet.modernbert": { + "*": { + "repo": "answerdotai/ModernBERT-base", + "pkg": { + "0": { + "transformers": "ModernBertModel" + } + }, + "tasks": [ + "ModernBertModel", + "ModernBertPreTrainedModel", + "ModernBertForMaskedLM", + "ModernBertForSequenceClassification", + "ModernBertForTokenClassification", + "ModernBertForQuestionAnswering", + "ModernBertForMultipleChoice" + ] + } + }, + "info.aet.test-dec": { + "*": { + "repo": "blab-jhu/test-32m-dec", + "pkg": { + "0": { + "transformers": "ModernBertDecoderModel" + } + }, + "tasks": [ + "ModernBertDecoderModel", + "ModernBertDecoderPreTrainedModel", + "ModernBertDecoderForCausalLM", + "ModernBertDecoderForSequenceClassification" + ] + } + }, + "info.stst.moonshine": { + "*": { + "repo": "UsefulSensors/moonshine-tiny", + "pkg": { + "0": { + "transformers": "MoonshineModel" + } + }, + "tasks": [ + "MoonshineModel", + "MoonshinePreTrainedModel", + "MoonshineForConditionalGeneration" + ] + } + }, + "info.stst.hf-moshiko": { + "*": { + "repo": "kmhf/hf-moshiko", + "pkg": { + "0": { + "transformers": "MoshiModel" + } + }, + "tasks": [ + "MoshiForCausalLM", + "MoshiForConditionalGeneration", + "MoshiModel", + "MoshiPreTrainedModel" + ] + } + }, + "info.art.mpnet": { + "*": { + "repo": "microsoft/mpnet-base", + "pkg": { + "0": { + "transformers": "MPNetModel" + } + }, + "tasks": [ + "MPNetForMaskedLM", + "MPNetForMultipleChoice", + "MPNetForQuestionAnswering", + "MPNetForSequenceClassification", + "MPNetForTokenClassification", + "MPNetLayer", + "MPNetModel", + "MPNetPreTrainedModel" + ] + } + }, + "info.art.mpt": { + "*": { + "repo": "mosaicml/mpt-7b", + "pkg": { + "0": { + "transformers": "MptModel" + } + }, + "tasks": [ + "MptForCausalLM", + "MptModel", + "MptPreTrainedModel", + "MptForSequenceClassification", + "MptForTokenClassification", + "MptForQuestionAnswering" + ] + } + }, + "info.art.mra-512-4": { + "*": { + "repo": "uw-madison/mra-base-512-4", + "pkg": { + "0": { + "transformers": "MraModel" + } + }, + "tasks": [ + "MraForMaskedLM", + "MraForMultipleChoice", + "MraForQuestionAnswering", + "MraForSequenceClassification", + "MraForTokenClassification", + "MraLayer", + "MraModel", + "MraPreTrainedModel" + ] + } + }, + "info.stst.mt5": { + "*": { + "repo": "google/mt5-small", + "pkg": { + "0": { + "transformers": "MT5Model" + } + }, + "identifiers": [ + [ + 250112, + 2048 + ], + "text_encoders.mt5xl.transformer.shared.weight" + ], + "file_256": [ + "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", + "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" + ], + "layer_b3": [ + "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51" + ], + "layer_256": [ + "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", + "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" + ], + "tasks": [ + "MT5EncoderModel", + "MT5ForConditionalGeneration", + "MT5ForQuestionAnswering", + "MT5ForSequenceClassification", + "MT5ForTokenClassification", + "MT5Model", + "MT5PreTrainedModel" + ] + } + }, + "info.art.musicgen": { + "*": { + "repo": "facebook/musicgen-small", + "pkg": { + "0": { + "transformers": "MusicgenModel" + } + }, + "tasks": [ + "MusicgenForConditionalGeneration", + "MusicgenForCausalLM", + "MusicgenModel", + "MusicgenPreTrainedModel" + ] + } + }, + "info.art.musicgen-melody": { + "*": { + "repo": "facebook/musicgen-melody", + "pkg": { + "0": { + "transformers": "MusicgenMelodyModel" + } + }, + "tasks": [ + "MusicgenMelodyForConditionalGeneration", + "MusicgenMelodyForCausalLM", + "MusicgenMelodyModel", + "MusicgenMelodyPreTrainedModel" + ] + } + }, + "info.stst.mvp": { + "*": { + "repo": "RUCAIBox/mvp", + "pkg": { + "0": { + "transformers": "MvpModel" + } + }, + "tasks": [ + "MvpForCausalLM", + "MvpForConditionalGeneration", + "MvpForQuestionAnswering", + "MvpForSequenceClassification", + "MvpModel", + "MvpPreTrainedModel" + ] + } + }, + "info.stst.nanochat-d32": { + "*": { + "repo": "karpathy/nanochat-d32", + "pkg": { + "0": { + "transformers": "NanoChatModel" + } + }, + "tasks": [ + "NanoChatPreTrainedModel", + "NanoChatModel", + "NanoChatForCausalLM" + ] + } + }, + "info.stst.nemotron-3-hf": { + "*": { + "repo": "mgoin/nemotron-3-8b-chat-4k-sft-hf", + "pkg": { + "0": { + "transformers": "NemotronModel" + } + }, + "tasks": [ + "NemotronForQuestionAnswering", + "NemotronForCausalLM", + "NemotronModel", + "NemotronPreTrainedModel", + "NemotronForSequenceClassification", + "NemotronForTokenClassification" + ] + } + }, + "info.moe.nllb-moe": { + "*": { + "repo": "facebook/nllb-moe-54b", + "pkg": { + "0": { + "transformers": "NllbMoeModel" + } + }, + "tasks": [ + "NllbMoeForConditionalGeneration", + "NllbMoeModel", + "NllbMoePreTrainedModel", + "NllbMoeTop2Router", + "NllbMoeSparseMLP" + ] + } + }, + "info.art.nystromformer-512": { + "*": { + "repo": "uw-madison/nystromformer-512", + "pkg": { + "0": { + "transformers": "NystromformerModel" + } + }, + "tasks": [ + "NystromformerForMaskedLM", + "NystromformerForMultipleChoice", + "NystromformerForQuestionAnswering", + "NystromformerForSequenceClassification", + "NystromformerForTokenClassification", + "NystromformerLayer", + "NystromformerModel", + "NystromformerPreTrainedModel" + ] + } + }, + "info.stst.olmo-hf": { + "*": { + "repo": "allenai/OLMo-7B-hf", + "pkg": { + "0": { + "transformers": "OlmoModel" + } + }, + "tasks": [ + "OlmoForCausalLM", + "OlmoModel", + "OlmoPreTrainedModel" + ] + } + }, + "info.stst.olmo2-1124-hf": { + "*": { + "repo": "allenai/Olmo-2-1124-7B", + "pkg": { + "0": { + "transformers": "Olmo2Model" + } + }, + "tasks": [ + "Olmo2ForCausalLM", + "Olmo2Model", + "Olmo2PreTrainedModel" + ] + } + }, + "info.stst.olmo-3-0725": { + "*": { + "repo": "allenai/OLMo-3-0725-1B", + "pkg": { + "0": { + "transformers": "Olmo3Model" + } + }, + "tasks": [ + "Olmo3ForCausalLM", + "Olmo3Model", + "Olmo3PreTrainedModel" + ] + } + }, + "info.moe.olmoe-0924": { + "*": { + "repo": "allenai/OLMoE-1B-7B-0924", + "pkg": { + "0": { + "transformers": "OlmoeModel" + } + }, + "tasks": [ + "OlmoeForCausalLM", + "OlmoeModel", + "OlmoePreTrainedModel" + ] + } + }, + "info.detr.omdet-turbo-swin-hf": { + "*": { + "repo": "omlab/omdet-turbo-swin-tiny-hf", + "pkg": { + "0": { + "transformers": "OmDetTurboForObjectDetection" + } + }, + "tasks": [ + "OmDetTurboForObjectDetection", + "OmDetTurboPreTrainedModel" + ] + } + }, + "info.detr.oneformer-ade-swin": { + "*": { + "repo": "shi-labs/oneformer_ade20k_swin_tiny", + "pkg": { + "0": { + "transformers": "OneFormerModel" + } + }, + "tasks": [ + "OneFormerForUniversalSegmentation", + "OneFormerModel", + "OneFormerPreTrainedModel" + ] + } + }, + "info.art.openai-gpt": { + "*": { + "repo": "openai-community/openai-gpt", + "pkg": { + "0": { + "transformers": "OpenAIGPTModel" + } + }, + "tasks": [ + "OpenAIGPTDoubleHeadsModel", + "OpenAIGPTForSequenceClassification", + "OpenAIGPTLMHeadModel", + "OpenAIGPTModel", + "OpenAIGPTPreTrainedModel" + ] + } + }, + "info.art.opt": { + "*": { + "repo": "facebook/opt-350m", + "pkg": { + "0": { + "transformers": "OPTModel" + } + }, + "tasks": [ + "OPTForCausalLM", + "OPTModel", + "OPTPreTrainedModel", + "OPTForSequenceClassification", + "OPTForQuestionAnswering" + ] + } + }, + "info.vit.ovis2-hf": { + "*": { + "repo": "thisisiron/Ovis2-1B-hf", + "pkg": { + "0": { + "transformers": "Ovis2Model" + } + }, + "tasks": [ + "Ovis2PreTrainedModel", + "Ovis2Model", + "Ovis2ForConditionalGeneration" + ] + } + }, + "info.vit.owlv2-patch16": { + "*": { + "repo": "google/owlv2-base-patch16", + "pkg": { + "0": { + "transformers": "Owlv2Model" + } + }, + "tasks": [ + "Owlv2Model", + "Owlv2PreTrainedModel", + "Owlv2TextModel", + "Owlv2VisionModel", + "Owlv2ForObjectDetection" + ] + } + }, + "info.vit.owlvit-patch32": { + "*": { + "repo": "google/owlvit-base-patch32", + "pkg": { + "0": { + "transformers": "OwlViTModel" + } + }, + "tasks": [ + "OwlViTModel", + "OwlViTPreTrainedModel", + "OwlViTTextModel", + "OwlViTVisionModel", + "OwlViTForObjectDetection" + ] + } + }, + "info.vit.paligemma": { + "*": { + "repo": "google/paligemma2-3b-mix-224", + "pkg": { + "0": { + "transformers": "PaliGemmaModel" + } + }, + "tasks": [ + "PaliGemmaForConditionalGeneration", + "PaliGemmaPreTrainedModel", + "PaliGemmaModel" + ] + } + }, + "info.aet.parakeet-ctc-b": { + "*": { + "repo": "nvidia/parakeet-ctc-1.1b", + "pkg": { + "0": { + "transformers": "ParakeetForCTC" + } + }, + "tasks": [ + "ParakeetForCTC", + "ParakeetEncoder", + "ParakeetPreTrainedModel" + ] + } + }, + "info.stst.parakeet-ctc-b": { + "*": { + "repo": "nvidia/parakeet-ctc-1.1b", + "pkg": { + "0": { + "transformers": "ParakeetEncoder" + } + }, + "tasks": [ + "ParakeetForCTC", + "ParakeetEncoder", + "ParakeetPreTrainedModel" + ] + } + }, + "info.mlp.patchtsmixer-etth1-pretrain": { + "*": { + "repo": "ibm/patchtsmixer-etth1-pretrain", + "pkg": { + "0": { + "transformers": "PatchTSMixerModel" + } + }, + "tasks": [ + "PatchTSMixerPreTrainedModel", + "PatchTSMixerModel", + "PatchTSMixerForPretraining", + "PatchTSMixerForPrediction", + "PatchTSMixerForTimeSeriesClassification", + "PatchTSMixerForRegression" + ] + } + }, + "info.art.patchtst": { + "*": { + "repo": "ibm/patchtst", + "pkg": { + "0": { + "transformers": "PatchTSTModel" + } + }, + "tasks": [ + "PatchTSTModel", + "PatchTSTPreTrainedModel", + "PatchTSTForPrediction", + "PatchTSTForPretraining", + "PatchTSTForRegression", + "PatchTSTForClassification" + ] + } + }, + "info.stst.pe-av": { + "*": { + "repo": "facebook/pe-av-large", + "pkg": { + "0": { + "transformers": "PeAudioModel" + } + }, + "tasks": [ + "PeAudioFrameLevelModel", + "PeAudioModel", + "PeAudioEncoder" + ] + } + }, + "info.aet.pe-av": { + "*": { + "repo": "facebook/pe-av-large", + "pkg": { + "0": { + "transformers": "PeAudioVideoModel" + } + }, + "tasks": [ + "PeAudioVideoModel", + "PeAudioVideoEncoder" + ] + } + }, + "info.vit.pe-av": { + "*": { + "repo": "facebook/pe-av-large", + "pkg": { + "0": { + "transformers": "PeVideoEncoder" + } + }, + "tasks": [ + "PeVideoEncoder", + "PeVideoModel" + ] + } + }, + "info.stst.pegasus": { + "*": { + "repo": "google/pegasus-large", + "pkg": { + "0": { + "transformers": "PegasusModel" + } + }, + "tasks": [ + "PegasusForCausalLM", + "PegasusForConditionalGeneration", + "PegasusModel", + "PegasusPreTrainedModel" + ] + } + }, + "info.stst.pegasus-x": { + "*": { + "repo": "google/pegasus-x-large", + "pkg": { + "0": { + "transformers": "PegasusXModel" + } + }, + "tasks": [ + "PegasusXForConditionalGeneration", + "PegasusXModel", + "PegasusXPreTrainedModel" + ] + } + }, + "info.vit.language-perceiver": { + "*": { + "repo": "deepmind/language-perceiver", + "pkg": { + "0": { + "transformers": "PerceiverModel" + } + }, + "tasks": [ + "PerceiverForImageClassificationConvProcessing", + "PerceiverForImageClassificationFourier", + "PerceiverForImageClassificationLearned", + "PerceiverForMaskedLM", + "PerceiverForMultimodalAutoencoding", + "PerceiverForOpticalFlow", + "PerceiverForSequenceClassification", + "PerceiverLayer", + "PerceiverModel", + "PerceiverPreTrainedModel" + ] + } + }, + "info.vit.perception-lm": { + "*": { + "repo": "facebook/Perception-LM-1B", + "pkg": { + "0": { + "transformers": "PerceptionLMModel" + } + }, + "tasks": [ + "PerceptionLMForConditionalGeneration", + "PerceptionLMPreTrainedModel", + "PerceptionLMModel" + ] + } + }, + "info.stst.persimmon": { + "*": { + "repo": "adept/persimmon-8b-base", + "pkg": { + "0": { + "transformers": "PersimmonModel" + } + }, + "tasks": [ + "PersimmonForCausalLM", + "PersimmonModel", + "PersimmonPreTrainedModel", + "PersimmonForSequenceClassification", + "PersimmonForTokenClassification" + ] + } + }, + "info.stst.phi-1": { + "*": { + "repo": "microsoft/phi-1", + "pkg": { + "0": { + "transformers": "PhiModel" + } + }, + "tasks": [ + "PhiPreTrainedModel", + "PhiModel", + "PhiForCausalLM", + "PhiForSequenceClassification", + "PhiForTokenClassification" + ] + } + }, + "info.stst.phi-3": { + "*": { + "repo": "microsoft/Phi-3-mini-4k-instruct", + "pkg": { + "0": { + "transformers": "Phi3Model" + } + }, + "tasks": [ + "Phi3PreTrainedModel", + "Phi3Model", + "Phi3ForCausalLM", + "Phi3ForSequenceClassification", + "Phi3ForTokenClassification" + ] + } + }, + "info.vit.phi-4": { + "*": { + "repo": "microsoft/Phi-4-multimodal-instruct", + "pkg": { + "0": { + "transformers": "Phi4MultimodalModel" + } + }, + "file_256": [ + "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" + ], + "layer_b3": [ + "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" + ], + "layer_256": [ + "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" + ], + "tasks": [ + "Phi4MultimodalAudioPreTrainedModel", + "Phi4MultimodalAudioModel", + "Phi4MultimodalVisionPreTrainedModel", + "Phi4MultimodalVisionModel", + "Phi4MultimodalPreTrainedModel", + "Phi4MultimodalModel", + "Phi4MultimodalForCausalLM" + ] + } + }, + "info.moe.phi-3-moe": { + "*": { + "repo": "microsoft/Phi-3.5-MoE-instruct", + "pkg": { + "0": { + "transformers": "PhimoeModel" + } + }, + "tasks": [ + "PhimoePreTrainedModel", + "PhimoeModel", + "PhimoeForCausalLM", + "PhimoeForSequenceClassification" + ] + } + }, + "info.vit.pixio-huge": { + "*": { + "repo": "facebook/pixio-huge", + "pkg": { + "0": { + "transformers": "PixioModel" + } + }, + "tasks": [ + "PixioModel", + "PixioPreTrainedModel", + "PixioBackbone" + ] + } + }, + "info.vit.pixtral": { + "*": { + "repo": "mistralai/Pixtral-12B-Base-2409", + "pkg": { + "0": { + "transformers": "PixtralVisionModel" + } + }, + "tasks": [ + "PixtralVisionModel", + "PixtralPreTrainedModel" + ] + } + }, + "info.stst.plbart": { + "*": { + "repo": "uclanlp/plbart-base", + "pkg": { + "0": { + "transformers": "PLBartModel" + } + }, + "tasks": [ + "PLBartForCausalLM", + "PLBartForConditionalGeneration", + "PLBartForSequenceClassification", + "PLBartModel", + "PLBartPreTrainedModel" + ] + } + }, + "info.vit.poolformer-s12": { + "*": { + "repo": "sail/poolformer_s12", + "pkg": { + "0": { + "transformers": "PoolFormerModel" + } + }, + "tasks": [ + "PoolFormerForImageClassification", + "PoolFormerModel", + "PoolFormerPreTrainedModel" + ] + } + }, + "info.stst.phetnet-uncased": { + "*": { + "repo": "microsoft/prophetnet-large-uncased", + "pkg": { + "0": { + "transformers": "ProphetNetModel" + } + }, + "tasks": [ + "ProphetNetDecoder", + "ProphetNetEncoder", + "ProphetNetForCausalLM", + "ProphetNetForConditionalGeneration", + "ProphetNetModel", + "ProphetNetPreTrainedModel" + ] + } + }, + "info.vit.pvt-224": { + "*": { + "repo": "Xrenya/pvt-tiny-224", + "pkg": { + "0": { + "transformers": "PvtModel" + } + }, + "tasks": [ + "PvtForImageClassification", + "PvtModel", + "PvtPreTrainedModel" + ] + } + }, + "info.vit.pvt-v2-b0": { + "*": { + "repo": "OpenGVLab/pvt_v2_b0", + "pkg": { + "0": { + "transformers": "PvtV2Model" + } + }, + "tasks": [ + "PvtV2ForImageClassification", + "PvtV2Model", + "PvtV2PreTrainedModel", + "PvtV2Backbone" + ] + } + }, + "info.stst.qwen2": { + "*": { + "repo": "Qwen/Qwen2-7B", + "pkg": { + "0": { + "transformers": "Qwen2Model" + } + }, + "tasks": [ + "Qwen2PreTrainedModel", + "Qwen2Model", + "Qwen2ForCausalLM", + "Qwen2RMSNorm", + "Qwen2ForSequenceClassification", + "Qwen2ForTokenClassification", + "Qwen2ForQuestionAnswering" + ] + } + }, + "info.vit.qwen2-vl": { + "*": { + "repo": "Qwen/Qwen2-VL-7B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen2_5_VLModel" + } + }, + "tasks": [ + "Qwen2_5_VLForConditionalGeneration", + "Qwen2_5_VLModel", + "Qwen2_5_VLPreTrainedModel", + "Qwen2_5_VLTextModel" + ] + } + }, + "info.stst.qwen2-vl": { + "*": { + "repo": "Qwen/Qwen2-VL-7B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen2_5_VLTextModel" + } + }, + "file_256": [ + "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", + "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", + "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", + "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" + ], + "layer_b3": [ + "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", + "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", + "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", + "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" + ], + "layer_256": [ + "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", + "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", + "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", + "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" + ], + "tasks": [ + "Qwen2_5_VLForConditionalGeneration", + "Qwen2_5_VLModel", + "Qwen2_5_VLPreTrainedModel", + "Qwen2_5_VLTextModel" + ] + } + }, + "info.aet.qwen2-audio": { + "*": { + "repo": "Qwen/Qwen2-Audio-7B", + "pkg": { + "0": { + "transformers": "Qwen2AudioEncoder" + } + }, + "tasks": [ + "Qwen2AudioForConditionalGeneration", + "Qwen2AudioPreTrainedModel", + "Qwen2AudioEncoder" + ] + } + }, + "info.moe.qwen15-moe-a": { + "*": { + "repo": "Qwen/Qwen1.5-MoE-A2.7B", + "pkg": { + "0": { + "transformers": "Qwen2MoeModel" + } + }, + "tasks": [ + "Qwen2MoeForCausalLM", + "Qwen2MoeForQuestionAnswering", + "Qwen2MoeModel", + "Qwen2MoePreTrainedModel", + "Qwen2MoeForSequenceClassification", + "Qwen2MoeForTokenClassification" + ] + } + }, + "info.stst.qwen3": { + "*": { + "repo": "Qwen/Qwen3-8B", + "pkg": { + "0": { + "transformers": "Qwen3Model" + } + }, + "tasks": [ + "Qwen3ForCausalLM", + "Qwen3ForQuestionAnswering", + "Qwen3PreTrainedModel", + "Qwen3Model", + "Qwen3ForSequenceClassification", + "Qwen3ForTokenClassification" + ] + } + }, + "info.moe.qwen3-a": { + "*": { + "repo": "Qwen/Qwen3-30B-A3B", + "pkg": { + "0": { + "transformers": "Qwen3MoeModel" + } + }, + "file_256": [ + "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" + ], + "layer_b3": [ + "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" + ], + "layer_256": [ + "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" + ], + "tasks": [ + "Qwen3MoeForCausalLM", + "Qwen3MoeForQuestionAnswering", + "Qwen3MoeModel", + "Qwen3MoePreTrainedModel", + "Qwen3MoeForSequenceClassification", + "Qwen3MoeForTokenClassification" + ] + } + }, + "info.moe.qwen3-next-a": { + "*": { + "repo": "Qwen/Qwen3-Next-80B-A3B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3NextModel" + } + }, + "tasks": [ + "Qwen3NextForCausalLM", + "Qwen3NextForQuestionAnswering", + "Qwen3NextModel", + "Qwen3NextPreTrainedModel", + "Qwen3NextForSequenceClassification", + "Qwen3NextForTokenClassification" + ] + } + }, + "info.vit.qwen3-vl": { + "*": { + "repo": "Qwen/Qwen3-VL-4B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLModel" + } + }, + "tasks": [ + "Qwen3VLVisionModel", + "Qwen3VLForConditionalGeneration", + "Qwen3VLModel", + "Qwen3VLPreTrainedModel", + "Qwen3VLTextModel" + ] + } + }, + "info.vit.qwen3-vl-a": { + "*": { + "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLMoeModel" + } + }, + "tasks": [ + "Qwen3VLMoeVisionModel", + "Qwen3VLMoeForConditionalGeneration", + "Qwen3VLMoeModel", + "Qwen3VLMoePreTrainedModel", + "Qwen3VLMoeTextModel" + ] + } + }, + "info.moe.qwen3-vl-a": { + "*": { + "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLMoeTextModel" + } + }, + "tasks": [ + "Qwen3VLMoeVisionModel", + "Qwen3VLMoeForConditionalGeneration", + "Qwen3VLMoeModel", + "Qwen3VLMoePreTrainedModel", + "Qwen3VLMoeTextModel" + ] + } + }, + "info.stst.qwen3-vl": { + "*": { + "repo": "Qwen/Qwen3-VL-4B-Instruct", + "pkg": { + "0": { + "transformers": "Qwen3VLTextModel" + } + }, + "tasks": [ + "Qwen3VLVisionModel", + "Qwen3VLForConditionalGeneration", + "Qwen3VLModel", + "Qwen3VLPreTrainedModel", + "Qwen3VLTextModel" + ] + } + }, + "info.rnn.recurrentgemma": { + "*": { + "repo": "google/recurrentgemma-2b", + "pkg": { + "0": { + "transformers": "RecurrentGemmaModel" + } + }, + "tasks": [ + "RecurrentGemmaForCausalLM", + "RecurrentGemmaModel", + "RecurrentGemmaPreTrainedModel" + ] + } + }, + "info.art.reformer-crime-and-punishment": { + "*": { + "repo": "google/reformer-crime-and-punishment", + "pkg": { + "0": { + "transformers": "ReformerModel" + } + }, + "tasks": [ + "ReformerAttention", + "ReformerForMaskedLM", + "ReformerForQuestionAnswering", + "ReformerForSequenceClassification", + "ReformerLayer", + "ReformerModel", + "ReformerModelWithLMHead", + "ReformerPreTrainedModel" + ] + } + }, + "info.vit.regnet-y-040": { + "*": { + "repo": "facebook/regnet-y-040", + "pkg": { + "0": { + "transformers": "RegNetModel" + } + }, + "tasks": [ + "RegNetForImageClassification", + "RegNetModel", + "RegNetPreTrainedModel" + ] + } + }, + "info.art.rembert": { + "*": { + "repo": "google/rembert", + "pkg": { + "0": { + "transformers": "RemBertModel" + } + }, + "tasks": [ + "RemBertForCausalLM", + "RemBertForMaskedLM", + "RemBertForMultipleChoice", + "RemBertForQuestionAnswering", + "RemBertForSequenceClassification", + "RemBertForTokenClassification", + "RemBertLayer", + "RemBertModel", + "RemBertPreTrainedModel" + ] + } + }, + "info.vit.resnet-50": { + "*": { + "repo": "microsoft/resnet-50", + "pkg": { + "0": { + "transformers": "ResNetModel" + } + }, + "tasks": [ + "ResNetForImageClassification", + "ResNetModel", + "ResNetPreTrainedModel", + "ResNetBackbone" + ] + } + }, + "info.art.roberta": { + "*": { + "repo": "FacebookAI/roberta-base", + "pkg": { + "0": { + "transformers": "RobertaModel" + } + }, + "tasks": [ + "RobertaForCausalLM", + "RobertaForMaskedLM", + "RobertaForMultipleChoice", + "RobertaForQuestionAnswering", + "RobertaForSequenceClassification", + "RobertaForTokenClassification", + "RobertaModel", + "RobertaPreTrainedModel" + ] + } + }, + "info.art.efficient-mlm-m0-0": { + "*": { + "repo": "andreasmadsen/efficient_mlm_m0.40", + "pkg": { + "0": { + "transformers": "RobertaPreLayerNormModel" + } + }, + "tasks": [ + "RobertaPreLayerNormForCausalLM", + "RobertaPreLayerNormForMaskedLM", + "RobertaPreLayerNormForMultipleChoice", + "RobertaPreLayerNormForQuestionAnswering", + "RobertaPreLayerNormForSequenceClassification", + "RobertaPreLayerNormForTokenClassification", + "RobertaPreLayerNormModel", + "RobertaPreLayerNormPreTrainedModel" + ] + } + }, + "info.art.roc-bert-zh": { + "*": { + "repo": "weiweishi/roc-bert-base-zh", + "pkg": { + "0": { + "transformers": "RoCBertModel" + } + }, + "tasks": [ + "RoCBertForCausalLM", + "RoCBertForMaskedLM", + "RoCBertForMultipleChoice", + "RoCBertForPreTraining", + "RoCBertForQuestionAnswering", + "RoCBertForSequenceClassification", + "RoCBertForTokenClassification", + "RoCBertLayer", + "RoCBertModel", + "RoCBertPreTrainedModel" + ] + } + }, + "info.art.roformer-chinese": { + "*": { + "repo": "junnyu/roformer_chinese_base", + "pkg": { + "0": { + "transformers": "RoFormerModel" + } + }, + "tasks": [ + "RoFormerForCausalLM", + "RoFormerForMaskedLM", + "RoFormerForMultipleChoice", + "RoFormerForQuestionAnswering", + "RoFormerForSequenceClassification", + "RoFormerForTokenClassification", + "RoFormerLayer", + "RoFormerModel", + "RoFormerPreTrainedModel" + ] + } + }, + "info.detr.rtdetr-r50vd": { + "*": { + "repo": "PekingU/rtdetr_r50vd", + "pkg": { + "0": { + "transformers": "RTDetrModel" + } + }, + "tasks": [ + "RTDetrForObjectDetection", + "RTDetrModel", + "RTDetrPreTrainedModel" + ] + } + }, + "info.detr.rtdetr-r18vd": { + "*": { + "repo": "PekingU/rtdetr_r18vd", + "pkg": { + "0": { + "transformers": "RTDetrV2Model" + } + }, + "tasks": [ + "RTDetrV2Model", + "RTDetrV2PreTrainedModel", + "RTDetrV2ForObjectDetection" + ] + } + }, + "info.rnn.rwkv-4-pile": { + "*": { + "repo": "RWKV/rwkv-4-169m-pile", + "pkg": { + "0": { + "transformers": "RwkvModel" + } + }, + "tasks": [ + "RwkvForCausalLM", + "RwkvModel", + "RwkvPreTrainedModel" + ] + } + }, + "info.vit.sam-vit-huge": { + "*": { + "repo": "facebook/sam-vit-huge", + "pkg": { + "0": { + "transformers": "SamModel" + } + }, + "tasks": [ + "SamVisionModel", + "SamModel", + "SamPreTrainedModel" + ] + } + }, + "info.vit.sam2-hiera": { + "*": { + "repo": "facebook/sam2.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "Sam2Model" + } + }, + "tasks": [ + "Sam2Model", + "Sam2VisionModel", + "Sam2PreTrainedModel", + "Sam2HieraDetModel" + ] + } + }, + "info.vit.sam3": { + "*": { + "repo": "facebook/sam3", + "pkg": { + "0": { + "transformers": "Sam3Model" + } + }, + "tasks": [ + "Sam3Model", + "Sam3VisionModel", + "Sam3ViTModel", + "Sam3PreTrainedModel" + ] + } + }, + "info.vit.sam3-tracker1-hiera": { + "*": { + "repo": "facebook/sam3_tracker.1-hiera-tiny", + "pkg": { + "0": { + "transformers": "Sam3TrackerModel" + } + }, + "tasks": [ + "Sam3TrackerModel", + "Sam3TrackerPreTrainedModel" + ] + } + }, + "info.stst.sam3": { + "*": { + "repo": "facebook/sam3", + "pkg": { + "0": { + "transformers": "Sam3VideoModel" + } + }, + "tasks": [ + "Sam3VideoModel", + "Sam3VideoPreTrainedModel", + "Sam3VideoInferenceSession", + "Sam3VideoSegmentationOutput" + ] + } + }, + "info.vit.sam-hq-vit-h": { + "*": { + "repo": "sushmanth/sam_hq_vit_h", + "pkg": { + "0": { + "transformers": "SamHQModel" + } + }, + "tasks": [ + "SamHQModel", + "SamHQPreTrainedModel", + "SamHQVisionModel" + ] + } + }, + "info.vit.sam-hq-vit-huge": { + "*": { + "repo": "syscv-community/sam-hq-vit-huge", + "pkg": { + "0": { + "transformers": "SamHQVisionModel" + } + }, + "tasks": [ + "SamHQModel", + "SamHQPreTrainedModel", + "SamHQVisionModel" + ] + } + }, + "info.aet.hf-seamless-m4t": { + "*": { + "repo": "facebook/hf-seamless-m4t-medium", + "pkg": { + "0": { + "transformers": "SeamlessM4TModel" + } + }, + "tasks": [ + "SeamlessM4TForTextToSpeech", + "SeamlessM4TForSpeechToSpeech", + "SeamlessM4TForTextToText", + "SeamlessM4TForSpeechToText", + "SeamlessM4TModel", + "SeamlessM4TPreTrainedModel", + "SeamlessM4TCodeHifiGan", + "SeamlessM4THifiGan", + "SeamlessM4TTextToUnitForConditionalGeneration", + "SeamlessM4TTextToUnitModel" + ] + } + }, + "info.stst.seamless-m4t-v2": { + "*": { + "repo": "facebook/seamless-m4t-v2-large", + "pkg": { + "0": { + "transformers": "SeamlessM4Tv2Model" + } + }, + "tasks": [ + "SeamlessM4Tv2ForTextToSpeech", + "SeamlessM4Tv2ForSpeechToSpeech", + "SeamlessM4Tv2ForTextToText", + "SeamlessM4Tv2ForSpeechToText", + "SeamlessM4Tv2Model", + "SeamlessM4Tv2PreTrainedModel" + ] + } + }, + "info.stst.seedoss": { + "*": { + "repo": "ByteDance-Seed/SeedOss-36B", + "pkg": { + "0": { + "transformers": "SeedOssModel" + } + }, + "tasks": [ + "SeedOssForCausalLM", + "SeedOssForQuestionAnswering", + "SeedOssPreTrainedModel", + "SeedOssModel", + "SeedOssForSequenceClassification", + "SeedOssForTokenClassification" + ] + } + }, + "info.vit.segformer-b0-finetuned-ade-512-512": { + "*": { + "repo": "nvidia/segformer-b0-finetuned-ade-512-512", + "pkg": { + "0": { + "transformers": "SegformerModel" + } + }, + "tasks": [ + "SegformerDecodeHead", + "SegformerForImageClassification", + "SegformerForSemanticSegmentation", + "SegformerLayer", + "SegformerModel", + "SegformerPreTrainedModel" + ] + } + }, + "info.vit.seggpt-vit": { + "*": { + "repo": "BAAI/seggpt-vit-large", + "pkg": { + "0": { + "transformers": "SegGptModel" + } + }, + "tasks": [ + "SegGptModel", + "SegGptPreTrainedModel", + "SegGptForImageSegmentation" + ] + } + }, + "info.aet.sew": { + "*": { + "repo": "asapp/sew-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWModel" + } + }, + "tasks": [ + "SEWForCTC", + "SEWForSequenceClassification", + "SEWModel", + "SEWPreTrainedModel" + ] + } + }, + "info.aet.sew-d": { + "*": { + "repo": "asapp/sew-d-tiny-100k", + "pkg": { + "0": { + "transformers": "SEWDModel" + } + }, + "tasks": [ + "SEWDForCTC", + "SEWDForSequenceClassification", + "SEWDModel", + "SEWDPreTrainedModel" + ] + } + }, + "info.vit.siglip2-patch16-224": { + "*": { + "repo": "google/siglip2-base-patch16-224", + "pkg": { + "0": { + "transformers": "Siglip2Model" + } + }, + "tasks": [ + "Siglip2Model", + "Siglip2PreTrainedModel", + "Siglip2TextModel", + "Siglip2VisionModel", + "Siglip2ForImageClassification" + ] + } + }, + "info.vit.siglip2-patch16-naflex": { + "*": { + "repo": "google/siglip2-base-patch16-naflex", + "pkg": { + "0": { + "transformers": "Siglip2VisionModel" + } + }, + "tasks": [ + "Siglip2Model", + "Siglip2PreTrainedModel", + "Siglip2TextModel", + "Siglip2VisionModel", + "Siglip2ForImageClassification" + ] + } + }, + "info.stst.smollm3": { + "*": { + "repo": "HuggingFaceTB/SmolLM3-3B", + "pkg": { + "0": { + "transformers": "SmolLM3Model" + } + }, + "tasks": [ + "SmolLM3PreTrainedModel", + "SmolLM3Model", + "SmolLM3ForCausalLM", + "SmolLM3ForSequenceClassification", + "SmolLM3ForTokenClassification", + "SmolLM3ForQuestionAnswering" + ] + } + }, + "info.vit.smolvlm": { + "*": { + "repo": "HuggingFaceTB/SmolVLM2-2.2B-Instruct", + "pkg": { + "0": { + "transformers": "SmolVLMModel" + } + }, + "tasks": [ + "SmolVLMForConditionalGeneration", + "SmolVLMPreTrainedModel", + "SmolVLMModel", + "SmolVLMVisionTransformer" + ] + } + }, + "info.vit.siglip-so-patch14-384": { + "*": { + "repo": "google/siglip-so400m-patch14-384", + "pkg": { + "0": { + "transformers": "SmolVLMVisionTransformer" + } + }, + "tasks": [ + "SmolVLMForConditionalGeneration", + "SmolVLMPreTrainedModel", + "SmolVLMModel", + "SmolVLMVisionTransformer" + ] + } + }, + "info.aet.s2t-librispeech-asr": { + "*": { + "repo": "facebook/s2t-small-librispeech-asr", + "pkg": { + "0": { + "transformers": "Speech2TextModel" + } + }, + "tasks": [ + "Speech2TextForConditionalGeneration", + "Speech2TextModel", + "Speech2TextPreTrainedModel" + ] + } + }, + "info.stst.speecht5-asr": { + "*": { + "repo": "microsoft/speecht5_asr", + "pkg": { + "0": { + "transformers": "SpeechT5Model" + } + }, + "tasks": [ + "SpeechT5ForSpeechToText", + "SpeechT5ForSpeechToSpeech", + "SpeechT5ForTextToSpeech", + "SpeechT5Model", + "SpeechT5PreTrainedModel", + "SpeechT5HifiGan" + ] + } + }, + "info.art.splinter": { + "*": { + "repo": "tau/splinter-base", + "pkg": { + "0": { + "transformers": "SplinterModel" + } + }, + "tasks": [ + "SplinterForQuestionAnswering", + "SplinterForPreTraining", + "SplinterLayer", + "SplinterModel", + "SplinterPreTrainedModel" + ] + } + }, + "info.art.squeezebert-uncased": { + "*": { + "repo": "squeezebert/squeezebert-uncased", + "pkg": { + "0": { + "transformers": "SqueezeBertModel" + } + }, + "tasks": [ + "SqueezeBertForMaskedLM", + "SqueezeBertForMultipleChoice", + "SqueezeBertForQuestionAnswering", + "SqueezeBertForSequenceClassification", + "SqueezeBertForTokenClassification", + "SqueezeBertModel", + "SqueezeBertModule", + "SqueezeBertPreTrainedModel" + ] + } + }, + "info.stst.stablelm-4e1t": { + "*": { + "repo": "stabilityai/stablelm-3b-4e1t", + "pkg": { + "0": { + "transformers": "StableLmModel" + } + }, + "tasks": [ + "StableLmForCausalLM", + "StableLmModel", + "StableLmPreTrainedModel", + "StableLmForSequenceClassification", + "StableLmForTokenClassification" + ] + } + }, + "info.stst.starcoder2": { + "*": { + "repo": "bigcode/starcoder2-7b", + "pkg": { + "0": { + "transformers": "Starcoder2Model" + } + }, + "tasks": [ + "Starcoder2ForCausalLM", + "Starcoder2Model", + "Starcoder2PreTrainedModel", + "Starcoder2ForSequenceClassification", + "Starcoder2ForTokenClassification" + ] + } + }, + "info.vit.swiftformer-xs": { + "*": { + "repo": "MBZUAI/swiftformer-xs", + "pkg": { + "0": { + "transformers": "SwiftFormerModel" + } + }, + "tasks": [ + "SwiftFormerForImageClassification", + "SwiftFormerModel", + "SwiftFormerPreTrainedModel" + ] + } + }, + "info.vit.swin2sr-classicalsr-x2-64": { + "*": { + "repo": "caidas/swin2sr-classicalsr-x2-64", + "pkg": { + "0": { + "transformers": "Swin2SRModel" + } + }, + "tasks": [ + "Swin2SRForImageSuperResolution", + "Swin2SRModel", + "Swin2SRPreTrainedModel" + ] + } + }, + "info.vit.swinv2-patch4-window8-256": { + "*": { + "repo": "microsoft/swinv2-tiny-patch4-window8-256", + "pkg": { + "0": { + "transformers": "Swinv2Model" + } + }, + "tasks": [ + "Swinv2ForImageClassification", + "Swinv2ForMaskedImageModeling", + "Swinv2Model", + "Swinv2PreTrainedModel", + "Swinv2Backbone" + ] + } + }, + "info.moe.switch-8": { + "*": { + "repo": "google/switch-base-8", + "pkg": { + "0": { + "transformers": "SwitchTransformersModel" + } + }, + "tasks": [ + "SwitchTransformersEncoderModel", + "SwitchTransformersForConditionalGeneration", + "SwitchTransformersModel", + "SwitchTransformersPreTrainedModel", + "SwitchTransformersTop1Router", + "SwitchTransformersSparseMLP" + ] + } + }, + "info.stst.t5": { + "*": { + "repo": "google-t5/t5-small", + "pkg": { + "0": { + "transformers": "T5Model" + } + }, + "identifiers": [ + [ + 4096 + ], + "encoder.embed_tokens.weight", + "text_encoders.t5xxl.transformer.shared.weight", + "t5xxl", + "encoder.block.0.layer.1.DenseReluDense.wi.weight" + ], + "file_256": [ + "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", + "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", + "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", + "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", + "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", + "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", + "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", + "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", + "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", + "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", + "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", + "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", + "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", + "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", + "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", + "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", + "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", + "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", + "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", + "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", + "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", + "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", + "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", + "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", + "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", + "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", + "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" + ], + "layer_b3": [ + "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", + "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", + "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", + "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", + "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", + "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", + "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", + "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", + "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", + "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", + "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", + "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", + "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", + "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", + "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", + "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", + "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", + "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", + "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", + "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", + "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", + "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", + "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", + "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", + "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", + "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", + "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", + "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", + "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", + "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" + ], + "layer_256": [ + "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", + "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", + "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", + "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", + "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", + "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", + "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", + "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", + "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", + "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", + "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", + "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", + "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", + "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", + "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", + "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", + "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", + "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", + "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", + "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", + "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", + "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", + "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", + "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", + "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", + "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", + "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", + "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" + ], + "tasks": [ + "T5EncoderModel", + "T5ForConditionalGeneration", + "T5Model", + "T5PreTrainedModel", + "T5ForQuestionAnswering", + "T5ForSequenceClassification", + "T5ForTokenClassification" + ] + } + }, + "info.stst.t5gemma-prefixlm": { + "*": { + "repo": "google/t5gemma-2b-2b-prefixlm-it", + "pkg": { + "0": { + "transformers": "T5GemmaModel" + } + }, + "tasks": [ + "T5GemmaForConditionalGeneration", + "T5GemmaModel", + "T5GemmaEncoderModel", + "T5GemmaPreTrainedModel", + "T5GemmaForSequenceClassification", + "T5GemmaForTokenClassification" + ] + } + }, + "info.stst.t5gemma-2": { + "*": { + "repo": "google/t5gemma-2-270m-270m", + "pkg": { + "0": { + "transformers": "T5Gemma2Model" + } + }, + "tasks": [ + "T5Gemma2ForConditionalGeneration", + "T5Gemma2Model", + "T5Gemma2PreTrainedModel", + "T5Gemma2ForSequenceClassification", + "T5Gemma2ForTokenClassification" + ] + } + }, + "info.detr.table-transformer-detection": { + "*": { + "repo": "microsoft/table-transformer-detection", + "pkg": { + "0": { + "transformers": "TableTransformerModel" + } + }, + "tasks": [ + "TableTransformerForObjectDetection", + "TableTransformerModel", + "TableTransformerPreTrainedModel" + ] + } + }, + "info.art.tapas-finetuned-sqa": { + "*": { + "repo": "google/tapas-base-finetuned-sqa", + "pkg": { + "0": { + "transformers": "TapasModel" + } + }, + "tasks": [ + "TapasForMaskedLM", + "TapasForQuestionAnswering", + "TapasForSequenceClassification", + "TapasModel", + "TapasPreTrainedModel" + ] + } + }, + "info.vit.textnet": { + "*": { + "repo": "czczup/textnet-base", + "pkg": { + "0": { + "transformers": "TextNetModel" + } + }, + "tasks": [ + "TextNetBackbone", + "TextNetModel", + "TextNetPreTrainedModel", + "TextNetForImageClassification" + ] + } + }, + "info.stst.time-series-transformer-tourism-monthly": { + "*": { + "repo": "huggingface/time-series-transformer-tourism-monthly", + "pkg": { + "0": { + "transformers": "TimeSeriesTransformerModel" + } + }, + "tasks": [ + "TimeSeriesTransformerForPrediction", + "TimeSeriesTransformerModel", + "TimeSeriesTransformerPreTrainedModel" + ] + } + }, + "info.art.timesfm-2-pytorch": { + "*": { + "repo": "google/timesfm-2.0-500m-pytorch", + "pkg": { + "0": { + "transformers": "TimesFmModel" + } + }, + "tasks": [ + "TimesFmModelForPrediction", + "TimesFmPreTrainedModel", + "TimesFmModel" + ] + } + }, + "info.vit.timesformer-finetuned-k600": { + "*": { + "repo": "facebook/timesformer-base-finetuned-k600", + "pkg": { + "0": { + "transformers": "TimesformerModel" + } + }, + "tasks": [ + "TimesformerModel", + "TimesformerForVideoClassification", + "TimesformerPreTrainedModel" + ] + } + }, + "info.detr.resnet18-a1-in": { + "*": { + "repo": "timm/resnet18.a1_in1k", + "pkg": { + "0": { + "transformers": "TimmWrapperModel" + } + }, + "tasks": [ + "TimmWrapperPreTrainedModel", + "TimmWrapperModel", + "TimmWrapperForImageClassification" + ] + } + }, + "info.detr.tvp": { + "*": { + "repo": "Intel/tvp-base", + "pkg": { + "0": { + "transformers": "TvpModel" + } + }, + "tasks": [ + "TvpModel", + "TvpPreTrainedModel", + "TvpForVideoGrounding" + ] + } + }, + "info.vit.udop": { + "*": { + "repo": "microsoft/udop-large", + "pkg": { + "0": { + "transformers": "UdopModel" + } + }, + "tasks": [ + "UdopForConditionalGeneration", + "UdopPreTrainedModel", + "UdopModel", + "UdopEncoderModel" + ] + } + }, + "info.stst.umt5": { + "*": { + "repo": "google/umt5-small", + "pkg": { + "0": { + "transformers": "UMT5Model" + } + }, + "identifiers": [ + "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" + ], + "file_256": [ + "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", + "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", + "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", + "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", + "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", + "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", + "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", + "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", + "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", + "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", + "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", + "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", + "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", + "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", + "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", + "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" + ], + "layer_b3": [ + "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", + "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", + "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", + "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", + "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", + "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", + "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", + "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", + "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", + "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", + "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", + "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", + "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", + "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", + "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", + "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", + "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", + "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" + ], + "layer_256": [ + "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", + "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", + "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", + "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", + "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", + "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", + "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", + "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", + "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", + "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", + "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", + "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", + "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", + "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", + "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", + "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", + "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", + "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" + ], + "tasks": [ + "UMT5EncoderModel", + "UMT5ForConditionalGeneration", + "UMT5ForQuestionAnswering", + "UMT5ForSequenceClassification", + "UMT5ForTokenClassification", + "UMT5Model", + "UMT5PreTrainedModel" + ] + } + }, + "info.aet.unispeech-1500h-cv": { + "*": { + "repo": "microsoft/unispeech-large-1500h-cv", + "pkg": { + "0": { + "transformers": "UniSpeechModel" + } + }, + "tasks": [ + "UniSpeechForCTC", + "UniSpeechForPreTraining", + "UniSpeechForSequenceClassification", + "UniSpeechModel", + "UniSpeechPreTrainedModel" + ] + } + }, + "info.aet.unispeech-sat-100h-libri-ft": { + "*": { + "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "pkg": { + "0": { + "transformers": "UniSpeechSatModel" + } + }, + "tasks": [ + "UniSpeechSatForAudioFrameClassification", + "UniSpeechSatForCTC", + "UniSpeechSatForPreTraining", + "UniSpeechSatForSequenceClassification", + "UniSpeechSatForXVector", + "UniSpeechSatModel", + "UniSpeechSatPreTrainedModel" + ] + } + }, + "info.gan.univnet-dev": { + "*": { + "repo": "dg845/univnet-dev", + "pkg": { + "0": { + "transformers": "UnivNetModel" + } + }, + "tasks": [ + "UnivNetModel" + ] + } + }, + "info.stst.vaultgemma": { + "*": { + "repo": "google/vaultgemma-7b", + "pkg": { + "0": { + "transformers": "VaultGemmaModel" + } + }, + "tasks": [ + "VaultGemmaForCausalLM", + "VaultGemmaModel", + "VaultGemmaPreTrainedModel" + ] + } + }, + "info.vit.videollama3-image-hf": { + "*": { + "repo": "lkhl/VideoLLaMA3-2B-Image-HF", + "pkg": { + "0": { + "transformers": "VideoLlama3Model" + } + }, + "tasks": [ + "VideoLlama3VisionModel", + "VideoLlama3PreTrainedModel", + "VideoLlama3Model", + "VideoLlama3ForConditionalGeneration" + ] + } + }, + "info.vit.video-llava-hf": { + "*": { + "repo": "LanguageBind/Video-LLaVA-7B-hf", + "pkg": { + "0": { + "transformers": "VideoLlavaModel" + } + }, + "tasks": [ + "VideoLlavaPreTrainedModel", + "VideoLlavaModel", + "VideoLlavaForConditionalGeneration" + ] + } + }, + "info.vit.videomae": { + "*": { + "repo": "MCG-NJU/videomae-base", + "pkg": { + "0": { + "transformers": "VideoMAEModel" } - } - }, - "megatron-bert-uncased": { + }, + "tasks": [ + "VideoMAEForPreTraining", + "VideoMAEModel", + "VideoMAEPreTrainedModel", + "VideoMAEForVideoClassification" + ] + } + }, + "info.vit.vilt-b32-mlm": { + "*": { + "repo": "dandelin/vilt-b32-mlm", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViltModel" } - } - }, - "grounding-dino": { + }, + "tasks": [ + "ViltForImageAndTextRetrieval", + "ViltForImagesAndTextClassification", + "ViltForTokenClassification", + "ViltForMaskedLM", + "ViltForQuestionAnswering", + "ViltLayer", + "ViltModel", + "ViltPreTrainedModel" + ] + } + }, + "info.vit.vip-llava-hf": { + "*": { + "repo": "ybelkada/vip-llava-7b-hf", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "VipLlavaModel" } - } - }, - "funnel": { + }, + "tasks": [ + "VipLlavaModel", + "VipLlavaForConditionalGeneration", + "VipLlavaPreTrainedModel" + ] + } + }, + "info.vit.japanese-clip-vit-h-14-bert-wider": { + "*": { + "repo": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "VisionTextDualEncoderModel" } - } - }, - "wav2vec2-conformer-rel-pos": { + }, + "tasks": [ + "VisionTextDualEncoderModel" + ] + } + }, + "info.art.visualbert-vqa-coco-pre": { + "*": { + "repo": "uclanlp/visualbert-vqa-coco-pre", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "15": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "16": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "17": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "18": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "19": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "VisualBertModel" } - } - }, - "mm-grounding-dino-o365v1-goldg-v3det": { + }, + "tasks": [ + "VisualBertForMultipleChoice", + "VisualBertForPreTraining", + "VisualBertForQuestionAnswering", + "VisualBertForRegionToPhraseAlignment", + "VisualBertForVisualReasoning", + "VisualBertLayer", + "VisualBertModel", + "VisualBertPreTrainedModel" + ] + } + }, + "info.vit.vit-patch16-224": { + "*": { + "repo": "google/vit-base-patch16-224", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViTModel" } - } - }, - "gpt2": { + }, + "tasks": [ + "ViTForImageClassification", + "ViTForMaskedImageModeling", + "ViTModel", + "ViTPreTrainedModel" + ] + } + }, + "info.vit.vit-mae": { + "*": { + "repo": "facebook/vit-mae-base", "pkg": { "0": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "1": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "2": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "3": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "4": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "5": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "6": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "7": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "8": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "9": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "10": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "11": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "12": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "13": { - "transformers": "transformers.utils.import_utils.transformers" - }, - "14": { - "transformers": "transformers.utils.import_utils.transformers" + "transformers": "ViTMAEModel" } - } + }, + "tasks": [ + "ViTMAEForPreTraining", + "ViTMAELayer", + "ViTMAEModel", + "ViTMAEPreTrainedModel" + ] } }, - "info.detr.omdet-turbo-swin-hf": { + "info.vit.vit-msn": { "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", + "repo": "facebook/vit-msn-base", "pkg": { "0": { - "transformers": "OmDetTurboForObjectDetection" + "transformers": "ViTMSNModel" } }, "tasks": [ - "OmDetTurboForObjectDetection", - "OmDetTurboPreTrainedModel" + "ViTMSNModel", + "ViTMSNForImageClassification", + "ViTMSNPreTrainedModel" ] } }, - "info.vit.blip2-opt": { + "info.vit.vitdet-patch16-224": { "*": { - "repo": "Salesforce/blip2-opt-2.7b", + "repo": "google/vitdet-base-patch16-224", "pkg": { "0": { - "transformers": "Blip2Model" + "transformers": "VitDetModel" } }, "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" + "VitDetModel", + "VitDetPreTrainedModel", + "VitDetBackbone" ] } }, - "info.art.deberta-v2-x": { + "info.art.mms-tts-eng": { "*": { - "repo": "microsoft/deberta-v2-xlarge", + "repo": "facebook/mms-tts-eng", "pkg": { "0": { - "transformers": "DebertaV2Model" + "transformers": "VitsModel" } }, "tasks": [ - "DebertaV2ForMaskedLM", - "DebertaV2ForMultipleChoice", - "DebertaV2ForQuestionAnswering", - "DebertaV2ForSequenceClassification", - "DebertaV2ForTokenClassification", - "DebertaV2Model", - "DebertaV2PreTrainedModel" + "VitsModel", + "VitsPreTrainedModel" ] } }, - "info.vit.ast-finetuned-audioset-10-10-0593": { + "info.vit.vivit16x2-kinetics400": { "*": { - "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", + "repo": "google/vivit-b-16x2-kinetics400", "pkg": { "0": { - "transformers": "ASTModel" + "transformers": "VivitModel" } }, "tasks": [ - "ASTForAudioClassification", - "ASTModel", - "ASTPreTrainedModel" + "VivitModel", + "VivitPreTrainedModel", + "VivitForVideoClassification" ] } }, - "info.detr.dab-detr": { + "info.vit.vjepa2-vitl-fpc64-256": { "*": { - "repo": "IDEA-Research/dab-detr-resnet-50", + "repo": "facebook/vjepa2-vitl-fpc64-256", "pkg": { "0": { - "transformers": "DabDetrModel" + "transformers": "VJEPA2Model" } }, "tasks": [ - "DabDetrForObjectDetection", - "DabDetrModel", - "DabDetrPreTrainedModel" + "VJEPA2Model", + "VJEPA2PreTrainedModel", + "VJEPA2ForVideoClassification" ] } }, - "info.aet.sew-d": { + "info.stst.voxtral-2507": { "*": { - "repo": "asapp/sew-d-tiny-100k", + "repo": "mistralai/Voxtral-Mini-3B-2507", "pkg": { "0": { - "transformers": "SEWDModel" + "transformers": "VoxtralForConditionalGeneration" } }, "tasks": [ - "SEWDForCTC", - "SEWDForSequenceClassification", - "SEWDModel", - "SEWDPreTrainedModel" + "VoxtralPreTrainedModel", + "VoxtralEncoder", + "VoxtralForConditionalGeneration" ] } }, - "info.art.bert-for-seq-generation-l-24-bbc-encoder": { + "info.aet.voxtral-2507": { "*": { - "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", + "repo": "mistralai/Voxtral-Mini-3B-2507", "pkg": { "0": { - "transformers": "BertGenerationEncoder" + "transformers": "VoxtralEncoder" } }, "tasks": [ - "BertGenerationDecoder", - "BertGenerationEncoder", - "BertGenerationPreTrainedModel" + "VoxtralPreTrainedModel", + "VoxtralEncoder", + "VoxtralForConditionalGeneration" + ] + } + }, + "info.aet.wav2vec2-960h": { + "*": { + "repo": "facebook/wav2vec2-base-960h", + "pkg": { + "0": { + "transformers": "Wav2Vec2Model" + } + }, + "tasks": [ + "Wav2Vec2ForAudioFrameClassification", + "Wav2Vec2ForCTC", + "Wav2Vec2ForMaskedLM", + "Wav2Vec2ForPreTraining", + "Wav2Vec2ForSequenceClassification", + "Wav2Vec2ForXVector", + "Wav2Vec2Model", + "Wav2Vec2PreTrainedModel" ] } }, @@ -5193,91 +12126,142 @@ ] } }, - "info.stst.nllb-moe": { + "info.aet.wav2vec2-conformer-rel-pos": { "*": { - "repo": "facebook/nllb-moe-54b", + "repo": "facebook/wav2vec2-conformer-rel-pos-large", "pkg": { "0": { - "transformers": "NllbMoeModel" + "transformers": "Wav2Vec2ConformerModel" } }, "tasks": [ - "NllbMoeForConditionalGeneration", - "NllbMoeModel", - "NllbMoePreTrainedModel", - "NllbMoeTop2Router", - "NllbMoeSparseMLP" + "Wav2Vec2ConformerForAudioFrameClassification", + "Wav2Vec2ConformerForCTC", + "Wav2Vec2ConformerForPreTraining", + "Wav2Vec2ConformerForSequenceClassification", + "Wav2Vec2ConformerForXVector", + "Wav2Vec2ConformerModel", + "Wav2Vec2ConformerPreTrainedModel" + ] + } + }, + "info.aet.wavlm": { + "*": { + "repo": "microsoft/wavlm-base", + "pkg": { + "0": { + "transformers": "WavLMModel" + } + }, + "tasks": [ + "WavLMForAudioFrameClassification", + "WavLMForCTC", + "WavLMForSequenceClassification", + "WavLMForXVector", + "WavLMModel", + "WavLMPreTrainedModel" + ] + } + }, + "info.aet.whisper": { + "*": { + "repo": "openai/whisper-tiny", + "pkg": { + "0": { + "transformers": "WhisperModel" + } + }, + "tasks": [ + "WhisperForCausalLM", + "WhisperForConditionalGeneration", + "WhisperModel", + "WhisperPreTrainedModel", + "WhisperForAudioClassification" + ] + } + }, + "info.vit.xclip-patch32": { + "*": { + "repo": "microsoft/xclip-base-patch32", + "pkg": { + "0": { + "transformers": "XCLIPModel" + } + }, + "tasks": [ + "XCLIPModel", + "XCLIPPreTrainedModel", + "XCLIPTextModel", + "XCLIPVisionModel" ] } }, - "info.art.efficient-mlm-m0-0": { + "info.gan.x-codec": { "*": { - "repo": "andreasmadsen/efficient_mlm_m0.40", + "repo": "Manel/X-Codec", "pkg": { "0": { - "transformers": "RobertaPreLayerNormModel" + "transformers": "XcodecModel" } }, "tasks": [ - "RobertaPreLayerNormForCausalLM", - "RobertaPreLayerNormForMaskedLM", - "RobertaPreLayerNormForMultipleChoice", - "RobertaPreLayerNormForQuestionAnswering", - "RobertaPreLayerNormForSequenceClassification", - "RobertaPreLayerNormForTokenClassification", - "RobertaPreLayerNormModel", - "RobertaPreLayerNormPreTrainedModel" + "XcodecModel", + "XcodecPreTrainedModel" ] } }, - "info.art.xlm-roberta": { + "info.art.xglm": { "*": { - "repo": "FacebookAI/xlm-roberta-base", + "repo": "facebook/xglm-564M", "pkg": { "0": { - "transformers": "XLMRobertaModel" + "transformers": "XGLMModel" } }, "tasks": [ - "XLMRobertaForCausalLM", - "XLMRobertaForMaskedLM", - "XLMRobertaForMultipleChoice", - "XLMRobertaForQuestionAnswering", - "XLMRobertaForSequenceClassification", - "XLMRobertaForTokenClassification", - "XLMRobertaModel", - "XLMRobertaPreTrainedModel" + "XGLMForCausalLM", + "XGLMModel", + "XGLMPreTrainedModel" ] } }, - "info.vit.mgp-str": { + "info.art.xlm-mlm-en-2048": { "*": { - "repo": "alibaba-damo/mgp-str-base", + "repo": "FacebookAI/xlm-mlm-en-2048", "pkg": { "0": { - "transformers": "MgpstrForSceneTextRecognition" + "transformers": "XLMModel" } }, "tasks": [ - "MgpstrModel", - "MgpstrPreTrainedModel", - "MgpstrForSceneTextRecognition" + "XLMForMultipleChoice", + "XLMForQuestionAnswering", + "XLMForQuestionAnsweringSimple", + "XLMForSequenceClassification", + "XLMForTokenClassification", + "XLMModel", + "XLMPreTrainedModel", + "XLMWithLMHeadModel" ] } }, - "info.stst.blenderbot": { + "info.art.xlm-roberta": { "*": { - "repo": "facebook/blenderbot_small-90M", + "repo": "FacebookAI/xlm-roberta-base", "pkg": { "0": { - "transformers": "BlenderbotSmallModel" + "transformers": "XLMRobertaModel" } }, "tasks": [ - "BlenderbotSmallForCausalLM", - "BlenderbotSmallForConditionalGeneration", - "BlenderbotSmallModel", - "BlenderbotSmallPreTrainedModel" + "XLMRobertaForCausalLM", + "XLMRobertaForMaskedLM", + "XLMRobertaForMultipleChoice", + "XLMRobertaForQuestionAnswering", + "XLMRobertaForSequenceClassification", + "XLMRobertaForTokenClassification", + "XLMRobertaModel", + "XLMRobertaPreTrainedModel" ] } }, @@ -5301,148 +12285,125 @@ ] } }, - "info.art.megatron-bert-uncased": { - "*": { - "repo": "nvidia/megatron-bert-uncased-345m", - "pkg": { - "0": { - "transformers": "MegatronBertModel" - } - }, - "tasks": [ - "MegatronBertForCausalLM", - "MegatronBertForMaskedLM", - "MegatronBertForMultipleChoice", - "MegatronBertForNextSentencePrediction", - "MegatronBertForPreTraining", - "MegatronBertForQuestionAnswering", - "MegatronBertForSequenceClassification", - "MegatronBertForTokenClassification", - "MegatronBertModel", - "MegatronBertPreTrainedModel" - ] - } - }, - "info.detr.grounding-dino": { + "info.art.xlnet-cased": { "*": { - "repo": "IDEA-Research/grounding-dino-tiny", + "repo": "xlnet/xlnet-large-cased", "pkg": { "0": { - "transformers": "GroundingDinoModel" + "transformers": "XLNetModel" } }, "tasks": [ - "GroundingDinoForObjectDetection", - "GroundingDinoModel", - "GroundingDinoPreTrainedModel" + "XLNetForMultipleChoice", + "XLNetForQuestionAnswering", + "XLNetForQuestionAnsweringSimple", + "XLNetForSequenceClassification", + "XLNetForTokenClassification", + "XLNetLMHeadModel", + "XLNetModel", + "XLNetPreTrainedModel" ] } }, - "info.detr.table-transformer-detection": { + "info.lstm.xlstm": { "*": { - "repo": "microsoft/table-transformer-detection", + "repo": "NX-AI/xLSTM-7b", "pkg": { "0": { - "transformers": "TableTransformerModel" + "transformers": "xLSTMModel" } }, "tasks": [ - "TableTransformerForObjectDetection", - "TableTransformerModel", - "TableTransformerPreTrainedModel" + "xLSTMForCausalLM", + "xLSTMModel", + "xLSTMPreTrainedModel" ] } }, - "info.aet.funnel": { + "info.art.xmod": { "*": { - "repo": "funnel-transformer/small", + "repo": "facebook/xmod-base", "pkg": { "0": { - "transformers": "FunnelModel" + "transformers": "XmodModel" } }, "tasks": [ - "FunnelBaseModel", - "FunnelForMaskedLM", - "FunnelForMultipleChoice", - "FunnelForPreTraining", - "FunnelForQuestionAnswering", - "FunnelForSequenceClassification", - "FunnelForTokenClassification", - "FunnelModel", - "FunnelPreTrainedModel" + "XmodForCausalLM", + "XmodForMaskedLM", + "XmodForMultipleChoice", + "XmodForQuestionAnswering", + "XmodForSequenceClassification", + "XmodForTokenClassification", + "XmodModel", + "XmodPreTrainedModel" ] } }, - "info.aet.unispeech-sat-100h-libri-ft": { + "info.cnn.yolos": { "*": { - "repo": "microsoft/unispeech-sat-base-100h-libri-ft", + "repo": "hustvl/yolos-base", "pkg": { "0": { - "transformers": "UniSpeechSatModel" + "transformers": "YolosModel" } }, "tasks": [ - "UniSpeechSatForAudioFrameClassification", - "UniSpeechSatForCTC", - "UniSpeechSatForPreTraining", - "UniSpeechSatForSequenceClassification", - "UniSpeechSatForXVector", - "UniSpeechSatModel", - "UniSpeechSatPreTrainedModel" + "YolosForObjectDetection", + "YolosModel", + "YolosPreTrainedModel" ] } }, - "info.aet.wav2vec2-conformer-rel-pos": { + "info.art.yoso-4096": { "*": { - "repo": "facebook/wav2vec2-conformer-rel-pos-large", + "repo": "uw-madison/yoso-4096", "pkg": { "0": { - "transformers": "Wav2Vec2ConformerModel" + "transformers": "YosoModel" } }, "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" + "YosoForMaskedLM", + "YosoForMultipleChoice", + "YosoForQuestionAnswering", + "YosoForSequenceClassification", + "YosoForTokenClassification", + "YosoLayer", + "YosoModel", + "YosoPreTrainedModel" ] } }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "info.ssm.zamba-v1": { "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "repo": "Zyphra/Zamba-7B-v1", "pkg": { "0": { - "transformers": "MMGroundingDinoModel" + "transformers": "ZambaModel" } }, "tasks": [ - "MMGroundingDinoForObjectDetection", - "MMGroundingDinoModel", - "MMGroundingDinoPreTrainedModel" + "ZambaForCausalLM", + "ZambaForSequenceClassification", + "ZambaModel", + "ZambaPreTrainedModel" ] } }, - "info.art.gpt2": { + "info.ssm.zamba2": { "*": { - "repo": "openai-community/gpt2", + "repo": "Zyphra/Zamba2-2.7B", "pkg": { "0": { - "transformers": "GPT2Model" + "transformers": "Zamba2Model" } }, "tasks": [ - "GPT2DoubleHeadsModel", - "GPT2ForQuestionAnswering", - "GPT2ForSequenceClassification", - "GPT2ForTokenClassification", - "GPT2LMHeadModel", - "GPT2Model", - "GPT2PreTrainedModel" + "Zamba2ForCausalLM", + "Zamba2ForSequenceClassification", + "Zamba2Model", + "Zamba2PreTrainedModel" ] } }, @@ -7154,6 +14115,167 @@ ] } }, + "info.dit.flux1-dev": { + "mystic": { + "repo": "enhanceaiteam/Mystic", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 16, + "guidance_scale": 7.5, + "width": 768, + "height": 1024 + } + } + }, + "file_256": [ + "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", + "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" + ], + "layer_256": [ + "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" + ], + "layer_b3": [ + "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" + ] + }, + "flux1-lite": { + "repo": "freepik/flux.1-lite-8b", + "pkg": { + "0": { + "generation": { + "num_inference_steps": 28 + } + } + }, + "file_256": [ + "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", + "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" + ], + "layer_256": [ + "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" + ], + "layer_b3": [ + "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" + ] + }, + "f-lite": { + "repo": "freepik/f-lite", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "f-lite-texture": { + "repo": "freepik/f-lite-texture", + "pkg": { + "0": { + "f_lite": "FLitePipeline", + "generation": { + "num_inference_steps": 28 + } + } + } + }, + "flux": { + "repo": "TencentARC/flux-mini", + "file_256": [ + "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" + ], + "layer_256": [ + "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" + ], + "layer_b3": [ + "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" + ] + }, + "flex2": { + "repo": "ostris/Flex.2-preview", + "file_256": [ + "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", + "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" + ], + "layer_256": [ + "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" + ], + "layer_b3": [ + "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" + ] + }, + "flex1-alpha": { + "repo": "ostris/Flex.1-alpha", + "file_256": [ + "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", + "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" + ], + "layer_256": [ + "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" + ], + "layer_b3": [ + "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" + ] + }, + "*": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 3.5, + "num_inference_steps": 50, + "max_sequence_length": 512 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "gudance": 3.5, + "num_inference_steps": 25 + } + } + }, + "file_256": [ + "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", + "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", + "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", + "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", + "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" + ], + "layer_b3": [ + "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", + "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", + "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" + ], + "layer_256": [ + "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", + "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", + "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" + ], + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ], + "tasks": [ + "Image", + "Redux", + "Kontext", + "Depth", + "Fill", + "ConceptAttention", + "ControlNet", + "CavTon", + "IC-Edit" + ] + } + }, "info.dit.wan2-flf2v-720p": { "diffusers": { "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", diff --git a/mir/config/constants.py b/mir/config/constants.py index 23632fd..a572017 100644 --- a/mir/config/constants.py +++ b/mir/config/constants.py @@ -41,7 +41,7 @@ def mapped_cls(model_identifier: str): return None -def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable: +def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable | None: """Convert two strings into a callable function or property\n :param module: The name of the module to import :param library_path: Base package for the module @@ -62,7 +62,7 @@ def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable: nfo("failed to find module {module}") -def extract_init_params(module: Callable | str, package_name: str | None = None) -> dict[str, list[str]]: +def extract_init_parameters(module: Callable | str, package_name: str | None = None) -> dict[str, list[str]]: """Pick apart a Diffusers or Transformers pipeline class and find its constituent parts (formerly root_class)\n :param module: Origin pipeline as a class or as a string :param library: name of a library to import the class from, only if a string is provided @@ -77,23 +77,12 @@ def extract_init_params(module: Callable | str, package_name: str | None = None) module_obj = module signature = inspect.signature(module_obj.__init__) class_names = {} - for folder, param in signature.parameters.items(): - if folder not in ["self", "kwargs", "use_cache"]: - sub_module = str(param.annotation).split("'") - if len(sub_module) > 1 and sub_module[1] not in [ - "bool", - "int", - "float", - "complex", - "str", - "list", - "tuple", - "dict", - "set", - "inspect", - "_empty", - ]: - class_names.setdefault(folder, sub_module[1].split(".")) + editable_signature = signature.parameters.copy() + editable_signature.pop("self", None) + editable_signature.pop("kwargs", None) + editable_signature.pop("use_cache", None) + for folder, param in editable_signature.items(): + class_names.setdefault(folder, True) return class_names @@ -110,9 +99,9 @@ class ClassMapEntry: def __post_init__(self): if self.model: - self.model_params = extract_init_params(self.model) + self.model_params = extract_init_parameters(self.model) if self.config: - self.config_params = extract_init_params(self.config) + self.config_params = extract_init_parameters(self.config) @dataclass diff --git a/mir/indexers.py b/mir/indexers.py index 0c155ce..573d877 100644 --- a/mir/indexers.py +++ b/mir/indexers.py @@ -8,7 +8,7 @@ from typing import Any, Callable from mir.config.console import nfo -from mir.config.constants import ClassMapEntry, extract_init_params +from mir.config.constants import ClassMapEntry, extract_init_parameters from mir.config.conversion import get_repo_from_class_map, import_submodules from mir.doc_parser import parse_docs, DocParseData from mir.tag import mir_prefix_from_forward_pass, mir_tag_from_config, tag_model_from_repo @@ -47,7 +47,7 @@ def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable mir_prefix = "info" if hasattr(diffusers, class_name): model_class_obj = getattr(diffusers, class_name) - sub_segments = extract_init_params(model_class_obj, "diffusers") + sub_segments = extract_init_parameters(model_class_obj, "diffusers") decoder = "decoder" in sub_segments if repo_path in ["kandinsky-community/kandinsky-3"]: mir_prefix = "info.unet" @@ -116,7 +116,7 @@ def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: model_class_obj = import_submodules(parsed_data.pipe_class, f"diffusers.pipelines.{extracted.package_name}.{extracted.file_name}") if not model_class_obj: continue - extract_init_params(model_class_obj) + extract_init_parameters(model_class_obj) try: series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) except TypeError: @@ -167,13 +167,14 @@ def transformers_index(): repo_path = get_repo_from_class_map(entry) if config := missing_config_params.get(entry.name, {}): entry.config_params = config.get("params", entry.config_params) - if not repo_path: + if not repo_path or entry.name == "gpt_oss": repo_path = config["repo_path"] if not repo_path: raise ValueError(f"Unable to determine repo from {entry}") - if entry.config_params and list(entry.config_params) != ["use_cache", "kwargs"]: + if entry.config_params: mir_series, mir_comp, mir_suffix = mir_tag_from_config(entry, repo_path) # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) + repo_path = check_migrations(repo_path) tk_pkg = {} tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) diff --git a/mir/inspect/metadata.py b/mir/inspect/metadata.py index 190d61b..613afae 100644 --- a/mir/inspect/metadata.py +++ b/mir/inspect/metadata.py @@ -4,7 +4,7 @@ from typing import Callable, Generator import diffusers -from mir.config.constants import ClassMapEntry, DocStringEntry, extract_init_params +from mir.config.constants import ClassMapEntry, DocStringEntry, extract_init_parameters from mir.config.conversion import retrieve_diffusers_docstrings diff --git a/mir/inspect/pipes.py b/mir/inspect/pipes.py index 8ef1d06..cdec5f7 100644 --- a/mir/inspect/pipes.py +++ b/mir/inspect/pipes.py @@ -9,13 +9,13 @@ def show_shared_hyperparameters(parameter_filter: Optional[str] = None) -> List[ :param from_match: Narrow the classes to only those with an exact key inside :return: A list of all Classes""" from mir.inspect.metadata import map_transformers_classes - from mir.config.constants import extract_init_params + from mir.config.constants import extract_init_parameters transformers_data = map_transformers_classes() config_data = [] for entry in transformers_data: if parameter_filter: - segments = extract_init_params(module=entry.config, package_name="transformers") + segments = extract_init_parameters(module=entry.config, package_name="transformers") if parameter_filter in list(segments): config_data.append(entry.config) else: diff --git a/mir/mir.json b/mir/mir.json index 4c9d44d..c897555 100644 --- a/mir/mir.json +++ b/mir/mir.json @@ -116,6 +116,29 @@ "0": { "diffusers": "MarigoldDepthPipeline" } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-depth-v1-1" + ] } } }, @@ -126,6 +149,29 @@ "0": { "diffusers": "MarigoldIntrinsicsPipeline" } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-iid-appearance-v1-1" + ] } } }, @@ -136,6 +182,29 @@ "0": { "diffusers": "MarigoldNormalsPipeline" } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + [ + "ops.scheduler.ddim", + "scheduler" + ], + [ + "ops.scheduler.lcm", + "scheduler" + ] + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "marigold-normals-v1-1" + ] } } }, @@ -146,6 +215,94 @@ "0": { "diffusers": "StableDiffusionPipeline" } + }, + "identifiers": [ + "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" + ], + "file_256": [ + "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", + "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", + "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", + "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", + "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", + "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", + "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" + ], + "layer_b3": [ + "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", + "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", + "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", + "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" + ], + "layer_256": [ + "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", + "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", + "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" + ], + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-v1-5" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "safety_checker": [ + "StableDiffusionSafetyChecker" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ] } } }, @@ -156,6 +313,80 @@ "0": { "diffusers": "StableUnCLIPPipeline" } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "prior_tokenizer": [ + "info.encoder.tokenizer", + "stable-unclip-2-1-l" + ], + "prior_text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "prior": [ + "PriorTransformer" + ], + "prior_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_normalizer": [ + "info.dit.flux1-schnell", + "*" + ], + "image_noising_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-unclip-2-1-l" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vae": [ + "AutoencoderKL" + ] } } }, @@ -166,6 +397,73 @@ "0": { "diffusers": "StableUnCLIPImg2ImgPipeline" } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "image_normalizer": [ + "info.dit.flux1-schnell", + "*" + ], + "image_noising_scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-2-1-unclip" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vae": [ + "AutoencoderKL" + ] } } }, @@ -174,9 +472,42 @@ "repo": "stabilityai/stable-diffusion-xl-base-1.0", "pkg": { "0": { - "diffusers": "StableDiffusionXLPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "denoising_end": 0.8, + "num_inference_steps": 40, + "output_type": "latent", + "safety_checker": false, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" } - } + }, + "file_256": [ + "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", + "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", + "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", + "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" + ], + "layer_256": [ + "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", + "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", + "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" + ], + "layer_b3": [ + "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", + "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", + "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" + ], + "identifiers": [ + "logit_scale", + "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", + "add_embedding.linear_2.bias" + ], + "pipe_names": {} }, "pony-diffusion": { "file_256": [ @@ -282,7 +613,8 @@ "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" - ] + ], + "pipe_names": {} }, "segmind-vega": { "repo": "segmind/Segmind-Vega", @@ -333,7 +665,81 @@ "pkg": { "0": { "diffusers": "StableDiffusionXLImg2ImgPipeline" + }, + "1": { + "diffusers": "DiffusionPipeline", + "generation": { + "num_inference_steps": 40, + "denoising_end": 0.8 + } } + }, + "identifiers": [ + "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" + ], + "file_256": [ + "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", + "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", + "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" + ], + "layer_b3": [ + "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", + "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", + "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" + ], + "layer_256": [ + "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", + "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", + "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" + ], + "tasks": [ + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-refiner-1" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "stable-diffusion-xl-refiner-1" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -344,6 +750,47 @@ "0": { "diffusers": "StableDiffusionXLInstructPix2PixPipeline" } + }, + "tasks": [ + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "sdxl-pix2pix-768" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "sdxl-pix2pix-768" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] } } }, @@ -352,9 +799,23 @@ "repo": "rhymes-ai/Allegro", "pkg": { "0": { - "diffusers": "AllegroPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "guidance_scale": 7.5, + "max_sequence_length": 512, + "num_inference_steps": 100 + } } - } + }, + "file_256": [ + "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" + ], + "layer_b3": [ + "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" + ], + "layer_256": [ + "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" + ] } }, "info.dit.amused-512": { @@ -364,6 +825,26 @@ "0": { "diffusers": "AmusedInpaintPipeline" } + }, + "pipe_names": { + "vqvae": [ + "VQModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "amused-512" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "transformer": [ + "UVit2DModel" + ], + "scheduler": [ + "ops.scheduler.amused", + "scheduler" + ] } } }, @@ -424,6 +905,40 @@ "0": { "diffusers": "BriaPipeline" } + }, + "pipe_names": { + "transformer": [ + "BriaTransformer2DModel" + ], + "scheduler": [ + [ + "ops.scheduler.euler", + "discrete" + ], + [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "bria-3" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -434,6 +949,27 @@ "0": { "diffusers": "Flux2Pipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "info.vit.mistral-3-2503", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux2-dev" + ], + "transformer": [ + "Flux2Transformer2DModel" + ] } } }, @@ -442,9 +978,54 @@ "repo": "black-forest-labs/FLUX.1-schnell", "pkg": { "0": { - "diffusers": "FluxInpaintPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 0.0, + "num_inference_steps": 4, + "max_sequence_length": 256 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "num_inference_steps": 4 + } } - } + }, + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ], + "file_256": [ + "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", + "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" + ], + "layer_b3": [ + "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", + "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", + "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" + ], + "layer_256": [ + "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", + "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", + "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" + ], + "tasks": [ + "Image", + "Redux", + "Kontext", + "Depth", + "Fill", + "ConceptAttention", + "ControlNet", + "CavTon", + "IC-Edit" + ] }, "shuttle-3-aesthetic": { "repo": "shuttleai/shuttle-3.1-aesthetic", @@ -566,6 +1147,46 @@ "0": { "diffusers": "FluxFillPipeline" } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-fill-dev" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-fill-dev" + ], + "transformer": [ + "FluxTransformer2DModel" + ] } } }, @@ -576,6 +1197,54 @@ "0": { "diffusers": "FluxKontextInpaintPipeline" } + }, + "tasks": [ + "FluxControlImg2ImgPipeline", + "FluxControlInpaintPipeline", + "FluxControlNetImg2ImgPipeline", + "FluxControlNetInpaintPipeline", + "FluxControlNetPipeline", + "FluxControlPipeline", + "FluxImg2ImgPipeline", + "FluxInpaintPipeline", + "FluxKontextPipeline", + "FluxPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "flux1-kontext-dev" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "flux1-kontext-dev" + ], + "transformer": [ + "FluxTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -586,6 +1255,31 @@ "0": { "diffusers": "PRXPipeline" } + }, + "pipe_names": { + "transformer": [ + "PRXTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder": [ + "info.stst.t5gemma-prefixlm", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "prx-512-t2i-sft" + ], + "vae": [ + "AutoencoderKL", + [ + "info.vae.dc", + "sana-1024px-bf16" + ], + "NoneType" + ] } } }, @@ -596,6 +1290,36 @@ "0": { "diffusers": "AudioLDMPipeline" } + }, + "file_256": [ + "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clap-htsat-fused", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "vocoder": [ + "info.stst.speecht5-asr", + "*" + ] } } }, @@ -604,9 +1328,22 @@ "repo": "cvssp/audioldm2", "pkg": { "0": { - "diffusers": "AudioLDM2Pipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } } - } + }, + "file_256": [ + "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" + ], + "layer_b3": [ + "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" + ], + "layer_256": [ + "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" + ] } }, "info.unet.blipdiffusion": { @@ -616,6 +1353,31 @@ "0": { "diffusers": "BlipDiffusionPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "blipdiffusion" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "scheduler": [ + "ops.scheduler.pndm", + "scheduler" + ], + "qformer": [ + "info.vit.blip2-opt", + "*" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -625,7 +1387,60 @@ "pkg": { "0": { "diffusers": "ChromaPipeline" + }, + "1": { + "generation": { + "neg_text": "", + "num_steps": "28", + "latent_size": [ + 64, + 64 + ] + } } + }, + "file_256": [ + "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", + "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", + "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", + "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" + ], + "layer_b3": [ + "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" + ], + "layer_256": [ + "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" + ], + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } }, "chroma1-hd": { @@ -659,7 +1474,38 @@ "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" - ] + ], + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] + } } }, "info.dit.chroma1-hd": { @@ -669,6 +1515,37 @@ "0": { "diffusers": "ChromaImg2ImgPipeline" } + }, + "tasks": [ + "ChromaPipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "chroma1-hd" + ], + "transformer": [ + "ChromaTransformer2DModel" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -677,9 +1554,24 @@ "repo": "zai-org/CogVideoX-2b", "pkg": { "0": { - "diffusers": "CogVideoXPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_videos_per_prompt": 1, + "num_inference_steps": 50, + "num_frames": 49, + "guidance_scale": 6 + } } - } + }, + "file_256": [ + "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" + ], + "layer_b3": [ + "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" + ], + "layer_256": [ + "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" + ] } }, "info.controlnet.cogvideox-fun-v-pose": { @@ -699,6 +1591,33 @@ "0": { "diffusers": "CogVideoXImageToVideoPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogvideox-i2v" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "vae": [ + "info.vae.cogvideox", + "cogvideox-i2v" + ], + "transformer": [ + "CogVideoXTransformer3DModel" + ], + "scheduler": [ + [ + "ops.scheduler.cogvideoxddim", + "scheduler" + ], + [ + "ops.scheduler.cogvideoxdpm", + "scheduler" + ] + ] } } }, @@ -707,7 +1626,14 @@ "repo": "zai-org/CogView3-Plus-3B", "pkg": { "0": { - "diffusers": "CogView3PlusPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "guidance_scale": 7.0, + "num_images_per_prompt": 1, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } } } } @@ -719,6 +1645,30 @@ "0": { "diffusers": "CogView4Pipeline" } + }, + "tasks": [ + "CogView4ControlPipeline", + "CogView4Pipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "cogview4" + ], + "text_encoder": [ + "info.stst.glm-4-chat", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "CogView4Transformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -739,6 +1689,30 @@ "0": { "diffusers": "Cosmos2_5_PredictBasePipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "pre-trianed" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] } } }, @@ -749,6 +1723,75 @@ "0": { "diffusers": "Cosmos2TextToImagePipeline" } + }, + "file_256": [ + "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", + "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", + "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", + "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", + "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", + "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", + "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", + "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", + "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", + "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", + "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", + "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", + "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" + ], + "layer_b3": [ + "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", + "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", + "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", + "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", + "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", + "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", + "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", + "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", + "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", + "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", + "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", + "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", + "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" + ], + "layer_256": [ + "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", + "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", + "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", + "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", + "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", + "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", + "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", + "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", + "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", + "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", + "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", + "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", + "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" + ], + "pipe_names": { + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-predict2-text2image" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] } } }, @@ -759,6 +1802,30 @@ "0": { "diffusers": "Cosmos2VideoToWorldPipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-predict2-video2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] } } }, @@ -769,6 +1836,30 @@ "0": { "diffusers": "CosmosTextToWorldPipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-1-diffusion-text2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "cosmos-1-diffusion-video2world" + ], + "scheduler": [ + "ops.scheduler.edmeuler", + "scheduler" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] } } }, @@ -779,6 +1870,30 @@ "0": { "diffusers": "CosmosVideoToWorldPipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "cosmos-1-diffusion-video2world" + ], + "transformer": [ + "CosmosTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "cosmos-1-diffusion-video2world" + ], + "scheduler": [ + "ops.scheduler.edmeuler", + "scheduler" + ], + "safety_checker": [ + "CosmosSafetyChecker" + ] } } }, @@ -789,6 +1904,24 @@ "0": { "diffusers": "IFSuperResolutionPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "if-ii-l-v1" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "scheduler": [ + "ops.scheduler.ddpm", + "scheduler" + ], + "image_noising_scheduler": [ + "ops.scheduler.ddpm", + "scheduler" + ] } } }, @@ -799,6 +1932,30 @@ "0": { "diffusers": "EasyAnimatePipeline" } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "easyanimatev5-zh" + ], + "text_encoder": [ + "Qwen2VLForConditionalGeneration", + [ + "info.art.bert-uncased", + "*" + ] + ], + "tokenizer": [ + "info.encoder.tokenizer", + "easyanimatev5-zh" + ], + "transformer": [ + "EasyAnimateTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -819,6 +1976,30 @@ "0": { "diffusers": "EasyAnimateInpaintPipeline" } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "easyanimatev5-zh" + ], + "text_encoder": [ + "Qwen2VLForConditionalGeneration", + [ + "info.art.bert-uncased", + "*" + ] + ], + "tokenizer": [ + "info.encoder.tokenizer", + "easyanimatev5-zh-inp" + ], + "transformer": [ + "EasyAnimateTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -829,6 +2010,60 @@ "0": { "diffusers": "HiDreamImagePipeline" } + }, + "file_256": [ + "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" + ], + "layer_b3": [ + "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" + ], + "layer_256": [ + "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_3": [ + "info.stst.t5", + "*" + ], + "tokenizer_3": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "text_encoder_4": [ + "info.stst.llama-2-hf", + "*" + ], + "tokenizer_4": [ + "info.encoder.tokenizer", + "hidream-i1" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -837,9 +2072,29 @@ "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", "pkg": { "0": { - "diffusers": "HunyuanDiTPipeline" + "precision": "ops.precision.float.F16" } - } + }, + "identifiers": [ + "extra_embedder", + "model.blocks", + "skip_norm.weight" + ], + "file_256": [ + "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", + "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", + "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" + ], + "layer_b3": [ + "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", + "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", + "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" + ], + "layer_256": [ + "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", + "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", + "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" + ] } }, "info.dit.hunyuanvideo": { @@ -849,6 +2104,44 @@ "0": { "diffusers": "HunyuanVideoPipeline" } + }, + "file_256": [ + "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" + ], + "layer_b3": [ + "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" + ], + "layer_256": [ + "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" + ], + "pipe_names": { + "text_encoder": [ + "info.stst.llama-2-hf", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo" + ], + "transformer": [ + "HunyuanVideoTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo" + ] } } }, @@ -859,6 +2152,39 @@ "0": { "diffusers": "HunyuanVideoImageToVideoPipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.vit.llava", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-i2v" + ], + "transformer": [ + "HunyuanVideoTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-i2v" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -869,6 +2195,38 @@ "0": { "diffusers": "HunyuanVideo15Pipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-t2v" + ], + "transformer": [ + "HunyuanVideo15Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-t2v" + ], + "guider": [ + "ClassifierFreeGuidance" + ] } } }, @@ -879,6 +2237,45 @@ "0": { "diffusers": "HunyuanVideo15ImageToVideoPipeline" } + }, + "pipe_names": { + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-i2v" + ], + "transformer": [ + "HunyuanVideo15Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanvideo-1-480p-i2v" + ], + "guider": [ + "ClassifierFreeGuidance" + ], + "image_encoder": [ + "SiglipVisionModel" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -889,6 +2286,36 @@ "0": { "diffusers": "HunyuanImagePipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanimage-2" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "hunyuanimage-2" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -899,6 +2326,28 @@ "0": { "diffusers": "HunyuanImageRefinerPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "hunyuanimage-2-refiner" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -909,6 +2358,47 @@ "0": { "diffusers": "KandinskyPriorPipeline" } + }, + "tasks": [ + "Kandinsky3Img2ImgPipeline", + "Kandinsky3Pipeline", + "KandinskyCombinedPipeline", + "KandinskyImg2ImgCombinedPipeline", + "KandinskyImg2ImgPipeline", + "KandinskyInpaintCombinedPipeline", + "KandinskyInpaintPipeline", + "KandinskyPipeline", + "KandinskyV22CombinedPipeline", + "KandinskyV22Img2ImgCombinedPipeline", + "KandinskyV22Img2ImgPipeline", + "KandinskyV22InpaintCombinedPipeline", + "KandinskyV22InpaintPipeline", + "KandinskyV22Pipeline" + ], + "pipe_names": { + "prior": [ + "PriorTransformer" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-2-1" + ], + "scheduler": [ + "ops.scheduler.unclip", + "scheduler" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -919,6 +2409,31 @@ "0": { "diffusers": "KandinskyV22PriorPipeline" } + }, + "pipe_names": { + "prior": [ + "PriorTransformer" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-2-2" + ], + "scheduler": [ + "ops.scheduler.unclip", + "scheduler" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -929,6 +2444,26 @@ "0": { "diffusers": "LattePipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "latte-1" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "LatteTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] } } }, @@ -939,6 +2474,27 @@ "0": { "diffusers": "LTXImageToVideoPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "ltx-video" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ltx-video" + ], + "transformer": [ + "LTXVideoTransformer3DModel" + ] } } }, @@ -949,6 +2505,27 @@ "0": { "diffusers": "LTXConditionPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "ltx-video" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ltx-video-09" + ], + "transformer": [ + "LTXVideoTransformer3DModel" + ] } } }, @@ -957,9 +2534,24 @@ "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", "pkg": { "0": { - "diffusers": "LuminaPipeline" + "precision": " ops.precision.bfloat.B16" } - } + }, + "identifiers": [ + "time_caption", + "feed_forward" + ], + "file_256": [ + "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" + ], + "layer_b3": [ + "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", + "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" + ], + "layer_256": [ + "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", + "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" + ] } }, "info.dit.lumina-image-2": { @@ -969,6 +2561,41 @@ "0": { "diffusers": "Lumina2Pipeline" } + }, + "file_256": [ + "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", + "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" + ], + "layer_b3": [ + "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" + ], + "layer_256": [ + "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" + ], + "tasks": [ + "Lumina2Pipeline" + ], + "pipe_names": { + "transformer": [ + "Lumina2Transformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.gemma2", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "lumina-image-2" + ] } }, "illustrious-lumina-v3": { @@ -987,6 +2614,34 @@ ] } }, + "info.dit.lucy-edit-dev": { + "*": { + "repo": "decart-ai/Lucy-Edit-Dev", + "pkg": { + "0": { + "diffusers": "LucyEditPipeline" + } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "lucy-edit-dev" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] + } + } + }, "info.dit.longcat-image": { "*": { "repo": "meituan-longcat/LongCat-Image", @@ -994,6 +2649,30 @@ "0": { "diffusers": "LongCatImagePipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "longcat-image" + ], + "text_processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1004,6 +2683,30 @@ "0": { "diffusers": "LongCatImageEditPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "longcat-image-edit" + ], + "text_processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1014,6 +2717,27 @@ "0": { "diffusers": "MochiPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "mochi-1" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "mochi-1" + ], + "transformer": [ + "MochiTransformer3DModel" + ] } } }, @@ -1022,9 +2746,21 @@ "repo": "ucsd-reach/musicldm", "pkg": { "0": { - "diffusers": "MusicLDMPipeline" + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } } - } + }, + "file_256": [ + "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ] } }, "info.dit.omnigen-v1": { @@ -1034,6 +2770,22 @@ "0": { "diffusers": "OmniGenPipeline" } + }, + "pipe_names": { + "transformer": [ + "OmniGenTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "omnigen-v1" + ] } } }, @@ -1044,6 +2796,30 @@ "0": { "diffusers": "OvisImagePipeline" } + }, + "tasks": [ + "OvisImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.stst.qwen3", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ovis-image" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1054,6 +2830,44 @@ "0": { "diffusers": "VisualClozeGenerationPipeline" } + }, + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "visualclozepipeline-384" + ], + "text_encoder_2": [ + "info.stst.t5", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "visualclozepipeline-384" + ], + "transformer": [ + "FluxTransformer2DModel" + ] + } + } + }, + "info.lora.pia-condition-adapter": { + "*": { + "repo": "openmmlab/PIA-condition-adapter", + "pkg": { + "0": { + "diffusers": "PIAPipeline" + } } } }, @@ -1064,6 +2878,44 @@ "0": { "diffusers": "PixArtAlphaPipeline" } + }, + "identifiers": [ + "aspect_ratio", + "y_embedding", + "emb.resolution", + "caption_projection" + ], + "file_256": [ + "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" + ], + "layer_b3": [ + "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" + ], + "layer_256": [ + "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" + ], + "tasks": [ + "PixArtAlphaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "pixart-xl-2-1024-ms" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "PixArtTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] } } }, @@ -1074,17 +2926,72 @@ "0": { "diffusers": "PixArtSigmaPipeline" } - } - } + }, + "identifiers": [ + "adaln_single", + "scale_shift_table" + ], + "file_256": [ + "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", + "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" + ], + "layer_b3": [ + "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", + "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" + ], + "layer_256": [ + "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", + "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" + ], + "tasks": [ + "PixArtAlphaPipeline", + "PixArtSigmaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "pixart-sigma-xl-2-1024-ms" + ], + "text_encoder": [ + "info.stst.t5", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "PixArtTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ] + } + } }, "info.dit.sana-1024px-bf16": { "diffusers": { "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", "pkg": { "0": { - "diffusers": "SanaPipeline" + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 4.5, + "num_inference_steps": 20 + }, + "precision": "ops.precision.bfloat.B16" } - } + }, + "file_256": [ + "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" + ], + "layer_b3": [ + "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" + ], + "layer_256": [ + "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" + ] } }, "info.controlnet.sana-1024px-controlnet": { @@ -1104,6 +3011,31 @@ "0": { "diffusers": "SanaSprintPipeline" } + }, + "tasks": [ + "SanaPAGPipeline", + "SanaPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "sana-sprint-1024px" + ], + "text_encoder": [ + "info.stst.gemma2", + "*" + ], + "vae": [ + "info.vae.dc", + "sana-1024px-bf16" + ], + "transformer": [ + "SanaTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.dpm", + "multistep" + ] } } }, @@ -1114,6 +3046,33 @@ "0": { "diffusers": "SanaImageToVideoPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "sana-video" + ], + "text_encoder": [ + "info.stst.gemma2", + "*" + ], + "vae": [ + [ + "info.vae.dc", + "sana-1024px-bf16" + ], + [ + "info.vae.kl", + "audioldm-s-v2" + ] + ], + "transformer": [ + "SanaVideoTransformer3DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1122,7 +3081,12 @@ "repo": "openai/shap-e", "pkg": { "0": { - "diffusers": "ShapEPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 64, + "size": 256, + "guidance_scale": 15 + } } } } @@ -1132,7 +3096,12 @@ "repo": "stabilityai/stable-audio-open-1.0", "pkg": { "0": { - "diffusers": "StableAudioPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_end_in_s": 10, + "num_waveforms_per_prompt": 3 + } } } } @@ -1142,9 +3111,85 @@ "repo": "stabilityai/stable-cascade-prior", "pkg": { "0": { - "diffusers": "StableCascadePriorPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "negative_prompt": "", + "num_images_per_prompt": 1, + "num_inference_steps": 20, + "guidance_scale": 4.0, + "width": 1024, + "height": 1024 + } + } + }, + "file_256": [ + "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", + "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", + "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", + "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", + "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", + "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" + ], + "layer_b3": [ + "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", + "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", + "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", + "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", + "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", + "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" + ], + "layer_256": [ + "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", + "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", + "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", + "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", + "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", + "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" + ], + "identifiers": [ + "down_blocks.0.2.kv_mapper", + "previewer", + "backbone" + ] + }, + "decoder": { + "pkg": { + "0": { + "generation": { + "negative_prompt": "", + "guidance_scale": 0.0, + "output_type": "pil", + "num_inference_steps": 10 + }, + "precision": "ops.precision.bfloat.B16" } - } + }, + "file_256": [ + "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", + "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", + "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", + "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", + "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" + ], + "layer_b3": [ + "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", + "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", + "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", + "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", + "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" + ], + "layer_256": [ + "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", + "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", + "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", + "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", + "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" + ], + "identifiers": [ + "0.2.channelwise", + "clip_mapper.bias", + ".12.self_attn.k_proj.weight" + ] } }, "info.dit.auraflow": { @@ -1154,6 +3199,55 @@ "0": { "diffusers": "AuraFlowPipeline" } + }, + "identifiers": [ + [ + 8192, + 3072 + ], + "mlpX.c_fc2.weight", + "joint_transformer_blocks.2.ff_context.linear_2.weight" + ], + "file_256": [ + "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", + "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", + "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", + "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" + ], + "layer_b3": [ + "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", + "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", + "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", + "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" + ], + "layer_256": [ + "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", + "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", + "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", + "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" + ], + "tasks": [ + "AuraFlowPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "auraflow" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "AutoencoderKL" + ], + "transformer": [ + "AuraFlowTransformer2DModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1162,9 +3256,27 @@ "repo": "stabilityai/stable-diffusion-3.5-medium", "pkg": { "0": { - "diffusers": "StableDiffusion3Pipeline" + "precision": "ops.precision.float.F16" } - } + }, + "identifiers": [ + "model.diffusion_model.joint_blocks.", + "transformer_blocks.21.norm1_context.linear.weight", + "transformer_blocks.31.norm1_context.linear.weight", + "blocks.11.ff.net.2.weight" + ], + "file_256": [ + "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", + "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" + ], + "layer_b3": [ + "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", + "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" + ], + "layer_256": [ + "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", + "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" + ] }, "stable-diffusion-3-turbo": { "repo": "tensorart/stable-diffusion-3.5-medium-turbo", @@ -1226,6 +3338,27 @@ "0": { "diffusers": "StableVideoDiffusionPipeline" } + }, + "pipe_names": { + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "unet": [ + "UNetSpatioTemporalConditionModel" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1236,6 +3369,64 @@ "0": { "diffusers": "StableDiffusionLDM3DPipeline" } + }, + "tasks": [ + "StableDiffusion3ControlNetInpaintingPipeline", + "StableDiffusion3ControlNetPipeline", + "StableDiffusion3Img2ImgPipeline", + "StableDiffusion3InpaintPipeline", + "StableDiffusion3PAGImg2ImgPipeline", + "StableDiffusion3PAGPipeline", + "StableDiffusion3Pipeline", + "StableDiffusionControlNetImg2ImgPipeline", + "StableDiffusionControlNetInpaintPipeline", + "StableDiffusionControlNetPAGInpaintPipeline", + "StableDiffusionControlNetPAGPipeline", + "StableDiffusionControlNetPipeline", + "StableDiffusionImg2ImgPipeline", + "StableDiffusionInpaintPipeline", + "StableDiffusionPAGImg2ImgPipeline", + "StableDiffusionPAGInpaintPipeline", + "StableDiffusionPAGPipeline", + "StableDiffusionPipeline", + "StableDiffusionXLControlNetImg2ImgPipeline", + "StableDiffusionXLControlNetInpaintPipeline", + "StableDiffusionXLControlNetPAGImg2ImgPipeline", + "StableDiffusionXLControlNetPAGPipeline", + "StableDiffusionXLControlNetPipeline", + "StableDiffusionXLControlNetUnionImg2ImgPipeline", + "StableDiffusionXLControlNetUnionInpaintPipeline", + "StableDiffusionXLControlNetUnionPipeline", + "StableDiffusionXLImg2ImgPipeline", + "StableDiffusionXLInpaintPipeline", + "StableDiffusionXLPAGImg2ImgPipeline", + "StableDiffusionXLPAGInpaintPipeline", + "StableDiffusionXLPAGPipeline", + "StableDiffusionXLPipeline" + ], + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "ldm3d-4c" + ], + "scheduler": [ + "ops.scheduler.karrasdiffusion", + "schedulers" + ], + "safety_checker": [ + "StableDiffusionSafetyChecker" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1246,6 +3437,34 @@ "0": { "diffusers": "I2VGenXLPipeline" } + }, + "pipe_names": { + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "i2vgen-xl" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "feature_extractor": [ + "info.dit.flux1-schnell", + "*" + ], + "unet": [ + "I2VGenXLUNet" + ], + "scheduler": [ + "ops.scheduler.ddim", + "scheduler" + ] } } }, @@ -1256,6 +3475,27 @@ "0": { "diffusers": "WuerstchenPriorPipeline" } + }, + "tasks": [ + "WuerstchenCombinedPipeline", + "WuerstchenDecoderPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wuerstchen" + ], + "text_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "prior": [ + "WuerstchenPrior" + ], + "scheduler": [ + "ops.scheduler.ddpmwuerstchen", + "scheduler" + ] } } }, @@ -1264,9 +3504,43 @@ "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", "pkg": { "0": { - "diffusers": "WanPipeline" + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } } - } + }, + "file_256": [ + "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", + "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", + "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", + "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", + "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", + "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", + "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", + "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" + ], + "layer_b3": [ + "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", + "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", + "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", + "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", + "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", + "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", + "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" + ], + "layer_256": [ + "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", + "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", + "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", + "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", + "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", + "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", + "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" + ] } }, "info.dit.wan-animate": { @@ -1276,6 +3550,40 @@ "0": { "diffusers": "WanAnimatePipeline" } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan-animate" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "transformer": [ + "WanAnimateTransformer3DModel" + ] } } }, @@ -1286,6 +3594,68 @@ "0": { "diffusers": "WanImageToVideoPipeline" } + }, + "file_256": [ + "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", + "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", + "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", + "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", + "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", + "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", + "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", + "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", + "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" + ], + "layer_b3": [ + "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", + "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", + "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", + "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", + "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" + ], + "layer_256": [ + "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", + "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", + "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", + "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", + "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" + ], + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan2-i2v-480p" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.wan", + "wan2-i2v-480p" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "transformer": [ + "WanTransformer3DModel" + ], + "transformer_2": [ + "WanTransformer3DModel" + ] } } }, @@ -1296,6 +3666,54 @@ "0": { "diffusers": "WanVACEPipeline" } + }, + "file_256": [ + "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", + "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", + "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", + "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", + "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" + ], + "layer_b3": [ + "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", + "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", + "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", + "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" + ], + "layer_256": [ + "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", + "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", + "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", + "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" + ], + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan21-vace" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "transformer": [ + "WanVACETransformer3DModel" + ], + "transformer_2": [ + "WanVACETransformer3DModel" + ] } } }, @@ -1304,8 +3722,38 @@ "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", "pkg": { "0": { - "diffusers": "WanVideoToVideoPipeline" + "diffusers": "WanPipeline", + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } } + }, + "tasks": [ + "WanImageToVideoPipeline", + "WanPipeline", + "WanVideoToVideoPipeline" + ], + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "wan21-t2v" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1316,6 +3764,35 @@ "0": { "diffusers": "Kandinsky5T2VPipeline" } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-t2v-lite-sft-5s" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-t2v-lite-sft-5s" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1326,6 +3803,34 @@ "0": { "diffusers": "Kandinsky5I2IPipeline" } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-i2i-lite-sft" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-i2i-lite-sft" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1336,6 +3841,35 @@ "0": { "diffusers": "Kandinsky5I2VPipeline" } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "hunyuanvideo-i2v" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-i2v-sft-5s" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-i2v-sft-5s" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1346,6 +3880,34 @@ "0": { "diffusers": "Kandinsky5T2IPipeline" } + }, + "pipe_names": { + "transformer": [ + "Kandinsky5Transformer3DModel" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "kandinsky-5-t2i-lite-sft" + ], + "text_encoder_2": [ + "info.vit.clip-vit-patch32", + "*" + ], + "tokenizer_2": [ + "info.encoder.tokenizer", + "kandinsky-5-t2i-lite-sft" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1356,6 +3918,41 @@ "0": { "diffusers": "ZImageOmniPipeline" } + }, + "tasks": [ + "ZImageControlNetInpaintPipeline", + "ZImageControlNetPipeline", + "ZImageImg2ImgPipeline", + "ZImageOmniPipeline", + "ZImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "AutoencoderKL" + ], + "text_encoder": [ + "PreTrainedModel" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "z-image-turbo" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ], + "siglip": [ + "info.vit.siglip2-patch16-224", + "*" + ], + "siglip_processor": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1376,6 +3973,27 @@ "0": { "diffusers": "SkyReelsV2Pipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-t2v-720p" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] } } }, @@ -1386,6 +4004,27 @@ "0": { "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-df-720p" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] } } }, @@ -1396,6 +4035,34 @@ "0": { "diffusers": "SkyReelsV2ImageToVideoPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "skyreels-v2-i2v-720p" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "image_processor": [ + "CLIPProcessor" + ], + "transformer": [ + "SkyReelsV2Transformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.unipc", + "multistep" + ] } } }, @@ -1406,6 +4073,46 @@ "0": { "diffusers": "QwenImageInpaintPipeline" } + }, + "file_256": [ + "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" + ], + "layer_b3": [ + "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" + ], + "layer_256": [ + "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" + ], + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1436,6 +4143,40 @@ "0": { "diffusers": "QwenImageEditInpaintPipeline" } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-edit" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1446,6 +4187,40 @@ "0": { "diffusers": "QwenImageEditPlusPipeline" } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-edit-2509" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1456,6 +4231,40 @@ "0": { "diffusers": "QwenImageLayeredPipeline" } + }, + "tasks": [ + "QwenImageControlNetPipeline", + "QwenImageEditInpaintPipeline", + "QwenImageEditPipeline", + "QwenImageEditPlusPipeline", + "QwenImageImg2ImgPipeline", + "QwenImageInpaintPipeline", + "QwenImagePipeline" + ], + "pipe_names": { + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ], + "vae": [ + "info.vae.kl", + "qwen-image" + ], + "text_encoder": [ + "info.vit.qwen2-vl", + "*" + ], + "tokenizer": [ + "info.encoder.tokenizer", + "qwen-image-layered" + ], + "processor": [ + "Qwen2VLProcessor" + ], + "transformer": [ + "info.dit.flux1-schnell", + "*" + ] } } }, @@ -1466,6 +4275,35 @@ "0": { "diffusers": "ChronoEditPipeline" } + }, + "pipe_names": { + "tokenizer": [ + "info.encoder.tokenizer", + "chronoedit" + ], + "text_encoder": [ + "info.stst.mt5", + "*" + ], + "image_encoder": [ + "info.vit.clip-vit-patch32", + "*" + ], + "image_processor": [ + "info.dit.flux1-schnell", + "*" + ], + "transformer": [ + "ChronoEditTransformer3DModel" + ], + "vae": [ + "info.vae.kl", + "audioldm-s-v2" + ], + "scheduler": [ + "ops.scheduler.euler", + "discrete" + ] } } }, @@ -1474,9 +4312,48 @@ "repo": "Kwai-Kolors/Kolors-diffusers", "pkg": { "0": { - "diffusers": "KolorsPipeline" + "precision": "ops.precision.float.F16", + "generation": { + "negative_prompt": "", + "guidance_scale": 5.0, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" } - } + }, + "file_256": [ + "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" + ], + "layer_b3": [ + "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" + ], + "layer_256": [ + "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" + ], + "identifiers": [ + ".DenseReluDense.wi.weight", + "encoder_hid_proj.weight" + ], + "pipe_names": {} + } + }, + "info.moe.trinity": { + "*": { + "repo": "arcee-ai/Trinity-Mini", + "pkg": { + "0": { + "transformers": "AfmoeModel" + } + }, + "tasks": [ + "AfmoeForCausalLM", + "AfmoeModel", + "AfmoePreTrainedModel" + ] } }, "info.encoder.tokenizer": { @@ -1501,6 +4378,13 @@ } } }, + "afm": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "aria": { "pkg": { "0": { @@ -1571,6 +4455,13 @@ } } }, + "bitnet-b18-4t": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "blenderbot": { "pkg": { "0": { @@ -1599,6 +4490,13 @@ } } }, + "blt": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "bridgetower": { "pkg": { "0": { @@ -1627,6 +4525,13 @@ } } }, + "chameleon": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "chinese-clip-vit-patch16": { "pkg": { "0": { @@ -1662,6 +4567,13 @@ } } }, + "llama-2-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "codegen-mono": { "pkg": { "0": { @@ -1669,6 +4581,13 @@ } } }, + "c4ai-command-r-v01": { + "pkg": { + "0": { + "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" + } + } + }, "conv-bert": { "pkg": { "0": { @@ -1676,6 +4595,20 @@ } } }, + "cpm-ant": { + "pkg": { + "0": { + "transformers": "transformers.models.cpmant.tokenization_cpmant.CpmAntTokenizer" + } + } + }, + "csm": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "ctrl": { "pkg": { "0": { @@ -1697,6 +4630,13 @@ } } }, + "dbrx": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, "deberta": { "pkg": { "0": { @@ -1711,80 +4651,164 @@ } } }, - "distilbert-uncased": { + "deepseek-v2-lite": { "pkg": { "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "dpr-ctx-encoder-single-nq": { + "deepseek-v3": { "pkg": { "0": { - "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "electra-discriminator": { + "deepseek-vl-chat": { "pkg": { "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "ernie-3-zh": { + "dia": { "pkg": { "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + "transformers": "transformers.models.dia.tokenization_dia.DiaTokenizer" } } }, - "ernie-4-vl-a-pt": { + "diffllama-handcut": { "pkg": { "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } }, - "esm": { + "distilbert-uncased": { "pkg": { "0": { - "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "falcon-mamba": { + "dpr-ctx-encoder-single-nq": { "pkg": { "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" } } }, - "flaubert-uncased": { + "electra-discriminator": { "pkg": { "0": { - "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "florence-2": { + "emu3-chat-hf": { "pkg": { "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" } } }, - "fnet": { + "ernie-3-zh": { "pkg": { "0": { - "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" } } }, - "wmt19-en-ru": { + "ernie-45-pt": { "pkg": { "0": { - "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "ernie-4-a-pt": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "ernie-4-vl-a-pt": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "esm": { + "pkg": { + "0": { + "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" + } + } + }, + "exaone-4": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "falcon": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "falcon-mamba": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "flaubert-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" + } + } + }, + "flava": { + "pkg": { + "0": { + "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" + } + } + }, + "flexolmo-7x-1t": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "florence-2": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, + "fnet": { + "pkg": { + "0": { + "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" + } + } + }, + "wmt19-en-ru": { + "pkg": { + "0": { + "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" } } }, @@ -1795,6 +4819,48 @@ } } }, + "fuyu": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "gemma": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma2": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma-3": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma3-text": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, + "gemma-3n-e": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, "git": { "pkg": { "0": { @@ -1802,6 +4868,27 @@ } } }, + "glm-4-chat": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4-0414": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "glm-4-a": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "glm-4v-thinking": { "pkg": { "0": { @@ -1823,6 +4910,13 @@ } } }, + "got-ocr-2-hf": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "gpt2": { "pkg": { "0": { @@ -1844,6 +4938,27 @@ } } }, + "gpt-neox": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "gpt-neox-japanese": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox_japanese.tokenization_gpt_neox_japanese.GPTNeoXJapaneseTokenizer" + } + } + }, + "gpt-oss": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "gpt-j": { "pkg": { "0": { @@ -1851,6 +4966,34 @@ } } }, + "granite": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "powermoe": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "granite-4-h": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "moe-active-shared-experts": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, "grounding-dino": { "pkg": { "0": { @@ -1865,6 +5008,13 @@ } } }, + "helium": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "hubert-ls960": { "pkg": { "0": { @@ -1914,6 +5064,13 @@ } } }, + "jais-2-chat": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, "jamba-v0": { "pkg": { "0": { @@ -1928,6 +5085,13 @@ } } }, + "jetmoe": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "kosmos-2-patch14-224": { "pkg": { "0": { @@ -2026,6 +5190,13 @@ } } }, + "longformer-4096": { + "pkg": { + "0": { + "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" + } + } + }, "long-t5-local": { "pkg": { "0": { @@ -2103,6 +5274,27 @@ } } }, + "max-text-01-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "stral-3-2512": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "mistral-v0": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "mistral-3-2503": { "pkg": { "0": { @@ -2110,6 +5302,13 @@ } } }, + "mixtral-8x": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, "llama-3-vision": { "pkg": { "0": { @@ -2138,6 +5337,20 @@ } } }, + "moonshine": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, + "hf-moshiko": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "mpnet": { "pkg": { "0": { @@ -2187,6 +5400,13 @@ } } }, + "nemotron-3-hf": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "nllb-moe": { "pkg": { "0": { @@ -2201,31 +5421,66 @@ } } }, - "omdet-turbo-swin-hf": { + "olmo-hf": { "pkg": { "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" } } }, - "openai-gpt": { + "olmo2-1124-hf": { "pkg": { "0": { - "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" } } }, - "opt": { + "olmo-3-0725": { "pkg": { "0": { "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" } } }, - "ovis2-hf": { + "olmoe-0924": { "pkg": { "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "omdet-turbo-swin-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "oneformer-ade-swin": { + "pkg": { + "0": { + "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" + } + } + }, + "openai-gpt": { + "pkg": { + "0": { + "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" + } + } + }, + "opt": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "ovis2-hf": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" } } }, @@ -2271,6 +5526,41 @@ } } }, + "persimmon": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "phi-1": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, + "phi-3": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "phi-3-moe": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } + }, + "pixtral": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "plbart": { "pkg": { "0": { @@ -2278,6 +5568,20 @@ } } }, + "phetnet-uncased": { + "pkg": { + "0": { + "transformers": "transformers.models.prophetnet.tokenization_prophetnet.ProphetNetTokenizer" + } + } + }, + "qwen2": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, "qwen2-vl": { "pkg": { "0": { @@ -2285,6 +5589,34 @@ } } }, + "qwen15-moe-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, + "qwen3-next-a": { + "pkg": { + "0": { + "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" + } + } + }, "qwen3-vl": { "pkg": { "0": { @@ -2299,6 +5631,13 @@ } } }, + "recurrentgemma": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, "reformer-crime-and-punishment": { "pkg": { "0": { @@ -2376,6 +5715,13 @@ } } }, + "smollm3": { + "pkg": { + "0": { + "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" + } + } + }, "s2t-librispeech-asr": { "pkg": { "0": { @@ -2404,6 +5750,20 @@ } } }, + "stablelm-4e1t": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" + } + } + }, + "starcoder2": { + "pkg": { + "0": { + "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" + } + } + }, "switch-8": { "pkg": { "0": { @@ -2418,6 +5778,13 @@ } } }, + "t5gemma-prefixlm": { + "pkg": { + "0": { + "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" + } + } + }, "tapas-finetuned-sqa": { "pkg": { "0": { @@ -2585,6 +5952,13 @@ "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" } } + }, + "zamba2": { + "pkg": { + "0": { + "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" + } + } } }, "info.vit.aimv2-patch14-224-lit": { @@ -2594,7 +5968,29 @@ "0": { "transformers": "Aimv2Model" } - } + }, + "tasks": [ + "Aimv2VisionModel", + "Aimv2Model", + "Aimv2PreTrainedModel", + "Aimv2TextModel" + ] + } + }, + "info.vit.aimv2-patch14-224": { + "*": { + "repo": "apple/aimv2-large-patch14-224", + "pkg": { + "0": { + "transformers": "Aimv2VisionModel" + } + }, + "tasks": [ + "Aimv2VisionModel", + "Aimv2Model", + "Aimv2PreTrainedModel", + "Aimv2TextModel" + ] } }, "info.art.albert-xx-v2": { @@ -2604,7 +6000,17 @@ "0": { "transformers": "AlbertModel" } - } + }, + "tasks": [ + "AlbertPreTrainedModel", + "AlbertModel", + "AlbertForPreTraining", + "AlbertForMaskedLM", + "AlbertForSequenceClassification", + "AlbertForTokenClassification", + "AlbertForQuestionAnswering", + "AlbertForMultipleChoice" + ] } }, "info.vit.align": { @@ -2614,7 +6020,13 @@ "0": { "transformers": "AlignModel" } - } + }, + "tasks": [ + "AlignPreTrainedModel", + "AlignTextModel", + "AlignVisionModel", + "AlignModel" + ] } }, "info.vit.altclip": { @@ -2624,7 +6036,47 @@ "0": { "transformers": "AltCLIPModel" } - } + }, + "tasks": [ + "AltCLIPPreTrainedModel", + "AltCLIPVisionModel", + "AltCLIPTextModel", + "AltCLIPModel" + ] + } + }, + "info.stst.apertus": { + "*": { + "repo": "swiss-ai/Apertus-8B", + "pkg": { + "0": { + "transformers": "ApertusModel" + } + }, + "tasks": [ + "ApertusModel", + "ApertusForCausalLM", + "ApertusForTokenClassification", + "ApertusPreTrainedModel" + ] + } + }, + "info.stst.afm": { + "*": { + "repo": "arcee-ai/AFM-4.5B", + "pkg": { + "0": { + "transformers": "ArceeModel" + } + }, + "tasks": [ + "ArceeForCausalLM", + "ArceeForQuestionAnswering", + "ArceeForSequenceClassification", + "ArceeForTokenClassification", + "ArceeModel", + "ArceePreTrainedModel" + ] } }, "info.vit.aria": { @@ -2634,7 +6086,15 @@ "0": { "transformers": "AriaModel" } - } + }, + "tasks": [ + "AriaForConditionalGeneration", + "AriaPreTrainedModel", + "AriaTextPreTrainedModel", + "AriaTextModel", + "AriaModel", + "AriaTextForCausalLM" + ] } }, "info.vit.ast-finetuned-audioset-10-10-0593": { @@ -2644,7 +6104,12 @@ "0": { "transformers": "ASTModel" } - } + }, + "tasks": [ + "ASTForAudioClassification", + "ASTModel", + "ASTPreTrainedModel" + ] } }, "info.stst.audio-flamingo-3-hf": { @@ -2654,7 +6119,12 @@ "0": { "transformers": "AudioFlamingo3ForConditionalGeneration" } - } + }, + "tasks": [ + "AudioFlamingo3ForConditionalGeneration", + "AudioFlamingo3PreTrainedModel", + "AudioFlamingo3Encoder" + ] } }, "info.aet.audio-flamingo-3-hf": { @@ -2664,7 +6134,12 @@ "0": { "transformers": "AudioFlamingo3Encoder" } - } + }, + "tasks": [ + "AudioFlamingo3ForConditionalGeneration", + "AudioFlamingo3PreTrainedModel", + "AudioFlamingo3Encoder" + ] } }, "info.stst.autoformer-tourism-monthly": { @@ -2674,7 +6149,12 @@ "0": { "transformers": "AutoformerModel" } - } + }, + "tasks": [ + "AutoformerForPrediction", + "AutoformerModel", + "AutoformerPreTrainedModel" + ] } }, "info.vit.aya-vision": { @@ -2684,7 +6164,27 @@ "0": { "transformers": "AyaVisionModel" } - } + }, + "tasks": [ + "AyaVisionForConditionalGeneration", + "AyaVisionPreTrainedModel", + "AyaVisionModel" + ] + } + }, + "info.ssm.bamba-t-hf": { + "*": { + "repo": "ibm-fms/Bamba-9.8b-2.2T-hf", + "pkg": { + "0": { + "transformers": "BambaModel" + } + }, + "tasks": [ + "BambaModel", + "BambaForCausalLM", + "BambaPreTrainedModel" + ] } }, "info.art.bark": { @@ -2694,7 +6194,15 @@ "0": { "transformers": "BarkModel" } - } + }, + "tasks": [ + "BarkFineModel", + "BarkSemanticModel", + "BarkCoarseModel", + "BarkModel", + "BarkPreTrainedModel", + "BarkCausalModel" + ] } }, "info.stst.bart": { @@ -2704,7 +6212,17 @@ "0": { "transformers": "BartModel" } - } + }, + "tasks": [ + "BartForCausalLM", + "BartForConditionalGeneration", + "BartForQuestionAnswering", + "BartForSequenceClassification", + "BartModel", + "BartPreTrainedModel", + "BartPretrainedModel", + "PretrainedBartModel" + ] } }, "info.vit.beit-patch16-224-pt": { @@ -2714,7 +6232,15 @@ "0": { "transformers": "BeitModel" } - } + }, + "tasks": [ + "BeitForImageClassification", + "BeitForMaskedImageModeling", + "BeitForSemanticSegmentation", + "BeitModel", + "BeitPreTrainedModel", + "BeitBackbone" + ] } }, "info.art.bert-uncased": { @@ -2724,7 +6250,29 @@ "0": { "transformers": "BertModel" } - } + }, + "file_256": [ + "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" + ], + "layer_b3": [ + "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" + ], + "layer_256": [ + "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" + ], + "tasks": [ + "BertForMaskedLM", + "BertForMultipleChoice", + "BertForNextSentencePrediction", + "BertForPreTraining", + "BertForQuestionAnswering", + "BertForSequenceClassification", + "BertForTokenClassification", + "BertLayer", + "BertLMHeadModel", + "BertModel", + "BertPreTrainedModel" + ] } }, "info.art.bert-for-seq-generation-l-24-bbc-encoder": { @@ -2734,7 +6282,12 @@ "0": { "transformers": "BertGenerationEncoder" } - } + }, + "tasks": [ + "BertGenerationDecoder", + "BertGenerationEncoder", + "BertGenerationPreTrainedModel" + ] } }, "info.art.bigbird-roberta": { @@ -2744,7 +6297,19 @@ "0": { "transformers": "BigBirdModel" } - } + }, + "tasks": [ + "BigBirdForCausalLM", + "BigBirdForMaskedLM", + "BigBirdForMultipleChoice", + "BigBirdForPreTraining", + "BigBirdForQuestionAnswering", + "BigBirdForSequenceClassification", + "BigBirdForTokenClassification", + "BigBirdLayer", + "BigBirdModel", + "BigBirdPreTrainedModel" + ] } }, "info.stst.bigbird-pegasus-arxiv": { @@ -2754,7 +6319,15 @@ "0": { "transformers": "BigBirdPegasusModel" } - } + }, + "tasks": [ + "BigBirdPegasusForCausalLM", + "BigBirdPegasusForConditionalGeneration", + "BigBirdPegasusForQuestionAnswering", + "BigBirdPegasusForSequenceClassification", + "BigBirdPegasusModel", + "BigBirdPegasusPreTrainedModel" + ] } }, "info.art.biogpt": { @@ -2764,7 +6337,14 @@ "0": { "transformers": "BioGptModel" } - } + }, + "tasks": [ + "BioGptForCausalLM", + "BioGptForTokenClassification", + "BioGptForSequenceClassification", + "BioGptModel", + "BioGptPreTrainedModel" + ] } }, "info.vit.bit-50": { @@ -2774,7 +6354,28 @@ "0": { "transformers": "BitModel" } - } + }, + "tasks": [ + "BitForImageClassification", + "BitModel", + "BitPreTrainedModel", + "BitBackbone" + ] + } + }, + "info.stst.bitnet-b18-4t": { + "*": { + "repo": "microsoft/bitnet-b1.58-2B-4T", + "pkg": { + "0": { + "transformers": "BitNetModel" + } + }, + "tasks": [ + "BitNetForCausalLM", + "BitNetModel", + "BitNetPreTrainedModel" + ] } }, "info.stst.blenderbot": { @@ -2784,7 +6385,13 @@ "0": { "transformers": "BlenderbotModel" } - } + }, + "tasks": [ + "BlenderbotForCausalLM", + "BlenderbotForConditionalGeneration", + "BlenderbotModel", + "BlenderbotPreTrainedModel" + ] } }, "info.vit.blip-vqa": { @@ -2794,7 +6401,16 @@ "0": { "transformers": "BlipModel" } - } + }, + "tasks": [ + "BlipModel", + "BlipPreTrainedModel", + "BlipForConditionalGeneration", + "BlipForQuestionAnswering", + "BlipVisionModel", + "BlipTextModel", + "BlipForImageTextRetrieval" + ] } }, "info.vit.blip2-opt": { @@ -2804,7 +6420,17 @@ "0": { "transformers": "Blip2Model" } - } + }, + "tasks": [ + "Blip2Model", + "Blip2VisionModelWithProjection", + "Blip2QFormerModel", + "Blip2PreTrainedModel", + "Blip2ForConditionalGeneration", + "Blip2ForImageTextRetrieval", + "Blip2VisionModel", + "Blip2TextModelWithProjection" + ] } }, "info.stst.blip2-opt": { @@ -2814,7 +6440,17 @@ "0": { "transformers": "Blip2QFormerModel" } - } + }, + "tasks": [ + "Blip2Model", + "Blip2VisionModelWithProjection", + "Blip2QFormerModel", + "Blip2PreTrainedModel", + "Blip2ForConditionalGeneration", + "Blip2ForImageTextRetrieval", + "Blip2VisionModel", + "Blip2TextModelWithProjection" + ] } }, "info.art.bloom": { @@ -2824,17 +6460,48 @@ "0": { "transformers": "BloomModel" } - } + }, + "tasks": [ + "BloomForCausalLM", + "BloomModel", + "BloomPreTrainedModel", + "BloomForSequenceClassification", + "BloomForTokenClassification", + "BloomForQuestionAnswering" + ] } }, - "info.vit.bridgetower": { + "info.vit.blt": { "*": { - "repo": "BridgeTower/bridgetower-base", + "repo": "facebook/blt", "pkg": { "0": { - "transformers": "BridgeTowerModel" + "transformers": "BltModel" } - } + }, + "tasks": [ + "BltPreTrainedModel", + "BltModel", + "BltPatcher", + "BltForCausalLM" + ] + } + }, + "info.vit.bridgetower": { + "*": { + "repo": "BridgeTower/bridgetower-base", + "pkg": { + "0": { + "transformers": "BridgeTowerModel" + } + }, + "tasks": [ + "BridgeTowerForContrastiveLearning", + "BridgeTowerForImageAndTextRetrieval", + "BridgeTowerForMaskedLM", + "BridgeTowerModel", + "BridgeTowerPreTrainedModel" + ] } }, "info.art.bros-uncased": { @@ -2844,7 +6511,14 @@ "0": { "transformers": "BrosModel" } - } + }, + "tasks": [ + "BrosPreTrainedModel", + "BrosModel", + "BrosForTokenClassification", + "BrosSpadeEEForTokenClassification", + "BrosSpadeELForTokenClassification" + ] } }, "info.art.camembert": { @@ -2854,7 +6528,17 @@ "0": { "transformers": "CamembertModel" } - } + }, + "tasks": [ + "CamembertForCausalLM", + "CamembertForMaskedLM", + "CamembertForMultipleChoice", + "CamembertForQuestionAnswering", + "CamembertForSequenceClassification", + "CamembertForTokenClassification", + "CamembertModel", + "CamembertPreTrainedModel" + ] } }, "info.art.canine-s": { @@ -2864,7 +6548,32 @@ "0": { "transformers": "CanineModel" } - } + }, + "tasks": [ + "CanineForMultipleChoice", + "CanineForQuestionAnswering", + "CanineForSequenceClassification", + "CanineForTokenClassification", + "CanineLayer", + "CanineModel", + "CaninePreTrainedModel" + ] + } + }, + "info.stst.chameleon": { + "*": { + "repo": "meta/chameleon-7B", + "pkg": { + "0": { + "transformers": "ChameleonModel" + } + }, + "tasks": [ + "ChameleonForConditionalGeneration", + "ChameleonModel", + "ChameleonPreTrainedModel", + "ChameleonVQVAE" + ] } }, "info.vit.chinese-clip-vit-patch16": { @@ -2874,7 +6583,13 @@ "0": { "transformers": "ChineseCLIPModel" } - } + }, + "tasks": [ + "ChineseCLIPModel", + "ChineseCLIPPreTrainedModel", + "ChineseCLIPTextModel", + "ChineseCLIPVisionModel" + ] } }, "info.vit.clap-htsat-fused": { @@ -2884,7 +6599,27 @@ "0": { "transformers": "ClapModel" } - } + }, + "file_256": [ + "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", + "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" + ], + "layer_b3": [ + "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", + "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" + ], + "layer_256": [ + "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", + "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" + ], + "tasks": [ + "ClapModel", + "ClapPreTrainedModel", + "ClapTextModel", + "ClapTextModelWithProjection", + "ClapAudioModel", + "ClapAudioModelWithProjection" + ] } }, "info.vit.clip-vit-patch32": { @@ -2894,7 +6629,16 @@ "0": { "transformers": "CLIPModel" } - } + }, + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" + ] } }, "info.vit.clipseg-rd64": { @@ -2904,7 +6648,14 @@ "0": { "transformers": "CLIPSegModel" } - } + }, + "tasks": [ + "CLIPSegModel", + "CLIPSegPreTrainedModel", + "CLIPSegTextModel", + "CLIPSegVisionModel", + "CLIPSegForImageSegmentation" + ] } }, "info.vit.clvp-dev": { @@ -2914,7 +6665,33 @@ "0": { "transformers": "ClvpModelForConditionalGeneration" } - } + }, + "tasks": [ + "ClvpModelForConditionalGeneration", + "ClvpForCausalLM", + "ClvpModel", + "ClvpPreTrainedModel", + "ClvpEncoder", + "ClvpDecoder" + ] + } + }, + "info.stst.llama-2-hf": { + "*": { + "repo": "meta-llama/Llama-2-7b-hf", + "pkg": { + "0": { + "transformers": "LlamaModel" + } + }, + "tasks": [ + "LlamaForCausalLM", + "LlamaModel", + "LlamaPreTrainedModel", + "LlamaForSequenceClassification", + "LlamaForQuestionAnswering", + "LlamaForTokenClassification" + ] } }, "info.art.codegen-mono": { @@ -2924,7 +6701,27 @@ "0": { "transformers": "CodeGenModel" } - } + }, + "tasks": [ + "CodeGenForCausalLM", + "CodeGenModel", + "CodeGenPreTrainedModel" + ] + } + }, + "info.stst.c4ai-command-r-v01": { + "*": { + "repo": "CohereForAI/c4ai-command-r-v01", + "pkg": { + "0": { + "transformers": "CohereModel" + } + }, + "tasks": [ + "CohereForCausalLM", + "CohereModel", + "CoherePreTrainedModel" + ] } }, "info.vit.command-a-vision-07-2025": { @@ -2934,7 +6731,12 @@ "0": { "transformers": "Cohere2VisionModel" } - } + }, + "tasks": [ + "Cohere2VisionForConditionalGeneration", + "Cohere2VisionPreTrainedModel", + "Cohere2VisionModel" + ] } }, "info.detr.conditional-detr-resnet-50": { @@ -2944,7 +6746,13 @@ "0": { "transformers": "ConditionalDetrModel" } - } + }, + "tasks": [ + "ConditionalDetrForObjectDetection", + "ConditionalDetrForSegmentation", + "ConditionalDetrModel", + "ConditionalDetrPreTrainedModel" + ] } }, "info.art.conv-bert": { @@ -2954,7 +6762,17 @@ "0": { "transformers": "ConvBertModel" } - } + }, + "tasks": [ + "ConvBertForMaskedLM", + "ConvBertForMultipleChoice", + "ConvBertForQuestionAnswering", + "ConvBertForSequenceClassification", + "ConvBertForTokenClassification", + "ConvBertLayer", + "ConvBertModel", + "ConvBertPreTrainedModel" + ] } }, "info.vit.convnext-224": { @@ -2964,7 +6782,13 @@ "0": { "transformers": "ConvNextModel" } - } + }, + "tasks": [ + "ConvNextForImageClassification", + "ConvNextModel", + "ConvNextPreTrainedModel", + "ConvNextBackbone" + ] } }, "info.vit.convnextv2-224": { @@ -2974,7 +6798,45 @@ "0": { "transformers": "ConvNextV2Model" } - } + }, + "tasks": [ + "ConvNextV2ForImageClassification", + "ConvNextV2Model", + "ConvNextV2PreTrainedModel", + "ConvNextV2Backbone" + ] + } + }, + "info.stst.cpm-ant": { + "*": { + "repo": "openbmb/cpm-ant-10b", + "pkg": { + "0": { + "transformers": "CpmAntModel" + } + }, + "tasks": [ + "CpmAntForCausalLM", + "CpmAntModel", + "CpmAntPreTrainedModel" + ] + } + }, + "info.stst.csm": { + "*": { + "repo": "sesame/csm-1b", + "pkg": { + "0": { + "transformers": "CsmForConditionalGeneration" + } + }, + "tasks": [ + "CsmPreTrainedModel", + "CsmBackboneModel", + "CsmDepthDecoderModel", + "CsmDepthDecoderForCausalLM", + "CsmForConditionalGeneration" + ] } }, "info.art.ctrl": { @@ -2984,7 +6846,13 @@ "0": { "transformers": "CTRLModel" } - } + }, + "tasks": [ + "CTRLForSequenceClassification", + "CTRLLMHeadModel", + "CTRLModel", + "CTRLPreTrainedModel" + ] } }, "info.vit.cvt-13": { @@ -2994,7 +6862,12 @@ "0": { "transformers": "CvtModel" } - } + }, + "tasks": [ + "CvtForImageClassification", + "CvtModel", + "CvtPreTrainedModel" + ] } }, "info.art.cwm": { @@ -3004,7 +6877,12 @@ "0": { "transformers": "CwmModel" } - } + }, + "tasks": [ + "CwmPreTrainedModel", + "CwmModel", + "CwmForCausalLM" + ] } }, "info.detr.dfine-x-coco": { @@ -3014,7 +6892,12 @@ "0": { "transformers": "DFineModel" } - } + }, + "tasks": [ + "DFineModel", + "DFinePreTrainedModel", + "DFineForObjectDetection" + ] } }, "info.detr.dab-detr": { @@ -3024,7 +6907,12 @@ "0": { "transformers": "DabDetrModel" } - } + }, + "tasks": [ + "DabDetrForObjectDetection", + "DabDetrModel", + "DabDetrPreTrainedModel" + ] } }, "info.gan.dac": { @@ -3034,7 +6922,11 @@ "0": { "transformers": "DacModel" } - } + }, + "tasks": [ + "DacModel", + "DacPreTrainedModel" + ] } }, "info.aet.data2vec-audio-960h": { @@ -3044,7 +6936,15 @@ "0": { "transformers": "Data2VecAudioModel" } - } + }, + "tasks": [ + "Data2VecAudioForAudioFrameClassification", + "Data2VecAudioForCTC", + "Data2VecAudioForSequenceClassification", + "Data2VecAudioForXVector", + "Data2VecAudioModel", + "Data2VecAudioPreTrainedModel" + ] } }, "info.art.data2vec-text": { @@ -3054,7 +6954,17 @@ "0": { "transformers": "Data2VecTextModel" } - } + }, + "tasks": [ + "Data2VecTextForCausalLM", + "Data2VecTextForMaskedLM", + "Data2VecTextForMultipleChoice", + "Data2VecTextForQuestionAnswering", + "Data2VecTextForSequenceClassification", + "Data2VecTextForTokenClassification", + "Data2VecTextModel", + "Data2VecTextPreTrainedModel" + ] } }, "info.vit.data2vec-vision": { @@ -3064,7 +6974,28 @@ "0": { "transformers": "Data2VecVisionModel" } - } + }, + "tasks": [ + "Data2VecVisionForImageClassification", + "Data2VecVisionForSemanticSegmentation", + "Data2VecVisionModel", + "Data2VecVisionPreTrainedModel" + ] + } + }, + "info.stst.dbrx": { + "*": { + "repo": "databricks/dbrx-instruct", + "pkg": { + "0": { + "transformers": "DbrxModel" + } + }, + "tasks": [ + "DbrxForCausalLM", + "DbrxModel", + "DbrxPreTrainedModel" + ] } }, "info.art.deberta": { @@ -3074,7 +7005,15 @@ "0": { "transformers": "DebertaModel" } - } + }, + "tasks": [ + "DebertaForMaskedLM", + "DebertaForQuestionAnswering", + "DebertaForSequenceClassification", + "DebertaForTokenClassification", + "DebertaModel", + "DebertaPreTrainedModel" + ] } }, "info.art.deberta-v2-x": { @@ -3084,7 +7023,16 @@ "0": { "transformers": "DebertaV2Model" } - } + }, + "tasks": [ + "DebertaV2ForMaskedLM", + "DebertaV2ForMultipleChoice", + "DebertaV2ForQuestionAnswering", + "DebertaV2ForSequenceClassification", + "DebertaV2ForTokenClassification", + "DebertaV2Model", + "DebertaV2PreTrainedModel" + ] } }, "info.art.decision-transformer-gym-hopper": { @@ -3094,7 +7042,61 @@ "0": { "transformers": "DecisionTransformerModel" } - } + }, + "tasks": [ + "DecisionTransformerGPT2Model", + "DecisionTransformerGPT2PreTrainedModel", + "DecisionTransformerModel", + "DecisionTransformerPreTrainedModel" + ] + } + }, + "info.moe.deepseek-v2-lite": { + "*": { + "repo": "deepseek-ai/DeepSeek-V2-Lite", + "pkg": { + "0": { + "transformers": "DeepseekV2Model" + } + }, + "tasks": [ + "DeepseekV2PreTrainedModel", + "DeepseekV2Model", + "DeepseekV2ForCausalLM", + "DeepseekV2ForSequenceClassification" + ] + } + }, + "info.moe.deepseek-v3": { + "*": { + "repo": "bzantium/tiny-deepseek-v3", + "pkg": { + "0": { + "transformers": "DeepseekV3Model" + } + }, + "tasks": [ + "DeepseekV3PreTrainedModel", + "DeepseekV3Model", + "DeepseekV3ForCausalLM", + "DeepseekV3ForSequenceClassification", + "DeepseekV3ForTokenClassification" + ] + } + }, + "info.vit.deepseek-vl-chat": { + "*": { + "repo": "deepseek-community/deepseek-vl-1.3b-chat", + "pkg": { + "0": { + "transformers": "DeepseekVLModel" + } + }, + "tasks": [ + "DeepseekVLPreTrainedModel", + "DeepseekVLModel", + "DeepseekVLForConditionalGeneration" + ] } }, "info.detr.deformable-detr": { @@ -3104,7 +7106,12 @@ "0": { "transformers": "DeformableDetrModel" } - } + }, + "tasks": [ + "DeformableDetrForObjectDetection", + "DeformableDetrModel", + "DeformableDetrPreTrainedModel" + ] } }, "info.vit.deit-distilled-patch16-224": { @@ -3114,7 +7121,14 @@ "0": { "transformers": "DeiTModel" } - } + }, + "tasks": [ + "DeiTForImageClassification", + "DeiTForImageClassificationWithTeacher", + "DeiTForMaskedImageModeling", + "DeiTModel", + "DeiTPreTrainedModel" + ] } }, "info.vit.depth": { @@ -3124,7 +7138,12 @@ "0": { "transformers": "DepthProModel" } - } + }, + "tasks": [ + "DepthProPreTrainedModel", + "DepthProModel", + "DepthProForDepthEstimation" + ] } }, "info.detr.detr-resnet-50": { @@ -3134,7 +7153,46 @@ "0": { "transformers": "DetrModel" } - } + }, + "tasks": [ + "DetrForObjectDetection", + "DetrForSegmentation", + "DetrModel", + "DetrPreTrainedModel" + ] + } + }, + "info.stst.dia": { + "*": { + "repo": "nari-labs/Dia-1.6B", + "pkg": { + "0": { + "transformers": "DiaModel" + } + }, + "tasks": [ + "DiaModel", + "DiaPreTrainedModel", + "DiaForConditionalGeneration" + ] + } + }, + "info.stst.diffllama-handcut": { + "*": { + "repo": "kajuma/DiffLlama-0.3B-handcut", + "pkg": { + "0": { + "transformers": "DiffLlamaModel" + } + }, + "tasks": [ + "DiffLlamaPreTrainedModel", + "DiffLlamaModel", + "DiffLlamaForCausalLM", + "DiffLlamaForSequenceClassification", + "DiffLlamaForQuestionAnswering", + "DiffLlamaForTokenClassification" + ] } }, "info.gan.dinat-in-224": { @@ -3144,7 +7202,13 @@ "0": { "transformers": "DinatModel" } - } + }, + "tasks": [ + "DinatForImageClassification", + "DinatModel", + "DinatPreTrainedModel", + "DinatBackbone" + ] } }, "info.vit.dinov2-patch16-224": { @@ -3154,7 +7218,13 @@ "0": { "transformers": "Dinov2Model" } - } + }, + "tasks": [ + "Dinov2ForImageClassification", + "Dinov2Model", + "Dinov2PreTrainedModel", + "Dinov2Backbone" + ] } }, "info.vit.dinov2-with-registers": { @@ -3164,7 +7234,43 @@ "0": { "transformers": "Dinov2WithRegistersModel" } - } + }, + "tasks": [ + "Dinov2WithRegistersPreTrainedModel", + "Dinov2WithRegistersModel", + "Dinov2WithRegistersForImageClassification", + "Dinov2WithRegistersBackbone" + ] + } + }, + "info.vit.dinov3-convnext-pretrain-lvd": { + "*": { + "repo": "facebook/dinov3-convnext-tiny-pretrain-lvd1689m", + "pkg": { + "0": { + "transformers": "DINOv3ConvNextModel" + } + }, + "tasks": [ + "DINOv3ConvNextModel", + "DINOv3ConvNextPreTrainedModel", + "DINOv3ConvNextBackbone" + ] + } + }, + "info.vit.dinov3-vits16-pretrain-lvd": { + "*": { + "repo": "facebook/dinov3-vits16-pretrain-lvd1689m", + "pkg": { + "0": { + "transformers": "DINOv3ViTModel" + } + }, + "tasks": [ + "DINOv3ViTModel", + "DINOv3ViTPreTrainedModel", + "DINOv3ViTBackbone" + ] } }, "info.art.distilbert-uncased": { @@ -3174,7 +7280,32 @@ "0": { "transformers": "DistilBertModel" } - } + }, + "tasks": [ + "DistilBertForMaskedLM", + "DistilBertForMultipleChoice", + "DistilBertForQuestionAnswering", + "DistilBertForSequenceClassification", + "DistilBertForTokenClassification", + "DistilBertModel", + "DistilBertPreTrainedModel" + ] + } + }, + "info.moe.doge": { + "*": { + "repo": "SmallDoge/Doge-320M", + "pkg": { + "0": { + "transformers": "DogeModel" + } + }, + "tasks": [ + "DogeForCausalLM", + "DogeModel", + "DogePreTrainedModel", + "DogeForSequenceClassification" + ] } }, "info.vit.donut": { @@ -3184,17 +7315,46 @@ "0": { "transformers": "DonutSwinModel" } - } + }, + "tasks": [ + "DonutSwinModel", + "DonutSwinPreTrainedModel", + "DonutSwinForImageClassification" + ] + } + }, + "info.moe.dots-llm1": { + "*": { + "repo": "rednote-hilab/dots.llm1.base", + "pkg": { + "0": { + "transformers": "Dots1Model" + } + }, + "tasks": [ + "Dots1PreTrainedModel", + "Dots1Model", + "Dots1ForCausalLM" + ] } }, - "info.art.dpr-ctx-encoder-single-nq": { + "info.vit.dpr-ctx-encoder-single-nq": { "*": { "repo": "facebook/dpr-ctx_encoder-single-nq-base", "pkg": { "0": { "transformers": "DPRQuestionEncoder" } - } + }, + "tasks": [ + "DPRContextEncoder", + "DPRPretrainedContextEncoder", + "DPRPreTrainedModel", + "DPRPretrainedQuestionEncoder", + "DPRPretrainedReader", + "DPRQuestionEncoder", + "DPRReader" + ] } }, "info.detr.dpt": { @@ -3204,7 +7364,13 @@ "0": { "transformers": "DPTModel" } - } + }, + "tasks": [ + "DPTForDepthEstimation", + "DPTForSemanticSegmentation", + "DPTModel", + "DPTPreTrainedModel" + ] } }, "info.vit.edgetam1-hiera": { @@ -3214,7 +7380,12 @@ "0": { "transformers": "EdgeTamModel" } - } + }, + "tasks": [ + "EdgeTamModel", + "EdgeTamVisionModel", + "EdgeTamPreTrainedModel" + ] } }, "info.vit.edgetam": { @@ -3224,8 +7395,43 @@ "0": { "transformers": "EdgeTamVideoModel" } - } - } + }, + "tasks": [ + "EdgeTamVideoModel", + "EdgeTamVideoInferenceSession", + "EdgeTamVideoPreTrainedModel" + ] + } + }, + "info.vit.efficientloftr": { + "*": { + "repo": "zju-community/efficientloftr", + "pkg": { + "0": { + "transformers": "EfficientLoFTRModel" + } + }, + "tasks": [ + "EfficientLoFTRPreTrainedModel", + "EfficientLoFTRModel", + "EfficientLoFTRForKeypointMatching" + ] + } + }, + "info.vit.efficientnet-b7": { + "*": { + "repo": "google/efficientnet-b7", + "pkg": { + "0": { + "transformers": "EfficientNetModel" + } + }, + "tasks": [ + "EfficientNetForImageClassification", + "EfficientNetModel", + "EfficientNetPreTrainedModel" + ] + } }, "info.art.electra-discriminator": { "*": { @@ -3234,7 +7440,36 @@ "0": { "transformers": "ElectraModel" } - } + }, + "tasks": [ + "ElectraForCausalLM", + "ElectraForMaskedLM", + "ElectraForMultipleChoice", + "ElectraForPreTraining", + "ElectraForQuestionAnswering", + "ElectraForSequenceClassification", + "ElectraForTokenClassification", + "ElectraModel", + "ElectraPreTrainedModel" + ] + } + }, + "info.art.emu3-chat-hf": { + "*": { + "repo": "Emu3-community/Emu3-Chat-hf", + "pkg": { + "0": { + "transformers": "Emu3Model" + } + }, + "tasks": [ + "Emu3ForConditionalGeneration", + "Emu3ForCausalLM", + "Emu3TextModel", + "Emu3PreTrainedModel", + "Emu3VQVAE", + "Emu3Model" + ] } }, "info.gan.encodec": { @@ -3244,7 +7479,11 @@ "0": { "transformers": "EncodecModel" } - } + }, + "tasks": [ + "EncodecModel", + "EncodecPreTrainedModel" + ] } }, "info.art.ernie-3-zh": { @@ -3254,7 +7493,49 @@ "0": { "transformers": "ErnieModel" } - } + }, + "tasks": [ + "ErnieForCausalLM", + "ErnieForMaskedLM", + "ErnieForMultipleChoice", + "ErnieForNextSentencePrediction", + "ErnieForPreTraining", + "ErnieForQuestionAnswering", + "ErnieForSequenceClassification", + "ErnieForTokenClassification", + "ErnieModel", + "ErniePreTrainedModel" + ] + } + }, + "info.stst.ernie-45-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-0.3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5Model" + } + }, + "tasks": [ + "Ernie4_5ForCausalLM", + "Ernie4_5Model", + "Ernie4_5PreTrainedModel" + ] + } + }, + "info.moe.ernie-4-a-pt": { + "*": { + "repo": "baidu/ERNIE-4.5-21B-A3B-PT", + "pkg": { + "0": { + "transformers": "Ernie4_5_MoeModel" + } + }, + "tasks": [ + "Ernie4_5_MoeForCausalLM", + "Ernie4_5_MoeModel", + "Ernie4_5_MoePreTrainedModel" + ] } }, "info.vit.ernie-4-vl-a-pt": { @@ -3264,7 +7545,15 @@ "0": { "transformers": "Ernie4_5_VL_MoeModel" } - } + }, + "tasks": [ + "Ernie4_5_VL_MoePreTrainedModel", + "Ernie4_5_VL_MoeForConditionalGeneration", + "Ernie4_5_VL_MoeModel", + "Ernie4_5_VL_MoeTextModel", + "Ernie4_5_VL_MoeVisionTransformerPretrainedModel", + "Ernie4_5_VL_MoeVariableResolutionResamplerModel" + ] } }, "info.aet.esm": { @@ -3274,7 +7563,80 @@ "0": { "transformers": "EsmModel" } - } + }, + "tasks": [ + "EsmForMaskedLM", + "EsmForSequenceClassification", + "EsmForTokenClassification", + "EsmModel", + "EsmPreTrainedModel" + ] + } + }, + "info.stst.evolla-hf": { + "*": { + "repo": "westlake-repl/Evolla-10B-hf", + "pkg": { + "0": { + "transformers": "EvollaModel" + } + }, + "tasks": [ + "EvollaForProteinText2Text", + "EvollaModel", + "EvollaPreTrainedModel" + ] + } + }, + "info.stst.exaone-4": { + "*": { + "repo": "LGAI-EXAONE/EXAONE-4.0-32B", + "pkg": { + "0": { + "transformers": "Exaone4Model" + } + }, + "tasks": [ + "Exaone4PreTrainedModel", + "Exaone4Model", + "Exaone4ForCausalLM", + "Exaone4ForSequenceClassification", + "Exaone4ForTokenClassification", + "Exaone4ForQuestionAnswering" + ] + } + }, + "info.ssm.falcon": { + "*": { + "repo": "tiiuae/falcon-7b", + "pkg": { + "0": { + "transformers": "FalconModel" + } + }, + "tasks": [ + "FalconForCausalLM", + "FalconModel", + "FalconPreTrainedModel", + "FalconForSequenceClassification", + "FalconForTokenClassification", + "FalconForQuestionAnswering" + ] + } + }, + "info.ssm.falconh1-t-hf": { + "*": { + "repo": "tiiuae/Falcon-H1-34B-Instruct", + "pkg": { + "0": { + "transformers": "FalconH1Model" + } + }, + "tasks": [ + "FalconH1Model", + "FalconH1ForCausalLM", + "FalconH1PreTrainedModel" + ] } }, "info.ssm.falcon-mamba": { @@ -3284,7 +7646,13 @@ "0": { "transformers": "FalconMambaModel" } - } + }, + "tasks": [ + "FalconMambaForCausalLM", + "FalconMambaModel", + "FalconMambaPreTrainedModel", + "FalconMambaCache" + ] } }, "info.vit.fastvlm": { @@ -3294,7 +7662,12 @@ "0": { "transformers": "FastVlmModel" } - } + }, + "tasks": [ + "FastVlmForConditionalGeneration", + "FastVlmModel", + "FastVlmPreTrainedModel" + ] } }, "info.aet.fastspeech2-conformer": { @@ -3304,7 +7677,29 @@ "0": { "transformers": "FastSpeech2ConformerModel" } - } + }, + "tasks": [ + "FastSpeech2ConformerWithHifiGan", + "FastSpeech2ConformerHifiGan", + "FastSpeech2ConformerModel", + "FastSpeech2ConformerPreTrainedModel" + ] + } + }, + "info.stst.fastspeech2-conformer": { + "*": { + "repo": "espnet/fastspeech2_conformer", + "pkg": { + "0": { + "transformers": "FastSpeech2ConformerWithHifiGan" + } + }, + "tasks": [ + "FastSpeech2ConformerWithHifiGan", + "FastSpeech2ConformerHifiGan", + "FastSpeech2ConformerModel", + "FastSpeech2ConformerPreTrainedModel" + ] } }, "info.art.flaubert-uncased": { @@ -3314,7 +7709,51 @@ "0": { "transformers": "FlaubertModel" } - } + }, + "tasks": [ + "FlaubertForMultipleChoice", + "FlaubertForQuestionAnswering", + "FlaubertForQuestionAnsweringSimple", + "FlaubertForSequenceClassification", + "FlaubertForTokenClassification", + "FlaubertModel", + "FlaubertWithLMHeadModel", + "FlaubertPreTrainedModel" + ] + } + }, + "info.vit.flava": { + "*": { + "repo": "facebook/flava-full", + "pkg": { + "0": { + "transformers": "FlavaModel" + } + }, + "tasks": [ + "FlavaForPreTraining", + "FlavaImageCodebook", + "FlavaImageModel", + "FlavaModel", + "FlavaMultimodalModel", + "FlavaPreTrainedModel", + "FlavaTextModel" + ] + } + }, + "info.moe.flexolmo-7x-1t": { + "*": { + "repo": "allenai/FlexOlmo-7x7B-1T", + "pkg": { + "0": { + "transformers": "FlexOlmoModel" + } + }, + "tasks": [ + "FlexOlmoForCausalLM", + "FlexOlmoModel", + "FlexOlmoPreTrainedModel" + ] } }, "info.vit.florence-2": { @@ -3324,7 +7763,14 @@ "0": { "transformers": "Florence2Model" } - } + }, + "tasks": [ + "Florence2Model", + "Florence2ForConditionalGeneration", + "Florence2PreTrainedModel", + "Florence2VisionBackbone", + "Florence2VisionPreTrainedModel" + ] } }, "info.art.fnet": { @@ -3334,7 +7780,19 @@ "0": { "transformers": "FNetModel" } - } + }, + "tasks": [ + "FNetForMaskedLM", + "FNetForMultipleChoice", + "FNetForNextSentencePrediction", + "FNetForPreTraining", + "FNetForQuestionAnswering", + "FNetForSequenceClassification", + "FNetForTokenClassification", + "FNetLayer", + "FNetModel", + "FNetPreTrainedModel" + ] } }, "info.vit.focalnet": { @@ -3344,7 +7802,14 @@ "0": { "transformers": "FocalNetModel" } - } + }, + "tasks": [ + "FocalNetForImageClassification", + "FocalNetForMaskedImageModeling", + "FocalNetBackbone", + "FocalNetModel", + "FocalNetPreTrainedModel" + ] } }, "info.stst.wmt19-en-ru": { @@ -3354,7 +7819,12 @@ "0": { "transformers": "FSMTModel" } - } + }, + "tasks": [ + "FSMTForConditionalGeneration", + "FSMTModel", + "PretrainedFSMTModel" + ] } }, "info.aet.funnel": { @@ -3364,997 +7834,2887 @@ "0": { "transformers": "FunnelModel" } - } + }, + "tasks": [ + "FunnelBaseModel", + "FunnelForMaskedLM", + "FunnelForMultipleChoice", + "FunnelForPreTraining", + "FunnelForQuestionAnswering", + "FunnelForSequenceClassification", + "FunnelForTokenClassification", + "FunnelModel", + "FunnelPreTrainedModel" + ] } }, - "info.vit.git": { + "info.vit.fuyu": { "*": { - "repo": "microsoft/git-base", + "repo": "adept/fuyu-8b", "pkg": { "0": { - "transformers": "GitModel" + "transformers": "FuyuModel" } - } + }, + "tasks": [ + "FuyuForCausalLM", + "FuyuPreTrainedModel", + "FuyuModel" + ] } }, - "info.vit.glm-4v-thinking": { + "info.stst.gemma": { "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", + "repo": "google/gemma-7b", "pkg": { "0": { - "transformers": "Glm46VModel" + "transformers": "GemmaModel" } - } + }, + "file_256": [ + "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" + ], + "layer_b3": [ + "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", + "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" + ], + "layer_256": [ + "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", + "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" + ], + "tasks": [ + "GemmaModel", + "GemmaForCausalLM", + "GemmaForSequenceClassification", + "GemmaForTokenClassification", + "GemmaPreTrainedModel" + ] } }, - "info.vit.glm-4v": { + "info.stst.gemma2": { "*": { - "repo": "zai-org/GLM-4.5V", + "repo": "google/gemma-2-9b", "pkg": { "0": { - "transformers": "Glm4vMoeModel" + "transformers": "Gemma2Model" } - } + }, + "file_256": [ + "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", + "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" + ], + "layer_b3": [ + "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", + "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" + ], + "layer_256": [ + "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", + "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" + ], + "tasks": [ + "Gemma2ForCausalLM", + "Gemma2Model", + "Gemma2PreTrainedModel", + "Gemma2ForSequenceClassification", + "Gemma2ForTokenClassification" + ] } }, - "info.stst.glm-asr-nano-2512": { + "info.vit.gemma-3": { "*": { - "repo": "zai-org/GLM-ASR-Nano-2512", + "repo": "google/gemma-3-4b-it", "pkg": { "0": { - "transformers": "GlmAsrForConditionalGeneration" + "transformers": "Gemma3Model" } - } + }, + "tasks": [ + "Gemma3PreTrainedModel", + "Gemma3TextModel", + "Gemma3ForCausalLM", + "Gemma3ForConditionalGeneration", + "Gemma3Model", + "Gemma3ForSequenceClassification", + "Gemma3TextForSequenceClassification" + ] } }, - "info.vit.glpn-kitti": { + "info.stst.gemma3-text": { "*": { - "repo": "vinvino02/glpn-kitti", + "repo": "google/gemma-3-12b-it", "pkg": { "0": { - "transformers": "GLPNModel" + "transformers": "Gemma3TextModel" } - } + }, + "tasks": [ + "Gemma3PreTrainedModel", + "Gemma3TextModel", + "Gemma3ForCausalLM", + "Gemma3ForConditionalGeneration", + "Gemma3Model", + "Gemma3ForSequenceClassification", + "Gemma3TextForSequenceClassification" + ] } }, - "info.art.gpt2": { + "info.vit.gemma-3n-e": { "*": { - "repo": "openai-community/gpt2", + "repo": "google/gemma-3n-E4B", "pkg": { "0": { - "transformers": "GPT2Model" + "transformers": "Gemma3nModel" } - } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] } }, - "info.art.gpt-bigcode-santacoder": { + "info.art.gemma-3n-e": { "*": { - "repo": "bigcode/gpt_bigcode-santacoder", + "repo": "google/gemma-3n-E4B", "pkg": { "0": { - "transformers": "GPTBigCodeModel" + "transformers": "Gemma3nAudioEncoder" } - } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] } }, - "info.art.gpt-neo": { + "info.stst.gemma-3n-e": { "*": { - "repo": "EleutherAI/gpt-neo-1.3B", + "repo": "google/gemma-3n-E4B", "pkg": { "0": { - "transformers": "GPTNeoModel" + "transformers": "Gemma3nTextModel" } - } + }, + "tasks": [ + "Gemma3nAudioEncoder", + "Gemma3nForCausalLM", + "Gemma3nForConditionalGeneration", + "Gemma3nModel", + "Gemma3nPreTrainedModel", + "Gemma3nTextModel" + ] } }, - "info.art.gpt-j": { + "info.vit.git": { "*": { - "repo": "EleutherAI/gpt-j-6B", + "repo": "microsoft/git-base", "pkg": { "0": { - "transformers": "GPTJModel" + "transformers": "GitModel" } - } + }, + "tasks": [ + "GitForCausalLM", + "GitModel", + "GitPreTrainedModel", + "GitVisionModel" + ] } }, - "info.vit.llava-v1-mistral-hf": { + "info.stst.glm-4-chat": { "*": { - "repo": "llava-hf/llava-v1.6-mistral-7b-hf", + "repo": "zai-org/glm-4-9b-chat", "pkg": { "0": { - "transformers": "LlavaNextModel" + "transformers": "GlmModel" } - } + }, + "tasks": [ + "GlmPreTrainedModel", + "GlmModel", + "GlmForCausalLM", + "GlmForSequenceClassification", + "GlmForTokenClassification" + ] } }, - "info.detr.grounding-dino": { + "info.stst.glm-4-0414": { "*": { - "repo": "IDEA-Research/grounding-dino-tiny", + "repo": "zai-org/GLM-4-9B-0414", "pkg": { "0": { - "transformers": "GroundingDinoModel" + "transformers": "Glm4Model" } - } + }, + "tasks": [ + "Glm4PreTrainedModel", + "Glm4Model", + "Glm4ForCausalLM", + "Glm4ForSequenceClassification", + "Glm4ForTokenClassification" + ] } }, - "info.vit.groupvit-gcc-yfcc": { + "info.vit.glm-4v-thinking": { "*": { - "repo": "nvidia/groupvit-gcc-yfcc", + "repo": "zai-org/GLM-4.1V-9B-Thinking", "pkg": { "0": { - "transformers": "GroupViTModel" + "transformers": "Glm46VModel" } - } + }, + "tasks": [ + "Glm46VModel", + "Glm46VPreTrainedModel", + "Glm46VForConditionalGeneration" + ] } }, - "info.vit.dfine-x-coco": { + "info.moe.glm-4-a": { "*": { - "repo": "ustc-community/dfine_x_coco", + "repo": "zai-org/GLM-4.5-Air", "pkg": { "0": { - "transformers": "HGNetV2Backbone" + "transformers": "Glm4MoeModel" } - } + }, + "tasks": [ + "Glm4MoePreTrainedModel", + "Glm4MoeModel", + "Glm4MoeForCausalLM" + ] } }, - "info.vit.hiera-224": { + "info.vit.glm-4v": { "*": { - "repo": "facebook/hiera-base-224-hf", + "repo": "zai-org/GLM-4.5V", "pkg": { "0": { - "transformers": "HieraModel" + "transformers": "Glm4vMoeModel" } - } + }, + "tasks": [ + "Glm4vMoeForConditionalGeneration", + "Glm4vMoeModel", + "Glm4vMoePreTrainedModel", + "Glm4vMoeTextModel", + "Glm4vMoeVisionModel" + ] } }, - "info.aet.hubert-ls960": { + "info.moe.glm-4v": { "*": { - "repo": "facebook/hubert-base-ls960", + "repo": "zai-org/GLM-4.5V", "pkg": { "0": { - "transformers": "HubertModel" + "transformers": "Glm4vMoeTextModel" } - } + }, + "tasks": [ + "Glm4vMoeForConditionalGeneration", + "Glm4vMoeModel", + "Glm4vMoePreTrainedModel", + "Glm4vMoeTextModel", + "Glm4vMoeVisionModel" + ] } }, - "info.art.ibert-roberta": { + "info.stst.glm-4v-thinking": { "*": { - "repo": "kssteven/ibert-roberta-base", + "repo": "zai-org/GLM-4.1V-9B-Thinking", "pkg": { "0": { - "transformers": "IBertModel" + "transformers": "Glm4vTextModel" } - } + }, + "tasks": [ + "Glm4vForConditionalGeneration", + "Glm4vModel", + "Glm4vPreTrainedModel", + "Glm4vTextModel", + "Glm4vVisionModel" + ] } }, - "info.vit.idefics": { + "info.stst.glm-asr-nano-2512": { "*": { - "repo": "HuggingFaceM4/idefics-9b", + "repo": "zai-org/GLM-ASR-Nano-2512", "pkg": { "0": { - "transformers": "IdeficsModel" + "transformers": "GlmAsrForConditionalGeneration" } - } + }, + "tasks": [ + "GlmAsrEncoder", + "GlmAsrForConditionalGeneration", + "GlmAsrPreTrainedModel" + ] } }, - "info.vit.idefics2": { + "info.vit.glpn-kitti": { "*": { - "repo": "HuggingFaceM4/idefics2-8b", + "repo": "vinvino02/glpn-kitti", "pkg": { "0": { - "transformers": "Idefics2Model" + "transformers": "GLPNModel" } - } + }, + "tasks": [ + "GLPNForDepthEstimation", + "GLPNLayer", + "GLPNModel", + "GLPNPreTrainedModel" + ] } }, - "info.vit.idefics3-llama3": { + "info.vit.got-ocr-2-hf": { "*": { - "repo": "HuggingFaceM4/Idefics3-8B-Llama3", + "repo": "stepfun-ai/GOT-OCR-2.0-hf", "pkg": { "0": { - "transformers": "Idefics3Model" + "transformers": "GotOcr2Model" } - } + }, + "tasks": [ + "GotOcr2PreTrainedModel", + "GotOcr2Model", + "GotOcr2ForConditionalGeneration" + ] } }, - "info.vit.siglip-patch16-224": { + "info.art.gpt2": { "*": { - "repo": "google/siglip-base-patch16-224", + "repo": "openai-community/gpt2", "pkg": { "0": { - "transformers": "Idefics3VisionTransformer" + "transformers": "GPT2Model" } - } + }, + "tasks": [ + "GPT2DoubleHeadsModel", + "GPT2ForQuestionAnswering", + "GPT2ForSequenceClassification", + "GPT2ForTokenClassification", + "GPT2LMHeadModel", + "GPT2Model", + "GPT2PreTrainedModel" + ] } }, - "info.vit.ijepa-vith14": { + "info.art.gpt-bigcode-santacoder": { "*": { - "repo": "facebook/ijepa_vith14_1k", + "repo": "bigcode/gpt_bigcode-santacoder", "pkg": { "0": { - "transformers": "IJepaModel" + "transformers": "GPTBigCodeModel" } - } + }, + "tasks": [ + "GPTBigCodeForSequenceClassification", + "GPTBigCodeForTokenClassification", + "GPTBigCodeForCausalLM", + "GPTBigCodeModel", + "GPTBigCodePreTrainedModel" + ] } }, - "info.art.imagegpt": { + "info.art.gpt-neo": { "*": { - "repo": "openai/imagegpt-small", + "repo": "EleutherAI/gpt-neo-1.3B", "pkg": { "0": { - "transformers": "ImageGPTModel" + "transformers": "GPTNeoModel" } - } + }, + "tasks": [ + "GPTNeoForCausalLM", + "GPTNeoForQuestionAnswering", + "GPTNeoForSequenceClassification", + "GPTNeoForTokenClassification", + "GPTNeoModel", + "GPTNeoPreTrainedModel" + ] } }, - "info.vit.blip-flan-t5": { + "info.stst.gpt-neox": { "*": { - "repo": "Salesforce/instructblip-flan-t5-xl", + "repo": "EleutherAI/gpt-neox-20b", "pkg": { "0": { - "transformers": "InstructBlipModel" + "transformers": "GPTNeoXModel" } - } + }, + "tasks": [ + "GPTNeoXForCausalLM", + "GPTNeoXForQuestionAnswering", + "GPTNeoXForSequenceClassification", + "GPTNeoXForTokenClassification", + "GPTNeoXLayer", + "GPTNeoXModel", + "GPTNeoXPreTrainedModel" + ] } }, - "info.vit.internvl3-hf": { + "info.stst.gpt-neox-japanese": { "*": { - "repo": "OpenGVLab/InternVL3-1B-hf", + "repo": "abeja/gpt-neox-japanese-2.7b", "pkg": { "0": { - "transformers": "InternVLModel" + "transformers": "GPTNeoXJapaneseModel" } - } + }, + "tasks": [ + "GPTNeoXJapaneseForCausalLM", + "GPTNeoXJapaneseLayer", + "GPTNeoXJapaneseModel", + "GPTNeoXJapanesePreTrainedModel" + ] } }, - "info.ssm.jamba-v0": { + "info.moe.gpt-oss": { "*": { - "repo": "ai21labs/Jamba-v0.1", + "repo": "openai/gpt-oss-120b", "pkg": { "0": { - "transformers": "JambaModel" + "transformers": "GptOssModel" } - } + }, + "file_256": [ + "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", + "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" + ], + "layer_b3": [ + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", + "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" + ], + "layer_256": [ + "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", + "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" + ], + "tasks": [ + "GptOssForCausalLM", + "GptOssForSequenceClassification", + "GptOssForTokenClassification", + "GptOssModel", + "GptOssPreTrainedModel" + ] } }, - "info.vit.janus": { + "info.art.gpt-j": { "*": { - "repo": "deepseek-community/Janus-Pro-1B", + "repo": "EleutherAI/gpt-j-6B", "pkg": { "0": { - "transformers": "JanusModel" + "transformers": "GPTJModel" } - } + }, + "tasks": [ + "GPTJForCausalLM", + "GPTJForQuestionAnswering", + "GPTJForSequenceClassification", + "GPTJModel", + "GPTJPreTrainedModel" + ] } }, - "info.vit.kosmos-2-patch14-224": { + "info.stst.granite": { "*": { - "repo": "microsoft/kosmos-2-patch14-224", + "repo": "ibm-granite/granite-3.3-2b-base", "pkg": { "0": { - "transformers": "Kosmos2Model" + "transformers": "GraniteModel" } - } + }, + "tasks": [ + "GraniteForCausalLM", + "GraniteModel", + "GranitePreTrainedModel" + ] } }, - "info.vit.kosmos-2": { + "info.moe.powermoe": { "*": { - "repo": "microsoft/kosmos-2.5", + "repo": "ibm-research/PowerMoE-3b", "pkg": { "0": { - "transformers": "Kosmos2_5Model" + "transformers": "GraniteMoeModel" } - } + }, + "tasks": [ + "GraniteMoeForCausalLM", + "GraniteMoeModel", + "GraniteMoePreTrainedModel" + ] } }, - "info.aet.todo": { + "info.ssm.granite-4-h": { "*": { - "repo": "TODO/TODO", + "repo": "ibm-granite/granite-4.0-h-small", "pkg": { "0": { - "transformers": "LasrForCTC" + "transformers": "GraniteMoeHybridModel" } - } + }, + "tasks": [ + "GraniteMoeHybridForCausalLM", + "GraniteMoeHybridModel", + "GraniteMoeHybridPreTrainedModel" + ] } }, - "info.stst.todo": { + "info.moe.moe-active-shared-experts": { "*": { - "repo": "TODO/TODO", + "repo": "ibm-research/moe-7b-1b-active-shared-experts", "pkg": { "0": { - "transformers": "LasrEncoder" + "transformers": "GraniteMoeSharedModel" } - } + }, + "tasks": [ + "GraniteMoeSharedForCausalLM", + "GraniteMoeSharedModel", + "GraniteMoeSharedPreTrainedModel" + ] } }, - "info.art.layoutlm-uncased": { + "info.vit.llava-v1-mistral-hf": { "*": { - "repo": "microsoft/layoutlm-base-uncased", + "repo": "llava-hf/llava-v1.6-mistral-7b-hf", "pkg": { "0": { - "transformers": "LayoutLMModel" + "transformers": "LlavaNextModel" } - } + }, + "tasks": [ + "LlavaNextForConditionalGeneration", + "LlavaNextPreTrainedModel", + "LlavaNextModel" + ] } }, - "info.art.layoutlmv2-uncased": { + "info.detr.grounding-dino": { "*": { - "repo": "microsoft/layoutlmv2-base-uncased", + "repo": "IDEA-Research/grounding-dino-tiny", "pkg": { "0": { - "transformers": "LayoutLMv2Model" + "transformers": "GroundingDinoModel" } - } + }, + "tasks": [ + "GroundingDinoForObjectDetection", + "GroundingDinoModel", + "GroundingDinoPreTrainedModel" + ] } }, - "info.vit.layoutlmv3": { + "info.vit.groupvit-gcc-yfcc": { "*": { - "repo": "microsoft/layoutlmv3-base", + "repo": "nvidia/groupvit-gcc-yfcc", "pkg": { "0": { - "transformers": "LayoutLMv3Model" + "transformers": "GroupViTModel" } - } + }, + "tasks": [ + "GroupViTModel", + "GroupViTPreTrainedModel", + "GroupViTTextModel", + "GroupViTVisionModel" + ] } }, - "info.stst.led-16384": { + "info.stst.helium": { "*": { - "repo": "allenai/led-base-16384", + "repo": "kyutai/helium-1-2b", "pkg": { "0": { - "transformers": "LEDModel" + "transformers": "HeliumModel" } - } + }, + "tasks": [ + "HeliumPreTrainedModel", + "HeliumModel", + "HeliumForCausalLM", + "HeliumForSequenceClassification", + "HeliumForTokenClassification" + ] } }, - "info.gan.levit-128s": { + "info.vit.dfine-x-coco": { "*": { - "repo": "facebook/levit-128S", + "repo": "ustc-community/dfine_x_coco", "pkg": { "0": { - "transformers": "LevitModel" + "transformers": "HGNetV2Backbone" } - } + }, + "tasks": [ + "HGNetV2Backbone", + "HGNetV2PreTrainedModel", + "HGNetV2ForImageClassification" + ] } }, - "info.stst.lfm2-a": { + "info.vit.hiera-224": { "*": { - "repo": "LiquidAI/LFM2-8B-A1B", + "repo": "facebook/hiera-base-224-hf", "pkg": { "0": { - "transformers": "Lfm2MoeModel" + "transformers": "HieraModel" } - } + }, + "tasks": [ + "HieraForImageClassification", + "HieraForPreTraining", + "HieraBackbone", + "HieraModel", + "HieraPreTrainedModel" + ] } }, - "info.vit.lfm2-vl": { + "info.aet.hubert-ls960": { "*": { - "repo": "LiquidAI/LFM2-VL-1.6B", + "repo": "facebook/hubert-base-ls960", "pkg": { "0": { - "transformers": "Lfm2VlModel" + "transformers": "HubertModel" } - } + }, + "tasks": [ + "HubertForCTC", + "HubertForSequenceClassification", + "HubertModel", + "HubertPreTrainedModel" + ] } }, - "info.aet.lightglue-superpoint": { + "info.stst.hunyuan": { "*": { - "repo": "ETH-CVG/lightglue_superpoint", + "repo": "tencent/Hunyuan-7B-Instruct", "pkg": { "0": { - "transformers": "LightGlueForKeypointMatching" + "transformers": "HunYuanDenseV1Model" } - } + }, + "tasks": [ + "HunYuanDenseV1ForCausalLM", + "HunYuanDenseV1Model", + "HunYuanDenseV1PreTrainedModel", + "HunYuanDenseV1ForSequenceClassification" + ] } }, - "info.art.lilt-roberta-en": { + "info.moe.hunyuan-a": { "*": { - "repo": "SCUT-DLVCLab/lilt-roberta-en-base", + "repo": "tencent/Hunyuan-A13B-Instruct", "pkg": { "0": { - "transformers": "LiltModel" + "transformers": "HunYuanMoEV1Model" } - } + }, + "tasks": [ + "HunYuanMoEV1ForCausalLM", + "HunYuanMoEV1Model", + "HunYuanMoEV1PreTrainedModel", + "HunYuanMoEV1ForSequenceClassification" + ] } }, - "info.vit.llama-4-scout-16e": { + "info.art.ibert-roberta": { "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", + "repo": "kssteven/ibert-roberta-base", "pkg": { "0": { - "transformers": "Llama4ForConditionalGeneration" + "transformers": "IBertModel" } - } + }, + "tasks": [ + "IBertForMaskedLM", + "IBertForMultipleChoice", + "IBertForQuestionAnswering", + "IBertForSequenceClassification", + "IBertForTokenClassification", + "IBertModel", + "IBertPreTrainedModel" + ] } }, - "info.moe.llama-4-scout-16e": { + "info.vit.idefics": { "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", + "repo": "HuggingFaceM4/idefics-9b", "pkg": { "0": { - "transformers": "Llama4TextModel" + "transformers": "IdeficsModel" } - } + }, + "tasks": [ + "IdeficsForVisionText2Text", + "IdeficsModel", + "IdeficsPreTrainedModel" + ] } }, - "info.vit.llava": { + "info.vit.idefics2": { "*": { - "repo": "llava-hf/llava-9b", + "repo": "HuggingFaceM4/idefics2-8b", "pkg": { "0": { - "transformers": "LlavaModel" + "transformers": "Idefics2Model" } - } + }, + "tasks": [ + "Idefics2ForConditionalGeneration", + "Idefics2PreTrainedModel", + "Idefics2Model" + ] } }, - "info.vit.llava-next-video-hf": { + "info.vit.idefics3-llama3": { "*": { - "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", + "repo": "HuggingFaceM4/Idefics3-8B-Llama3", "pkg": { "0": { - "transformers": "LlavaNextVideoModel" + "transformers": "Idefics3Model" } - } + }, + "tasks": [ + "Idefics3ForConditionalGeneration", + "Idefics3PreTrainedModel", + "Idefics3Model", + "Idefics3VisionTransformer" + ] } }, - "info.vit.llava-onevision-qwen2-ov-hf": { + "info.vit.siglip-patch16-224": { "*": { - "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", + "repo": "google/siglip-base-patch16-224", "pkg": { "0": { - "transformers": "LlavaOnevisionModel" + "transformers": "Idefics3VisionTransformer" } - } + }, + "tasks": [ + "Idefics3ForConditionalGeneration", + "Idefics3PreTrainedModel", + "Idefics3Model", + "Idefics3VisionTransformer" + ] } }, - "info.stst.long-t5-local": { + "info.vit.ijepa-vith14": { "*": { - "repo": "google/long-t5-local-base", + "repo": "facebook/ijepa_vith14_1k", "pkg": { "0": { - "transformers": "LongT5Model" + "transformers": "IJepaModel" } - } + }, + "tasks": [ + "IJepaPreTrainedModel", + "IJepaModel", + "IJepaForImageClassification" + ] } }, - "info.art.luke": { + "info.art.imagegpt": { "*": { - "repo": "studio-ousia/luke-base", + "repo": "openai/imagegpt-small", "pkg": { "0": { - "transformers": "LukeModel" + "transformers": "ImageGPTModel" } - } + }, + "tasks": [ + "ImageGPTForCausalImageModeling", + "ImageGPTForImageClassification", + "ImageGPTModel", + "ImageGPTPreTrainedModel" + ] } }, - "info.art.lxmert-uncased": { + "info.stst.informer-tourism-monthly": { "*": { - "repo": "unc-nlp/lxmert-base-uncased", + "repo": "huggingface/informer-tourism-monthly", "pkg": { "0": { - "transformers": "LxmertModel" + "transformers": "InformerModel" } - } + }, + "tasks": [ + "InformerForPrediction", + "InformerModel", + "InformerPreTrainedModel" + ] } }, - "info.stst.m": { + "info.vit.blip-flan-t5": { "*": { - "repo": "facebook/m2m100_418M", + "repo": "Salesforce/instructblip-flan-t5-xl", + "pkg": { + "0": { + "transformers": "InstructBlipModel" + } + }, + "tasks": [ + "InstructBlipQFormerModel", + "InstructBlipPreTrainedModel", + "InstructBlipModel", + "InstructBlipForConditionalGeneration", + "InstructBlipVisionModel" + ] + } + }, + "info.vit.internvl3-hf": { + "*": { + "repo": "OpenGVLab/InternVL3-1B-hf", + "pkg": { + "0": { + "transformers": "InternVLModel" + } + }, + "tasks": [ + "InternVLVisionPreTrainedModel", + "InternVLVisionModel", + "InternVLPreTrainedModel", + "InternVLModel", + "InternVLForConditionalGeneration" + ] + } + }, + "info.stst.jais-2-chat": { + "*": { + "repo": "inceptionai/Jais-2-8B-Chat", + "pkg": { + "0": { + "transformers": "Jais2Model" + } + }, + "tasks": [ + "Jais2Model", + "Jais2ForCausalLM", + "Jais2PreTrainedModel" + ] + } + }, + "info.ssm.jamba-v0": { + "*": { + "repo": "ai21labs/Jamba-v0.1", + "pkg": { + "0": { + "transformers": "JambaModel" + } + }, + "tasks": [ + "JambaForCausalLM", + "JambaForSequenceClassification", + "JambaModel", + "JambaPreTrainedModel" + ] + } + }, + "info.vit.janus": { + "*": { + "repo": "deepseek-community/Janus-Pro-1B", + "pkg": { + "0": { + "transformers": "JanusModel" + } + }, + "tasks": [ + "JanusPreTrainedModel", + "JanusForConditionalGeneration", + "JanusModel", + "JanusVQVAE", + "JanusVisionModel" + ] + } + }, + "info.moe.jetmoe": { + "*": { + "repo": "jetmoe/jetmoe-8b", + "pkg": { + "0": { + "transformers": "JetMoeModel" + } + }, + "tasks": [ + "JetMoeForCausalLM", + "JetMoeModel", + "JetMoePreTrainedModel", + "JetMoeForSequenceClassification" + ] + } + }, + "info.vit.kosmos-2-patch14-224": { + "*": { + "repo": "microsoft/kosmos-2-patch14-224", + "pkg": { + "0": { + "transformers": "Kosmos2Model" + } + }, + "tasks": [ + "Kosmos2ForConditionalGeneration", + "Kosmos2Model", + "Kosmos2PreTrainedModel" + ] + } + }, + "info.vit.kosmos-2": { + "*": { + "repo": "microsoft/kosmos-2.5", + "pkg": { + "0": { + "transformers": "Kosmos2_5Model" + } + }, + "tasks": [ + "Kosmos2_5ForConditionalGeneration", + "Kosmos2_5Model", + "Kosmos2_5PreTrainedModel" + ] + } + }, + "info.stst.stt-en-trfs": { + "*": { + "repo": "kyutai/stt-2.6b-en-trfs", + "pkg": { + "0": { + "transformers": "KyutaiSpeechToTextModel" + } + }, + "tasks": [ + "KyutaiSpeechToTextPreTrainedModel", + "KyutaiSpeechToTextModel", + "KyutaiSpeechToTextForConditionalGeneration" + ] + } + }, + "info.aet.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrForCTC" + } + }, + "tasks": [ + "LasrForCTC", + "LasrEncoder", + "LasrPreTrainedModel" + ] + } + }, + "info.stst.todo": { + "*": { + "repo": "TODO/TODO", + "pkg": { + "0": { + "transformers": "LasrEncoder" + } + }, + "tasks": [ + "LasrForCTC", + "LasrEncoder", + "LasrPreTrainedModel" + ] + } + }, + "info.art.layoutlm-uncased": { + "*": { + "repo": "microsoft/layoutlm-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMModel" + } + }, + "tasks": [ + "LayoutLMForMaskedLM", + "LayoutLMForSequenceClassification", + "LayoutLMForTokenClassification", + "LayoutLMForQuestionAnswering", + "LayoutLMModel", + "LayoutLMPreTrainedModel" + ] + } + }, + "info.art.layoutlmv2-uncased": { + "*": { + "repo": "microsoft/layoutlmv2-base-uncased", + "pkg": { + "0": { + "transformers": "LayoutLMv2Model" + } + }, + "tasks": [ + "LayoutLMv2ForQuestionAnswering", + "LayoutLMv2ForSequenceClassification", + "LayoutLMv2ForTokenClassification", + "LayoutLMv2Layer", + "LayoutLMv2Model", + "LayoutLMv2PreTrainedModel" + ] + } + }, + "info.vit.layoutlmv3": { + "*": { + "repo": "microsoft/layoutlmv3-base", + "pkg": { + "0": { + "transformers": "LayoutLMv3Model" + } + }, + "tasks": [ + "LayoutLMv3ForQuestionAnswering", + "LayoutLMv3ForSequenceClassification", + "LayoutLMv3ForTokenClassification", + "LayoutLMv3Model", + "LayoutLMv3PreTrainedModel" + ] + } + }, + "info.stst.led-16384": { + "*": { + "repo": "allenai/led-base-16384", + "pkg": { + "0": { + "transformers": "LEDModel" + } + }, + "tasks": [ + "LEDForConditionalGeneration", + "LEDForQuestionAnswering", + "LEDForSequenceClassification", + "LEDModel", + "LEDPreTrainedModel" + ] + } + }, + "info.gan.levit-128s": { + "*": { + "repo": "facebook/levit-128S", + "pkg": { + "0": { + "transformers": "LevitModel" + } + }, + "tasks": [ + "LevitForImageClassification", + "LevitForImageClassificationWithTeacher", + "LevitModel", + "LevitPreTrainedModel" + ] + } + }, + "info.stst.lfm": { + "*": { + "repo": "LiquidAI/LFM2-1.2B", + "pkg": { + "0": { + "transformers": "Lfm2Model" + } + }, + "tasks": [ + "Lfm2ForCausalLM", + "Lfm2Model", + "Lfm2PreTrainedModel" + ] + } + }, + "info.moe.lfm2-a": { + "*": { + "repo": "LiquidAI/LFM2-8B-A1B", + "pkg": { + "0": { + "transformers": "Lfm2MoeModel" + } + }, + "tasks": [ + "Lfm2MoeForCausalLM", + "Lfm2MoeModel", + "Lfm2MoePreTrainedModel" + ] + } + }, + "info.vit.lfm2-vl": { + "*": { + "repo": "LiquidAI/LFM2-VL-1.6B", + "pkg": { + "0": { + "transformers": "Lfm2VlModel" + } + }, + "tasks": [ + "Lfm2VlForConditionalGeneration", + "Lfm2VlPreTrainedModel", + "Lfm2VlModel" + ] + } + }, + "info.aet.lightglue-superpoint": { + "*": { + "repo": "ETH-CVG/lightglue_superpoint", + "pkg": { + "0": { + "transformers": "LightGlueForKeypointMatching" + } + }, + "tasks": [ + "LightGluePreTrainedModel", + "LightGlueForKeypointMatching" + ] + } + }, + "info.art.lilt-roberta-en": { + "*": { + "repo": "SCUT-DLVCLab/lilt-roberta-en-base", + "pkg": { + "0": { + "transformers": "LiltModel" + } + }, + "tasks": [ + "LiltForQuestionAnswering", + "LiltForSequenceClassification", + "LiltForTokenClassification", + "LiltModel", + "LiltPreTrainedModel" + ] + } + }, + "info.vit.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4ForConditionalGeneration" + } + }, + "tasks": [ + "Llama4PreTrainedModel", + "Llama4TextModel", + "Llama4VisionModel", + "Llama4ForCausalLM", + "Llama4ForConditionalGeneration" + ] + } + }, + "info.moe.llama-4-scout-16e": { + "*": { + "repo": "meta-llama/Llama-4-Scout-17B-16E", + "pkg": { + "0": { + "transformers": "Llama4TextModel" + } + }, + "tasks": [ + "Llama4PreTrainedModel", + "Llama4TextModel", + "Llama4VisionModel", + "Llama4ForCausalLM", + "Llama4ForConditionalGeneration" + ] + } + }, + "info.vit.llava": { + "*": { + "repo": "llava-hf/llava-9b", + "pkg": { + "0": { + "transformers": "LlavaModel" + } + }, + "file_256": [ + "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" + ], + "layer_b3": [ + "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" + ], + "layer_256": [ + "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" + ], + "tasks": [ + "LlavaForConditionalGeneration", + "LlavaPreTrainedModel", + "LlavaModel" + ] + } + }, + "info.vit.llava-next-video-hf": { + "*": { + "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", + "pkg": { + "0": { + "transformers": "LlavaNextVideoModel" + } + }, + "tasks": [ + "LlavaNextVideoForConditionalGeneration", + "LlavaNextVideoModel", + "LlavaNextVideoPreTrainedModel" + ] + } + }, + "info.vit.llava-onevision-qwen2-ov-hf": { + "*": { + "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", + "pkg": { + "0": { + "transformers": "LlavaOnevisionModel" + } + }, + "tasks": [ + "LlavaOnevisionModel", + "LlavaOnevisionForConditionalGeneration", + "LlavaOnevisionPreTrainedModel" + ] + } + }, + "info.stst.longcat-flash-chat": { + "*": { + "repo": "meituan-longcat/LongCat-Flash-Chat", + "pkg": { + "0": { + "transformers": "LongcatFlashModel" + } + }, + "tasks": [ + "LongcatFlashPreTrainedModel", + "LongcatFlashModel", + "LongcatFlashForCausalLM" + ] + } + }, + "info.art.longformer-4096": { + "*": { + "repo": "allenai/longformer-base-4096", + "pkg": { + "0": { + "transformers": "LongformerModel" + } + }, + "tasks": [ + "LongformerForMaskedLM", + "LongformerForMultipleChoice", + "LongformerForQuestionAnswering", + "LongformerForSequenceClassification", + "LongformerForTokenClassification", + "LongformerModel", + "LongformerPreTrainedModel", + "LongformerSelfAttention" + ] + } + }, + "info.stst.long-t5-local": { + "*": { + "repo": "google/long-t5-local-base", + "pkg": { + "0": { + "transformers": "LongT5Model" + } + }, + "tasks": [ + "LongT5EncoderModel", + "LongT5ForConditionalGeneration", + "LongT5Model", + "LongT5PreTrainedModel" + ] + } + }, + "info.art.luke": { + "*": { + "repo": "studio-ousia/luke-base", + "pkg": { + "0": { + "transformers": "LukeModel" + } + }, + "tasks": [ + "LukeForEntityClassification", + "LukeForEntityPairClassification", + "LukeForEntitySpanClassification", + "LukeForMultipleChoice", + "LukeForQuestionAnswering", + "LukeForSequenceClassification", + "LukeForTokenClassification", + "LukeForMaskedLM", + "LukeModel", + "LukePreTrainedModel" + ] + } + }, + "info.art.lxmert-uncased": { + "*": { + "repo": "unc-nlp/lxmert-base-uncased", + "pkg": { + "0": { + "transformers": "LxmertModel" + } + }, + "tasks": [ + "LxmertEncoder", + "LxmertForPreTraining", + "LxmertForQuestionAnswering", + "LxmertModel", + "LxmertPreTrainedModel", + "LxmertVisualFeatureEncoder", + "LxmertXLayer" + ] + } + }, + "info.stst.m": { + "*": { + "repo": "facebook/m2m100_418M", + "pkg": { + "0": { + "transformers": "M2M100Model" + } + }, + "tasks": [ + "M2M100ForConditionalGeneration", + "M2M100Model", + "M2M100PreTrainedModel" + ] + } + }, + "info.ssm.mamba": { + "*": { + "repo": "state-spaces/mamba-2.8b", + "pkg": { + "0": { + "transformers": "MambaModel" + } + }, + "tasks": [ + "MambaForCausalLM", + "MambaModel", + "MambaPreTrainedModel", + "MambaCache" + ] + } + }, + "info.ssm.mamba2": { + "*": { + "repo": "AntonV/mamba2-2.7b-hf", + "pkg": { + "0": { + "transformers": "Mamba2Model" + } + }, + "tasks": [ + "Mamba2ForCausalLM", + "Mamba2Model", + "Mamba2PreTrainedModel" + ] + } + }, + "info.stst.opus-mt-en-de": { + "*": { + "repo": "Helsinki-NLP/opus-mt-en-de", + "pkg": { + "0": { + "transformers": "MarianModel" + } + }, + "tasks": [ + "MarianForCausalLM", + "MarianModel", + "MarianMTModel", + "MarianPreTrainedModel" + ] + } + }, + "info.art.markuplm": { + "*": { + "repo": "microsoft/markuplm-base", + "pkg": { + "0": { + "transformers": "MarkupLMModel" + } + }, + "tasks": [ + "MarkupLMForQuestionAnswering", + "MarkupLMForSequenceClassification", + "MarkupLMForTokenClassification", + "MarkupLMModel", + "MarkupLMPreTrainedModel" + ] + } + }, + "info.detr.mask2former-swin-coco-instance": { + "*": { + "repo": "facebook/mask2former-swin-small-coco-instance", + "pkg": { + "0": { + "transformers": "Mask2FormerModel" + } + }, + "tasks": [ + "Mask2FormerForUniversalSegmentation", + "Mask2FormerModel", + "Mask2FormerPreTrainedModel" + ] + } + }, + "info.detr.maskformer-swin-ade": { + "*": { + "repo": "facebook/maskformer-swin-base-ade", + "pkg": { + "0": { + "transformers": "MaskFormerModel" + } + }, + "tasks": [ + "MaskFormerForInstanceSegmentation", + "MaskFormerModel", + "MaskFormerPreTrainedModel" + ] + } + }, + "info.vit.swin-patch4-window7-224": { + "*": { + "repo": "microsoft/swin-tiny-patch4-window7-224", + "pkg": { + "0": { + "transformers": "MaskFormerSwinModel" + } + }, + "tasks": [ + "MaskFormerSwinBackbone", + "MaskFormerSwinModel", + "MaskFormerSwinPreTrainedModel" + ] + } + }, + "info.stst.mbart-cc25": { + "*": { + "repo": "facebook/mbart-large-cc25", + "pkg": { + "0": { + "transformers": "MBartModel" + } + }, + "tasks": [ + "MBartForCausalLM", + "MBartForConditionalGeneration", + "MBartForQuestionAnswering", + "MBartForSequenceClassification", + "MBartModel", + "MBartPreTrainedModel" + ] + } + }, + "info.art.megatron-bert-uncased": { + "*": { + "repo": "nvidia/megatron-bert-uncased-345m", + "pkg": { + "0": { + "transformers": "MegatronBertModel" + } + }, + "tasks": [ + "MegatronBertForCausalLM", + "MegatronBertForMaskedLM", + "MegatronBertForMultipleChoice", + "MegatronBertForNextSentencePrediction", + "MegatronBertForPreTraining", + "MegatronBertForQuestionAnswering", + "MegatronBertForSequenceClassification", + "MegatronBertForTokenClassification", + "MegatronBertModel", + "MegatronBertPreTrainedModel" + ] + } + }, + "info.vit.metaclip-2-worldwide-huge-quickgelu": { + "*": { + "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", + "pkg": { + "0": { + "transformers": "MetaClip2Model" + } + }, + "tasks": [ + "MetaClip2Model", + "MetaClip2PreTrainedModel", + "MetaClip2TextModel", + "MetaClip2TextModelWithProjection", + "MetaClip2VisionModel", + "MetaClip2VisionModelWithProjection", + "MetaClip2ForImageClassification" + ] + } + }, + "info.vit.mgp-str": { + "*": { + "repo": "alibaba-damo/mgp-str-base", + "pkg": { + "0": { + "transformers": "MgpstrForSceneTextRecognition" + } + }, + "tasks": [ + "MgpstrModel", + "MgpstrPreTrainedModel", + "MgpstrForSceneTextRecognition" + ] + } + }, + "info.gan.mimi": { + "*": { + "repo": "kyutai/mimi", + "pkg": { + "0": { + "transformers": "MimiModel" + } + }, + "tasks": [ + "MimiModel", + "MimiPreTrainedModel" + ] + } + }, + "info.moe.max-text-01-hf": { + "*": { + "repo": "MiniMaxAI/MiniMax-Text-01-hf", + "pkg": { + "0": { + "transformers": "MiniMaxModel" + } + }, + "tasks": [ + "MiniMaxPreTrainedModel", + "MiniMaxModel", + "MiniMaxForCausalLM", + "MiniMaxForSequenceClassification", + "MiniMaxForTokenClassification", + "MiniMaxForQuestionAnswering" + ] + } + }, + "info.stst.stral-2410": { + "*": { + "repo": "mistralai/Ministral-8B-Instruct-2410", + "pkg": { + "0": { + "transformers": "MinistralModel" + } + }, + "tasks": [ + "MinistralPreTrainedModel", + "MinistralModel", + "MinistralForCausalLM", + "MinistralForSequenceClassification", + "MinistralForTokenClassification", + "MinistralForQuestionAnswering" + ] + } + }, + "info.stst.stral-3-2512": { + "*": { + "repo": "mistralai/Ministral-3-8B-Base-2512", + "pkg": { + "0": { + "transformers": "Ministral3Model" + } + }, + "tasks": [ + "Ministral3ForCausalLM", + "Ministral3ForQuestionAnswering", + "Ministral3Model", + "Ministral3PreTrainedModel", + "Ministral3ForSequenceClassification", + "Ministral3ForTokenClassification" + ] + } + }, + "info.stst.mistral-v0": { + "*": { + "repo": "mistralai/Mistral-7B-v0.1", "pkg": { "0": { - "transformers": "M2M100Model" + "transformers": "MistralModel" } - } + }, + "tasks": [ + "MistralForCausalLM", + "MistralForQuestionAnswering", + "MistralModel", + "MistralPreTrainedModel", + "MistralForSequenceClassification", + "MistralForTokenClassification" + ] } }, - "info.ssm.mamba": { + "info.vit.mistral-3-2503": { "*": { - "repo": "state-spaces/mamba-2.8b", + "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "pkg": { "0": { - "transformers": "MambaModel" + "transformers": "Mistral3Model" } - } + }, + "tasks": [ + "Mistral3Model", + "Mistral3PreTrainedModel", + "Mistral3ForConditionalGeneration" + ] } }, - "info.ssm.mamba2": { + "info.moe.mixtral-8x": { "*": { - "repo": "AntonV/mamba2-2.7b-hf", + "repo": "mistralai/Mixtral-8x7B-v0.1", "pkg": { "0": { - "transformers": "Mamba2Model" + "transformers": "MixtralModel" } - } + }, + "tasks": [ + "MixtralForCausalLM", + "MixtralForQuestionAnswering", + "MixtralModel", + "MixtralPreTrainedModel", + "MixtralForSequenceClassification", + "MixtralForTokenClassification" + ] + } + }, + "info.vit.mlcd-vit-bigg-patch14-336": { + "*": { + "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", + "pkg": { + "0": { + "transformers": "MLCDVisionModel" + } + }, + "tasks": [ + "MLCDPreTrainedModel", + "MLCDVisionModel" + ] + } + }, + "info.vit.llama-3-vision": { + "*": { + "repo": "meta-llama/Llama-3.2-11B-Vision", + "pkg": { + "0": { + "transformers": "MllamaModel" + } + }, + "tasks": [ + "MllamaForConditionalGeneration", + "MllamaForCausalLM", + "MllamaTextModel", + "MllamaVisionModel", + "MllamaPreTrainedModel", + "MllamaModel" + ] + } + }, + "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "*": { + "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "pkg": { + "0": { + "transformers": "MMGroundingDinoModel" + } + }, + "tasks": [ + "MMGroundingDinoForObjectDetection", + "MMGroundingDinoModel", + "MMGroundingDinoPreTrainedModel" + ] + } + }, + "info.art.mobilebert-uncased": { + "*": { + "repo": "google/mobilebert-uncased", + "pkg": { + "0": { + "transformers": "MobileBertModel" + } + }, + "tasks": [ + "MobileBertForMaskedLM", + "MobileBertForMultipleChoice", + "MobileBertForNextSentencePrediction", + "MobileBertForPreTraining", + "MobileBertForQuestionAnswering", + "MobileBertForSequenceClassification", + "MobileBertForTokenClassification", + "MobileBertLayer", + "MobileBertModel", + "MobileBertPreTrainedModel" + ] + } + }, + "info.vit.mobilenet-v1-1--224": { + "*": { + "repo": "google/mobilenet_v1_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV1Model" + } + }, + "tasks": [ + "MobileNetV1ForImageClassification", + "MobileNetV1Model", + "MobileNetV1PreTrainedModel" + ] + } + }, + "info.vit.mobilenet-v2-1--224": { + "*": { + "repo": "google/mobilenet_v2_1.0_224", + "pkg": { + "0": { + "transformers": "MobileNetV2Model" + } + }, + "tasks": [ + "MobileNetV2ForImageClassification", + "MobileNetV2ForSemanticSegmentation", + "MobileNetV2Model", + "MobileNetV2PreTrainedModel" + ] + } + }, + "info.vit.mobilevit": { + "*": { + "repo": "apple/mobilevit-small", + "pkg": { + "0": { + "transformers": "MobileViTModel" + } + }, + "tasks": [ + "MobileViTForImageClassification", + "MobileViTForSemanticSegmentation", + "MobileViTModel", + "MobileViTPreTrainedModel" + ] + } + }, + "info.vit.mobilevitv2-1": { + "*": { + "repo": "apple/mobilevitv2-1.0-imagenet1k-256", + "pkg": { + "0": { + "transformers": "MobileViTV2Model" + } + }, + "tasks": [ + "MobileViTV2ForImageClassification", + "MobileViTV2ForSemanticSegmentation", + "MobileViTV2Model", + "MobileViTV2PreTrainedModel" + ] + } + }, + "info.aet.modernbert": { + "*": { + "repo": "answerdotai/ModernBERT-base", + "pkg": { + "0": { + "transformers": "ModernBertModel" + } + }, + "tasks": [ + "ModernBertModel", + "ModernBertPreTrainedModel", + "ModernBertForMaskedLM", + "ModernBertForSequenceClassification", + "ModernBertForTokenClassification", + "ModernBertForQuestionAnswering", + "ModernBertForMultipleChoice" + ] + } + }, + "info.aet.test-dec": { + "*": { + "repo": "blab-jhu/test-32m-dec", + "pkg": { + "0": { + "transformers": "ModernBertDecoderModel" + } + }, + "tasks": [ + "ModernBertDecoderModel", + "ModernBertDecoderPreTrainedModel", + "ModernBertDecoderForCausalLM", + "ModernBertDecoderForSequenceClassification" + ] + } + }, + "info.stst.moonshine": { + "*": { + "repo": "UsefulSensors/moonshine-tiny", + "pkg": { + "0": { + "transformers": "MoonshineModel" + } + }, + "tasks": [ + "MoonshineModel", + "MoonshinePreTrainedModel", + "MoonshineForConditionalGeneration" + ] + } + }, + "info.stst.hf-moshiko": { + "*": { + "repo": "kmhf/hf-moshiko", + "pkg": { + "0": { + "transformers": "MoshiModel" + } + }, + "tasks": [ + "MoshiForCausalLM", + "MoshiForConditionalGeneration", + "MoshiModel", + "MoshiPreTrainedModel" + ] + } + }, + "info.art.mpnet": { + "*": { + "repo": "microsoft/mpnet-base", + "pkg": { + "0": { + "transformers": "MPNetModel" + } + }, + "tasks": [ + "MPNetForMaskedLM", + "MPNetForMultipleChoice", + "MPNetForQuestionAnswering", + "MPNetForSequenceClassification", + "MPNetForTokenClassification", + "MPNetLayer", + "MPNetModel", + "MPNetPreTrainedModel" + ] + } + }, + "info.art.mpt": { + "*": { + "repo": "mosaicml/mpt-7b", + "pkg": { + "0": { + "transformers": "MptModel" + } + }, + "tasks": [ + "MptForCausalLM", + "MptModel", + "MptPreTrainedModel", + "MptForSequenceClassification", + "MptForTokenClassification", + "MptForQuestionAnswering" + ] + } + }, + "info.art.mra-512-4": { + "*": { + "repo": "uw-madison/mra-base-512-4", + "pkg": { + "0": { + "transformers": "MraModel" + } + }, + "tasks": [ + "MraForMaskedLM", + "MraForMultipleChoice", + "MraForQuestionAnswering", + "MraForSequenceClassification", + "MraForTokenClassification", + "MraLayer", + "MraModel", + "MraPreTrainedModel" + ] + } + }, + "info.stst.mt5": { + "*": { + "repo": "google/mt5-small", + "pkg": { + "0": { + "transformers": "MT5Model" + } + }, + "identifiers": [ + [ + 250112, + 2048 + ], + "text_encoders.mt5xl.transformer.shared.weight" + ], + "file_256": [ + "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", + "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" + ], + "layer_b3": [ + "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51" + ], + "layer_256": [ + "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", + "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" + ], + "tasks": [ + "MT5EncoderModel", + "MT5ForConditionalGeneration", + "MT5ForQuestionAnswering", + "MT5ForSequenceClassification", + "MT5ForTokenClassification", + "MT5Model", + "MT5PreTrainedModel" + ] + } + }, + "info.art.musicgen": { + "*": { + "repo": "facebook/musicgen-small", + "pkg": { + "0": { + "transformers": "MusicgenModel" + } + }, + "tasks": [ + "MusicgenForConditionalGeneration", + "MusicgenForCausalLM", + "MusicgenModel", + "MusicgenPreTrainedModel" + ] + } + }, + "info.art.musicgen-melody": { + "*": { + "repo": "facebook/musicgen-melody", + "pkg": { + "0": { + "transformers": "MusicgenMelodyModel" + } + }, + "tasks": [ + "MusicgenMelodyForConditionalGeneration", + "MusicgenMelodyForCausalLM", + "MusicgenMelodyModel", + "MusicgenMelodyPreTrainedModel" + ] + } + }, + "info.stst.mvp": { + "*": { + "repo": "RUCAIBox/mvp", + "pkg": { + "0": { + "transformers": "MvpModel" + } + }, + "tasks": [ + "MvpForCausalLM", + "MvpForConditionalGeneration", + "MvpForQuestionAnswering", + "MvpForSequenceClassification", + "MvpModel", + "MvpPreTrainedModel" + ] + } + }, + "info.stst.nanochat-d32": { + "*": { + "repo": "karpathy/nanochat-d32", + "pkg": { + "0": { + "transformers": "NanoChatModel" + } + }, + "tasks": [ + "NanoChatPreTrainedModel", + "NanoChatModel", + "NanoChatForCausalLM" + ] + } + }, + "info.stst.nemotron-3-hf": { + "*": { + "repo": "mgoin/nemotron-3-8b-chat-4k-sft-hf", + "pkg": { + "0": { + "transformers": "NemotronModel" + } + }, + "tasks": [ + "NemotronForQuestionAnswering", + "NemotronForCausalLM", + "NemotronModel", + "NemotronPreTrainedModel", + "NemotronForSequenceClassification", + "NemotronForTokenClassification" + ] + } + }, + "info.moe.nllb-moe": { + "*": { + "repo": "facebook/nllb-moe-54b", + "pkg": { + "0": { + "transformers": "NllbMoeModel" + } + }, + "tasks": [ + "NllbMoeForConditionalGeneration", + "NllbMoeModel", + "NllbMoePreTrainedModel", + "NllbMoeTop2Router", + "NllbMoeSparseMLP" + ] } }, - "info.stst.opus-mt-en-de": { + "info.art.nystromformer-512": { "*": { - "repo": "Helsinki-NLP/opus-mt-en-de", + "repo": "uw-madison/nystromformer-512", "pkg": { "0": { - "transformers": "MarianModel" + "transformers": "NystromformerModel" } - } + }, + "tasks": [ + "NystromformerForMaskedLM", + "NystromformerForMultipleChoice", + "NystromformerForQuestionAnswering", + "NystromformerForSequenceClassification", + "NystromformerForTokenClassification", + "NystromformerLayer", + "NystromformerModel", + "NystromformerPreTrainedModel" + ] } }, - "info.art.markuplm": { + "info.stst.olmo-hf": { "*": { - "repo": "microsoft/markuplm-base", + "repo": "allenai/OLMo-7B-hf", "pkg": { "0": { - "transformers": "MarkupLMModel" + "transformers": "OlmoModel" } - } + }, + "tasks": [ + "OlmoForCausalLM", + "OlmoModel", + "OlmoPreTrainedModel" + ] } }, - "info.vit.swin-patch4-window7-224": { + "info.stst.olmo2-1124-hf": { "*": { - "repo": "microsoft/swin-tiny-patch4-window7-224", + "repo": "allenai/Olmo-2-1124-7B", "pkg": { "0": { - "transformers": "MaskFormerSwinModel" + "transformers": "Olmo2Model" } - } + }, + "tasks": [ + "Olmo2ForCausalLM", + "Olmo2Model", + "Olmo2PreTrainedModel" + ] } }, - "info.stst.mbart-cc25": { + "info.stst.olmo-3-0725": { "*": { - "repo": "facebook/mbart-large-cc25", + "repo": "allenai/OLMo-3-0725-1B", "pkg": { "0": { - "transformers": "MBartModel" + "transformers": "Olmo3Model" } - } + }, + "tasks": [ + "Olmo3ForCausalLM", + "Olmo3Model", + "Olmo3PreTrainedModel" + ] } }, - "info.art.megatron-bert-uncased": { + "info.moe.olmoe-0924": { "*": { - "repo": "nvidia/megatron-bert-uncased-345m", + "repo": "allenai/OLMoE-1B-7B-0924", "pkg": { "0": { - "transformers": "MegatronBertModel" + "transformers": "OlmoeModel" } - } + }, + "tasks": [ + "OlmoeForCausalLM", + "OlmoeModel", + "OlmoePreTrainedModel" + ] } }, - "info.vit.metaclip-2-worldwide-huge-quickgelu": { + "info.detr.omdet-turbo-swin-hf": { "*": { - "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", + "repo": "omlab/omdet-turbo-swin-tiny-hf", "pkg": { "0": { - "transformers": "MetaClip2Model" + "transformers": "OmDetTurboForObjectDetection" } - } + }, + "tasks": [ + "OmDetTurboForObjectDetection", + "OmDetTurboPreTrainedModel" + ] } }, - "info.vit.mgp-str": { + "info.detr.oneformer-ade-swin": { "*": { - "repo": "alibaba-damo/mgp-str-base", + "repo": "shi-labs/oneformer_ade20k_swin_tiny", "pkg": { "0": { - "transformers": "MgpstrForSceneTextRecognition" + "transformers": "OneFormerModel" } - } + }, + "tasks": [ + "OneFormerForUniversalSegmentation", + "OneFormerModel", + "OneFormerPreTrainedModel" + ] } }, - "info.vit.mistral-3-2503": { + "info.art.openai-gpt": { "*": { - "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", + "repo": "openai-community/openai-gpt", "pkg": { "0": { - "transformers": "Mistral3Model" + "transformers": "OpenAIGPTModel" } - } + }, + "tasks": [ + "OpenAIGPTDoubleHeadsModel", + "OpenAIGPTForSequenceClassification", + "OpenAIGPTLMHeadModel", + "OpenAIGPTModel", + "OpenAIGPTPreTrainedModel" + ] } }, - "info.vit.mlcd-vit-bigg-patch14-336": { + "info.art.opt": { "*": { - "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", + "repo": "facebook/opt-350m", "pkg": { "0": { - "transformers": "MLCDVisionModel" + "transformers": "OPTModel" } - } + }, + "tasks": [ + "OPTForCausalLM", + "OPTModel", + "OPTPreTrainedModel", + "OPTForSequenceClassification", + "OPTForQuestionAnswering" + ] } }, - "info.vit.llama-3-vision": { + "info.vit.ovis2-hf": { "*": { - "repo": "meta-llama/Llama-3.2-11B-Vision", + "repo": "thisisiron/Ovis2-1B-hf", "pkg": { "0": { - "transformers": "MllamaModel" + "transformers": "Ovis2Model" } - } + }, + "tasks": [ + "Ovis2PreTrainedModel", + "Ovis2Model", + "Ovis2ForConditionalGeneration" + ] } }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { + "info.vit.owlv2-patch16": { "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", + "repo": "google/owlv2-base-patch16", "pkg": { "0": { - "transformers": "MMGroundingDinoModel" + "transformers": "Owlv2Model" } - } + }, + "tasks": [ + "Owlv2Model", + "Owlv2PreTrainedModel", + "Owlv2TextModel", + "Owlv2VisionModel", + "Owlv2ForObjectDetection" + ] } }, - "info.art.mobilebert-uncased": { + "info.vit.owlvit-patch32": { "*": { - "repo": "google/mobilebert-uncased", + "repo": "google/owlvit-base-patch32", "pkg": { "0": { - "transformers": "MobileBertModel" + "transformers": "OwlViTModel" } - } + }, + "tasks": [ + "OwlViTModel", + "OwlViTPreTrainedModel", + "OwlViTTextModel", + "OwlViTVisionModel", + "OwlViTForObjectDetection" + ] } }, - "info.vit.mobilenet-v1-1--224": { + "info.vit.paligemma": { "*": { - "repo": "google/mobilenet_v1_1.0_224", + "repo": "google/paligemma2-3b-mix-224", "pkg": { "0": { - "transformers": "MobileNetV1Model" + "transformers": "PaliGemmaModel" } - } + }, + "tasks": [ + "PaliGemmaForConditionalGeneration", + "PaliGemmaPreTrainedModel", + "PaliGemmaModel" + ] } }, - "info.vit.mobilenet-v2-1--224": { + "info.aet.parakeet-ctc-b": { "*": { - "repo": "google/mobilenet_v2_1.0_224", + "repo": "nvidia/parakeet-ctc-1.1b", "pkg": { "0": { - "transformers": "MobileNetV2Model" + "transformers": "ParakeetForCTC" } - } + }, + "tasks": [ + "ParakeetForCTC", + "ParakeetEncoder", + "ParakeetPreTrainedModel" + ] } }, - "info.vit.mobilevit": { + "info.stst.parakeet-ctc-b": { "*": { - "repo": "apple/mobilevit-small", + "repo": "nvidia/parakeet-ctc-1.1b", "pkg": { "0": { - "transformers": "MobileViTModel" + "transformers": "ParakeetEncoder" } - } + }, + "tasks": [ + "ParakeetForCTC", + "ParakeetEncoder", + "ParakeetPreTrainedModel" + ] } }, - "info.vit.mobilevitv2-1": { + "info.mlp.patchtsmixer-etth1-pretrain": { "*": { - "repo": "apple/mobilevitv2-1.0-imagenet1k-256", + "repo": "ibm/patchtsmixer-etth1-pretrain", "pkg": { "0": { - "transformers": "MobileViTV2Model" + "transformers": "PatchTSMixerModel" } - } + }, + "tasks": [ + "PatchTSMixerPreTrainedModel", + "PatchTSMixerModel", + "PatchTSMixerForPretraining", + "PatchTSMixerForPrediction", + "PatchTSMixerForTimeSeriesClassification", + "PatchTSMixerForRegression" + ] } }, - "info.aet.modernbert": { + "info.art.patchtst": { "*": { - "repo": "answerdotai/ModernBERT-base", + "repo": "ibm/patchtst", "pkg": { "0": { - "transformers": "ModernBertModel" + "transformers": "PatchTSTModel" } - } + }, + "tasks": [ + "PatchTSTModel", + "PatchTSTPreTrainedModel", + "PatchTSTForPrediction", + "PatchTSTForPretraining", + "PatchTSTForRegression", + "PatchTSTForClassification" + ] } }, - "info.art.mpnet": { + "info.stst.pe-av": { "*": { - "repo": "microsoft/mpnet-base", + "repo": "facebook/pe-av-large", "pkg": { "0": { - "transformers": "MPNetModel" + "transformers": "PeAudioModel" } - } + }, + "tasks": [ + "PeAudioFrameLevelModel", + "PeAudioModel", + "PeAudioEncoder" + ] } }, - "info.art.mpt": { + "info.aet.pe-av": { "*": { - "repo": "mosaicml/mpt-7b", + "repo": "facebook/pe-av-large", "pkg": { "0": { - "transformers": "MptModel" + "transformers": "PeAudioVideoModel" } - } + }, + "tasks": [ + "PeAudioVideoModel", + "PeAudioVideoEncoder" + ] } }, - "info.art.mra-512-4": { + "info.vit.pe-av": { "*": { - "repo": "uw-madison/mra-base-512-4", + "repo": "facebook/pe-av-large", "pkg": { "0": { - "transformers": "MraModel" + "transformers": "PeVideoEncoder" } - } + }, + "tasks": [ + "PeVideoEncoder", + "PeVideoModel" + ] } }, - "info.stst.mt5": { + "info.stst.pegasus": { "*": { - "repo": "google/mt5-small", + "repo": "google/pegasus-large", "pkg": { "0": { - "transformers": "MT5Model" + "transformers": "PegasusModel" } - } + }, + "tasks": [ + "PegasusForCausalLM", + "PegasusForConditionalGeneration", + "PegasusModel", + "PegasusPreTrainedModel" + ] } }, - "info.art.musicgen": { + "info.stst.pegasus-x": { "*": { - "repo": "facebook/musicgen-small", + "repo": "google/pegasus-x-large", "pkg": { "0": { - "transformers": "MusicgenModel" + "transformers": "PegasusXModel" } - } + }, + "tasks": [ + "PegasusXForConditionalGeneration", + "PegasusXModel", + "PegasusXPreTrainedModel" + ] } }, - "info.art.musicgen-melody": { + "info.vit.language-perceiver": { "*": { - "repo": "facebook/musicgen-melody", + "repo": "deepmind/language-perceiver", "pkg": { "0": { - "transformers": "MusicgenMelodyModel" + "transformers": "PerceiverModel" } - } + }, + "tasks": [ + "PerceiverForImageClassificationConvProcessing", + "PerceiverForImageClassificationFourier", + "PerceiverForImageClassificationLearned", + "PerceiverForMaskedLM", + "PerceiverForMultimodalAutoencoding", + "PerceiverForOpticalFlow", + "PerceiverForSequenceClassification", + "PerceiverLayer", + "PerceiverModel", + "PerceiverPreTrainedModel" + ] } }, - "info.stst.mvp": { + "info.vit.perception-lm": { "*": { - "repo": "RUCAIBox/mvp", + "repo": "facebook/Perception-LM-1B", "pkg": { "0": { - "transformers": "MvpModel" + "transformers": "PerceptionLMModel" } - } + }, + "tasks": [ + "PerceptionLMForConditionalGeneration", + "PerceptionLMPreTrainedModel", + "PerceptionLMModel" + ] } }, - "info.stst.nllb-moe": { + "info.stst.persimmon": { "*": { - "repo": "facebook/nllb-moe-54b", + "repo": "adept/persimmon-8b-base", "pkg": { "0": { - "transformers": "NllbMoeModel" + "transformers": "PersimmonModel" } - } + }, + "tasks": [ + "PersimmonForCausalLM", + "PersimmonModel", + "PersimmonPreTrainedModel", + "PersimmonForSequenceClassification", + "PersimmonForTokenClassification" + ] } }, - "info.art.nystromformer-512": { + "info.stst.phi-1": { "*": { - "repo": "uw-madison/nystromformer-512", + "repo": "microsoft/phi-1", "pkg": { "0": { - "transformers": "NystromformerModel" + "transformers": "PhiModel" } - } + }, + "tasks": [ + "PhiPreTrainedModel", + "PhiModel", + "PhiForCausalLM", + "PhiForSequenceClassification", + "PhiForTokenClassification" + ] } }, - "info.detr.omdet-turbo-swin-hf": { + "info.stst.phi-3": { "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", + "repo": "microsoft/Phi-3-mini-4k-instruct", "pkg": { "0": { - "transformers": "OmDetTurboForObjectDetection" + "transformers": "Phi3Model" } - } + }, + "tasks": [ + "Phi3PreTrainedModel", + "Phi3Model", + "Phi3ForCausalLM", + "Phi3ForSequenceClassification", + "Phi3ForTokenClassification" + ] } }, - "info.art.openai-gpt": { + "info.vit.phi-4": { "*": { - "repo": "openai-community/openai-gpt", + "repo": "microsoft/Phi-4-multimodal-instruct", "pkg": { "0": { - "transformers": "OpenAIGPTModel" + "transformers": "Phi4MultimodalModel" } - } + }, + "file_256": [ + "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" + ], + "layer_b3": [ + "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" + ], + "layer_256": [ + "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" + ], + "tasks": [ + "Phi4MultimodalAudioPreTrainedModel", + "Phi4MultimodalAudioModel", + "Phi4MultimodalVisionPreTrainedModel", + "Phi4MultimodalVisionModel", + "Phi4MultimodalPreTrainedModel", + "Phi4MultimodalModel", + "Phi4MultimodalForCausalLM" + ] } }, - "info.art.opt": { + "info.moe.phi-3-moe": { "*": { - "repo": "facebook/opt-350m", + "repo": "microsoft/Phi-3.5-MoE-instruct", "pkg": { "0": { - "transformers": "OPTModel" + "transformers": "PhimoeModel" } - } + }, + "tasks": [ + "PhimoePreTrainedModel", + "PhimoeModel", + "PhimoeForCausalLM", + "PhimoeForSequenceClassification" + ] } }, - "info.vit.ovis2-hf": { + "info.vit.pixio-huge": { "*": { - "repo": "thisisiron/Ovis2-1B-hf", + "repo": "facebook/pixio-huge", "pkg": { "0": { - "transformers": "Ovis2Model" + "transformers": "PixioModel" } - } + }, + "tasks": [ + "PixioModel", + "PixioPreTrainedModel", + "PixioBackbone" + ] } }, - "info.vit.owlv2-patch16": { + "info.vit.pixtral": { "*": { - "repo": "google/owlv2-base-patch16", + "repo": "mistralai/Pixtral-12B-Base-2409", "pkg": { "0": { - "transformers": "Owlv2Model" + "transformers": "PixtralVisionModel" } - } + }, + "tasks": [ + "PixtralVisionModel", + "PixtralPreTrainedModel" + ] } }, - "info.vit.owlvit-patch32": { + "info.stst.plbart": { "*": { - "repo": "google/owlvit-base-patch32", + "repo": "uclanlp/plbart-base", "pkg": { "0": { - "transformers": "OwlViTModel" + "transformers": "PLBartModel" } - } + }, + "tasks": [ + "PLBartForCausalLM", + "PLBartForConditionalGeneration", + "PLBartForSequenceClassification", + "PLBartModel", + "PLBartPreTrainedModel" + ] } }, - "info.vit.paligemma": { + "info.vit.poolformer-s12": { "*": { - "repo": "google/paligemma2-3b-mix-224", + "repo": "sail/poolformer_s12", "pkg": { "0": { - "transformers": "PaliGemmaModel" + "transformers": "PoolFormerModel" } - } + }, + "tasks": [ + "PoolFormerForImageClassification", + "PoolFormerModel", + "PoolFormerPreTrainedModel" + ] } }, - "info.aet.parakeet-ctc-b": { + "info.stst.phetnet-uncased": { "*": { - "repo": "nvidia/parakeet-ctc-1.1b", + "repo": "microsoft/prophetnet-large-uncased", "pkg": { "0": { - "transformers": "ParakeetForCTC" + "transformers": "ProphetNetModel" } - } + }, + "tasks": [ + "ProphetNetDecoder", + "ProphetNetEncoder", + "ProphetNetForCausalLM", + "ProphetNetForConditionalGeneration", + "ProphetNetModel", + "ProphetNetPreTrainedModel" + ] } }, - "info.stst.parakeet-ctc-b": { + "info.vit.pvt-224": { "*": { - "repo": "nvidia/parakeet-ctc-1.1b", + "repo": "Xrenya/pvt-tiny-224", "pkg": { "0": { - "transformers": "ParakeetEncoder" + "transformers": "PvtModel" } - } + }, + "tasks": [ + "PvtForImageClassification", + "PvtModel", + "PvtPreTrainedModel" + ] } }, - "info.stst.pe-av": { + "info.vit.pvt-v2-b0": { "*": { - "repo": "facebook/pe-av-large", + "repo": "OpenGVLab/pvt_v2_b0", "pkg": { "0": { - "transformers": "PeAudioModel" + "transformers": "PvtV2Model" } - } + }, + "tasks": [ + "PvtV2ForImageClassification", + "PvtV2Model", + "PvtV2PreTrainedModel", + "PvtV2Backbone" + ] } }, - "info.aet.pe-av": { + "info.stst.qwen2": { "*": { - "repo": "facebook/pe-av-large", + "repo": "Qwen/Qwen2-7B", "pkg": { "0": { - "transformers": "PeAudioVideoModel" + "transformers": "Qwen2Model" } - } + }, + "tasks": [ + "Qwen2PreTrainedModel", + "Qwen2Model", + "Qwen2ForCausalLM", + "Qwen2RMSNorm", + "Qwen2ForSequenceClassification", + "Qwen2ForTokenClassification", + "Qwen2ForQuestionAnswering" + ] } }, - "info.stst.pegasus": { + "info.vit.qwen2-vl": { "*": { - "repo": "google/pegasus-large", + "repo": "Qwen/Qwen2-VL-7B-Instruct", "pkg": { "0": { - "transformers": "PegasusModel" + "transformers": "Qwen2_5_VLModel" } - } + }, + "tasks": [ + "Qwen2_5_VLForConditionalGeneration", + "Qwen2_5_VLModel", + "Qwen2_5_VLPreTrainedModel", + "Qwen2_5_VLTextModel" + ] } }, - "info.stst.pegasus-x": { + "info.stst.qwen2-vl": { "*": { - "repo": "google/pegasus-x-large", + "repo": "Qwen/Qwen2-VL-7B-Instruct", "pkg": { "0": { - "transformers": "PegasusXModel" + "transformers": "Qwen2_5_VLTextModel" } - } + }, + "file_256": [ + "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", + "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", + "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", + "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" + ], + "layer_b3": [ + "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", + "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", + "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", + "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" + ], + "layer_256": [ + "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", + "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", + "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", + "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" + ], + "tasks": [ + "Qwen2_5_VLForConditionalGeneration", + "Qwen2_5_VLModel", + "Qwen2_5_VLPreTrainedModel", + "Qwen2_5_VLTextModel" + ] } }, - "info.vit.language-perceiver": { + "info.aet.qwen2-audio": { "*": { - "repo": "deepmind/language-perceiver", + "repo": "Qwen/Qwen2-Audio-7B", "pkg": { "0": { - "transformers": "PerceiverModel" + "transformers": "Qwen2AudioEncoder" } - } + }, + "tasks": [ + "Qwen2AudioForConditionalGeneration", + "Qwen2AudioPreTrainedModel", + "Qwen2AudioEncoder" + ] } }, - "info.vit.perception-lm": { + "info.moe.qwen15-moe-a": { "*": { - "repo": "facebook/Perception-LM-1B", + "repo": "Qwen/Qwen1.5-MoE-A2.7B", "pkg": { "0": { - "transformers": "PerceptionLMModel" + "transformers": "Qwen2MoeModel" } - } + }, + "tasks": [ + "Qwen2MoeForCausalLM", + "Qwen2MoeForQuestionAnswering", + "Qwen2MoeModel", + "Qwen2MoePreTrainedModel", + "Qwen2MoeForSequenceClassification", + "Qwen2MoeForTokenClassification" + ] } }, - "info.vit.pixio-huge": { + "info.stst.qwen3": { "*": { - "repo": "facebook/pixio-huge", + "repo": "Qwen/Qwen3-8B", "pkg": { "0": { - "transformers": "PixioModel" + "transformers": "Qwen3Model" } - } + }, + "tasks": [ + "Qwen3ForCausalLM", + "Qwen3ForQuestionAnswering", + "Qwen3PreTrainedModel", + "Qwen3Model", + "Qwen3ForSequenceClassification", + "Qwen3ForTokenClassification" + ] } }, - "info.stst.plbart": { + "info.moe.qwen3-a": { "*": { - "repo": "uclanlp/plbart-base", + "repo": "Qwen/Qwen3-30B-A3B", "pkg": { "0": { - "transformers": "PLBartModel" + "transformers": "Qwen3MoeModel" } - } + }, + "file_256": [ + "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" + ], + "layer_b3": [ + "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" + ], + "layer_256": [ + "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" + ], + "tasks": [ + "Qwen3MoeForCausalLM", + "Qwen3MoeForQuestionAnswering", + "Qwen3MoeModel", + "Qwen3MoePreTrainedModel", + "Qwen3MoeForSequenceClassification", + "Qwen3MoeForTokenClassification" + ] } }, - "info.vit.poolformer-s12": { + "info.moe.qwen3-next-a": { "*": { - "repo": "sail/poolformer_s12", + "repo": "Qwen/Qwen3-Next-80B-A3B-Instruct", "pkg": { "0": { - "transformers": "PoolFormerModel" + "transformers": "Qwen3NextModel" } - } + }, + "tasks": [ + "Qwen3NextForCausalLM", + "Qwen3NextForQuestionAnswering", + "Qwen3NextModel", + "Qwen3NextPreTrainedModel", + "Qwen3NextForSequenceClassification", + "Qwen3NextForTokenClassification" + ] } }, - "info.vit.pvt-v2-b0": { + "info.vit.qwen3-vl": { "*": { - "repo": "OpenGVLab/pvt_v2_b0", + "repo": "Qwen/Qwen3-VL-4B-Instruct", "pkg": { "0": { - "transformers": "PvtV2Model" + "transformers": "Qwen3VLModel" } - } + }, + "tasks": [ + "Qwen3VLVisionModel", + "Qwen3VLForConditionalGeneration", + "Qwen3VLModel", + "Qwen3VLPreTrainedModel", + "Qwen3VLTextModel" + ] } }, - "info.vit.qwen2-vl": { + "info.vit.qwen3-vl-a": { "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", + "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", "pkg": { "0": { - "transformers": "Qwen2_5_VLModel" + "transformers": "Qwen3VLMoeModel" } - } + }, + "tasks": [ + "Qwen3VLMoeVisionModel", + "Qwen3VLMoeForConditionalGeneration", + "Qwen3VLMoeModel", + "Qwen3VLMoePreTrainedModel", + "Qwen3VLMoeTextModel" + ] } }, - "info.aet.qwen2-audio": { + "info.moe.qwen3-vl-a": { "*": { - "repo": "Qwen/Qwen2-Audio-7B", + "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", "pkg": { "0": { - "transformers": "Qwen2AudioEncoder" + "transformers": "Qwen3VLMoeTextModel" } - } + }, + "tasks": [ + "Qwen3VLMoeVisionModel", + "Qwen3VLMoeForConditionalGeneration", + "Qwen3VLMoeModel", + "Qwen3VLMoePreTrainedModel", + "Qwen3VLMoeTextModel" + ] } }, - "info.vit.qwen3-vl": { + "info.stst.qwen3-vl": { "*": { "repo": "Qwen/Qwen3-VL-4B-Instruct", "pkg": { "0": { - "transformers": "Qwen3VLModel" + "transformers": "Qwen3VLTextModel" } - } + }, + "tasks": [ + "Qwen3VLVisionModel", + "Qwen3VLForConditionalGeneration", + "Qwen3VLModel", + "Qwen3VLPreTrainedModel", + "Qwen3VLTextModel" + ] } }, - "info.vit.qwen3-vl-a": { + "info.rnn.recurrentgemma": { "*": { - "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "repo": "google/recurrentgemma-2b", "pkg": { "0": { - "transformers": "Qwen3VLMoeModel" + "transformers": "RecurrentGemmaModel" } - } + }, + "tasks": [ + "RecurrentGemmaForCausalLM", + "RecurrentGemmaModel", + "RecurrentGemmaPreTrainedModel" + ] } }, "info.art.reformer-crime-and-punishment": { @@ -4364,7 +10724,17 @@ "0": { "transformers": "ReformerModel" } - } + }, + "tasks": [ + "ReformerAttention", + "ReformerForMaskedLM", + "ReformerForQuestionAnswering", + "ReformerForSequenceClassification", + "ReformerLayer", + "ReformerModel", + "ReformerModelWithLMHead", + "ReformerPreTrainedModel" + ] } }, "info.vit.regnet-y-040": { @@ -4374,7 +10744,12 @@ "0": { "transformers": "RegNetModel" } - } + }, + "tasks": [ + "RegNetForImageClassification", + "RegNetModel", + "RegNetPreTrainedModel" + ] } }, "info.art.rembert": { @@ -4384,7 +10759,18 @@ "0": { "transformers": "RemBertModel" } - } + }, + "tasks": [ + "RemBertForCausalLM", + "RemBertForMaskedLM", + "RemBertForMultipleChoice", + "RemBertForQuestionAnswering", + "RemBertForSequenceClassification", + "RemBertForTokenClassification", + "RemBertLayer", + "RemBertModel", + "RemBertPreTrainedModel" + ] } }, "info.vit.resnet-50": { @@ -4394,7 +10780,13 @@ "0": { "transformers": "ResNetModel" } - } + }, + "tasks": [ + "ResNetForImageClassification", + "ResNetModel", + "ResNetPreTrainedModel", + "ResNetBackbone" + ] } }, "info.art.roberta": { @@ -4404,7 +10796,17 @@ "0": { "transformers": "RobertaModel" } - } + }, + "tasks": [ + "RobertaForCausalLM", + "RobertaForMaskedLM", + "RobertaForMultipleChoice", + "RobertaForQuestionAnswering", + "RobertaForSequenceClassification", + "RobertaForTokenClassification", + "RobertaModel", + "RobertaPreTrainedModel" + ] } }, "info.art.efficient-mlm-m0-0": { @@ -4414,7 +10816,17 @@ "0": { "transformers": "RobertaPreLayerNormModel" } - } + }, + "tasks": [ + "RobertaPreLayerNormForCausalLM", + "RobertaPreLayerNormForMaskedLM", + "RobertaPreLayerNormForMultipleChoice", + "RobertaPreLayerNormForQuestionAnswering", + "RobertaPreLayerNormForSequenceClassification", + "RobertaPreLayerNormForTokenClassification", + "RobertaPreLayerNormModel", + "RobertaPreLayerNormPreTrainedModel" + ] } }, "info.art.roc-bert-zh": { @@ -4424,7 +10836,19 @@ "0": { "transformers": "RoCBertModel" } - } + }, + "tasks": [ + "RoCBertForCausalLM", + "RoCBertForMaskedLM", + "RoCBertForMultipleChoice", + "RoCBertForPreTraining", + "RoCBertForQuestionAnswering", + "RoCBertForSequenceClassification", + "RoCBertForTokenClassification", + "RoCBertLayer", + "RoCBertModel", + "RoCBertPreTrainedModel" + ] } }, "info.art.roformer-chinese": { @@ -4434,7 +10858,18 @@ "0": { "transformers": "RoFormerModel" } - } + }, + "tasks": [ + "RoFormerForCausalLM", + "RoFormerForMaskedLM", + "RoFormerForMultipleChoice", + "RoFormerForQuestionAnswering", + "RoFormerForSequenceClassification", + "RoFormerForTokenClassification", + "RoFormerLayer", + "RoFormerModel", + "RoFormerPreTrainedModel" + ] } }, "info.detr.rtdetr-r50vd": { @@ -4444,7 +10879,12 @@ "0": { "transformers": "RTDetrModel" } - } + }, + "tasks": [ + "RTDetrForObjectDetection", + "RTDetrModel", + "RTDetrPreTrainedModel" + ] } }, "info.detr.rtdetr-r18vd": { @@ -4454,7 +10894,12 @@ "0": { "transformers": "RTDetrV2Model" } - } + }, + "tasks": [ + "RTDetrV2Model", + "RTDetrV2PreTrainedModel", + "RTDetrV2ForObjectDetection" + ] } }, "info.rnn.rwkv-4-pile": { @@ -4464,7 +10909,12 @@ "0": { "transformers": "RwkvModel" } - } + }, + "tasks": [ + "RwkvForCausalLM", + "RwkvModel", + "RwkvPreTrainedModel" + ] } }, "info.vit.sam-vit-huge": { @@ -4474,7 +10924,12 @@ "0": { "transformers": "SamModel" } - } + }, + "tasks": [ + "SamVisionModel", + "SamModel", + "SamPreTrainedModel" + ] } }, "info.vit.sam2-hiera": { @@ -4484,7 +10939,13 @@ "0": { "transformers": "Sam2Model" } - } + }, + "tasks": [ + "Sam2Model", + "Sam2VisionModel", + "Sam2PreTrainedModel", + "Sam2HieraDetModel" + ] } }, "info.vit.sam3": { @@ -4494,7 +10955,13 @@ "0": { "transformers": "Sam3Model" } - } + }, + "tasks": [ + "Sam3Model", + "Sam3VisionModel", + "Sam3ViTModel", + "Sam3PreTrainedModel" + ] } }, "info.vit.sam3-tracker1-hiera": { @@ -4504,7 +10971,11 @@ "0": { "transformers": "Sam3TrackerModel" } - } + }, + "tasks": [ + "Sam3TrackerModel", + "Sam3TrackerPreTrainedModel" + ] } }, "info.stst.sam3": { @@ -4514,7 +10985,13 @@ "0": { "transformers": "Sam3VideoModel" } - } + }, + "tasks": [ + "Sam3VideoModel", + "Sam3VideoPreTrainedModel", + "Sam3VideoInferenceSession", + "Sam3VideoSegmentationOutput" + ] } }, "info.vit.sam-hq-vit-h": { @@ -4524,7 +11001,12 @@ "0": { "transformers": "SamHQModel" } - } + }, + "tasks": [ + "SamHQModel", + "SamHQPreTrainedModel", + "SamHQVisionModel" + ] } }, "info.vit.sam-hq-vit-huge": { @@ -4534,7 +11016,12 @@ "0": { "transformers": "SamHQVisionModel" } - } + }, + "tasks": [ + "SamHQModel", + "SamHQPreTrainedModel", + "SamHQVisionModel" + ] } }, "info.aet.hf-seamless-m4t": { @@ -4544,7 +11031,19 @@ "0": { "transformers": "SeamlessM4TModel" } - } + }, + "tasks": [ + "SeamlessM4TForTextToSpeech", + "SeamlessM4TForSpeechToSpeech", + "SeamlessM4TForTextToText", + "SeamlessM4TForSpeechToText", + "SeamlessM4TModel", + "SeamlessM4TPreTrainedModel", + "SeamlessM4TCodeHifiGan", + "SeamlessM4THifiGan", + "SeamlessM4TTextToUnitForConditionalGeneration", + "SeamlessM4TTextToUnitModel" + ] } }, "info.stst.seamless-m4t-v2": { @@ -4554,7 +11053,33 @@ "0": { "transformers": "SeamlessM4Tv2Model" } - } + }, + "tasks": [ + "SeamlessM4Tv2ForTextToSpeech", + "SeamlessM4Tv2ForSpeechToSpeech", + "SeamlessM4Tv2ForTextToText", + "SeamlessM4Tv2ForSpeechToText", + "SeamlessM4Tv2Model", + "SeamlessM4Tv2PreTrainedModel" + ] + } + }, + "info.stst.seedoss": { + "*": { + "repo": "ByteDance-Seed/SeedOss-36B", + "pkg": { + "0": { + "transformers": "SeedOssModel" + } + }, + "tasks": [ + "SeedOssForCausalLM", + "SeedOssForQuestionAnswering", + "SeedOssPreTrainedModel", + "SeedOssModel", + "SeedOssForSequenceClassification", + "SeedOssForTokenClassification" + ] } }, "info.vit.segformer-b0-finetuned-ade-512-512": { @@ -4564,7 +11089,15 @@ "0": { "transformers": "SegformerModel" } - } + }, + "tasks": [ + "SegformerDecodeHead", + "SegformerForImageClassification", + "SegformerForSemanticSegmentation", + "SegformerLayer", + "SegformerModel", + "SegformerPreTrainedModel" + ] } }, "info.vit.seggpt-vit": { @@ -4574,7 +11107,12 @@ "0": { "transformers": "SegGptModel" } - } + }, + "tasks": [ + "SegGptModel", + "SegGptPreTrainedModel", + "SegGptForImageSegmentation" + ] } }, "info.aet.sew": { @@ -4584,7 +11122,13 @@ "0": { "transformers": "SEWModel" } - } + }, + "tasks": [ + "SEWForCTC", + "SEWForSequenceClassification", + "SEWModel", + "SEWPreTrainedModel" + ] } }, "info.aet.sew-d": { @@ -4594,7 +11138,13 @@ "0": { "transformers": "SEWDModel" } - } + }, + "tasks": [ + "SEWDForCTC", + "SEWDForSequenceClassification", + "SEWDModel", + "SEWDPreTrainedModel" + ] } }, "info.vit.siglip2-patch16-224": { @@ -4604,7 +11154,14 @@ "0": { "transformers": "Siglip2Model" } - } + }, + "tasks": [ + "Siglip2Model", + "Siglip2PreTrainedModel", + "Siglip2TextModel", + "Siglip2VisionModel", + "Siglip2ForImageClassification" + ] } }, "info.vit.siglip2-patch16-naflex": { @@ -4614,7 +11171,32 @@ "0": { "transformers": "Siglip2VisionModel" } - } + }, + "tasks": [ + "Siglip2Model", + "Siglip2PreTrainedModel", + "Siglip2TextModel", + "Siglip2VisionModel", + "Siglip2ForImageClassification" + ] + } + }, + "info.stst.smollm3": { + "*": { + "repo": "HuggingFaceTB/SmolLM3-3B", + "pkg": { + "0": { + "transformers": "SmolLM3Model" + } + }, + "tasks": [ + "SmolLM3PreTrainedModel", + "SmolLM3Model", + "SmolLM3ForCausalLM", + "SmolLM3ForSequenceClassification", + "SmolLM3ForTokenClassification", + "SmolLM3ForQuestionAnswering" + ] } }, "info.vit.smolvlm": { @@ -4624,7 +11206,13 @@ "0": { "transformers": "SmolVLMModel" } - } + }, + "tasks": [ + "SmolVLMForConditionalGeneration", + "SmolVLMPreTrainedModel", + "SmolVLMModel", + "SmolVLMVisionTransformer" + ] } }, "info.vit.siglip-so-patch14-384": { @@ -4634,7 +11222,13 @@ "0": { "transformers": "SmolVLMVisionTransformer" } - } + }, + "tasks": [ + "SmolVLMForConditionalGeneration", + "SmolVLMPreTrainedModel", + "SmolVLMModel", + "SmolVLMVisionTransformer" + ] } }, "info.aet.s2t-librispeech-asr": { @@ -4644,7 +11238,12 @@ "0": { "transformers": "Speech2TextModel" } - } + }, + "tasks": [ + "Speech2TextForConditionalGeneration", + "Speech2TextModel", + "Speech2TextPreTrainedModel" + ] } }, "info.stst.speecht5-asr": { @@ -4654,7 +11253,15 @@ "0": { "transformers": "SpeechT5Model" } - } + }, + "tasks": [ + "SpeechT5ForSpeechToText", + "SpeechT5ForSpeechToSpeech", + "SpeechT5ForTextToSpeech", + "SpeechT5Model", + "SpeechT5PreTrainedModel", + "SpeechT5HifiGan" + ] } }, "info.art.splinter": { @@ -4664,17 +11271,68 @@ "0": { "transformers": "SplinterModel" } - } + }, + "tasks": [ + "SplinterForQuestionAnswering", + "SplinterForPreTraining", + "SplinterLayer", + "SplinterModel", + "SplinterPreTrainedModel" + ] + } + }, + "info.art.squeezebert-uncased": { + "*": { + "repo": "squeezebert/squeezebert-uncased", + "pkg": { + "0": { + "transformers": "SqueezeBertModel" + } + }, + "tasks": [ + "SqueezeBertForMaskedLM", + "SqueezeBertForMultipleChoice", + "SqueezeBertForQuestionAnswering", + "SqueezeBertForSequenceClassification", + "SqueezeBertForTokenClassification", + "SqueezeBertModel", + "SqueezeBertModule", + "SqueezeBertPreTrainedModel" + ] + } + }, + "info.stst.stablelm-4e1t": { + "*": { + "repo": "stabilityai/stablelm-3b-4e1t", + "pkg": { + "0": { + "transformers": "StableLmModel" + } + }, + "tasks": [ + "StableLmForCausalLM", + "StableLmModel", + "StableLmPreTrainedModel", + "StableLmForSequenceClassification", + "StableLmForTokenClassification" + ] } }, - "info.art.squeezebert-uncased": { + "info.stst.starcoder2": { "*": { - "repo": "squeezebert/squeezebert-uncased", + "repo": "bigcode/starcoder2-7b", "pkg": { "0": { - "transformers": "SqueezeBertModel" + "transformers": "Starcoder2Model" } - } + }, + "tasks": [ + "Starcoder2ForCausalLM", + "Starcoder2Model", + "Starcoder2PreTrainedModel", + "Starcoder2ForSequenceClassification", + "Starcoder2ForTokenClassification" + ] } }, "info.vit.swiftformer-xs": { @@ -4684,7 +11342,12 @@ "0": { "transformers": "SwiftFormerModel" } - } + }, + "tasks": [ + "SwiftFormerForImageClassification", + "SwiftFormerModel", + "SwiftFormerPreTrainedModel" + ] } }, "info.vit.swin2sr-classicalsr-x2-64": { @@ -4694,7 +11357,12 @@ "0": { "transformers": "Swin2SRModel" } - } + }, + "tasks": [ + "Swin2SRForImageSuperResolution", + "Swin2SRModel", + "Swin2SRPreTrainedModel" + ] } }, "info.vit.swinv2-patch4-window8-256": { @@ -4704,17 +11372,32 @@ "0": { "transformers": "Swinv2Model" } - } + }, + "tasks": [ + "Swinv2ForImageClassification", + "Swinv2ForMaskedImageModeling", + "Swinv2Model", + "Swinv2PreTrainedModel", + "Swinv2Backbone" + ] } }, - "info.stst.switch-8": { + "info.moe.switch-8": { "*": { "repo": "google/switch-base-8", "pkg": { "0": { "transformers": "SwitchTransformersModel" } - } + }, + "tasks": [ + "SwitchTransformersEncoderModel", + "SwitchTransformersForConditionalGeneration", + "SwitchTransformersModel", + "SwitchTransformersPreTrainedModel", + "SwitchTransformersTop1Router", + "SwitchTransformersSparseMLP" + ] } }, "info.stst.t5": { @@ -4724,7 +11407,151 @@ "0": { "transformers": "T5Model" } - } + }, + "identifiers": [ + [ + 4096 + ], + "encoder.embed_tokens.weight", + "text_encoders.t5xxl.transformer.shared.weight", + "t5xxl", + "encoder.block.0.layer.1.DenseReluDense.wi.weight" + ], + "file_256": [ + "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", + "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", + "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", + "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", + "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", + "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", + "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", + "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", + "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", + "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", + "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", + "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", + "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", + "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", + "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", + "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", + "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", + "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", + "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", + "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", + "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", + "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", + "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", + "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", + "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", + "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", + "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" + ], + "layer_b3": [ + "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", + "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", + "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", + "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", + "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", + "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", + "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", + "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", + "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", + "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", + "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", + "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", + "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", + "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", + "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", + "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", + "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", + "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", + "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", + "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", + "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", + "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", + "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", + "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", + "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", + "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", + "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", + "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", + "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", + "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" + ], + "layer_256": [ + "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", + "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", + "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", + "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", + "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", + "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", + "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", + "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", + "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", + "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", + "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", + "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", + "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", + "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", + "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", + "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", + "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", + "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", + "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", + "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", + "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", + "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", + "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", + "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", + "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", + "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", + "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", + "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" + ], + "tasks": [ + "T5EncoderModel", + "T5ForConditionalGeneration", + "T5Model", + "T5PreTrainedModel", + "T5ForQuestionAnswering", + "T5ForSequenceClassification", + "T5ForTokenClassification" + ] + } + }, + "info.stst.t5gemma-prefixlm": { + "*": { + "repo": "google/t5gemma-2b-2b-prefixlm-it", + "pkg": { + "0": { + "transformers": "T5GemmaModel" + } + }, + "tasks": [ + "T5GemmaForConditionalGeneration", + "T5GemmaModel", + "T5GemmaEncoderModel", + "T5GemmaPreTrainedModel", + "T5GemmaForSequenceClassification", + "T5GemmaForTokenClassification" + ] + } + }, + "info.stst.t5gemma-2": { + "*": { + "repo": "google/t5gemma-2-270m-270m", + "pkg": { + "0": { + "transformers": "T5Gemma2Model" + } + }, + "tasks": [ + "T5Gemma2ForConditionalGeneration", + "T5Gemma2Model", + "T5Gemma2PreTrainedModel", + "T5Gemma2ForSequenceClassification", + "T5Gemma2ForTokenClassification" + ] } }, "info.detr.table-transformer-detection": { @@ -4734,7 +11561,12 @@ "0": { "transformers": "TableTransformerModel" } - } + }, + "tasks": [ + "TableTransformerForObjectDetection", + "TableTransformerModel", + "TableTransformerPreTrainedModel" + ] } }, "info.art.tapas-finetuned-sqa": { @@ -4744,7 +11576,14 @@ "0": { "transformers": "TapasModel" } - } + }, + "tasks": [ + "TapasForMaskedLM", + "TapasForQuestionAnswering", + "TapasForSequenceClassification", + "TapasModel", + "TapasPreTrainedModel" + ] } }, "info.vit.textnet": { @@ -4754,7 +11593,43 @@ "0": { "transformers": "TextNetModel" } - } + }, + "tasks": [ + "TextNetBackbone", + "TextNetModel", + "TextNetPreTrainedModel", + "TextNetForImageClassification" + ] + } + }, + "info.stst.time-series-transformer-tourism-monthly": { + "*": { + "repo": "huggingface/time-series-transformer-tourism-monthly", + "pkg": { + "0": { + "transformers": "TimeSeriesTransformerModel" + } + }, + "tasks": [ + "TimeSeriesTransformerForPrediction", + "TimeSeriesTransformerModel", + "TimeSeriesTransformerPreTrainedModel" + ] + } + }, + "info.art.timesfm-2-pytorch": { + "*": { + "repo": "google/timesfm-2.0-500m-pytorch", + "pkg": { + "0": { + "transformers": "TimesFmModel" + } + }, + "tasks": [ + "TimesFmModelForPrediction", + "TimesFmPreTrainedModel", + "TimesFmModel" + ] } }, "info.vit.timesformer-finetuned-k600": { @@ -4764,7 +11639,27 @@ "0": { "transformers": "TimesformerModel" } - } + }, + "tasks": [ + "TimesformerModel", + "TimesformerForVideoClassification", + "TimesformerPreTrainedModel" + ] + } + }, + "info.detr.resnet18-a1-in": { + "*": { + "repo": "timm/resnet18.a1_in1k", + "pkg": { + "0": { + "transformers": "TimmWrapperModel" + } + }, + "tasks": [ + "TimmWrapperPreTrainedModel", + "TimmWrapperModel", + "TimmWrapperForImageClassification" + ] } }, "info.detr.tvp": { @@ -4774,7 +11669,12 @@ "0": { "transformers": "TvpModel" } - } + }, + "tasks": [ + "TvpModel", + "TvpPreTrainedModel", + "TvpForVideoGrounding" + ] } }, "info.vit.udop": { @@ -4784,7 +11684,13 @@ "0": { "transformers": "UdopModel" } - } + }, + "tasks": [ + "UdopForConditionalGeneration", + "UdopPreTrainedModel", + "UdopModel", + "UdopEncoderModel" + ] } }, "info.stst.umt5": { @@ -4794,7 +11700,77 @@ "0": { "transformers": "UMT5Model" } - } + }, + "identifiers": [ + "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" + ], + "file_256": [ + "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", + "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", + "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", + "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", + "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", + "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", + "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", + "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", + "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", + "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", + "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", + "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", + "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", + "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", + "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", + "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" + ], + "layer_b3": [ + "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", + "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", + "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", + "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", + "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", + "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", + "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", + "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", + "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", + "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", + "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", + "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", + "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", + "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", + "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", + "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", + "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", + "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" + ], + "layer_256": [ + "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", + "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", + "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", + "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", + "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", + "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", + "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", + "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", + "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", + "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", + "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", + "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", + "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", + "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", + "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", + "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", + "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", + "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" + ], + "tasks": [ + "UMT5EncoderModel", + "UMT5ForConditionalGeneration", + "UMT5ForQuestionAnswering", + "UMT5ForSequenceClassification", + "UMT5ForTokenClassification", + "UMT5Model", + "UMT5PreTrainedModel" + ] } }, "info.aet.unispeech-1500h-cv": { @@ -4804,7 +11780,14 @@ "0": { "transformers": "UniSpeechModel" } - } + }, + "tasks": [ + "UniSpeechForCTC", + "UniSpeechForPreTraining", + "UniSpeechForSequenceClassification", + "UniSpeechModel", + "UniSpeechPreTrainedModel" + ] } }, "info.aet.unispeech-sat-100h-libri-ft": { @@ -4814,7 +11797,16 @@ "0": { "transformers": "UniSpeechSatModel" } - } + }, + "tasks": [ + "UniSpeechSatForAudioFrameClassification", + "UniSpeechSatForCTC", + "UniSpeechSatForPreTraining", + "UniSpeechSatForSequenceClassification", + "UniSpeechSatForXVector", + "UniSpeechSatModel", + "UniSpeechSatPreTrainedModel" + ] } }, "info.gan.univnet-dev": { @@ -4824,7 +11816,25 @@ "0": { "transformers": "UnivNetModel" } - } + }, + "tasks": [ + "UnivNetModel" + ] + } + }, + "info.stst.vaultgemma": { + "*": { + "repo": "google/vaultgemma-7b", + "pkg": { + "0": { + "transformers": "VaultGemmaModel" + } + }, + "tasks": [ + "VaultGemmaForCausalLM", + "VaultGemmaModel", + "VaultGemmaPreTrainedModel" + ] } }, "info.vit.videollama3-image-hf": { @@ -4834,7 +11844,13 @@ "0": { "transformers": "VideoLlama3Model" } - } + }, + "tasks": [ + "VideoLlama3VisionModel", + "VideoLlama3PreTrainedModel", + "VideoLlama3Model", + "VideoLlama3ForConditionalGeneration" + ] } }, "info.vit.video-llava-hf": { @@ -4844,7 +11860,12 @@ "0": { "transformers": "VideoLlavaModel" } - } + }, + "tasks": [ + "VideoLlavaPreTrainedModel", + "VideoLlavaModel", + "VideoLlavaForConditionalGeneration" + ] } }, "info.vit.videomae": { @@ -4854,7 +11875,13 @@ "0": { "transformers": "VideoMAEModel" } - } + }, + "tasks": [ + "VideoMAEForPreTraining", + "VideoMAEModel", + "VideoMAEPreTrainedModel", + "VideoMAEForVideoClassification" + ] } }, "info.vit.vilt-b32-mlm": { @@ -4864,7 +11891,17 @@ "0": { "transformers": "ViltModel" } - } + }, + "tasks": [ + "ViltForImageAndTextRetrieval", + "ViltForImagesAndTextClassification", + "ViltForTokenClassification", + "ViltForMaskedLM", + "ViltForQuestionAnswering", + "ViltLayer", + "ViltModel", + "ViltPreTrainedModel" + ] } }, "info.vit.vip-llava-hf": { @@ -4874,7 +11911,12 @@ "0": { "transformers": "VipLlavaModel" } - } + }, + "tasks": [ + "VipLlavaModel", + "VipLlavaForConditionalGeneration", + "VipLlavaPreTrainedModel" + ] } }, "info.vit.japanese-clip-vit-h-14-bert-wider": { @@ -4884,7 +11926,10 @@ "0": { "transformers": "VisionTextDualEncoderModel" } - } + }, + "tasks": [ + "VisionTextDualEncoderModel" + ] } }, "info.art.visualbert-vqa-coco-pre": { @@ -4894,7 +11939,17 @@ "0": { "transformers": "VisualBertModel" } - } + }, + "tasks": [ + "VisualBertForMultipleChoice", + "VisualBertForPreTraining", + "VisualBertForQuestionAnswering", + "VisualBertForRegionToPhraseAlignment", + "VisualBertForVisualReasoning", + "VisualBertLayer", + "VisualBertModel", + "VisualBertPreTrainedModel" + ] } }, "info.vit.vit-patch16-224": { @@ -4904,7 +11959,13 @@ "0": { "transformers": "ViTModel" } - } + }, + "tasks": [ + "ViTForImageClassification", + "ViTForMaskedImageModeling", + "ViTModel", + "ViTPreTrainedModel" + ] } }, "info.vit.vit-mae": { @@ -4914,7 +11975,13 @@ "0": { "transformers": "ViTMAEModel" } - } + }, + "tasks": [ + "ViTMAEForPreTraining", + "ViTMAELayer", + "ViTMAEModel", + "ViTMAEPreTrainedModel" + ] } }, "info.vit.vit-msn": { @@ -4924,7 +11991,12 @@ "0": { "transformers": "ViTMSNModel" } - } + }, + "tasks": [ + "ViTMSNModel", + "ViTMSNForImageClassification", + "ViTMSNPreTrainedModel" + ] } }, "info.vit.vitdet-patch16-224": { @@ -4934,7 +12006,12 @@ "0": { "transformers": "VitDetModel" } - } + }, + "tasks": [ + "VitDetModel", + "VitDetPreTrainedModel", + "VitDetBackbone" + ] } }, "info.art.mms-tts-eng": { @@ -4944,7 +12021,11 @@ "0": { "transformers": "VitsModel" } - } + }, + "tasks": [ + "VitsModel", + "VitsPreTrainedModel" + ] } }, "info.vit.vivit16x2-kinetics400": { @@ -4954,7 +12035,12 @@ "0": { "transformers": "VivitModel" } - } + }, + "tasks": [ + "VivitModel", + "VivitPreTrainedModel", + "VivitForVideoClassification" + ] } }, "info.vit.vjepa2-vitl-fpc64-256": { @@ -4964,7 +12050,12 @@ "0": { "transformers": "VJEPA2Model" } - } + }, + "tasks": [ + "VJEPA2Model", + "VJEPA2PreTrainedModel", + "VJEPA2ForVideoClassification" + ] } }, "info.stst.voxtral-2507": { @@ -4974,7 +12065,12 @@ "0": { "transformers": "VoxtralForConditionalGeneration" } - } + }, + "tasks": [ + "VoxtralPreTrainedModel", + "VoxtralEncoder", + "VoxtralForConditionalGeneration" + ] } }, "info.aet.voxtral-2507": { @@ -4984,7 +12080,12 @@ "0": { "transformers": "VoxtralEncoder" } - } + }, + "tasks": [ + "VoxtralPreTrainedModel", + "VoxtralEncoder", + "VoxtralForConditionalGeneration" + ] } }, "info.aet.wav2vec2-960h": { @@ -4994,7 +12095,17 @@ "0": { "transformers": "Wav2Vec2Model" } - } + }, + "tasks": [ + "Wav2Vec2ForAudioFrameClassification", + "Wav2Vec2ForCTC", + "Wav2Vec2ForMaskedLM", + "Wav2Vec2ForPreTraining", + "Wav2Vec2ForSequenceClassification", + "Wav2Vec2ForXVector", + "Wav2Vec2Model", + "Wav2Vec2PreTrainedModel" + ] } }, "info.aet.wav2vec2-bert-rel-pos": { @@ -5004,7 +12115,15 @@ "0": { "transformers": "Wav2Vec2BertModel" } - } + }, + "tasks": [ + "Wav2Vec2BertForAudioFrameClassification", + "Wav2Vec2BertForCTC", + "Wav2Vec2BertForSequenceClassification", + "Wav2Vec2BertForXVector", + "Wav2Vec2BertModel", + "Wav2Vec2BertPreTrainedModel" + ] } }, "info.aet.wav2vec2-conformer-rel-pos": { @@ -5014,7 +12133,16 @@ "0": { "transformers": "Wav2Vec2ConformerModel" } - } + }, + "tasks": [ + "Wav2Vec2ConformerForAudioFrameClassification", + "Wav2Vec2ConformerForCTC", + "Wav2Vec2ConformerForPreTraining", + "Wav2Vec2ConformerForSequenceClassification", + "Wav2Vec2ConformerForXVector", + "Wav2Vec2ConformerModel", + "Wav2Vec2ConformerPreTrainedModel" + ] } }, "info.aet.wavlm": { @@ -5024,7 +12152,15 @@ "0": { "transformers": "WavLMModel" } - } + }, + "tasks": [ + "WavLMForAudioFrameClassification", + "WavLMForCTC", + "WavLMForSequenceClassification", + "WavLMForXVector", + "WavLMModel", + "WavLMPreTrainedModel" + ] } }, "info.aet.whisper": { @@ -5034,7 +12170,14 @@ "0": { "transformers": "WhisperModel" } - } + }, + "tasks": [ + "WhisperForCausalLM", + "WhisperForConditionalGeneration", + "WhisperModel", + "WhisperPreTrainedModel", + "WhisperForAudioClassification" + ] } }, "info.vit.xclip-patch32": { @@ -5044,7 +12187,27 @@ "0": { "transformers": "XCLIPModel" } - } + }, + "tasks": [ + "XCLIPModel", + "XCLIPPreTrainedModel", + "XCLIPTextModel", + "XCLIPVisionModel" + ] + } + }, + "info.gan.x-codec": { + "*": { + "repo": "Manel/X-Codec", + "pkg": { + "0": { + "transformers": "XcodecModel" + } + }, + "tasks": [ + "XcodecModel", + "XcodecPreTrainedModel" + ] } }, "info.art.xglm": { @@ -5054,7 +12217,12 @@ "0": { "transformers": "XGLMModel" } - } + }, + "tasks": [ + "XGLMForCausalLM", + "XGLMModel", + "XGLMPreTrainedModel" + ] } }, "info.art.xlm-mlm-en-2048": { @@ -5064,7 +12232,17 @@ "0": { "transformers": "XLMModel" } - } + }, + "tasks": [ + "XLMForMultipleChoice", + "XLMForQuestionAnswering", + "XLMForQuestionAnsweringSimple", + "XLMForSequenceClassification", + "XLMForTokenClassification", + "XLMModel", + "XLMPreTrainedModel", + "XLMWithLMHeadModel" + ] } }, "info.art.xlm-roberta": { @@ -5074,7 +12252,17 @@ "0": { "transformers": "XLMRobertaModel" } - } + }, + "tasks": [ + "XLMRobertaForCausalLM", + "XLMRobertaForMaskedLM", + "XLMRobertaForMultipleChoice", + "XLMRobertaForQuestionAnswering", + "XLMRobertaForSequenceClassification", + "XLMRobertaForTokenClassification", + "XLMRobertaModel", + "XLMRobertaPreTrainedModel" + ] } }, "info.art.xlm-roberta-xl": { @@ -5084,7 +12272,17 @@ "0": { "transformers": "XLMRobertaXLModel" } - } + }, + "tasks": [ + "XLMRobertaXLForCausalLM", + "XLMRobertaXLForMaskedLM", + "XLMRobertaXLForMultipleChoice", + "XLMRobertaXLForQuestionAnswering", + "XLMRobertaXLForSequenceClassification", + "XLMRobertaXLForTokenClassification", + "XLMRobertaXLModel", + "XLMRobertaXLPreTrainedModel" + ] } }, "info.art.xlnet-cased": { @@ -5094,7 +12292,17 @@ "0": { "transformers": "XLNetModel" } - } + }, + "tasks": [ + "XLNetForMultipleChoice", + "XLNetForQuestionAnswering", + "XLNetForQuestionAnsweringSimple", + "XLNetForSequenceClassification", + "XLNetForTokenClassification", + "XLNetLMHeadModel", + "XLNetModel", + "XLNetPreTrainedModel" + ] } }, "info.lstm.xlstm": { @@ -5104,7 +12312,12 @@ "0": { "transformers": "xLSTMModel" } - } + }, + "tasks": [ + "xLSTMForCausalLM", + "xLSTMModel", + "xLSTMPreTrainedModel" + ] } }, "info.art.xmod": { @@ -5114,7 +12327,17 @@ "0": { "transformers": "XmodModel" } - } + }, + "tasks": [ + "XmodForCausalLM", + "XmodForMaskedLM", + "XmodForMultipleChoice", + "XmodForQuestionAnswering", + "XmodForSequenceClassification", + "XmodForTokenClassification", + "XmodModel", + "XmodPreTrainedModel" + ] } }, "info.cnn.yolos": { @@ -5124,7 +12347,12 @@ "0": { "transformers": "YolosModel" } - } + }, + "tasks": [ + "YolosForObjectDetection", + "YolosModel", + "YolosPreTrainedModel" + ] } }, "info.art.yoso-4096": { @@ -5134,7 +12362,17 @@ "0": { "transformers": "YosoModel" } - } + }, + "tasks": [ + "YosoForMaskedLM", + "YosoForMultipleChoice", + "YosoForQuestionAnswering", + "YosoForSequenceClassification", + "YosoForTokenClassification", + "YosoLayer", + "YosoModel", + "YosoPreTrainedModel" + ] } }, "info.ssm.zamba-v1": { @@ -5144,7 +12382,29 @@ "0": { "transformers": "ZambaModel" } - } + }, + "tasks": [ + "ZambaForCausalLM", + "ZambaForSequenceClassification", + "ZambaModel", + "ZambaPreTrainedModel" + ] + } + }, + "info.ssm.zamba2": { + "*": { + "repo": "Zyphra/Zamba2-2.7B", + "pkg": { + "0": { + "transformers": "Zamba2Model" + } + }, + "tasks": [ + "Zamba2ForCausalLM", + "Zamba2ForSequenceClassification", + "Zamba2Model", + "Zamba2PreTrainedModel" + ] } }, "ops.precision.uint": { @@ -6791,6 +14051,15 @@ ], "layer_b3": [ "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" + ], + "tasks": [ + "Wav2Vec2ConformerForAudioFrameClassification", + "Wav2Vec2ConformerForCTC", + "Wav2Vec2ConformerForPreTraining", + "Wav2Vec2ConformerForSequenceClassification", + "Wav2Vec2ConformerForXVector", + "Wav2Vec2ConformerModel", + "Wav2Vec2ConformerPreTrainedModel" ] } }, @@ -6949,6 +14218,62 @@ "layer_b3": [ "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" ] + }, + "*": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 3.5, + "num_inference_steps": 50, + "max_sequence_length": 512 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "gudance": 3.5, + "num_inference_steps": 25 + } + } + }, + "file_256": [ + "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", + "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", + "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", + "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", + "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" + ], + "layer_b3": [ + "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", + "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", + "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" + ], + "layer_256": [ + "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", + "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", + "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" + ], + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ], + "tasks": [ + "Image", + "Redux", + "Kontext", + "Depth", + "Fill", + "ConceptAttention", + "ControlNet", + "CavTon", + "IC-Edit" + ] } }, "info.dit.wan2-flf2v-720p": { @@ -7103,6 +14428,15 @@ "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" ] } }, @@ -7143,6 +14477,15 @@ "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" ] } }, @@ -7168,6 +14511,15 @@ "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" + ], + "tasks": [ + "CLIPModel", + "CLIPPreTrainedModel", + "CLIPTextModel", + "CLIPTextModelWithProjection", + "CLIPVisionModel", + "CLIPVisionModelWithProjection", + "CLIPForImageClassification" ] } }, diff --git a/mir/spec/missing_params.json b/mir/spec/missing_params.json index de3dc44..c3aebdc 100644 --- a/mir/spec/missing_params.json +++ b/mir/spec/missing_params.json @@ -53,8 +53,19 @@ "timm_backbone": { "repo_path": "microsoft/resnet-50" }, + "gpt_oss": { + "repo_path": "openai/gpt-oss-120b" + }, + "bert": { + "repo_path": "google-bert/bert-base-uncased" + }, "timm_wrapper": { - "repo_path": "timm/resnet18.a1_in1k" + "repo_path": "timm/resnet18.a1_in1k", + "params": { + "_resnet_": [ + "" + ] + } }, "vision-text-dual-encoder": { "repo_path": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" diff --git a/mir/spec/template.json b/mir/spec/template.json index 8479db5..66e5fc3 100644 --- a/mir/spec/template.json +++ b/mir/spec/template.json @@ -18,6 +18,9 @@ "resnet": "" }, "transformer": { + "mlp": [ + "prediction_channel_indices" + ], "lstm": [ "sequence_kernel" ], @@ -69,7 +72,9 @@ "fusion_hidden_size" ], "moe": [ - "num_experts_per_tok" + "num_experts_per_tok", + "num_experts", + "moe_intermediate_size" ], "aet": [ "classifier_proj_size", @@ -97,6 +102,8 @@ "router_ignore_padding_tokens", "d_ff", "d_kv", + "vocoder_config", + "prompt_length", "audio_config", "convolution_bias", "rope_parameters", diff --git a/mir/tag.py b/mir/tag.py index fc95b7a..3c1fec4 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -94,12 +94,12 @@ def tag_base_model(repo_path: str, class_name: str, addendum: dict | None = None :param class_name: The HF transformers class for the model :return: A segmented MIR tag useful for appending index entries""" - from mir.config.constants import extract_init_params + from mir.config.constants import extract_init_parameters - annotations = extract_init_params(class_name.replace("Model", "Config"), "transformers") + annotations = extract_init_parameters(class_name.replace("Model", "Config"), "transformers") if not annotations: class_name = class_name.replace("Config", "Model") - annotations = extract_init_params(class_name, "transformers") + annotations = extract_init_parameters(class_name, "transformers") if not annotations: raise TypeError("No mode type returned") mir_prefix = mir_prefix_from_forward_pass(True, **annotations) From 6b5c95e2581caac8569633aff80a29ad33d5f8c4 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Mon, 12 Jan 2026 21:58:49 -0500 Subject: [PATCH 05/16] ~fast and danger2 --- data/__init__.py | 19 + data/diffusers_adds.json | 890 + data/exclusions.json | 32 + data/migrations.json | 58 + data/mir.json | 3 + mir/spec/template.json => data/nn_filter.json | 0 data/parameters.json | 30 + data/prefixes.json | 34 + mir/spec/modes.json => data/tag_scrape.json | 25 - data/transformers_adds.json | 332 + mir/__init__.py | 42 +- mir/__main__.py | 68 - mir/config/console.py | 10 - mir/config/constants.py | 174 - mir/config/conversion.py | 115 - mir/generate/.notes.txt | 66 + mir/{config => generate}/__init__.py | 0 mir/generate/__main__.py | 276 + mir/generate/_extras.py | 191 + mir/{ => generate}/automata.py | 1372 +- mir/generate/diffusers/__init__.py | 31 + mir/generate/diffusers/attention.py | 26 + .../diffusers/doc_parse.py} | 31 +- mir/generate/diffusers/guiders.py | 61 + mir/generate/diffusers/index.py | 233 + mir/generate/diffusers/schedulers.py | 74 + mir/generate/from_module.py | 125 + mir/generate/indexers.py | 19 + mir/{inspect => generate/mlx}/__init__.py | 0 mir/generate/mlx/index.py | 103 + mir/{inspect => generate}/tasks.py | 194 +- mir/generate/torch/__init__.py | 0 mir/generate/torch/dtypes.py | 60 + mir/generate/transformers/__init__.py | 33 + mir/generate/transformers/index.py | 216 + mir/generate/write_to_mir.py | 31 + mir/indexers.py | 319 - mir/inspect/classes.py | 91 - mir/inspect/metadata.py | 98 - mir/inspect/parenting.py | 32 - mir/inspect/pipes.py | 46 - mir/{config => }/json_io.py | 6 +- mir/mir.json | 14941 ---------------- mir/spec/__init__.py | 30 +- mir/spec/{versions.json => regex.json} | 5 +- mir/tag.py | 119 +- pyproject.toml | 2 +- tests/test_deconstructors_root.py | 6 +- tests/test_seek_class.py | 3 +- tests/test_taskanalyzer.py | 10 +- 50 files changed, 3028 insertions(+), 17654 deletions(-) create mode 100644 data/__init__.py create mode 100644 data/diffusers_adds.json create mode 100644 data/exclusions.json create mode 100644 data/migrations.json create mode 100644 data/mir.json rename mir/spec/template.json => data/nn_filter.json (100%) create mode 100644 data/parameters.json create mode 100644 data/prefixes.json rename mir/spec/modes.json => data/tag_scrape.json (99%) create mode 100644 data/transformers_adds.json delete mode 100644 mir/__main__.py delete mode 100644 mir/config/console.py delete mode 100644 mir/config/constants.py delete mode 100644 mir/config/conversion.py create mode 100644 mir/generate/.notes.txt rename mir/{config => generate}/__init__.py (100%) create mode 100644 mir/generate/__main__.py create mode 100644 mir/generate/_extras.py rename mir/{ => generate}/automata.py (54%) create mode 100644 mir/generate/diffusers/__init__.py create mode 100644 mir/generate/diffusers/attention.py rename mir/{doc_parser.py => generate/diffusers/doc_parse.py} (83%) create mode 100644 mir/generate/diffusers/guiders.py create mode 100644 mir/generate/diffusers/index.py create mode 100644 mir/generate/diffusers/schedulers.py create mode 100644 mir/generate/from_module.py create mode 100644 mir/generate/indexers.py rename mir/{inspect => generate/mlx}/__init__.py (100%) create mode 100644 mir/generate/mlx/index.py rename mir/{inspect => generate}/tasks.py (55%) create mode 100644 mir/generate/torch/__init__.py create mode 100644 mir/generate/torch/dtypes.py create mode 100644 mir/generate/transformers/__init__.py create mode 100644 mir/generate/transformers/index.py create mode 100644 mir/generate/write_to_mir.py delete mode 100644 mir/indexers.py delete mode 100644 mir/inspect/classes.py delete mode 100644 mir/inspect/metadata.py delete mode 100644 mir/inspect/parenting.py delete mode 100644 mir/inspect/pipes.py rename mir/{config => }/json_io.py (87%) delete mode 100644 mir/mir.json rename mir/spec/{versions.json => regex.json} (68%) diff --git a/data/__init__.py b/data/__init__.py new file mode 100644 index 0000000..c766341 --- /dev/null +++ b/data/__init__.py @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import os + +from mir import ROOT_PATH +from mir.json_io import read_json_file + +MIR_PATH_NAMED = os.path.join(ROOT_PATH, "mir.json") + + +DIFFUSERS_ADDS = read_json_file(os.path.join(ROOT_PATH, "data", "diffusers_adds.json")) +EXCLUSIONS = read_json_file(os.path.join(ROOT_PATH, "data", "exclusions.json")) +MIGRATIONS = read_json_file(os.path.join(ROOT_PATH, "data", "migrations.json")) +NN_FILTER = read_json_file(os.path.join(ROOT_PATH, "data", "nn_filter.json")) +PARAMETERS = read_json_file(os.path.join(ROOT_PATH, "data", "parameters.json")) +PREFIXES = read_json_file(os.path.join(ROOT_PATH, "data", "prefixes.json")) +TAG_SCRAPE = read_json_file(os.path.join(ROOT_PATH, "data", "tag_scrape.json")) +TRANSFORMERS_ADDS = read_json_file(os.path.join(ROOT_PATH, "data", "transformers_adds.json")) diff --git a/data/diffusers_adds.json b/data/diffusers_adds.json new file mode 100644 index 0000000..6f39afd --- /dev/null +++ b/data/diffusers_adds.json @@ -0,0 +1,890 @@ +{ + "stabilityai/stable-diffusion-xl-base-1.0": { + "StableDiffusionXLPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "denoising_end": 0.8, + "num_inference_steps": 40, + "output_type": "latent", + "safety_checker": false, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" + } + }, + "file_256": [ + "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", + "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", + "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", + "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" + ], + "layer_256": [ + "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", + "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", + "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" + ], + "layer_b3": [ + "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", + "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", + "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" + ], + "identifiers": [ + "logit_scale", + "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", + "add_embedding.linear_2.bias" + ] + } + }, + "stabilityai/stable-diffusion-xl-refiner-1.0": { + "StableDiffusionXLImg2ImgPipeline": { + "pkg": { + "1": { + "diffusers": "DiffusionPipeline", + "generation": { + "num_inference_steps": 40, + "denoising_end": 0.8 + } + } + }, + "identifiers": [ + "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" + ], + "file_256": [ + "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", + "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", + "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" + ], + "layer_b3": [ + "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", + "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", + "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" + ], + "layer_256": [ + "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", + "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", + "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" + ] + } + }, + "lodestones/Chroma": { + "ChromaPipeline": { + "pkg": { + "1": { + "generation": { + "neg_text": "", + "num_steps": "28", + "latent_size": [ + 64, + 64 + ] + } + } + }, + "file_256": [ + "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", + "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", + "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", + "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" + ], + "layer_b3": [ + "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" + ], + "layer_256": [ + "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" + ] + } + }, + "fal/AuraFlow": { + "AuraFlowPipeline": { + "identifiers": [ + [ + 8192, + 3072 + ], + "mlpX.c_fc2.weight", + "joint_transformer_blocks.2.ff_context.linear_2.weight" + ], + "file_256": [ + "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", + "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", + "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", + "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" + ], + "layer_b3": [ + "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", + "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", + "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", + "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" + ], + "layer_256": [ + "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", + "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", + "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", + "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" + ] + } + }, + "Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers": { + "HunyuanDiTPipeline": { + "identifiers": [ + "extra_embedder", + "model.blocks", + "skip_norm.weight" + ], + "file_256": [ + "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", + "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", + "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" + ], + "layer_b3": [ + "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", + "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", + "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" + ], + "layer_256": [ + "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", + "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", + "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" + ] + } + }, + "Alpha-VLLM/Lumina-Next-SFT-diffusers": { + "LuminaPipeline": { + "pkg": { + "0": { + "precision": " ops.precision.bfloat.B16" + } + }, + "identifiers": [ + "time_caption", + "feed_forward" + ], + "file_256": [ + "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" + ], + "layer_b3": [ + "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", + "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" + ], + "layer_256": [ + "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", + "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" + ] + } + }, + "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS": { + "PixArtSigmaPipeline": { + "identifiers": [ + "adaln_single", + "scale_shift_table" + ], + "file_256": [ + "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", + "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" + ], + "layer_b3": [ + "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", + "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" + ], + "layer_256": [ + "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", + "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" + ] + } + }, + "PixArt-alpha/PixArt-XL-2-1024-MS": { + "PixArtAlphaPipeline": { + "identifiers": [ + "aspect_ratio", + "y_embedding", + "emb.resolution", + "caption_projection" + ], + "file_256": [ + "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" + ], + "layer_b3": [ + "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" + ], + "layer_256": [ + "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" + ] + } + }, + "stabilityai/stable-diffusion-3.5-medium": { + "StableDiffusion3Pipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16" + } + }, + "identifiers": [ + "model.diffusion_model.joint_blocks.", + "transformer_blocks.21.norm1_context.linear.weight", + "transformer_blocks.31.norm1_context.linear.weight", + "blocks.11.ff.net.2.weight" + ], + "file_256": [ + "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", + "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" + ], + "layer_b3": [ + "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", + "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" + ], + "layer_256": [ + "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", + "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" + ] + } + }, + "Efficient-Large-Model/Sana-1600M-1024px-BF16-diffusers": { + "SanaPipeline": { + "pkg": { + "0": { + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 4.5, + "num_inference_steps": 20 + }, + "precision": "ops.precision.bfloat.B16" + } + }, + "file_256": [ + "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" + ], + "layer_b3": [ + "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" + ], + "layer_256": [ + "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" + ] + } + }, + "stable-diffusion-v1-5/stable-diffusion-v1-5": { + "StableDiffusionPipeline": { + "identifiers": [ + "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" + ], + "file_256": [ + "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", + "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", + "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", + "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", + "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", + "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", + "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" + ], + "layer_b3": [ + "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", + "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", + "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", + "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" + ], + "layer_256": [ + "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", + "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", + "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" + ] + } + }, + "stabilityai/stable-cascade-prior": { + "StableCascadePriorPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "negative_prompt": "", + "num_images_per_prompt": 1, + "num_inference_steps": 20, + "guidance_scale": 4.0, + "width": 1024, + "height": 1024 + } + } + }, + "file_256": [ + "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", + "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", + "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", + "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", + "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", + "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" + ], + "layer_b3": [ + "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", + "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", + "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", + "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", + "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", + "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" + ], + "layer_256": [ + "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", + "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", + "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", + "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", + "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", + "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" + ], + "identifiers": [ + "down_blocks.0.2.kv_mapper", + "previewer", + "backbone" + ] + } + }, + "black-forest-labs/FLUX.1-dev": { + "FluxPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 3.5, + "num_inference_steps": 50, + "max_sequence_length": 512 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "gudance": 3.5, + "num_inference_steps": 25 + } + } + }, + "file_256": [ + "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", + "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", + "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", + "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", + "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" + ], + "layer_b3": [ + "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", + "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", + "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" + ], + "layer_256": [ + "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", + "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", + "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" + ], + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ] + } + }, + "black-forest-labs/FLUX.1-schnell": { + "FluxPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 1024, + "width": 1024, + "guidance_scale": 0.0, + "num_inference_steps": 4, + "max_sequence_length": 256 + } + }, + "1": { + "mflux": "flux.flux.Flux1", + "generation": { + "height": 1024, + "width": 1024, + "num_inference_steps": 4 + } + } + }, + "identifiers": [ + "double_blocks.12.txt_mod.lin.weight", + "add_q_proj.weight", + "single_transformer_blocks.9.norm.linear.weight" + ], + "file_256": [ + "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", + "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" + ], + "layer_b3": [ + "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", + "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", + "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" + ], + "layer_256": [ + "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", + "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", + "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" + ] + } + }, + "stabilityai/stable-cascade": { + "StableCascadeDecoderPipeline": { + "pkg": { + "0": { + "generation": { + "negative_prompt": "", + "guidance_scale": 0.0, + "output_type": "pil", + "num_inference_steps": 10 + }, + "precision": "ops.precision.bfloat.B16" + } + }, + "file_256": [ + "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", + "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", + "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", + "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", + "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" + ], + "layer_b3": [ + "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", + "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", + "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", + "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", + "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" + ], + "layer_256": [ + "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", + "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", + "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", + "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", + "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" + ], + "identifiers": [ + "0.2.channelwise", + "clip_mapper.bias", + ".12.self_attn.k_proj.weight" + ] + } + }, + "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers": { + "WanImageToVideoPipeline": { + "file_256": [ + "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", + "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", + "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", + "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", + "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", + "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", + "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", + "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", + "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" + ], + "layer_b3": [ + "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", + "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", + "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", + "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", + "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" + ], + "layer_256": [ + "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", + "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", + "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", + "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", + "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" + ] + } + }, + "Qwen/Qwen-Image": { + "QwenImagePipeline": { + "file_256": [ + "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" + ], + "layer_b3": [ + "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" + ], + "layer_256": [ + "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" + ] + } + }, + "Wan-AI/Wan2.1-VACE-1.3B-diffusers": { + "WanVACEPipeline": { + "file_256": [ + "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", + "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", + "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", + "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", + "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" + ], + "layer_b3": [ + "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", + "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", + "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", + "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" + ], + "layer_256": [ + "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", + "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", + "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", + "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" + ] + } + }, + "Wan-AI/Wan2.1-T2V-14B-Diffusers": { + "WanPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } + } + }, + "file_256": [ + "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", + "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", + "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", + "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", + "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", + "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", + "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", + "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" + ], + "layer_b3": [ + "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", + "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", + "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", + "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", + "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", + "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", + "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" + ], + "layer_256": [ + "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", + "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", + "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", + "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", + "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", + "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", + "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" + ] + } + }, + "Wan-AI/Wan2.1-T2V-1.3B-Diffusers": { + "WanVideoToVideoPipeline": { + "pkg": { + "0": { + "diffusers": "WanPipeline", + "precision": "ops.precision.bfloat.B16", + "generation": { + "height": 480, + "width": 832, + "num_frames": 81, + "guidance_scale": 5.0 + } + } + } + } + }, + "nvidia/cosmos-predict2-text2image": { + "Cosmos2TextToImagePipeline": { + "file_256": [ + "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", + "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", + "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", + "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", + "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", + "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", + "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", + "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", + "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", + "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", + "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", + "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", + "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" + ], + "layer_b3": [ + "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", + "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", + "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", + "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", + "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", + "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", + "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", + "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", + "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", + "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", + "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", + "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", + "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" + ], + "layer_256": [ + "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", + "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", + "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", + "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", + "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", + "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", + "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", + "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", + "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", + "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", + "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", + "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", + "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" + ] + } + }, + "rhymes-ai/Allegro": { + "AllegroPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.bfloat.B16", + "generation": { + "guidance_scale": 7.5, + "max_sequence_length": 512, + "num_inference_steps": 100 + } + } + }, + "file_256": [ + "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" + ], + "layer_b3": [ + "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" + ], + "layer_256": [ + "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" + ] + } + }, + "audioldm-s-v2": { + "AudioLDMPipeline": { + "file_256": [ + "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ] + } + }, + "zai-org/CogVideoX-2b": { + "CogVideoXPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "num_videos_per_prompt": 1, + "num_inference_steps": 50, + "num_frames": 49, + "guidance_scale": 6 + } + } + }, + "file_256": [ + "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" + ], + "layer_b3": [ + "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" + ], + "layer_256": [ + "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" + ] + } + }, + "HiDream-ai/HiDream-I1-Full": { + "StableDiffusion3Pipeline": { + "file_256": [ + "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" + ], + "layer_b3": [ + "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" + ], + "layer_256": [ + "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" + ] + } + }, + "cvssp/audioldm2": { + "AudioLDM2Pipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } + } + }, + "file_256": [ + "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" + ], + "layer_b3": [ + "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" + ], + "layer_256": [ + "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" + ] + } + }, + "Alpha-VLLM/Lumina-Image-2.0": { + "Lumina2Pipeline": { + "pkg": {}, + "file_256": [ + "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", + "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" + ], + "layer_b3": [ + "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" + ], + "layer_256": [ + "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", + "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" + ] + } + }, + "ucsd-reach/musicldm": { + "MusicLDMPipeline": { + "pkg": { + "0": { + "generation": { + "num_inference_steps": 200, + "audio_length_in_s": 10.0 + } + } + }, + "file_256": [ + "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" + ], + "layer_b3": [ + "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" + ], + "layer_256": [ + "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" + ] + } + }, + "openai/shap-e": { + "ShapEPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 64, + "size": 256, + "guidance_scale": 15 + } + } + } + } + }, + "hunyuanvideo-community/HunyuanVideo": { + "HunyuanVideoPipeline": { + "file_256": [ + "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" + ], + "layer_b3": [ + "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" + ], + "layer_256": [ + "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" + ] + } + }, + "zai-org/CogView3-Plus-3B": { + "CogView3PlusPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "guidance_scale": 7.0, + "num_images_per_prompt": 1, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } + } + } + } + }, + "stabilityai/stable-audio-open-1.0": { + "StableAudioPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "num_inference_steps": 200, + "audio_end_in_s": 10, + "num_waveforms_per_prompt": 3 + } + } + } + } + }, + "Kwai-Kolors/Kolors-diffusers": { + "KolorsPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16", + "generation": { + "negative_prompt": "", + "guidance_scale": 5.0, + "num_inference_steps": 50, + "width": 1024, + "height": 1024 + } + }, + "1": { + "diffusers": "DiffusionPipeline" + } + }, + "file_256": [ + "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" + ], + "layer_b3": [ + "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" + ], + "layer_256": [ + "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" + ], + "identifiers": [ + ".DenseReluDense.wi.weight", + "encoder_hid_proj.weight" + ] + } + }, + "tencent-hunyuan/hunyuandiT-v1.2-diffusers": { + "HunyuanDiTPipeline": { + "pkg": { + "0": { + "precision": "ops.precision.float.F16" + } + }, + "file_256": [ + "7d31ac8fa389ff39dd0a81430010e52c43b59f15adc00c83625a47881e16830e" + ], + "layer_b3": [ + "bccd37ecc9f85d132b46d0bb67b4facb49fc6c091428a4feba9ab9a93140f5fe" + ], + "layer_256": [ + "ed25d241d58ca298d28abd5919e70341ad194e77dce4859436b52ea4d8fcb616" + ] + } + } +} \ No newline at end of file diff --git a/data/exclusions.json b/data/exclusions.json new file mode 100644 index 0000000..e386bb2 --- /dev/null +++ b/data/exclusions.json @@ -0,0 +1,32 @@ +{ + "exclusion_list": [ + "auto_pipeline", + "consistency_models", + "pipeline_utils", + "deprecated", + "ddim", + "ddpm", + "deprecated", + "autopipeline", + "dance_diffusion", + "diffusionpipeline", + "dit", + "latent_consistency_models", + "latent_diffusion", + "ledits_pp", + "pag", + "paint_by_example", + "semantic_stable_diffusion", + "stable_diffusion_attend_and_excite", + "stable_diffusion_diffedit", + "stable_diffusion_k_diffusion", + "stable_diffusion_panorama", + "stable_diffusion_safe", + "stable_diffusion_sag", + "t2i_adapter", + "text_to_video_synthesis", + "unclip", + "unidiffuser", + "controlnet_hunyuandit" + ] +} \ No newline at end of file diff --git a/data/migrations.json b/data/migrations.json new file mode 100644 index 0000000..8f696e7 --- /dev/null +++ b/data/migrations.json @@ -0,0 +1,58 @@ +{ + "repo": { + "/helium-2b": "/helium-1-2b", + "allenai/Olmo2-7B-1124-hf": "allenai/Olmo-2-1124-7B", + "apple/mobilevitv2-1.0": "apple/mobilevitv2-1.0-imagenet1k-256", + "caidas/swin2SR-classical-sr-x2-64": "caidas/swin2SR-classical-sr-x2-64", + "facebook/hiera-base-224": "facebook/hiera-base-224-hf", + "facebook/sam_hq-vit-huge": "syscv-community/sam-hq-vit-huge", + "facebook/vit_msn_base": "facebook/vit-msn-base", + "facebook/wav2vec2-bert-rel-pos-large": "facebook/w2v-bert-2.0", + "google/gemma-3-4b": "google/gemma-3-4b-it", + "google/gemma2-7b": "google/gemma-2-9b", + "google/gemma3_text-7b": "google/gemma-3-12b-it", + "IDEA-Research/dab_detr-base": "IDEA-Research/dab-detr-resnet-50", + "LGAI-EXAONE/EXAONE-4.0-Instruct": "LGAI-EXAONE/EXAONE-4.0-32B", + "meta/chameleon-7b'": "facebook/chameleon-7b", + "mixtralai/Mixtral-8x7B": "mistralai/Mixtral-8x7B-v0.1", + "paligemma-hf/paligemma-2b": "google/paligemma2-3b-mix-224", + "pixtral-hf/pixtral-9b": "mistralai/Pixtral-12B-Base-2409", + "Qwen/Qwen2-7B-beta": "Qwen/Qwen2-7B", + "Qwen/Qwen3-15B-A2B": "Qwen/Qwen3-30B-A3B", + "s-JoL/Open-Llama-V1": "openlm-research/open_llama_3b", + "Salesforce/instruct-blip-flan-t5": "Salesforce/instructblip-flan-t5-xl", + "state-spaces/mamba2-2.8b": "AntonV/mamba2-2.7b-hf", + "ibm-fms/FalconH1-9.8b-2.2T-hf": "tiiuae/Falcon-H1-34B-Instruct", + "nvidia/nemotron-3-8b-base-4k-hf": "mgoin/nemotron-3-8b-chat-4k-sft-hf", + "THUDM/": "zai-org/", + "THUDM/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", + "zai-org/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air" + }, + "model": { + "bark": "suno/bark", + "aria_text": "rhymes-ai/Aria-Chat", + "cwm": "facebook/cwm", + "decision_transformer": "edbeeching/decision-transformer-gym-hopper-medium", + "distilbert": "distilbert-base-uncased", + "gpt_bigcode": "bigcode/gpt_bigcode-santacoder", + "granite": "ibm-granite/granite-3.3-2b-base", + "granitemoe": "ibm-research/PowerMoE-3b", + "granitemoehybrid": "ibm-granite/granite-4.0-h-small", + "musicgen": "facebook/musicgen-small", + "seamless_m4t_v2": "facebook/seamless-m4t-v2-large", + "timm_backbone": "microsoft/resnet-50", + "gpt_oss": "openai/gpt-oss-120b", + "bert": "google-bert/bert-base-uncased", + "timm_wrapper": "timm/resnet18.a1_in1k", + "vision-text-dual-encoder": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" + }, + "module": { + "blip_diffusion": "blip_diffusion", + "cogvideo": "cogvideox", + "cogview3": "cogview3plus", + "deepfloyd_if": "if", + "cosmos": "cosmos2_text2image", + "visualcloze": "visualcloze_generation", + "marigold": "marigold_depth" + } +} \ No newline at end of file diff --git a/data/mir.json b/data/mir.json new file mode 100644 index 0000000..59ae13b --- /dev/null +++ b/data/mir.json @@ -0,0 +1,3 @@ +{ + "expected": "data" +} \ No newline at end of file diff --git a/mir/spec/template.json b/data/nn_filter.json similarity index 100% rename from mir/spec/template.json rename to data/nn_filter.json diff --git a/data/parameters.json b/data/parameters.json new file mode 100644 index 0000000..5a3f650 --- /dev/null +++ b/data/parameters.json @@ -0,0 +1,30 @@ +{ + "bark": { + "n_head": [ + "" + ] + }, + "aria_text": { + "vision_config": [ + "" + ], + "text_config": [ + "" + ] + }, + "cwm": { + "n_head": [ + "" + ] + }, + "bert": { + "act_dropout": [ + "" + ] + }, + "timm_wrapper": { + "_resnet_": [ + "" + ] + } +} \ No newline at end of file diff --git a/data/prefixes.json b/data/prefixes.json new file mode 100644 index 0000000..6f535f8 --- /dev/null +++ b/data/prefixes.json @@ -0,0 +1,34 @@ +{ + "pipe_variables": [ + ">>> motion_adapter = ", + ">>> adapter = ", + ">>> controlnet = ", + ">>> super_res_1_pipe = ", + ">>> pipe_prior = ", + ">>> pipe_prior_redux = ", + ">>> pipe = ", + ">>> pipeline = ", + ">>> blip_diffusion_pipe = ", + ">>> prior_pipe = ", + ">>> gen_pipe = ", + "pipe = " + ], + "repo_variables": [ + "controlnet_model", + "controlnet_id", + "base_model", + "model_id_or_path", + "model_ckpt", + "model_id", + "repo_base", + "repo", + "motion_adapter_id" + ], + "call_methods": [ + ".from_pretrained(", + ".from_single_file(" + ], + "staged_call_methods": [ + ".from_pretrain(" + ] +} \ No newline at end of file diff --git a/mir/spec/modes.json b/data/tag_scrape.json similarity index 99% rename from mir/spec/modes.json rename to data/tag_scrape.json index 24a95e3..9448114 100644 --- a/mir/spec/modes.json +++ b/data/tag_scrape.json @@ -4692,31 +4692,6 @@ "region:us" ] }, - "info.art.bert-uncased.*": { - "pipeline": "fill-mask", - "library": "transformers", - "tags": [ - "transformers", - "pytorch", - "tf", - "jax", - "rust", - "coreml", - "onnx", - "safetensors", - "bert", - "fill-mask", - "exbert", - "en", - "dataset:bookcorpus", - "dataset:wikipedia", - "arxiv:1810.04805", - "license:apache-2.0", - "autotrain_compatible", - "endpoints_compatible", - "region:us" - ] - }, "info.aet.mra-512-4.*": { "pipeline": "fill-mask", "library": "transformers", diff --git a/data/transformers_adds.json b/data/transformers_adds.json new file mode 100644 index 0000000..c26af2d --- /dev/null +++ b/data/transformers_adds.json @@ -0,0 +1,332 @@ +{ + "google-t5/t5-small": { + "T5Model": { + "identifiers": [ + [ + 4096 + ], + "encoder.embed_tokens.weight", + "text_encoders.t5xxl.transformer.shared.weight", + "t5xxl", + "encoder.block.0.layer.1.DenseReluDense.wi.weight" + ], + "file_256": [ + "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", + "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", + "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", + "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", + "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", + "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", + "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", + "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", + "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", + "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", + "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", + "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", + "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", + "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", + "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", + "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", + "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", + "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", + "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", + "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", + "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", + "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", + "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", + "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", + "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", + "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", + "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" + ], + "layer_b3": [ + "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", + "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", + "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", + "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", + "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", + "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", + "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", + "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", + "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", + "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", + "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", + "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", + "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", + "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", + "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", + "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", + "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", + "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", + "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", + "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", + "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", + "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", + "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", + "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", + "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", + "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", + "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", + "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", + "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", + "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" + ], + "layer_256": [ + "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", + "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", + "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", + "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", + "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", + "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", + "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", + "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", + "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", + "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", + "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", + "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", + "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", + "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", + "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", + "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", + "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", + "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", + "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", + "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", + "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", + "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", + "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", + "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", + "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", + "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", + "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", + "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" + ] + } + }, + "google/umt5-small": { + "UMT5Model": { + "identifiers": [ + "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" + ], + "file_256": [ + "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", + "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", + "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", + "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", + "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", + "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", + "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", + "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", + "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", + "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", + "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", + "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", + "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", + "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", + "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", + "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" + ], + "layer_b3": [ + "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", + "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", + "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", + "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", + "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", + "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", + "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", + "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", + "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", + "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", + "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", + "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", + "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", + "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", + "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", + "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", + "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", + "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" + ], + "layer_256": [ + "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", + "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", + "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", + "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", + "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", + "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", + "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", + "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", + "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", + "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", + "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", + "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", + "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", + "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", + "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", + "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", + "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", + "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" + ] + } + }, + "google/gemma2-9b": { + "Gemma2Model": { + "file_256": [ + "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", + "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" + ], + "layer_b3": [ + "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", + "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" + ], + "layer_256": [ + "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", + "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" + ] + } + }, + "google/gemma-7b": { + "GemmaModel": { + "file_256": [ + "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" + ], + "layer_b3": [ + "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", + "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" + ], + "layer_256": [ + "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", + "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" + ] + } + }, + "google/mt5-small": { + "MT5Model": { + "identifiers": [ + [ + 250112, + 2048 + ], + "text_encoders.mt5xl.transformer.shared.weight" + ], + "file_256": [ + "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", + "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" + ], + "layer_b3": [ + "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51", + "bc71d4259f4feaa0fb27c1f288765004840f39247cddc98b3ac37329ff1354d0" + ], + "layer_256": [ + "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", + "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" + ] + } + }, + "Qwen/Qwen3-15B-A2B": { + "Qwen3MoeModel": { + "file_256": [ + "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" + ], + "layer_b3": [ + "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" + ], + "layer_256": [ + "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" + ] + } + }, + "Qwen/Qwen2-VL-7B-Instruct": { + "Qwen2VLTextModel": { + "file_256": [ + "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", + "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", + "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", + "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" + ], + "layer_b3": [ + "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", + "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", + "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", + "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" + ], + "layer_256": [ + "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", + "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", + "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", + "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" + ] + } + }, + "openai/gpt-oss-120b": { + "GptOssModel": { + "file_256": [ + "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", + "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" + ], + "layer_b3": [ + "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", + "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", + "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" + ], + "layer_256": [ + "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", + "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" + ] + } + }, + "microsoft/Phi-4-multimodal-instruct": { + "Phi4MultimodalModel": { + "file_256": [ + "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" + ], + "layer_b3": [ + "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" + ], + "layer_256": [ + "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" + ] + } + }, + "laion/clap-htsat-fused": { + "ClapModel": { + "file_256": [ + "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", + "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" + ], + "layer_b3": [ + "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", + "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" + ], + "layer_256": [ + "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", + "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" + ] + } + }, + "google-bert/bert-base-uncased": { + "BertModel": { + "file_256": [ + "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" + ], + "layer_b3": [ + "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" + ], + "layer_256": [ + "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" + ] + } + }, + "llava-hf/llava-9b": { + "LlavaModel": { + "file_256": [ + "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" + ], + "layer_b3": [ + "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" + ], + "layer_256": [ + "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" + ] + } + } +} \ No newline at end of file diff --git a/mir/__init__.py b/mir/__init__.py index 2942506..c2ad045 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -1,28 +1,18 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # - - -def main(): - import mir.maid - from mir.maid import main as mir_main - - mir_main() - from mir.inspect.tasks import main - - main() - from mir.inspect.tasks import pipe - - pipe() - - import os - import shutil - - try: - os.remove("mir.json") - except FileNotFoundError: - pass - shutil.copy2(os.path.join(os.path.dirname(mir.maid.__file__), "mir.json"), os.path.join(os.getcwd(), "mir.json")) - - -if __name__ == "__main__": - main() +import os + +from mir.json_io import read_json_file +from logging import DEBUG, INFO, Logger + +NFO = Logger(INFO).info +DBUQ = Logger(DEBUG).debug + +ROOT_PATH = os.path.dirname(__file__) +MIR_PATH_NAMED = os.path.join(ROOT_PATH, "mir.json") +BREAKING = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["breaking"] +SEARCH = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["search"] +PARAMETERS = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["parameters"] +SEMANTIC = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["semantic"] +SUFFIX = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["suffix"] +IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] diff --git a/mir/__main__.py b/mir/__main__.py deleted file mode 100644 index ab1a1aa..0000000 --- a/mir/__main__.py +++ /dev/null @@ -1,68 +0,0 @@ -# # # -# # # - - -from mir.maid import MIRDatabase -from mir.inspect.tasks import TaskAnalyzer - - -def main(mir_db: MIRDatabase = None): - """Parse arguments to feed to dict header reader""" - import argparse - import asyncio - from mir.automata import assimilate - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", - usage="mir-tasks", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - if not mir_db: - mir_db = MIRDatabase() - - tasker = TaskAnalyzer() - task_tuple = asyncio.run(tasker.detect_tasks(mir_db)) - - assimilate(mir_db, [task for task in task_tuple]) - - mir_db.write_to_disk() - return mir_db - - -def run_task(): - main() - - -def pipe(mir_db: MIRDatabase = None): - import argparse - import asyncio - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", - usage="mir-pipe", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - from mir.automata import assimilate - - if not mir_db: - mir_db = MIRDatabase() - - tasker = TaskAnalyzer() - pipe_tuple = asyncio.run(tasker.detect_pipes(mir_db)) - assimilate(mir_db, [pipe for pipe in pipe_tuple]) - mir_db.write_to_disk() - return mir_db - - -# if __name__ == "__main__": -# pipe() diff --git a/mir/config/console.py b/mir/config/console.py deleted file mode 100644 index a5ad63a..0000000 --- a/mir/config/console.py +++ /dev/null @@ -1,10 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from logging import DEBUG, INFO, Logger - -nfo_obj = Logger(INFO) -dbuq_obj = Logger(DEBUG) - -nfo = nfo_obj.info -dbuq = dbuq_obj.debug diff --git a/mir/config/constants.py b/mir/config/constants.py deleted file mode 100644 index a572017..0000000 --- a/mir/config/constants.py +++ /dev/null @@ -1,174 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# -import os -from dataclasses import dataclass, field -from typing import Callable, List - -import transformers -from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES -from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES - -from mir.config.json_io import read_json_file -from mir.config.console import nfo - - -def mapped_cls(model_identifier: str): - """Get model class from identifier without calling huggingface_hub.\n - :param model_identifier: Model identifier like "bert-base-uncased" or "gpt2" - :return: Model class (e.g., BertModel, GPT2Model) - """ - code_name = model_identifier.split("/")[-1].split("-")[0].lower() - - model_class_name = MODEL_MAPPING_NAMES.get(code_name, None) - - config_class_name = CONFIG_MAPPING_NAMES.get(code_name) - if config_class_name: - config_class = getattr(transformers, config_class_name, None) - if config_class: - model_class = MODEL_MAPPING.get(config_class, None) - if model_class: - if isinstance(model_class, tuple): - model_class = model_class[0] - return model_class - - normalized = code_name.replace("_", "-") - if normalized != code_name: - if model_class_name := MODEL_MAPPING_NAMES.get(normalized, None): - if isinstance(model_class_name, tuple): - model_class_name = model_class_name[0] - return getattr(transformers, model_class_name, None) - - return None - - -def import_submodules(module_name: str, pkg_name_or_abs_path: str) -> Callable | None: - """Convert two strings into a callable function or property\n - :param module: The name of the module to import - :param library_path: Base package for the module - :return: The callable attribute or property - """ - from importlib import import_module - - module = module_name.strip() - library = pkg_name_or_abs_path.strip() - try: - base_library = import_module(library, module) - except SyntaxError: - base_library = None - nfo(f"Syntax error attempting to import {module_name}") - if module := getattr(base_library, module, None): - return module - else: - nfo("failed to find module {module}") - - -def extract_init_parameters(module: Callable | str, package_name: str | None = None) -> dict[str, list[str]]: - """Pick apart a Diffusers or Transformers pipeline class and find its constituent parts (formerly root_class)\n - :param module: Origin pipeline as a class or as a string - :param library: name of a library to import the class from, only if a string is provided - :return: Dictionary of sub-classes from the `module`""" - - import inspect - - if package_name and isinstance(module, str): - module_obj: Callable = import_submodules(module, package_name) - else: - assert isinstance(module, Callable) - module_obj = module - signature = inspect.signature(module_obj.__init__) - class_names = {} - editable_signature = signature.parameters.copy() - editable_signature.pop("self", None) - editable_signature.pop("kwargs", None) - editable_signature.pop("use_cache", None) - for folder, param in editable_signature.items(): - class_names.setdefault(folder, True) - return class_names - - -@dataclass -class ClassMapEntry: - """Represents a structured entry of the name of the class and its associated attributes.""" - - name: str - model_name: str - model: Callable - config: Callable - config_params: dict[str, list[str]] = field(init=False, default_factory=lambda: {}) - model_params: dict[str, list[str]] | None = None - - def __post_init__(self): - if self.model: - self.model_params = extract_init_parameters(self.model) - if self.config: - self.config_params = extract_init_parameters(self.config) - - -@dataclass -class DocStringEntry: - """Represents a structured entry of package name, file name, and docstring.""" - - package_name: str - file_name: str - doc_string: str - - -class DocParseData: - pipe_class: str - pipe_repo: str - staged_class: str | None = None - staged_repo: str | None = None - - def __init__(self, pipe_class: str, pipe_repo: str, staged_class: str | None = None, staged_repo: str | None = None): - self.pipe_class = pipe_class - self.pipe_repo = pipe_repo - self.staged_class = staged_class - self.staged_repo = staged_repo - - -class DocStringParserConstants: - """Constants used by DocStringParser for parsing docstrings.""" - - pipe_prefixes: List[str] = [ - ">>> motion_adapter = ", - ">>> adapter = ", # if this moves, also change motion_adapter check - ">>> controlnet = ", - ">>> super_res_1_pipe = ", - ">>> pipe_prior = ", - ">>> pipe_prior_redux = ", - ">>> pipe = ", - ">>> pipeline = ", - ">>> blip_diffusion_pipe = ", - ">>> prior_pipe = ", - ">>> gen_pipe = ", - "pipe = ", - ] - repo_variables: List[str] = [ - "controlnet_model", - "controlnet_id", - "base_model", - "model_id_or_path", - "model_ckpt", - "model_id", - "repo_base", - "repo", - "motion_adapter_id", - ] - call_types: List[str] = [".from_pretrained(", ".from_single_file("] - staged_call_types: List[str] = [ - ".from_pretrain(", - ] - - -package_map = { - "diffusers": ("_import_structure", "diffusers.pipelines"), - "transformers": ("MODEL_MAPPING_NAMES", "transformers.models.auto.modeling_auto"), -} -root_path = os.path.join(os.getcwd(), "mir") -versions = read_json_file(os.path.join(root_path, "spec", "versions.json")) -template = read_json_file(os.path.join(root_path, "spec", "template.json")) -MIR_PATH_NAMED = os.path.join(root_path, "mir.json") - -BREAKING_SUFFIX = r".*(?:-)(prior)$|.*(?:-)(diffusers)$|.*[_-](\d{3,4}px|-T2V$|-I2V$)" -PARAMETERS_SUFFIX = r"(\d{1,4}[KkMmBb]|[._-]\d+[\._-]\d+[Bb][._-]).*?$" -SEARCH_SUFFIX = r"\d+[._-]?\d+[BbMmKk](it)?|[._-]\d+[BbMmKk](it)?" diff --git a/mir/config/conversion.py b/mir/config/conversion.py deleted file mode 100644 index beaee14..0000000 --- a/mir/config/conversion.py +++ /dev/null @@ -1,115 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from typing import Callable, Optional, Union, Type, List, Generator, Dict - -from mir.config.console import dbuq, nfo -from mir.config.constants import DocStringEntry, ClassMapEntry, import_submodules - - -def retrieve_diffusers_docstrings( - package_name: str, - file_names: list[str], -) -> Generator[DocStringEntry]: - """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n - :param pkg_name: Package under ``diffusers.pipelines``.\n - :param file_names: A list of related file names.\n - :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n - :return: DocString Entry class.\n - """ - import os - from importlib import import_module - - module_location: str | None = import_module("diffusers.pipelines").__file__ - module_path = os.path.dirname(module_location) - - for file_name in file_names: - assert isinstance(file_name, str) - if file_name == "pipeline_stable_diffusion_xl_inpaint": - continue - - pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" - dbuq(pkg_path) - - if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): - pipe_file = import_submodules(file_name, pkg_path) or import_module(pkg_path) or nfo(f"Failed to import {pkg_path}") - if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): - yield DocStringEntry(package_name=package_name, file_name=file_name, doc_string=doc_string) - else: - nfo(f"Doc string attribute missing for {package_name}/{file_name}") - else: - nfo(f"Path not found for {package_name}/{file_name}") - - return - - -def get_repo_from_class_map(class_map: ClassMapEntry) -> str | None: - """The name of the repository that is associated with a transformers configuration class - :param class_map: Transformers class information extracted from dependency - :returns: A string matching the repo path for the class""" - - import re - - doc_attempt = [] - if hasattr(class_map.config, "forward"): - doc_attempt = [getattr(class_map.config, "forward")] - doc_attempt.append(class_map.config) - for pattern in doc_attempt: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) - if matches: - try: - repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - nfo(f"ERROR >>{matches} : LOG >> {error_log}") - continue - return repo_path - return None - - -def class_to_mir_tag(mir_db: Dict[str, str], code_name: str) -> Optional[str]: - """Converts a class identifier to its corresponding MIR tag.\n - :param mir_db: A dictionary mapping series-compatibility pairs to their respective data. - :param code_name: The Transformers class identifier to convert. - :return: An optional list containing the series and compatibility if found, otherwise None.""" - from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - from mir.config.constants import template - - template_data = template["arch"]["transformer"] - - for series, compatibility_data in mir_db.database.items(): - if any([template for template in template_data if template in series.split(".")[1]]): - for compatibility, field_data in compatibility_data.items(): - if code_name == series.split(".")[2]: - return [series, compatibility] - - class_name = MODEL_MAPPING_NAMES.get(code_name, False) - if not class_name: # second pass without separators - recoded_mapping = {code.replace("-", "").replace("_", ""): model for code, model in MODEL_MAPPING_NAMES.items()} - class_name = recoded_mapping.get(code_name, False) - if not class_name: - return None - pkg_data = field_data.get("pkg") - if pkg_data: - for _, pkg_type_data in pkg_data.items(): - maybe_class = pkg_type_data.get("transformers") - if maybe_class == class_name: - return [series, compatibility] - return None - - -def slice_number(text: str) -> Union[int, float, str]: - """Separate a numeral value appended to a string\n - :return: Converted value as int or float, or unmodified string - """ - for index, char in enumerate(text): # Traverse forwards - if char.isdigit(): - numbers = text[index:] - if "." in numbers: - return float(numbers) - try: - return int(numbers) - except ValueError: - return numbers - return text diff --git a/mir/generate/.notes.txt b/mir/generate/.notes.txt new file mode 100644 index 0000000..e133139 --- /dev/null +++ b/mir/generate/.notes.txt @@ -0,0 +1,66 @@ +# type: ignore +# ruff: noqa + +tag_model_from_repo + +mir_tag_from_config +import_submodules + + +constants +tag_scheduler +read_json_file +mir_prefix_from_forward_pass + +Set Data Format +Find classes +get_repo_from_class_map +check repo/model migration + +transformers_index + classmapentry + + find_transformers_classes + +check_migrations + get_repo_from_class_map + mir_tag_from_config + check_migrations + import_submodules tokenizers + + +diffusers_index + docstringentry + find_diffusers_classes + check_migrations + retrieve_diffusers_docstrings + import_submodules module for model class + import_submodules model class + extract_init_parameters + create_pipe_entry + extract_init_parameters + mir_prefix_from_forward_pass + tag_model_from_repo + check_migrations + +add_mir_dtype + + tag_dtype + MIRDatabase + +add_mir_schedulers + tag_scheduler + + +task_analysis + import_submodules + mapped_cls + import_submodules + tag_scheduler + resolve_code_names + + +# def create_model_tag(model_header,metadata_dict): +# parse_file = parse_model_header(model_header) +# reconstructed_file_path = os.path.join(disk_path,each_file) +# attribute_dict = metadata_dict | {"disk_path": reconstructed_file_path} +# file_metadata = parse_file | attribute_dict +# index_tag = create_model_tag(file_metadata) +# \ No newline at end of file diff --git a/mir/config/__init__.py b/mir/generate/__init__.py similarity index 100% rename from mir/config/__init__.py rename to mir/generate/__init__.py diff --git a/mir/generate/__main__.py b/mir/generate/__main__.py new file mode 100644 index 0000000..8a1e85b --- /dev/null +++ b/mir/generate/__main__.py @@ -0,0 +1,276 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import os +from mir.maid import MIRDatabase +from mir.generate.tasks import TaskAnalyzer +from typing import Callable + + +def run_task() -> None: + main() + + +def pipe(mir_db: MIRDatabase) -> MIRDatabase: + import argparse + import asyncio + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", + usage="mir-pipe", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + from mir.generate.automata import assimilate + + if not mir_db: + mir_db = MIRDatabase() + + tasker = TaskAnalyzer() + pipe_tuple = asyncio.run(tasker.detect_pipes(mir_db)) + assimilate(mir_db, [pipe for pipe in pipe_tuple]) + mir_db.write_to_disk() + return mir_db + + +# if __name__ == "__main__": +# pipe() + + +def main(): + # import ordered to prevent file lock + import mir.maid + from mir.maid import main as mir_main + + mir_main() + from mir.generate.tasks import main + + main() + from mir.generate.tasks import pipe + + pipe() + + import os + import shutil + + try: + os.remove("mir.json") + except FileNotFoundError: + pass + shutil.copy2(os.path.join(os.path.dirname(mir.maid.__file__), "mir.json"), os.path.join(os.getcwd(), "mir.json")) + + +if __name__ == "__main__": + main() + + +def main(mir_db: MIRDatabase | None = None) -> MIRDatabase: + """Parse arguments to feed to dict header reader""" + import argparse + import asyncio + from mir.generate.automata import assimilate + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", + usage="mir-tasks", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + if not mir_db: + mir_db = MIRDatabase() + + tasker = TaskAnalyzer() + task_tuple = asyncio.run(tasker.detect_tasks(mir_db)) + + assimilate(mir_db, [task for task in task_tuple]) + + mir_db.write_to_disk() + return mir_db + + +def main(mir_db: Callable | None = None, remake: bool = True) -> None: + """Build the database""" + from sys import modules as sys_modules + + if __name__ != "__main__" and "pytest" not in sys_modules: # + import argparse + + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", + usage="mir-maid", + epilog="""Does NOT include results of `mir-task` and `mir-pipe`. These commands should be run separately. Output: + 2025-08-03 14:22:47 INFO ('Wrote 0 lines to MIR database file.',) + 2025-08-03 14:22:47 INFO ('Wrote #### lines to MIR database file.',)""", + ) + parser.add_argument( + "-r", + "--remake_off", + action="store_true", + default=False, + help="Prevent erasing and remaking the MIR database file (default: False, always start from a completely empty MIR file)", + ) + + args = parser.parse_args() + remake = not args.remake_off + + from mir.generate.automata import ( + add_mir_audio, + add_mir_diffusion, + add_mir_dtype, + add_mir_llm, + add_mir_lora, + add_mir_schedulers, + add_mir_vae, + hf_pkg_to_mir, + mir_update, + ) + from mir.json_io import write_json_file + + if remake: + os.remove(MIR_PATH_NAMED) + folder_path_named = os.path.dirname(MIR_PATH_NAMED) + mode = "x" + else: + mode = "w" + write_json_file(folder_path_named, file_name="mir.json", data={"expected": "data"}, mode=mode) + mir_db = MIRDatabase() + mir_db.database.pop("expected", {}) + hf_pkg_to_mir(mir_db) + add_mir_dtype(mir_db) + add_mir_schedulers(mir_db) + add_mir_lora(mir_db) + add_mir_audio(mir_db) + add_mir_diffusion(mir_db) + add_mir_llm(mir_db) + add_mir_vae(mir_db) + mir_db.write_to_disk() + mir_db = MIRDatabase() + mir_db = MIRDatabase() + mir_update(mir_db) + mir_db.write_to_disk() + + +if __name__ == "__main__": + remake: bool = True + tasks = True + pipes = True + + from sys import modules as sys_modules + + if "pytest" not in sys_modules: # + import argparse + + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", + usage="python -m nnll.mir.maid", + epilog="""Includes `mir-task` and `mir-pipe` by default. Output: + 2025-08-15 19:41:18 INFO ('Wrote 0 lines to MIR database file.',) + 2025-08-15 19:38:48 INFO ('Wrote ### lines to MIR database file.',) + INFO ('Wrote ### lines to MIR database file.',) + INFO ('Wrote ### lines to MIR database file.',)""", + ) + parser.add_argument( + "-r", + "--remake_off", + action="store_true", + default=False, + help="Don't erase and remake the MIR database (default: False)", + ) + parser.add_argument( + "-t", + "--tasks_off", + action="store_true", + default=False, + help="Don't append task information to the MIR database (default: False)", + ) + parser.add_argument( + "-p", + "--pipes_off", + action="store_true", + default=False, + help="Don't append pipeline information to the MIR database (default: False)", + ) + + args = parser.parse_args() + remake = not args.remake_off + tasks = not args.tasks_off + pipes = not args.pipes_off + + main(remake=remake) + + from mir.generate.tasks import pipe, run_task + + mir_db = run_task() + pipe(mir_db) + + +def main(mir_db: MIRDatabase = None): + """Parse arguments to feed to dict header reader""" + import argparse + import asyncio + from mir.automata import assimilate + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", + usage="mir-tasks", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + if not mir_db: + mir_db = MIRDatabase() + + auto_pkg = TaskAnalyzer() + task_tuple = asyncio.run(auto_pkg.detect_tasks(mir_db)) + + assimilate(mir_db, [task for task in task_tuple]) + + mir_db.write_to_disk() + return mir_db + + +def run_task(): + main() + + +def pipe(mir_db: MIRDatabase = None): + import argparse + import asyncio + from sys import modules as sys_modules + + if "pytest" not in sys_modules: + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", + usage="mir-pipe", + epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", + ) + parser.parse_args() + + from mir.automata import assimilate + + if not mir_db: + mir_db = MIRDatabase() + + auto_pkg = TaskAnalyzer() + pipe_tuple = asyncio.run(auto_pkg.detect_pipes(mir_db)) + assimilate(mir_db, [pipe for pipe in pipe_tuple]) + mir_db.write_to_disk() + return mir_db + + +if __name__ == "__main__": + pipe() diff --git a/mir/generate/_extras.py b/mir/generate/_extras.py new file mode 100644 index 0000000..c1b0366 --- /dev/null +++ b/mir/generate/_extras.py @@ -0,0 +1,191 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Callable, Dict, List, Optional, Union + +from mir import NFO +from mir.generate.from_module import import_object_named, show_path_for +from mir.generate.tasks import TaskAnalyzer + + +def _class_parent(code_name: str, pkg_name: str) -> Optional[List[str]]: + """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n + ### NOTE: in most cases `__module__` makes this redundant + :param code_name: The internal name for the model in the third-party API. + :param pkg_name: The API Package + :return: A list corresponding to the path of the model, or None if not found + :raises KeyError: for invalid pkg_name + """ + import os + from importlib import import_module + + pkg_paths = { + "diffusers": "pipelines", + "transformers": "models", + } + folder_name = code_name.replace("-", "_") + pkg_name = pkg_name.lower() + folder_path = pkg_paths[pkg_name] + package_obj = import_module(pkg_name) + folder_path_named = [folder_path, folder_name] + pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) + # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) + if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: + import_path = [pkg_name] + import_path.extend(folder_path_named) + return import_path + + +def _extract_inherited_classes(model_class: Union[Callable, str], pkg_name: Optional[str] = None) -> Optional[Dict[str, List[str]]]: + """Strips tags from module's base classes and extracts inherited class members.\n + If `module` is a string, it requires the `library` argument to convert it into a callable.\n + :param module: A module or string representing a module. + :param library: Library name required if `module` is a string. Defaults to None. + :returns: Mapping indices to class path segments, or None if invalid input.""" + + if isinstance(model_class, str): + if not pkg_name: + NFO("Provide a library type argument to process strings") + return None + model_class = import_object_named(model_class, pkg_name) + signature = model_class.__bases__ + class_names = [] + for index, class_annotation in enumerate(signature): + tag_stripped = str(class_annotation)[8:-2] + module_segments = tag_stripped.split(".") + class_names.append(module_segments) + return class_names + + +def _trace_classes(pipe_class: str, pkg_name: str) -> Dict[str, List[str]]: + """Retrieve all compatible pipe forms\n + NOTE: Mainly for Diffusers + :param pipe_class: Origin pipe + :param pkg_name: Dependency package + :return: A dictionary of pipelines""" + + related_pipes = [] + code_name = show_path_for(pipe_class, pkg_name) + if pkg_name == "diffusers": + related_pipe_class_name = pipe_class + else: + related_pipe_class_name = None + related_pipes: list[str] = TaskAnalyzer.show_diffusers_tasks(code_name=code_name, class_name=related_pipe_class_name) + # for i in range(len(auto_tasks)): + # auto_tasks.setdefault(i, revealed_tasks[i]) + parent_folder = class_parent(code_name, pkg_name) + if pkg_name == "diffusers": + pkg_folder = import_object_named(parent_folder[0], ".".join(parent_folder)) + else: + pkg_folder = import_object_named("__init__", ".".join(parent_folder[:-1])) + if hasattr(pkg_folder, "_import_structure"): + related_pipes.extend(next(iter(x)) for x in pkg_folder._import_structure.values()) + related_pipes = set(related_pipes) + related_pipes.update(tuple(x) for x in _extract_inherited_classes(model_class=pipe_class, pkg_name=pkg_name)) + return related_pipes + + +def _show_shared_hyperparameters(parameter_filter: Optional[str] = None) -> List[str]: + """Show all config classes in the Transformer package with the specified init annotation\n + :param from_match: Narrow the classes to only those with an exact key inside + :return: A list of all Classes""" + from mir.config.constants import extract_init_parameters + from mir.inspect.metadata import find_transformers_classes + + transformers_data = find_transformers_classes() + config_data = [] + for entry in transformers_data: + if parameter_filter: + segments = extract_init_parameters(module=entry.config, package_name="transformers") + if parameter_filter in list(segments): + config_data.append(entry.config) + else: + config_data.append(entry.config) + return config_data + + +def _get_class_parent_folder(class_name: str, pkg_name: str) -> List[str]: + """Retrieve the folder path within a class. Only returns if it is a valid path in the system (formerly seek_class_path)\n + ### NOTE: in most cases `__module__` makes this redundant + :param class_name: The internal name for the model in the third-party API. + :param pkg_name: The API Package + :return: A list corresponding to the path of the model, or None if not found + :raises KeyError: for invalid pkg_name + """ + from mir.config.console import dbuq + from mir.config.constants import extract_init_parameters + from mir.inspect.classes import resolve_code_names + + pkg_name = pkg_name.lower() + if pkg_name == "diffusers": + parent_folder: List[str] = resolve_code_names(class_name=class_name, pkg_name=pkg_name, path_format=True) + if not parent_folder or not parent_folder[-1].strip(): + dbuq("Data not found for", " class_name = {class_name},pkg_name = {pkg_name},{parent_folder} = parent_folder") + return None + elif pkg_name == "transformers": + print(class_name) + module_path = extract_init_parameters(class_name, "transformers") + print(module_path) + config = str(module_path.get("config")) + print(config) + config = config.split(": ")[-1].split(".") + parent_folder = config[:3] + return parent_folder + + +def _class_to_mir_tag(mir_db: Dict[str, str], code_name: str) -> Optional[str]: + """Converts a class identifier to its corresponding MIR tag.\n + :param mir_db: A dictionary mapping series-compatibility pairs to their respective data. + :param code_name: The Transformers class identifier to convert. + :return: An optional list containing the series and compatibility if found, otherwise None.""" + + from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES + + from mir.config.constants import TEMPLATE + + template_data = TEMPLATE["arch"]["transformer"] + + for series, compatibility_data in mir_db.database.items(): + if any([template for template in template_data if template in series.split(".")[1]]): + for compatibility, field_data in compatibility_data.items(): + if code_name == series.split(".")[2]: + return [series, compatibility] + + class_name = MODEL_MAPPING_NAMES.get(code_name, False) + if not class_name: # second pass without separators + recoded_mapping = {code.replace("-", "").replace("_", ""): model for code, model in MODEL_MAPPING_NAMES.items()} + class_name = recoded_mapping.get(code_name, False) + if not class_name: + return None + pkg_data = field_data.get("pkg") + if pkg_data: + for _, pkg_type_data in pkg_data.items(): + maybe_class = pkg_type_data.get("transformers") + if maybe_class == class_name: + return [series, compatibility] + return None + + +def tag_transformers_model(repo_path: str, class_name: str, addendum: dict | None = None) -> tuple[str, str, str | dict[str, dict]]: + """Convert model repo paths to MIR tags, classifying by feature\n + :param name: Repo path + :param class_name: The HF transformers class for the model + :return: A segmented MIR tag useful for appending index entries""" + + from mir.config.constants import extract_init_parameters + + annotations = extract_init_parameters(class_name.replace("Model", "Config"), "transformers") + if not annotations: + class_name = class_name.replace("Config", "Model") + annotations = extract_init_parameters(class_name, "transformers") + if not annotations: + raise TypeError("No mode type returned") + if "Bert" in class_name: + print(annotations) + mir_prefix = mir_prefix_from_forward_pass(True, **annotations) + base_series, base_comp = tag_model_from_repo(repo_path) + if not addendum: + return mir_prefix, base_series, base_comp + else: + mir_prefix = f"info.{mir_prefix}" + return mir_prefix, base_series, {base_comp: addendum} diff --git a/mir/automata.py b/mir/generate/automata.py similarity index 54% rename from mir/automata.py rename to mir/generate/automata.py index 227f4ab..da548b5 100644 --- a/mir/automata.py +++ b/mir/generate/automata.py @@ -9,13 +9,10 @@ from importlib import import_module import re -from typing import Dict, List, Tuple +from typing import Dict, List, Tuple, Any -from diffusers import _import_structure import torch -from mir.config.console import dbuq, nfo -from mir.config.conversion import slice_number from mir.indexers import diffusers_index, transformers_index from mir.maid import MIRDatabase from mir.spec import mir_entry @@ -30,88 +27,8 @@ vega_series, vega_comp = tag_model_from_repo("segmind/Segmind-Vega") sd3_series, sd3_comp = tag_model_from_repo("stable-diffusion-3.5-medium") # -# def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet -# from diffusers.models.attention_processor import AttentionProcessor -# mir_data -# for series, comp_name in mir_data.items(): -# id_segment = series.split(".") -# for compatibility in comp_name: -# dbug(id_segment) -# try: -# mir_db.add( -# mir_entry( -# domain=id_segment[0], -# arch=id_segment[1], -# series=id_segment[2], -# comp=compatibility, -# **mir_data[series][compatibility], -# ), -# ) -# except IndexError as error_log: -# nfo(f"Failed to create series: {series} compatibility: {comp_name} ") -# dbug(error_log) - - -# def gen_guiders(mir_db: MIRDatabase): # upstream not quite ready for this yet -# from nnll.metadata.helpers import snake_caseify -# from diffusers.guider import GuiderType - -# guider_type = GuiderType -# for comp_name in guider_type.items(): -# class_obj = comp_name.__name__ -# mir_data = {"pkg": {0: {"diffusers": class_obj}}} -# try: -# mir_db.add( -# mir_entry( -# domain="ops", -# arch="noise_prediction", -# series="guider", -# comp=snake_caseify(class_obj), -# **mir_data, -# ), -# ) -# except IndexError as error_log: -# nfo(f"Failed to create compatibility: {class_obj}") -# dbug(error_log) - - -# ( -# "info.unet", -# "stable-cascade", -# { -# "combined": { -# "pkg": { -# 0: { # decoder=decoder_unet -# "precision": "ops.precision.bfloat.B16", -# "generation": { -# "negative_prompt": "", -# "num_inference_steps": 20, -# "guidance_scale": 4.0, -# "num_images_per_prompt": 1, -# "width": 1024, -# "height": 1024, -# }, -# }, -# "pkg_alt": { -# 0: { -# "diffusers": { -# "StableCascadeCombinedPipeline": { -# "negative_prompt": "", -# "num_inference_steps": 10, -# "prior_num_inference_steps": 20, -# "prior_guidance_scale": 3.0, -# } -# }, -# } -# }, -# } -# } -# }, -# ), - - -def assimilate(mir_db: MIRDatabase, data_tuple: List[Tuple[Dict[str, any]]]) -> None: +def assimilate(mir_db: MIRDatabase, data_tuple: List[Tuple[Dict[str, Any]]]) -> None: """Merge new data into a pre-generated MIR database, updating while preserving existing data structures.\n :param mir_db: The MIRDatabase instance :param data_tuple: A list of tuples, each containing:\n @@ -153,105 +70,6 @@ def update_nested_dict(target, source): update_nested_dict(mir_data[comp][field][definition], sub_def_data) -def hf_pkg_to_mir(mir_db: MIRDatabase): - """Generate MIR HF Hub model database""" - mir_data = diffusers_index() | transformers_index() - for series, comp_name in mir_data.items(): - id_segment = series.split(".") - for compatibility in comp_name: - # dbug(id_segment) - try: - mir_db.add( - mir_entry( - domain=id_segment[0], - arch=id_segment[1], - series=id_segment[2], - comp=compatibility, - **mir_data[series][compatibility], - ), - ) - except IndexError: # as error_log: - nfo(f"Failed to create series: {series} compatibility: {comp_name} ") - # dbug(error_log) - - -def add_mir_dtype(mir_db: MIRDatabase): - """Create mir info database""" - - available_dtypes: List[str] = [dtype for dtype in torch.__dict__.values() if isinstance(dtype, torch.dtype)] - series_name = "_" - for precision in available_dtypes: - dep_name, class_name = str(precision).split(".") - if "_" in class_name: - comp_name = class_name[0].upper() + "8_" + class_name.split("_")[1].upper() - if comp_name.endswith("FN"): - comp_name = comp_name[:-2] - else: - comp_name = class_name[0].upper() + str(slice_number(class_name)) - variant_name = class_name.replace("bfloat", "bf").replace("float", "fp") - dbuq(variant_name) - patterns = [r"complex", r"bits", r"quint", r"uint", r"int", r"bfloat", r"float", r"bool"] - for precision_name in patterns: - compiled = re.compile(precision_name) - dtype = re.search(compiled, class_name) - if dtype: - series_name = dtype.group() - break - - mir_db.add( - mir_entry( - domain="ops", - arch="precision", - series=series_name, - comp=comp_name, - pkg={0: {dep_name.lower(): {class_name.lower(): {"variant": variant_name}}}}, - ) - ) - - -def add_mir_schedulers(mir_db: MIRDatabase): - """Create mir info database""" - - for class_name in _import_structure["schedulers"]: - if class_name != "SchedulerMixin": - series_name, comp_name = tag_scheduler(class_name) - class_obj = import_module("diffusers.schedulers") - class_path = getattr(class_obj, class_name).__module__ - mir_db.add( - mir_entry( - domain="ops", - arch="scheduler", - series=series_name, - comp=comp_name.lower(), - pkg={ - 0: { - "diffusers": class_name, - "module_path": class_path, - }, - }, - ) - ) - - class_name = "KarrasDiffusionSchedulers" - series_name, comp_name = tag_scheduler(class_name) - class_obj = import_module("diffusers.schedulers.scheduling_utils") - class_path = getattr(class_obj, class_name).__module__ - mir_db.add( - mir_entry( - domain="ops", - arch="scheduler", - series=series_name, - comp=comp_name, - pkg={ - 0: { - "diffusers": class_name, - "module_path": class_path, - }, - }, - ), - ) - - # def auto_gan etc etc # ai-forever/Real-ESRGAN @@ -259,1192 +77,6 @@ def add_mir_schedulers(mir_db: MIRDatabase): def mir_update(mir_db: MIRDatabase, task_list: list = None, pipe_list: list = None): """Create mir unet info database""" - diffusers_addons = [ - ( - "stabilityai/stable-diffusion-xl-base-1.0", - "StableDiffusionXLPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": { - "denoising_end": 0.8, - "num_inference_steps": 40, - "output_type": "latent", - "safety_checker": False, - "width": 1024, - "height": 1024, - }, - }, - 1: {"diffusers": "DiffusionPipeline"}, - }, - "file_256": [ - "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", # diffusers - "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", # fp16 diffusers - "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", # modelspec sai - "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf", # onnx - ], - "layer_256": [ - "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", # any modelspec sai - "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", # diffusers - "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da", # diffusers fp16 - ], - "layer_b3": [ - "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", # any modelspec sai - "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", # diffusers - "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b", # diffusers fp16 - ], - "identifiers": ["logit_scale", "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", "add_embedding.linear_2.bias"], - }, - ), - ( - "stabilityai/stable-diffusion-xl-refiner-1.0", - "StableDiffusionXLImg2ImgPipeline", - { - "pkg": { - 1: { - "diffusers": "DiffusionPipeline", - "generation": {"num_inference_steps": 40, "denoising_end": 0.8}, - } - }, - "identifiers": ["conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias"], - "file_256": [ - "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", # diffusers - "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", # modelspec sai - "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe", # fp16 diffusers - ], - "layer_b3": [ - "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", - "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", - "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683", - ], - "layer_256": [ - "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", - "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", - "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6", - ], - }, - ), - ( - "lodestones/Chroma", - "ChromaPipeline", - { - "pkg": { - 1: { - "generation": {"neg_text": "", "num_steps": "28", "latent_size": [64, 64]}, - } - }, - "file_256": [ - "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", # v1 - "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", # v46, - "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", # v37 detail - "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8", # mlx chroma / v36 detail - ], - "layer_b3": [ - "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479", - ], - "layer_256": ["a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882"], - }, - ), - ( - "fal/AuraFlow", - "AuraFlowPipeline", - { - "identifiers": [[8192, 3072], "mlpX.c_fc2.weight", "joint_transformer_blocks.2.ff_context.linear_2.weight"], - "file_256": [ - "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", - "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", # sai - "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", # diffusers fp16 - "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb", # diffusers - ], - "layer_b3": [ - "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", - "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", # sai - "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", - "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d", - ], - "layer_256": [ - "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", - "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", - "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", - "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5", - ], - }, - ), - ( - "Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers", - "HunyuanDiTPipeline", - { - "identifiers": ["extra_embedder", "model.blocks", "skip_norm.weight"], - "file_256": [ - "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", # normal - "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", # distilled - "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d", # 1.2 - ], - "layer_b3": [ - "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", - "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", # distilled - "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700", - ], - "layer_256": [ - "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", - "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", # distilled - "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c", # 1.2 - ], - }, - ), - ( - "Alpha-VLLM/Lumina-Next-SFT-diffusers", - "LuminaPipeline", - { - "pkg": { - 0: { - "precision": " ops.precision.bfloat.B16", - }, - }, - "identifiers": ["time_caption", "feed_forward"], - "file_256": [ - "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd", - ], - "layer_b3": [ - "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", - "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839", - ], - "layer_256": [ - "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", - "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0", - ], - }, - ), - ( - "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", - "PixArtSigmaPipeline", - { - "identifiers": ["adaln_single", "scale_shift_table"], - "file_256": [ - "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", - "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239", - ], - "layer_b3": [ - "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", - "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3", - ], - "layer_256": [ - "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", - "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c", - ], - }, - ), - ( - "PixArt-alpha/PixArt-XL-2-1024-MS", - "PixArtAlphaPipeline", - { - "identifiers": ["aspect_ratio", "y_embedding", "emb.resolution", "caption_projection"], - "file_256": ["809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8"], - "layer_b3": ["c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee"], - "layer_256": ["117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5"], - }, - ), - ( - "stabilityai/stable-diffusion-3.5-medium", - "StableDiffusion3Pipeline", - { - "pkg": { - 0: {"precision": "ops.precision.float.F16"}, - }, - "identifiers": [ - "model.diffusion_model.joint_blocks.", - "transformer_blocks.21.norm1_context.linear.weight", - "transformer_blocks.31.norm1_context.linear.weight", - "blocks.11.ff.net.2.weight", - ], - "file_256": [ - "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", # large - "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de", # medium - ], - "layer_b3": [ - "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", - "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746", # med - ], - "layer_256": [ - "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", - "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463", # med - ], - }, - ), - ( - "Efficient-Large-Model/Sana-1600M-1024px-BF16-diffusers", - "SanaPipeline", - { - "pkg": { - 0: { - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 4.5, - "num_inference_steps": 20, - }, - "precision": "ops.precision.bfloat.B16", - }, - }, - "file_256": [ - "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe", - ], - "layer_b3": [ - "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd", - ], - "layer_256": [ - "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e", - ], - }, - ), - ( - "stable-diffusion-v1-5/stable-diffusion-v1-5", - "StableDiffusionPipeline", - { - "identifiers": ["up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight"], - "file_256": [ - "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", # pruned ema only original safetensors - "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", # pruned original safetensors - "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", # ema pruned original ckpt - "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", # pruned ema original ckpt - "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", # diffusers safetensors - "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", # diffusers non ema safetensors - "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21", # diffusers fp16 - ], - "layer_b3": [ - "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", # ckpt - "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", # safetensors ema pruned - "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", # safetensors pruned - "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", # diffusers - "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c", # diffusers fp16 - ], - "layer_256": [ - "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", - "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", # st - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", # ckpt - "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb", # st fp16 - ], - }, - ), - ( - "stabilityai/stable-cascade-prior", - "StableCascadePriorPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": { - "negative_prompt": "", - "num_images_per_prompt": 1, - "num_inference_steps": 20, - "guidance_scale": 4.0, - "width": 1024, - "height": 1024, - }, - } - }, - "file_256": [ - "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", # lite bf16 - "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", # pretrained - "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", # stage c modelspec sai - "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", # stage c - "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", # stage c lite - "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099", # bf16 - ], - "layer_b3": [ - "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", - "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", - "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", - "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", - "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", - "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f", - ], - "layer_256": [ - "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", - "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", - "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", - "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", - "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", - "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb", - ], - "identifiers": ["down_blocks.0.2.kv_mapper", "previewer", "backbone"], - }, - ), - ( - "black-forest-labs/FLUX.1-dev", - "FluxPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 3.5, - "num_inference_steps": 50, - "max_sequence_length": 512, - }, - }, - 1: { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "gudance": 3.5, - "num_inference_steps": 25, - }, - }, - }, - "file_256": [ - "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", # krea sai - "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", # krea diffusers - "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", # modelspec sai - "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", # diffusers - "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d", # qwen2 - ], - "layer_b3": [ - "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", - "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", # modelspec sai - "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb", # diffusers - ], - "layer_256": [ - "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", - "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", # diffusers - "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881", # modelspec sai - ], - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight", - ], - }, - ), - ( - "black-forest-labs/FLUX.1-schnell", - "FluxPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 0.0, - "num_inference_steps": 4, - "max_sequence_length": 256, - }, - }, - 1: { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "num_inference_steps": 4, - }, - }, - }, - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight", - ], - "file_256": [ - "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", # sai modelspec - "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820", # diffusers - ], - "layer_b3": [ - "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", - "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", # sai modelspec - "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790", # diffusers - ], - "layer_256": [ - "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", - "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", # sai modelspec - "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649", # diffusers - ], - }, - ), - ( - "stabilityai/stable-cascade", - "StableCascadeDecoderPipeline", - { - "pkg": { # prior=prior_unet - 0: { - "generation": { # image_embeddings=prior_output.image_embeddings, - "negative_prompt": "", - "guidance_scale": 0.0, - "output_type": "pil", - "num_inference_steps": 10, - }, - "precision": "ops.precision.bfloat.B16", - }, - }, - "file_256": [ - "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", # lite bf16 - "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", # bf16 - "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", # b modelspec sai - "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", # lite - "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43", # b - ], - "layer_b3": [ - "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", - "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", - "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", - "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", - "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96", - ], - "layer_256": [ - "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", - "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", - "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", - "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", - "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733", - ], - "identifiers": ["0.2.channelwise", "clip_mapper.bias", ".12.self_attn.k_proj.weight"], - }, - ), - ( - "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", - "WanImageToVideoPipeline", - { - "file_256": [ - "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", # 480 diffusers - "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", # 720 fp8 scaled sai - "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", # 720 fp8 sai - "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", # 720 fp16 sai - "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", # 720 bf16 sai - "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", # 480 fp8e4m scaled sai - "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", # 480 fp8 scaled - "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", # 480 bf16 sai - "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253", # 480 fp16 sai - ], - "layer_b3": [ - "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", - "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", # fp8 scaled - "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", # fp8 - "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", # fp16 - "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6", # bf16 - ], - "layer_256": [ - "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", - "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", # fp8 scaled - "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", - "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", - "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5", - ], - }, - ), - ( - "Qwen/Qwen-Image", - "QwenImagePipeline", - { - "file_256": [ - "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd", - ], - "layer_b3": [ - "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150", # diffusers - ], - "layer_256": [ - "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9", # diffusers - ], - }, - ), - ( - "Wan-AI/Wan2.1-VACE-1.3B-diffusers", - "WanVACEPipeline", - { - "file_256": [ - "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", # diffusers 14 - "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", # diffusers 1.3 - "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", # 14 fp16 sai - "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", # 1.3 preview fp16 sai - "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2", # 1.3 fp16 sai - ], - "layer_b3": [ - "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", # diffusers 14 - "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", # diffusers 1.3 - "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", # 14 fp16 sai - "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac", # 1.3 fp16 sai - ], - "layer_256": [ - "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", # diffusers 14 - "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", # diffusers 1.3 - "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", # 14 fp16 sai - "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0", # 1.3 fp16 sai - ], - }, - ), - ( - "Wan-AI/Wan2.1-T2V-14B-Diffusers", - "WanPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0, - }, - }, - }, - "file_256": [ - "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", # diffusers - "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", # diffusers 2 - "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", # fp16 sai 1.3 - "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", # bf16 sai 1.3 - "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", # fp8 scaled sai - "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", # fp8 sai - "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", # fp16 sai - "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8", # bf16 sai - ], - "layer_b3": [ - "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", # diff - "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", # fp16 sai 1.3 - "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", # bf16 sai - "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", # fp8 scaled sai - "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", # fp8 sai - "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", # fp16 sai - "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66", - ], - "layer_256": [ - "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", - "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", - "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", - "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", - "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", - "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", - "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d", - ], - }, - ), - ( - "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", - "WanVideoToVideoPipeline", - { - "pkg": { - 0: { - "diffusers": "WanPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": {"height": 480, "width": 832, "num_frames": 81, "guidance_scale": 5.0}, - }, - } - }, - ), - ( - "nvidia/cosmos-predict2-text2image", - "Cosmos2TextToImagePipeline", - { - "file_256": [ - "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", # gguf - "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", - "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", - "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", - "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", - "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", - "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", - "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", - "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", - "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", - "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", - "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", - "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c", - ], - "layer_b3": [ - "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", # gguf - "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", - "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", - "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", - "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", - "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", - "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", - "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", - "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", - "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", - "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", - "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", - "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d", - ], - "layer_256": [ - "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", # gguf - "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", - "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", - "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", - "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", - "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", - "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", - "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", - "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", - "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", - "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", - "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", - "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5", - ], - }, - ), - ( - "rhymes-ai/Allegro", - "AllegroPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": { - "guidance_scale": 7.5, - "max_sequence_length": 512, - "num_inference_steps": 100, - }, - }, - }, - "file_256": ["6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7"], - "layer_b3": ["8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e"], - "layer_256": ["9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd"], - }, - ), - ( - "audioldm-s-v2", - "AudioLDMPipeline", - { - "file_256": ["fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a"], - "layer_b3": ["82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a"], - "layer_256": ["d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8"], - }, - ), - ( - "zai-org/CogVideoX-2b", - "CogVideoXPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": {"num_videos_per_prompt": 1, "num_inference_steps": 50, "num_frames": 49, "guidance_scale": 6}, - } - }, - "file_256": ["8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7"], - "layer_b3": ["1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb"], - "layer_256": ["edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd"], - }, - ), - ( - "HiDream-ai/HiDream-I1-Full", - "StableDiffusion3Pipeline", - { - "file_256": ["3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26"], - "layer_b3": ["612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6"], - "layer_256": ["78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df"], - }, - ), - ( - "cvssp/audioldm2", - "AudioLDM2Pipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": {"num_inference_steps": 200, "audio_length_in_s": 10.0}, - }, - }, - "file_256": ["359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2"], - "layer_b3": ["eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962"], - "layer_256": ["ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb"], - }, - ), - ( - "Alpha-VLLM/Lumina-Image-2.0", - "Lumina2Pipeline", - { - "pkg": {}, - "file_256": [ - "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", - "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d", # pth single file - ], - "layer_b3": [ - "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - ], - "layer_256": [ - "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", - ], - }, - ), - ( - "ucsd-reach/musicldm", - "MusicLDMPipeline", - { - "pkg": { - 0: { - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0, - }, - } - }, - "file_256": [ - "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f", # - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" # - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8", # - ], - }, - ), - ( - "openai/shap-e", - "ShapEPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": {"num_inference_steps": 64, "size": 256, "guidance_scale": 15}, - } - }, - }, - ), - ( - "hunyuanvideo-community/HunyuanVideo", - "HunyuanVideoPipeline", - { - "file_256": [ - "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7", # - ], - "layer_b3": [ - "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" # - ], - "layer_256": [ - "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4", # - ], - }, - ), - ( - "zai-org/CogView3-Plus-3B", - "CogView3PlusPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": { - "guidance_scale": 7.0, - "num_images_per_prompt": 1, - "num_inference_steps": 50, - "width": 1024, - "height": 1024, - }, - }, - }, - }, - ), - ( - "stabilityai/stable-audio-open-1.0", - "StableAudioPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_end_in_s": 10, - "num_waveforms_per_prompt": 3, - }, - } - } - }, - ), - ( - "Kwai-Kolors/Kolors-diffusers", - "KolorsPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - "generation": { - "negative_prompt": "", - "guidance_scale": 5.0, - "num_inference_steps": 50, - "width": 1024, - "height": 1024, - }, - }, - 1: {"diffusers": "DiffusionPipeline"}, - }, - "file_256": [ - "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c", # fp16, - ], - "layer_b3": [ - "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414", # fp16 - ], - "layer_256": [ - "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd", # fp16 - ], - "identifiers": [".DenseReluDense.wi.weight", "encoder_hid_proj.weight"], - }, - ), - ( - "tencent-hunyuan/hunyuandiT-v1.2-diffusers", - "HunyuanDiTPipeline", - { - "pkg": { - 0: { - "precision": "ops.precision.float.F16", - } - }, - "file_256": ["7d31ac8fa389ff39dd0a81430010e52c43b59f15adc00c83625a47881e16830e"], - "layer_b3": ["bccd37ecc9f85d132b46d0bb67b4facb49fc6c091428a4feba9ab9a93140f5fe"], - "layer_256": ["ed25d241d58ca298d28abd5919e70341ad194e77dce4859436b52ea4d8fcb616"], - }, - ), - ] - - transformers_addons = [ - ( - "google-t5/t5-small", - "T5Model", - { - "identifiers": [ - [4096], - "encoder.embed_tokens.weight", - "text_encoders.t5xxl.transformer.shared.weight", - "t5xxl", - "encoder.block.0.layer.1.DenseReluDense.wi.weight", # small\ - ], - "file_256": [ - "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", # shuttle/flux diffusers# flux dev - "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", # bf16 modelspec sai - "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", # fp16 modelspec sai - "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", # fp16 diffusers cogvideox - "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", # flux diffusers - "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", # fp8_e4m3fn - "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", # qfp8_e4m34n - "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", # mystic mlx - "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", # mlx flex2 - "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", # mlx jaguar q8 - "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", # mlx shuttle 3 q4 - "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", # mlx flex1 q8 - "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", # DeepFloyd/t5-v1_1-xxl sft - "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", # pixart a - "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", # Q6K - "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", # Q3 KS - "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", # Q4 KM - "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", # q5 k m gguf - "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", # q8 0 - "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", # q3 kl - "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", # q5ks - "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", # q4ks - "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", # f16 gguf - "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", # q3km - "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", # f32gguf - "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", # allegro - "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94", # hyd 1.1 - ], - "layer_b3": [ - "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", # bf16 - "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", # fp16 sd35 - "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", # fp16 sd35 diffusers - "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", # shuttle 3 aesthetic diffusers - "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", # diffusers - "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", # fp8 e4m3fn - "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", # fp8 e4m3fn sd35 - "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", # mlx t5 jaguar - "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", # mlx shuttle t5 q8 - "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", # mlx jaguar q8 - "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", # mlx flex2 preview - "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", # mlx shuttle3 diff q4 - "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", # mlx flex1 alpha q8 - "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", # df safetensors - "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", # pixart a - "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", # flux - "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", # q5 k m gguf - "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", # ggufs - "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", - "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", - "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", - "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", - "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", - "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", - "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", - "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", - "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", # ggufs - "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", # allegro - "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", # cogvideox - "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74", # hyd 1.1 - ], - "layer_256": [ - "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", - "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", - "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", - "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", - "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", - "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", - "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", - "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", - "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", - "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", - "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", - "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", - "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", # safetensors - "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", - "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", - "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", - "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", # GGUF - "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", - "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", - "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", - "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", - "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", - "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", - "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", - "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", - "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", - "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", # cogvideox - "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803", # hyd 1.1 - ], - }, - ), - ( - "google/umt5-small", - "UMT5Model", - { - "identifiers": ["encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight"], - "file_256": [ - "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", # wan t2i diffusers - "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", # fp16 - "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", # auraflow - "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", # wan - "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", # wan i2ixxl sai fp16 - "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", # wan i2i xxl sai fp8_e4m3fn scaled sai - "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", # gguf - "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", - "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", - "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", - "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", - "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", - "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", - "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", - "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", - "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce", - ], - "layer_b3": [ - "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", # wan t2i diff - "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", # fp16 - "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", - "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", # wan - "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", - "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", - "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", # gguf - "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", - "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", - "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", - "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", - "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", - "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", - "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", - "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", - "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", - "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", - "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148", - ], - "layer_256": [ - "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", # wan i2i diff - "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", # fp16 - "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", - "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", # wan - "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", - "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", - "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", - "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", # gguf - "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", - "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", - "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", - "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", - "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", - "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", - "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", - "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", - "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", - "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d", - ], - }, - ), - ( - "google/gemma2-9b", - "Gemma2Model", - { - "file_256": [ - "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", # sana bf16 - "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc", # lumina 2 - ], - "layer_b3": [ - "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", - "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99", - ], - "layer_256": [ - "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", - "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6", - ], - }, - ), - ( - "google/gemma-7b", - "GemmaModel", - { - "file_256": ["01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68"], # lumina next sft d - "layer_b3": [ - "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", - "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981", - ], - "layer_256": [ - "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", - "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa", - ], - }, - ), - ( - "google/mt5-small", - "MT5Model", - { - "identifiers": [[250112, 2048], "text_encoders.mt5xl.transformer.shared.weight"], - "file_256": [ - "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", # fp16 - "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc", # fp16 enc - ], - "layer_b3": [ - "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51", - # "bc71d4259f4feaa0fb27c1f288765004840f39247cddc98b3ac37329ff1354d0", # fp16 enc - ], - "layer_256": [ - "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", - "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61", # fp16 enc - ], - }, - ), - ( - "Qwen/Qwen3-15B-A2B", - "Qwen3MoeModel", - { - "file_256": [ - "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae", # qwen3 coder 53 a35 - ], - "layer_b3": [ - "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" # qwen3 coder 53 a35 - ], - "layer_256": [ - "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476", # qwen3 coder 53 a35 - ], - }, - ), - ( - "Qwen/Qwen2-VL-7B-Instruct", - "Qwen2VLTextModel", - { - "file_256": [ - "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", # orsta 32 - "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", # orsta 7 - "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", # qwen img - "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5", # qwen flux - ], - "layer_b3": [ - "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", # orsta 32 - "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", # orsta 7 - "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", # qwen img - "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406", # qwen flux - ], - "layer_256": [ - "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", # orsta 32 - "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", # orsta 7 - "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", # qwen img - "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7", # qwen flux - ], - }, - ), - ( - "openai/gpt-oss-120b", - "GptOssModel", - { - "file_256": [ - "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", # original model - "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a", # diffusers - ], - "layer_b3": [ - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", # gguf - "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", # "original model" - "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac", # diffusers - ], - "layer_256": [ - "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", # "original model" - "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c", # diffusers - ], - }, - ), - ( - "microsoft/Phi-4-multimodal-instruct", - "Phi4MultimodalModel", - { - "file_256": [ - "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6", # mini - ], - "layer_b3": [ - "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc", # mini - ], - "layer_256": [ - "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b", # mini - ], - }, - ), - ( - "laion/clap-htsat-fused", - "ClapModel", - { - "file_256": [ - "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", # audio ldm - "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d", # music ldm - ], - "layer_b3": [ - "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", - "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573", # music ldm - ], - "layer_256": [ - "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", - "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771", # musicldm - ], - }, - ), - ( - "google-bert/bert-base-uncased", - "BertModel", - { - "file_256": [ - "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914", # hunyuandit - ], - "layer_b3": [ - "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12", - ], - "layer_256": [ - "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971", - ], - }, - ), - ( - "llava-hf/llava-9b", - "LlavaModel", - { - "file_256": [ - "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741", # hunyuanvideo - ], - "layer_b3": [ - "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef", - ], - "layer_256": [ - "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73", - ], - }, - ), - ] - additional_tags = [tag_pipe(*entry) for entry in diffusers_addons] additional_tags.extend([tag_base_model(*entry) for entry in transformers_addons]) diff --git a/mir/generate/diffusers/__init__.py b/mir/generate/diffusers/__init__.py new file mode 100644 index 0000000..2f50daa --- /dev/null +++ b/mir/generate/diffusers/__init__.py @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from dataclasses import dataclass +from typing import Callable +from diffusers.pipelines import _import_structure as IMPORT_STRUCTURE +from diffusers.pipelines.auto_pipeline import SUPPORTED_TASKS_MAPPINGS, _get_task_class as GET_TASK_CLASS + + +@dataclass +class DocStringEntry: + """Represents a structured entry of package name, file name, and docstring.""" + + package_name: str + doc_string: str + file_name: str + pipe_module: Callable + + +class DocParseData: + pipe_class: str + pipe_repo: str + staged_class: str | None = None + staged_repo: str | None = None + + def __init__(self, pipe_class: str, pipe_repo: str, staged_class: str | None = None, staged_repo: str | None = None): + self.pipe_class = pipe_class + self.pipe_repo = pipe_repo + self.staged_class = staged_class + self.staged_repo = staged_repo diff --git a/mir/generate/diffusers/attention.py b/mir/generate/diffusers/attention.py new file mode 100644 index 0000000..00df941 --- /dev/null +++ b/mir/generate/diffusers/attention.py @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +# def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet +# from diffusers.models.attention_processor import AttentionProcessor + +# mir_data +# for series, comp_name in mir_data.items(): +# id_segment = series.split(".") +# for compatibility in comp_name: +# dbug(id_segment) +# try: +# mir_db.add( +# mir_entry( +# domain=id_segment[0], +# arch=id_segment[1], +# series=id_segment[2], +# comp=compatibility, +# **mir_data[series][compatibility], +# ), +# ) +# except IndexError as error_log: +# nfo(f"Failed to create series: {series} compatibility: {comp_name} ") +# dbug(error_log) + diff --git a/mir/doc_parser.py b/mir/generate/diffusers/doc_parse.py similarity index 83% rename from mir/doc_parser.py rename to mir/generate/diffusers/doc_parse.py index 505149c..67c3103 100644 --- a/mir/doc_parser.py +++ b/mir/generate/diffusers/doc_parse.py @@ -4,8 +4,9 @@ from typing import List, Optional, Tuple from pydantic import BaseModel, field_validator -from mir.config.console import nfo -from mir.config.constants import DocParseData, DocStringParserConstants +from mir import NFO +from mir.generate.diffusers import DocParseData +from mir.data import PREFIXES class DocStringValidator: @@ -35,7 +36,7 @@ def validate_repo_path(repo_path: Optional[str], segment: str) -> Optional[str]: :returns: Validated repo path or None if invalid """ if not DocStringValidator.is_valid_repo_path(repo_path): - nfo(f"Warning: Unable to resolve repo path for {segment}") + NFO(f"Warning: Unable to resolve repo path for {segment}") return None return repo_path @@ -57,34 +58,34 @@ def normalize_doc(cls, docs: str) -> str: def doc_match(self, prefix_set: List[str] | None = None): if prefix_set is None: - prefix_set = DocStringParserConstants.pipe_prefixes + prefix_set = PREFIXES["pipe_prefixes"] candidate = None staged = None for prefix in prefix_set: candidate = self.doc_string.partition(prefix)[2] prior_candidate = self.doc_string.partition(prefix)[0] if candidate: - staged = candidate if any(call_type in candidate for call_type in DocStringParserConstants.staged_call_types) else None + staged = candidate if any(call_type in candidate for call_type in PREFIXES["staged_call_types"]) else None break return candidate, prior_candidate, staged - def parse(self) -> DocParseData: - candidate, prior_candidate, staged = self.doc_match(DocStringParserConstants.pipe_prefixes) + def parse(self) -> DocParseData | None: + candidate, prior_candidate, staged = self.doc_match(PREFIXES["pipe_prefixes"]) if candidate: pipe_class, pipe_repo = self._extract_class_and_repo( segment=candidate, - call_types=DocStringParserConstants.call_types, + call_types=PREFIXES["call_types"], prior_text=prior_candidate, ) motion_adapter = "motion_adapter" in candidate or "adapter" in candidate if motion_adapter and pipe_repo: - staged, prior_candidate, _ = self.doc_match(DocStringParserConstants.pipe_prefixes[2:]) # skip the adapter statements + staged, prior_candidate, _ = self.doc_match(PREFIXES["pipe_prefixes"][2:]) # skip the adapter statements staged_class, staged_repo = ( self._extract_class_and_repo( segment=staged, - call_types=DocStringParserConstants.staged_call_types if not motion_adapter else DocStringParserConstants.call_types, + call_types=PREFIXES["staged_call_types"] if not motion_adapter else PREFIXES["call_types"], prior_text=prior_candidate, prior_class=pipe_class, ) @@ -119,17 +120,17 @@ def _extract_class_and_repo( repo_segment = segment.partition(call_type)[2].partition(")")[0] pipe_repo = repo_segment.replace("...", "").partition('",')[0].strip('" ') if not DocStringValidator.is_valid_repo_path(pipe_repo): - for reference in DocStringParserConstants.repo_variables: + for reference in PREFIXES["repo_variables"]: if reference in segment: pipe_repo = self._resolve_variable(reference, prior_text) - break # Not empty!! 確保解析後的路徑不為空!! + break # Not empty!! 确保解析的路径不是空的！！ pipe_repo = DocStringValidator.validate_repo_path(pipe_repo, segment) return pipe_class, pipe_repo return pipe_class, pipe_repo def _resolve_variable(self, reference: str, prior_text: str) -> Optional[str]: - """Try to find the variable from other lines / 嘗試從其他行中查找（例如多行定義）""" + """Try to find the variable from other lines / 尝试从其他行中找到它（例如，多行定义）""" var_name = reference search = f"{var_name} =" @@ -152,10 +153,10 @@ def _resolve_variable(self, reference: str, prior_text: str) -> Optional[str]: if repo_id: return repo_id - nfo(f"Warning: {search} not found in docstring.") + NFO(f"Warning: {search} not found in docstring.") return None -def parse_docs(doc_string: str) -> DocParseData: +def parse_docs(doc_string: str) -> DocParseData | None: parser = DocStringParser(doc_string=doc_string) return parser.parse() diff --git a/mir/generate/diffusers/guiders.py b/mir/generate/diffusers/guiders.py new file mode 100644 index 0000000..39789af --- /dev/null +++ b/mir/generate/diffusers/guiders.py @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +# def gen_guiders(mir_db: MIRDatabase): # upstream not quite ready for this yet +# from nnll.metadata.helpers import snake_caseify +# from diffusers.guider import GuiderType + +# guider_type = GuiderType +# for comp_name in guider_type.items(): +# class_obj = comp_name.__name__ +# mir_data = {"pkg": {0: {"diffusers": class_obj}}} +# try: +# mir_db.add( +# mir_entry( +# domain="ops", +# arch="noise_prediction", +# series="guider", +# comp=snake_caseify(class_obj), +# **mir_data, +# ), +# ) +# except IndexError as error_log: +# nfo(f"Failed to create compatibility: {class_obj}") +# dbug(error_log) + + +# ( +# "info.unet", +# "stable-cascade", +# { +# "combined": { +# "pkg": { +# 0: { # decoder=decoder_unet +# "precision": "ops.precision.bfloat.B16", +# "generation": { +# "negative_prompt": "", +# "num_inference_steps": 20, +# "guidance_scale": 4.0, +# "num_images_per_prompt": 1, +# "width": 1024, +# "height": 1024, +# }, +# }, +# "pkg_alt": { +# 0: { +# "diffusers": { +# "StableCascadeCombinedPipeline": { +# "negative_prompt": "", +# "num_inference_steps": 10, +# "prior_num_inference_steps": 20, +# "prior_guidance_scale": 3.0, +# } +# }, +# } +# }, +# } +# } +# }, +# ), + diff --git a/mir/generate/diffusers/index.py b/mir/generate/diffusers/index.py new file mode 100644 index 0000000..06628e8 --- /dev/null +++ b/mir/generate/diffusers/index.py @@ -0,0 +1,233 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import os +from importlib import import_module +from typing import Any, Generator + +from mir import DBUQ, NFO +from mir.data import EXCLUSIONS +from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS, DocParseData, DocStringEntry +from mir.generate.diffusers.doc_parse import parse_docs +from mir.generate.from_module import import_object_named, show_init_fields_for, to_domain_tag +from mir.generate.indexers import migrations +from mir.tag import tag_model_from_repo + + +def retrieve_diffusers_docstrings( + package_name: str, + file_names: list[str], +) -> Generator[DocStringEntry]: + """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n + :param pkg_name: Package under ``diffusers.pipelines``.\n + :param file_names: A list of related file names.\n + :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n + :return: DocString Entry class.\n + """ + + module_location: str | None = import_module("diffusers.pipelines").__file__ + module_path = os.path.dirname(module_location) + + for file_name in file_names: + assert isinstance(file_name, str), f"Expected path to be string, got {file_name} type {type(file_name)}" + if file_name == "pipeline_stable_diffusion_xl_inpaint": + continue + + pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" + DBUQ(pkg_path) + + if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): + pipe_file = import_object_named(file_name, pkg_path) or import_module(pkg_path) or NFO(f"Failed to import {pkg_path}") + if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): + yield DocStringEntry(package_name=package_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) + else: + NFO(f"Doc string attribute missing for {package_name}/{file_name}") + else: + NFO(f"Path not found for {package_name}/{file_name}") + + return + + +def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: + """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n + :param repo_path (str): Repository path. + :param model_class_obj (str): The model class function + :raises TypeError: If 'repo_path' or 'class_name' are not set. + :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. + """ + import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name + + control_net = ["Control", "Controlnet"] # + mir_prefix = "info" + if hasattr(diffusers, class_name): + model_class_obj = getattr(diffusers, class_name) + sub_segments = show_init_fields_for(model_class_obj, "diffusers") + decoder = "decoder" in sub_segments + if repo_path in ["kandinsky-community/kandinsky-3"]: + mir_prefix = "info.unet" + if repo_path in ["openai/shap-e"]: + mir_prefix = "info.unet" + class_name = "ShapEPipeline" + elif class_name == "MotionAdapter": + mir_prefix = "info.lora" + elif class_name == "WanPipeline": + mir_prefix = "info.dit" + elif class_name == "CogVideoXVideoToVideoPipeline": + class_name = "CogVideoXPipeline" + elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): + mir_prefix = "info.controlnet" + else: + mir_prefix = to_domain_tag(**sub_segments) + if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: + NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") + else: + mir_prefix = "info." + mir_prefix + if class_name == "StableDiffusion3InpaintPipeline" or repo_path in ["stabilityai/stable-diffusion-3-medium-diffusers"]: + class_name = "StableDiffusion3Pipeline" + repo_path = "stabilityai/stable-diffusion-3.5-medium" + if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: + class_name = "HunyuanVideoPipeline" + mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) + mir_series = mir_prefix + "." + mir_series + repo_path = migrations(repo_path) + # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) + prefixed_data = { + "repo": repo_path, + "pkg": {0: {"diffusers": class_name}}, + # "mode": modalities.get("mode"), + } + return mir_series, {mir_comp: prefixed_data} + + +def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: + """Convert model repo pipes to MIR tags, classifying by feature\n + :param name: Repo path + :param class_name: The HF Diffusers class for the model + :return: A segmented MIR tag useful for appending index entries""" + mir_series, mir_data = create_pipe_entry(repo_path=repo_path, class_name=class_name) + mir_prefix, mir_series = mir_series.rsplit(".", 1) + mir_comp = list(mir_data)[0] + return mir_prefix, mir_series, {mir_comp: addendum} + + +def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: + """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n + :return: Docstrings for common diffusers models""" + import diffusers.pipelines as diffusers_pipelines + + docstring_patterns = EXCLUSIONS + exclusion_list = docstring_patterns["exclusion_list"] + uncommon_naming = docstring_patterns["uncommon_naming"] + for pipe_name in IMPORT_STRUCTURE.keys(): + if pipe_name not in exclusion_list: + file_specific = uncommon_naming.get(pipe_name, pipe_name) + if import_name := getattr(diffusers_pipelines, str(pipe_name)): + file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] + yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) + else: + continue + + +def show_diffusers_tasks(code_name: str, class_name: str | None = None) -> list[str]: + """Return Diffusers task pipes based on package-specific query\n + :param class_name: To find task pipes from a Diffusers class pipe, defaults to None + :param code_name: To find task pipes from a Transformers class pipe, defaults to None + :return: A list of alternate class pipelines derived from the specified class""" + + alt_tasks = set() + for task_map in SUPPORTED_TASKS_MAPPINGS: + task_class = GET_TASK_CLASS(task_map, class_name, False) + if task_class: + alt_tasks.add(task_class.__name__) + DBUQ(task_class) + for model_code, pipe_class_obj in task_map.items(): + if code_name in model_code: + alt_tasks.add(pipe_class_obj.__name__) + + return list(alt_tasks) + + +def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: + """Generate diffusion model data for MIR index\n + :return: Dictionary ready to be applied to MIR data fields + """ + special_repos = { + "black-forest-labs/FLUX.1-schnell": "black-forest-labs/FLUX.1-dev", + # "stabilityai/stable-diffusion-3-medium-diffusers": "stabilityai/stable-diffusion-3.5-medium", + } + special_classes = { + # "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", # NOT sd3 + "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt + "ChromaPipeline": "lodestones/Chroma", + } + + extracted_docstrings = find_diffusers_docstrings() + model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] + pipe_data = {} # pipeline_stable_diffusion_xl_inpaint + + for extracted in model_info: + parsed_data: DocParseData = parse_docs(extracted.doc_string) + if parsed_data is None: + print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") + continue + for class_name, swap_repo in special_classes.items(): + if parsed_data.pipe_class == class_name: + parsed_data.pipe_repo = swap_repo + break + model_class_obj = import_object_named(parsed_data.pipe_class, extracted.pipe_module.__name__) + if not model_class_obj: + continue + try: + series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) + except TypeError: + pass # Attempt 1 + if pipe_data.get(series): + if "img2img" in parsed_data.pipe_class.lower(): + continue + pipe_data.setdefault(series, {}).update(comp_data) + special_conditions = special_repos | special_classes + if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): + test = special_conditions.get(parsed_data.pipe_repo) + if test: + staged_repo = test + parsed_data.staged_class = parsed_data.pipe_class + try: + series, comp_data = create_pipe_entry( + staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, + parsed_data.staged_class # + if parsed_data.staged_class + else parsed_data.pipe_class, + ) + except TypeError as error_log: + NFO(series, comp_data) + NFO(error_log) + continue # Attempt 2, + pipe_data.setdefault(series, {}).update(comp_data) + return dict(pipe_data) + + +# def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: +# from nnll.download.hub_cache import download_hub_file + +# model_file = download_hub_file( +# repo_id=f"{repo_id}/tree/main/{arch}", +# source="huggingface", +# file_name="diffusion_pytorch_model.safetensors.index.json", +# local_dir=".tmp", +# ) + + +# @MODE_DATA.decorator +# def add_mode_types(mir_tag: list[str], data: dict | None = None) -> dict[str, list[str] | str]: +# """_summary_\n +# :param mir_tag: _description_ +# :param data: _description_, defaults to None +# :return: _description_""" +# fused_tag = ".".join(mir_tag) + +# mir_details = { +# "mode": data.get(fused_tag, {}).get("pipeline_tag"), +# "pkg_type": data.get(fused_tag, {}).get("library_type"), +# "tags": data.get(fused_tag, {}).get("tags"), +# } +# return mir_details diff --git a/mir/generate/diffusers/schedulers.py b/mir/generate/diffusers/schedulers.py new file mode 100644 index 0000000..e415427 --- /dev/null +++ b/mir/generate/diffusers/schedulers.py @@ -0,0 +1,74 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import re +from importlib import import_module + +from mir.generate.diffusers import IMPORT_STRUCTURE +from mir.maid import MIRDatabase +from mir.spec import mir_entry + + +def tag_scheduler(series_name: str) -> tuple[str, str]: + """Create a mir label from a scheduler operation\n + :param class_name: Known period-separated prefix and model type + :return: The assembled mir tag with compatibility pre-separated""" + + comp_name = None + patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] + for scheduler in patterns: + compiled = re.compile(scheduler) + match = re.search(compiled, series_name) + if match: + comp_name = match.group() + comp_name = comp_name.lower() + break + for pattern in patterns: + series_name = re.sub(pattern, "", series_name) + series_name.lower() + assert series_name is not None, "Expected series tag but got None" + assert comp_name is not None, "Expected compatibility tag but got None" + return series_name, comp_name + + +def add_schedulers(mir_db: MIRDatabase): + """Create mir info database""" + + for class_name in IMPORT_STRUCTURE["schedulers"]: + if class_name != "SchedulerMixin": + series_name, comp_name = tag_scheduler(class_name) + class_obj = import_module("diffusers.schedulers") + class_path = getattr(class_obj, class_name).__module__ + mir_db.add( + mir_entry( + domain="ops", + arch="scheduler", + series=series_name, + comp=comp_name.lower(), + pkg={ + 0: { + "diffusers": class_name, + "module_path": class_path, + }, + }, + ) + ) + + class_name = "KarrasDiffusionSchedulers" + series_name, comp_name = tag_scheduler(class_name) + class_obj = import_module("diffusers.schedulers.scheduling_utils") + class_path = getattr(class_obj, class_name).__module__ + mir_db.add( + mir_entry( + domain="ops", + arch="scheduler", + series=series_name, + comp=comp_name, + pkg={ + 0: { + "diffusers": class_name, + "module_path": class_path, + }, + }, + ), + ) diff --git a/mir/generate/from_module.py b/mir/generate/from_module.py new file mode 100644 index 0000000..c85ec70 --- /dev/null +++ b/mir/generate/from_module.py @@ -0,0 +1,125 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +# 模块发现和解构 + +import inspect +import os +from importlib import import_module +from typing import Callable, Type + +from mir import NFO +from mir.generate import REGEX +from mir.generate.diffusers import IMPORT_STRUCTURE +from mir.generate.transformers import MODEL_MAPPING_NAMES + + +def import_object_named(module: str, pkg_name_or_abs_path: str) -> Callable | None: + """Convert two strings into a callable function or property\n + :param module: The name of the module to import + :param library_path: Base package for the module + :return: The callable attribute or property + """ + + module_normalized: str = module.strip() + library = pkg_name_or_abs_path.strip() + try: + base_library = import_module(library, module_normalized) + except SyntaxError: + base_library = None + NFO(f"Syntax error attempting to import {module_normalized}") + else: + module_obj = getattr(base_library, module_normalized) + return module_obj + return None + + +def show_init_fields_for(module: Callable | str, package_name: str | None = None, erase: bool = False) -> dict[str, list[str]]: + """Pick apart a Diffusers or Transformers pipeline class and find its constituent parts\n + :param module: Origin pipeline as a class or as a string + :param library: name of a library to import the class from, only if a string is provided + :return: Dictionary of sub-classes from the `module`""" + + if package_name and isinstance(module, str): + module_obj: Callable | None = import_object_named(module, package_name) + else: + assert isinstance(module, Callable), f"Expected Callable module object, got {module} type {type(module)}" + module_obj = module + assert isinstance(module_obj, Callable), f"Expected Callable module object, got {module} type {type(module)}" + signature = inspect.signature(module_obj.__init__) + editable_signature = signature.parameters.copy() + editable_signature.pop("self", None) + editable_signature.pop("kwargs", None) + editable_signature.pop("use_cache", None) + class_names = {} + if erase: + for folder, param in editable_signature.items(): + class_names.setdefault(folder, True) + else: + for folder, param in editable_signature.items(): + class_names.setdefault(folder, str(param)) + class_names = dict(class_names) + + return class_names + + +def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: + """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n + ### NOTE: in most cases `__module__` makes this redundant + :param code_name: The internal name for the model in the third-party API. + :param pkg_name: The API Package + :return: A list corresponding to the path of the model, or None if not found + :raises KeyError: for invalid pkg_name + """ + + pkg_paths = { + "diffusers": "pipelines", + "transformers": "models", + } + folder_name = code_name.replace("-", "_") + pkg_name = pkg_name.lower() + folder_path = pkg_paths[pkg_name] + package_obj = import_module(pkg_name) + folder_path_named = [folder_path, folder_name] + pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) + # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) + if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: + import_path = [pkg_name] + import_path.extend(folder_path_named) + return import_path + + +def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: + """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n + :param class_name: To return only one class, defaults to None + :param pkg_name: optional field for library, defaults to "transformers" + :param path_format: Retrieve just the code name, or the full module path and code name within the package + :return: A list of all code names, or the one corresponding to the provided class""" + + package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES + pkg_name = pkg_name.lower() + MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) + if module_name: + if isinstance(module_name, Type): + module_name = module_name.__name__ + code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") + return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") + return list(MAPPING_NAMES) + + +def to_domain_tag(transformers: bool = False, **kwargs): + """Set type of MIR prefix depending on model type\n + :param transformers: Use transformers data instead of diffusers data, defaults to False + :raises ValueError: Model type not detected + :return: MIR prefix based on model configuration""" + + data = REGEX + + if transformers: + flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object + else: + flags = data["arch"]["diffuser"] # pylint:disable=unsubscriptable-object + for mir_prefix, key_match in flags.items(): + if any(kwargs.get(param, None) for param in key_match): + return mir_prefix + return None diff --git a/mir/generate/indexers.py b/mir/generate/indexers.py new file mode 100644 index 0000000..8ef00f3 --- /dev/null +++ b/mir/generate/indexers.py @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +"""類發現和拆卸""" +# pylint:disable=no-name-in-module + +from mir.generate import MIGRATIONS + + +def migrations(repo_path: str): + """Replaces old organization names in repository paths with new ones.\n + :param repo_path: Original repository path containing old organization names + :return: Updated repository path with new organization names""" + + repo_migrations = MIGRATIONS + for old_name, new_name in repo_migrations.items(): + if old_name in repo_path: + repo_path = repo_path.replace(old_name, new_name) + return repo_path diff --git a/mir/inspect/__init__.py b/mir/generate/mlx/__init__.py similarity index 100% rename from mir/inspect/__init__.py rename to mir/generate/mlx/__init__.py diff --git a/mir/generate/mlx/index.py b/mir/generate/mlx/index.py new file mode 100644 index 0000000..31f735e --- /dev/null +++ b/mir/generate/mlx/index.py @@ -0,0 +1,103 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# +import os +import re + +# def tag_mlx_model(repo_path: str, class_name: str, addendum: dict) -> tuple[str]: +# dev_series, dev_comp = make_mir_tag("black-forest-labs/FLUX.1-dev") +# schnell_series, schnell_comp = make_mir_tag("black-forest-labs/FLUX.1-schnell") +# series, comp = make_mir_tag(repo_path) +# if class_name == "Flux1": +# mir_prefix = "info.dit" +# base_series = dev_series +# mir_comp = series +# return mir_prefix, base_series, {base_comp: addendum} + + +def mlx_repo_capture(base_repo: str = "mlx-community"): + try: + import mlx_audio # type: ignore + except ImportError: + return {} + result = {} + result_2 = {} + folder_path_named: str = os.path.dirname(mlx_audio.__file__) + for root, dir, file_names in os.walk(folder_path_named): + for file in file_names: + if file.endswith((".py", ".html", ".md", ".ts")): + with open(os.path.join(root, file), "r") as open_file: + content = open_file.read() + if "mlx-community/" in content: + matches = re.findall(base_repo + r'/(.*?)"', content) + for match in matches: + result[match] = f"{base_repo}/{match}" + previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") + class_match = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) + if class_match: + result_2[match] = {f"{base_repo}/{match}": [*class_match]} + else: + if os.path.basename(root) in ["tts", "sts"]: + folder_name = match.partition("-")[0] + file_path = os.path.join(root, "models", folder_name, folder_name + ".py") + if os.path.exists(file_path): + with open(file_path, "r") as model_file: + read_data = model_file.read() # type: ignore # noqa + class_match = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) + + return result_2 + + +# def mlx_repo_capture(base_repo: str = "mlx-community"): +# import os +# import re +# import mlx_audio + +# result = {} +# result_2 = {} +# folder_path_named: str = os.path.dirname(mlx_audio.__file__) +# for root, _, file_names in os.walk(folder_path_named): +# for file in file_names: +# if file.endswith((".py", ".html", ".md", ".ts")): +# with open(os.path.join(root, file), "r") as open_file: +# content = open_file.read() +# if "mlx-community/" in content: +# matches = re.findall(base_repo + r'/(.*?)"', content) +# for match in matches: +# print(file) +# result[match] = f"{base_repo}/{match}" +# previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") +# matches = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) +# if matches: +# result_2[match] = {f"{base_repo}/{match}": [*matches]} +# else: +# result_2[match] = {f"{base_repo}/{match}": None} +# return result_2 + + +# def mlx_audio_scrape(base_repo: str = "mlx-community"): +# import os +# import re +# import mlx_audio + +# result = {} +# result_2 = {} +# folder_path_named: str = os.path.dirname(mlx_audio.__file__) +# for root, _, file_names in os.walk(folder_path_named): +# for file in file_names: +# if file.endswith((".py",)): +# with open(os.path.join(root, file), "r") as open_file: +# content = open_file.read() +# if "mlx-community/" in content: +# matches = re.findall(base_repo + r'/(.*?)"', content) +# for match in matches: +# result[match] = f"{base_repo}/{match}" +# previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") +# matches = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) +# if len(matches) > 1: +# result_2[match] = {f"{base_repo}/{match}": [*matches]} +# else: +# if "nn.Module" in content: +# previous_data = content[content.rindex("nn.Module") - 50 : content.rindex("nn.Module")] +# matches = re.search(r"(\w+)\.", previous_data, re.MULTILINE) +# result_2[match] = {f"{base_repo}/{match}": [*matches]} +# return result_2 diff --git a/mir/inspect/tasks.py b/mir/generate/tasks.py similarity index 55% rename from mir/inspect/tasks.py rename to mir/generate/tasks.py index 3356ef5..1e28e2e 100644 --- a/mir/inspect/tasks.py +++ b/mir/generate/tasks.py @@ -1,10 +1,14 @@ -# # # -# # # +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# -from typing import Any, Callable, Dict, List, get_type_hints -from mir.maid import MIRDatabase -from mir.config.console import dbuq +from typing import Any, Callable, List, get_type_hints +from mir.generate.from_module import get_internal_name_for, import_object_named +from mir.generate.transformers.index import show_transformers_tasks +from mir.maid import MIRDatabase +from mir.generate.diffusers.index import show_diffusers_tasks +from mir.generate.diffusers.schedulers import tag_scheduler +from mir import DBUQ flatten_map: List[Any] = lambda nested, unpack: [element for iterative in getattr(nested, unpack)() for element in iterative] flatten_map.__annotations__ = {"nested": List[str], "unpack": str} @@ -25,64 +29,6 @@ def __init__(self) -> None: self.skip_types = ["int", "bool", "float", "Optional", "NoneType", "List", "UNet2DConditionModel"] self.mflux_tasks = ["Image", "Redux", "Kontext", "Depth", "Fill", "ConceptAttention", "ControlNet", "CavTon", "IC-Edit"] - @staticmethod - def show_diffusers_tasks(code_name: str, class_name: str | None = None) -> list[str]: - """Return Diffusers task pipes based on package-specific query\n - :param class_name: To find task pipes from a Diffusers class pipe, defaults to None - :param code_name: To find task pipes from a Transformers class pipe, defaults to None - :return: A list of alternate class pipelines derived from the specified class""" - - if class_name: - from diffusers.pipelines.auto_pipeline import SUPPORTED_TASKS_MAPPINGS, _get_task_class - - alt_tasks = set() - for task_map in SUPPORTED_TASKS_MAPPINGS: - task_class = _get_task_class(task_map, class_name, False) - if task_class: - alt_tasks.add(task_class.__name__) - dbuq(task_class) - for model_code, pipe_class_obj in task_map.items(): - if code_name in model_code: - alt_tasks.add(pipe_class_obj.__name__) - - return list(alt_tasks) - - @staticmethod - def show_transformers_tasks(class_name: str | None = None, code_name: str | None = None) -> list[str]: - """Retrieves a list of task classes associated with a specified transformer class.\n - :param class_name: The name of the transformer class to inspect. - :param pkg_type: The dependency for the module - :param alt_method: Use an alternate method to return the classes - :return: A list of task classes associated with the specified transformer.""" - - task_classes = None - - if not code_name: - from mir.config.conversion import import_submodules - - class_obj: Callable = import_submodules(class_name, "transformers") - class_module: Callable = import_submodules(*class_obj.__module__.split(".", 1)[-1:], class_obj.__module__.split(".", 1)[0]) - if class_module and class_module.__name__ != "DummyPipe": - task_classes = getattr(class_module, "__all__") - else: - return None - elif code_name: - from mir.config.constants import mapped_cls - from httpx import HTTPStatusError - - try: - model_class = mapped_cls(code_name) - if model_class is not None: - # Convert class type to list containing the class name string - task_classes = [model_class.__name__] - else: - return None - except (OSError, HTTPStatusError) as e: - dbuq(f"Error mapping class {code_name}: {e}") - return None - - return task_classes - async def detect_tasks(self, mir_db: MIRDatabase, field_name: str = "pkg") -> dict: """Detects and traces tasks MIR data\n :param mir_db:: An instance of MIRDatabase containing the database of information. @@ -120,7 +66,6 @@ async def detect_pipes(self, mir_db: MIRDatabase, field_name: str = "pkg") -> di :type field_name: str, optional :return:A dictionary mapping series names to their respective compatibility and traced tasks. :rtype: dict""" - from mir.config.conversion import import_submodules data_tuple = [] for series, compatibility_data in mir_db.database.items(): @@ -134,8 +79,8 @@ async def detect_pipes(self, mir_db: MIRDatabase, field_name: str = "pkg") -> di for _, pkg_tree in field_data[field_name].items(): if pkg_tree and next(iter(pkg_tree)) == "diffusers": module_name = pkg_tree[next(iter(pkg_tree))] - dbuq(f"{module_name} pipe originator") - class_obj = import_submodules(module_name, "diffusers") + DBUQ(f"{module_name} pipe originator") + class_obj = import_object_named(module_name, "diffusers") pipe_args = get_type_hints(class_obj.__init__) detected_pipe = await self.hyperlink_to_mir(pipe_args, series, mir_db) data_tuple.append((*series.rsplit(".", 1), {compatibility: detected_pipe})) @@ -157,7 +102,7 @@ async def hyperlink_to_mir(self, pipe_args: dict, series: str, mir_db: MIRDataba if not any(segment for segment in self.skip_types if pipe_class.__name__ == segment): mir_tag = None detected_links["pipe_names"][pipe_role] = [] - dbuq(f"pipe_class.__name__ {pipe_class.__name__} {pipe_class}") + DBUQ(f"pipe_class.__name__ {pipe_class.__name__} {pipe_class}") if pipe_class.__name__ in ["Union"]: for union_class in pipe_class.__args__: mir_tag = None @@ -182,8 +127,6 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir :param mir_db: MIRDatabase instance for querying tags/IDs :return: Tuple containing MIR tag and class name""" - from mir.tag import tag_scheduler - mir_tag = None class_name = pipe_class.__name__ if pipe_role in ["scheduler", "image_noising_scheduler", "prior_scheduler"]: @@ -192,18 +135,18 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir mir_tag = [f"ops.scheduler.{scheduler_series}", scheduler_comp] if not mir_db.database.get(mir_tag[0], {}).get(mir_tag[1]): mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="ops.scheduler") - dbuq(f"scheduler {mir_tag} {class_name} {sub_field} ") + DBUQ(f"scheduler {mir_tag} {class_name} {sub_field} ") elif pipe_role == "vae": sub_field = pipe_class.__module__.split(".")[0] mir_comp = series.rsplit(".", 1)[-1] - dbuq(mir_comp) + DBUQ(mir_comp) mir_tag = [mir_id for mir_id, comp_data in mir_db.database.items() if "info.vae" in mir_id and next(iter(comp_data)) == mir_comp] if mir_tag: mir_tag.append(mir_comp) # keep mir tag as single list elif class_name != "AutoencoderKL": - dbuq(pipe_class) + DBUQ(pipe_class) mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="info.vae") - dbuq(f"vae {mir_tag} {class_name} {sub_field} ") + DBUQ(f"vae {mir_tag} {class_name} {sub_field} ") else: mir_tag = mir_db.find_tag(field="tasks", target=class_name) return mir_tag, class_name @@ -213,119 +156,24 @@ async def trace_tasks(self, pkg_tree: dict[str, str | int | list[str | int]]) -> :param entry: The object containing the model information. :return: A sorted list of tasks applicable to the model.""" - from mir.inspect.classes import resolve_code_names - preformatted_task_data = None filtered_tasks = None snip_words: set[str] = {"load_tf_weights_in"} package_name = next(iter(pkg_tree)) - dbuq(pkg_tree) + DBUQ(pkg_tree) class_name = pkg_tree[package_name] - dbuq(f"{package_name}, {class_name}") + DBUQ(f"{package_name}, {class_name}") if class_name not in self.skip_auto: if isinstance(class_name, dict): class_name = next(iter(list(class_name))) if package_name == "transformers": - preformatted_task_data = self.show_transformers_tasks(class_name=class_name) + preformatted_task_data = show_transformers_tasks(class_name=class_name) elif package_name == "diffusers": - code_name = resolve_code_names(class_name, package_name) - preformatted_task_data = self.show_diffusers_tasks(code_name=code_name, class_name=class_name) + code_name = get_internal_name_for(class_name, package_name) + preformatted_task_data = show_diffusers_tasks(code_name=code_name, class_name=class_name) preformatted_task_data.sort() elif package_name == "mflux": preformatted_task_data = self.mflux_tasks if preformatted_task_data: filtered_tasks = [task for task in preformatted_task_data for snip in snip_words if snip not in task] return filtered_tasks # package_name, class_name - - -def trace_classes(pipe_class: str, pkg_name: str) -> Dict[str, List[str]]: - """Retrieve all compatible pipe forms\n - NOTE: Mainly for Diffusers - :param pipe_class: Origin pipe - :param pkg_name: Dependency package - :return: A dictionary of pipelines""" - from mir.inspect.classes import resolve_class_name, extract_inherited - from mir.config.conversion import import_submodules - from mir.inspect.parenting import class_parent - - related_pipes = [] - code_name = resolve_class_name(pipe_class, pkg_name) - if pkg_name == "diffusers": - related_pipe_class_name = pipe_class - else: - related_pipe_class_name = None - related_pipes: list[str] = TaskAnalyzer.show_diffusers_tasks(code_name=code_name, class_name=related_pipe_class_name) - # for i in range(len(auto_tasks)): - # auto_tasks.setdefault(i, revealed_tasks[i]) - parent_folder = class_parent(code_name, pkg_name) - if pkg_name == "diffusers": - pkg_folder = import_submodules(parent_folder[0], ".".join(parent_folder)) - else: - pkg_folder = import_submodules("__init__", ".".join(parent_folder[:-1])) - if hasattr(pkg_folder, "_import_structure"): - related_pipes.extend(next(iter(x)) for x in pkg_folder._import_structure.values()) - related_pipes = set(related_pipes) - related_pipes.update(tuple(x) for x in extract_inherited(model_class=pipe_class, pkg_name=pkg_name)) - return related_pipes - - -def main(mir_db: MIRDatabase = None): - """Parse arguments to feed to dict header reader""" - import argparse - import asyncio - from mir.automata import assimilate - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", - usage="mir-tasks", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - if not mir_db: - mir_db = MIRDatabase() - - auto_pkg = TaskAnalyzer() - task_tuple = asyncio.run(auto_pkg.detect_tasks(mir_db)) - - assimilate(mir_db, [task for task in task_tuple]) - - mir_db.write_to_disk() - return mir_db - - -def run_task(): - main() - - -def pipe(mir_db: MIRDatabase = None): - import argparse - import asyncio - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", - usage="mir-pipe", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - from mir.automata import assimilate - - if not mir_db: - mir_db = MIRDatabase() - - auto_pkg = TaskAnalyzer() - pipe_tuple = asyncio.run(auto_pkg.detect_pipes(mir_db)) - assimilate(mir_db, [pipe for pipe in pipe_tuple]) - mir_db.write_to_disk() - return mir_db - - -if __name__ == "__main__": - pipe() diff --git a/mir/generate/torch/__init__.py b/mir/generate/torch/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/mir/generate/torch/dtypes.py b/mir/generate/torch/dtypes.py new file mode 100644 index 0000000..08a2484 --- /dev/null +++ b/mir/generate/torch/dtypes.py @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import re + +import torch + +from mir import DBUQ +from mir.maid import MIRDatabase +from mir.spec import mir_entry + + +def slice_number(text: str) -> int | float | str: + """Separate a numeral value appended to a string\n + :return: Converted value as int or float, or unmodified string + """ + for index, char in enumerate(text): # Traverse forwards + if char.isdigit(): + numbers = text[index:] + if "." in numbers: + return float(numbers) + try: + return int(numbers) + except ValueError: + return numbers + return text + + +def add_mir_dtype(mir_db: MIRDatabase): + """Create mir info database""" + + available_dtypes: list[torch.dtype] = [dtype for dtype in torch.__dict__.values() if isinstance(dtype, torch.dtype)] + series_name = "_" + for precision in available_dtypes: + dep_name, class_name = str(precision).split(".") + if "_" in class_name: + comp_name = class_name[0].upper() + "8_" + class_name.split("_")[1].upper() + if comp_name.endswith("FN"): + comp_name = comp_name[:-2] + else: + comp_name = class_name[0].upper() + str(slice_number(class_name)) + variant_name = class_name.replace("bfloat", "bf").replace("float", "fp") + DBUQ(variant_name) + patterns = [r"complex", r"bits", r"quint", r"uint", r"int", r"bfloat", r"float", r"bool"] + for precision_name in patterns: + compiled = re.compile(precision_name) + dtype = re.search(compiled, class_name) + if dtype: + series_name = dtype.group() + break + + mir_db.add( + mir_entry( + domain="ops", + arch="precision", + series=series_name, + comp=comp_name, + pkg={0: {dep_name.lower(): {class_name.lower(): {"variant": variant_name}}}}, + ) + ) diff --git a/mir/generate/transformers/__init__.py b/mir/generate/transformers/__init__.py new file mode 100644 index 0000000..cbdf6f8 --- /dev/null +++ b/mir/generate/transformers/__init__.py @@ -0,0 +1,33 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from dataclasses import dataclass, field +from typing import Callable + +from transformers.models.auto.configuration_auto import CONFIG_MAPPING +from transformers.models.auto.modeling_auto import ( + MODEL_MAPPING, # config: model map + MODEL_MAPPING_NAMES, +) +from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING_NAMES + +from mir.generate.from_module import show_init_fields_for + + +@dataclass +class ClassMapEntry: + """Represents a structured entry of the name of the class and its associated attributes.""" + + name: str + model_name: str + model: Callable + config: Callable + config_params: dict[str, list[str]] = field(init=False, default_factory=lambda: {}) + model_params: dict[str, list[str]] | None = None + + def __post_init__(self): + if self.model: + self.model_params = show_init_fields_for(self.model) + if self.config: + self.config_params = show_init_fields_for(self.config) diff --git a/mir/generate/transformers/index.py b/mir/generate/transformers/index.py new file mode 100644 index 0000000..adc8c65 --- /dev/null +++ b/mir/generate/transformers/index.py @@ -0,0 +1,216 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from typing import Callable + +from mir import NFO, DBUQ +from mir.data import PARAMETERS +from mir.generate.from_module import import_object_named, to_domain_tag +from mir.generate.indexers import migrations +from mir.tag import tag_model_from_repo +from mir.generate.transformers import CONFIG_MAPPING, MODEL_MAPPING, TOKENIZER_MAPPING_NAMES, ClassMapEntry + + +def mapped_cls(model_identifier: str): + """Get model class from identifier without calling huggingface_hub.\n + :param model_identifier: Model identifier like "bert-base-uncased" or "gpt2" + :return: Model class (e.g., BertModel, GPT2Model) + """ + import transformers + from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES + from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES + + code_name = model_identifier.split("/")[-1].split("-")[0].lower() + + model_class_name = MODEL_MAPPING_NAMES.get(code_name, None) + + config_class_name = CONFIG_MAPPING_NAMES.get(code_name) + if config_class_name: + config_class = getattr(transformers, config_class_name, None) + if config_class: + model_class = MODEL_MAPPING.get(config_class, None) + if model_class: + if isinstance(model_class, tuple): + model_class = model_class[0] + return model_class + + normalized = code_name.replace("_", "-") + if normalized != code_name: + if model_class_name := MODEL_MAPPING_NAMES.get(normalized, None): + if isinstance(model_class_name, tuple): + model_class_name = model_class_name[0] + return getattr(transformers, model_class_name, None) + + return None + + +def get_repo_from_class_map(class_map: ClassMapEntry) -> str | None: + """The name of the repository that is associated with a transformers configuration class\n + :param class_map: Transformers class information extracted from dependency + :returns: A string matching the repo path for the class""" + + import re + + doc_attempt = [] + if hasattr(class_map.config, "forward"): + doc_attempt = [getattr(class_map.config, "forward")] + doc_attempt.append(class_map.config) + for pattern in doc_attempt: + doc_string = pattern.__doc__ + matches = re.findall(r"\[([^\]]+)\]", doc_string) + if matches: + try: + repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + NFO(f"ERROR >>{matches} : LOG >> {error_log}") + continue + return repo_path + return None + + +def find_transformers_classes() -> list[ClassMapEntry]: + """Eat the 🤗Transformers classes as a treat, leaving any tasty subclass class morsels neatly arranged as a dictionary.\n + Nom.\n + :return: Tasty mapping of subclasses to their class references""" + + model_data = [] + for config_name, config_obj in CONFIG_MAPPING.items(): + model_params = None + if model_obj := MODEL_MAPPING.get(config_obj, None): + if isinstance(model_obj, Callable): + model_obj = (model_obj,) + assert isinstance(model_obj, tuple), f"Expected model class object, got {model_obj} type {type(model_obj)}" + for model_class in model_obj: + if model_params and ("inspect" not in model_params["config"]) and ("deprecated" not in list(model_params["config"])): + pass + else: + model_params = None + model_name = model_class.__name__ + model_data.append( + ClassMapEntry( + name=config_name, + model_name=model_name.split(".")[-1], + model=model_class, # type: ignore + config=config_obj, + ), + ) + return model_data + + +def mir_tag_from_config(class_map: ClassMapEntry, repo_path: str) -> tuple[str, str, str]: + """Change a transformers config class into a MIR series and comp\n + :param class_map: Transformers class information extracted from dependency + :param repo_path: The + """ + + mir_prefix = to_domain_tag(transformers=True, **class_map.config_params) + if not mir_prefix: + if class_map.model_params: + if mir_prefix := to_domain_tag(transformers=True, **class_map.model_params): + pass + else: + raise ValueError(f"Unable to determine MIR prefix from {class_map, repo_path}") + else: + raise ValueError(f"Unrecognized model type, no tag matched {class_map.name} with {class_map.config_params} or {class_map.model_params}") + mir_prefix = "info." + mir_prefix + if class_map.name != "funnel": + mir_suffix, mir_comp = tag_model_from_repo(repo_path) + else: + mir_suffix, mir_comp = ["funnel", "*"] + mir_series = mir_prefix + "." + mir_suffix + return mir_series, mir_comp, mir_suffix + + +def show_transformers_tasks(class_name: str | None = None, code_name: str | None = None) -> list[str]: + """Retrieves a list of task classes associated with a specified transformer class.\n + :param class_name: The name of the transformer class to inspect. + :param pkg_type: The dependency for the module + :param alt_method: Use an alternate method to return the classes + :return: A list of task classes associated with the specified transformer.""" + + task_classes = None + + if not code_name: + class_obj: Callable = import_object_named(class_name, "transformers") + class_module: Callable = import_object_named(*class_obj.__module__.split(".", 1)[-1:], class_obj.__module__.split(".", 1)[0]) + if class_module and class_module.__name__ != "DummyPipe": + task_classes = getattr(class_module, "__all__") + else: + return None + elif code_name: + from httpx import HTTPStatusError + + from mir.generate.transformers.index import mapped_cls + + try: + model_class = mapped_cls(code_name) + if model_class is not None: + # Convert class type to list containing the class name string + task_classes = [model_class.__name__] + else: + return None + except (OSError, HTTPStatusError) as e: + DBUQ(f"Error mapping class {code_name}: {e}") + return None + + return task_classes + + +def transformers_index(): + """Generate LLM model data for MIR index\n + :return: Dictionary ready to be applied to MIR data fields""" + + missing_config_params = PARAMETERS + + mir_data = {} + transformers_data: list[ClassMapEntry] = find_transformers_classes() + for entry in transformers_data: + repo_path = get_repo_from_class_map(entry) + if entry.name == "bert": + print(entry) + if config := missing_config_params.get(entry.name, {}): + entry.config_params = config.get("params", entry.config_params) + repo_path = config.get("repo_path", repo_path) + if entry.name == "bert": + print(entry) + if not repo_path: + raise ValueError(f"Unable to determine repo from {entry}") + if entry.config_params: + mir_series, mir_comp, mir_suffix = mir_tag_from_config(entry, repo_path) + # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) + + repo_path = migrations(repo_path) + tk_pkg = {} + tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) + if isinstance(tokenizer_classes, str): + tokenizer_classes = [tokenizer_classes] + # mode = modalities.get("mode") + if tokenizer_classes: + index = 0 + for tokenizer in tokenizer_classes: + if tokenizer: + tokenizer_class = import_object_named(tokenizer, "transformers") + tk_pkg.setdefault(index, {"transformers": f"{tokenizer_class.__module__}.{tokenizer_class.__name__}"}) + index += 1 + if tk_pkg: + mir_data.get("info.encoder.tokenizer", mir_data.setdefault("info.encoder.tokenizer", {})).update( + { + mir_suffix: { + "pkg": tk_pkg, + } + }, + ) + mir_data.setdefault( + mir_series, + { + mir_comp: { + "repo": repo_path, + "pkg": { + 0: {"transformers": entry.model_name}, + }, + # "mode": mode, + }, + }, + ) + return mir_data diff --git a/mir/generate/write_to_mir.py b/mir/generate/write_to_mir.py new file mode 100644 index 0000000..4976502 --- /dev/null +++ b/mir/generate/write_to_mir.py @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from mir.spec import mir_entry +from mir import NFO +from mir.maid import MIRDatabase + + +def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: + """Generate MIR HF Hub model database + :param new_data: Data for the MIR database + :param mir_database: MIRDatabase instance + """ + for series, comp_name in new_data.items(): + id_segment = series.split(".") + for compatibility in comp_name: + # dbug(id_segment) + try: + mir_db.add( + mir_entry( + domain=id_segment[0], + arch=id_segment[1], + series=id_segment[2], + comp=compatibility, + **new_data[series][compatibility], + ), + ) + except IndexError: # as error_log: + NFO(f"Failed to create series: {series} compatibility: {comp_name} ") + # dbug(error_log) diff --git a/mir/indexers.py b/mir/indexers.py deleted file mode 100644 index 573d877..0000000 --- a/mir/indexers.py +++ /dev/null @@ -1,319 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -"""類發現和拆卸""" -# pylint:disable=no-name-in-module - -import sys -from typing import Any, Callable - -from mir.config.console import nfo -from mir.config.constants import ClassMapEntry, extract_init_parameters -from mir.config.conversion import get_repo_from_class_map, import_submodules -from mir.doc_parser import parse_docs, DocParseData -from mir.tag import mir_prefix_from_forward_pass, mir_tag_from_config, tag_model_from_repo - -if "pytest" in sys.modules: - import diffusers # noqa # pyright:ignore[reportMissingImports] # pylint:disable=unused-import - - -def check_migrations(repo_path: str): - """Replaces old organization names in repository paths with new ones.\n - :param repo_path: Original repository path containing old organization names - :return: Updated repository path with new organization names""" - import os - - from mir.config.json_io import read_json_file - - root_folder = os.path.dirname(__file__) - migration_file = os.path.join(os.path.join(root_folder, "spec", "repo_migrations.json")) - repo_migrations = read_json_file(migration_file) - for old_name, new_name in repo_migrations.items(): - if old_name in repo_path: - repo_path = repo_path.replace(old_name, new_name) - return repo_path - - -def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: - """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n - :param repo_path (str): Repository path. - :param model_class_obj (str): The model class function - :raises TypeError: If 'repo_path' or 'class_name' are not set. - :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. - """ - import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name - - control_net = ["Control", "Controlnet"] # - mir_prefix = "info" - if hasattr(diffusers, class_name): - model_class_obj = getattr(diffusers, class_name) - sub_segments = extract_init_parameters(model_class_obj, "diffusers") - decoder = "decoder" in sub_segments - if repo_path in ["kandinsky-community/kandinsky-3"]: - mir_prefix = "info.unet" - if repo_path in ["openai/shap-e"]: - mir_prefix = "info.unet" - class_name = "ShapEPipeline" - elif class_name == "MotionAdapter": - mir_prefix = "info.lora" - elif class_name == "WanPipeline": - mir_prefix = "info.dit" - elif class_name == "CogVideoXVideoToVideoPipeline": - class_name = "CogVideoXPipeline" - elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): - mir_prefix = "info.controlnet" - else: - mir_prefix = mir_prefix_from_forward_pass(**sub_segments) - if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: - nfo(f"Failed to detect type for {class_name} {list(sub_segments)}\n") - else: - mir_prefix = "info." + mir_prefix - if class_name == "StableDiffusion3InpaintPipeline" or repo_path in ["stabilityai/stable-diffusion-3-medium-diffusers"]: - class_name = "StableDiffusion3Pipeline" - repo_path = "stabilityai/stable-diffusion-3.5-medium" - if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: - class_name = "HunyuanVideoPipeline" - mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) - mir_series = mir_prefix + "." + mir_series - repo_path = check_migrations(repo_path) - # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) - prefixed_data = { - "repo": repo_path, - "pkg": {0: {"diffusers": class_name}}, - # "mode": modalities.get("mode"), - } - return mir_series, {mir_comp: prefixed_data} - - -def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: - """Generate diffusion model data for MIR index\n - :return: Dictionary ready to be applied to MIR data fields - """ - special_repos = { - "black-forest-labs/FLUX.1-schnell": "black-forest-labs/FLUX.1-dev", - # "stabilityai/stable-diffusion-3-medium-diffusers": "stabilityai/stable-diffusion-3.5-medium", - } - special_classes = { - # "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", # NOT sd3 - "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt - "ChromaPipeline": "lodestones/Chroma", - } - from mir.inspect.metadata import find_diffusers_docstrings - - extracted_docstrings = find_diffusers_docstrings() - model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] - pipe_data = {} # pipeline_stable_diffusion_xl_inpaint - - for extracted in model_info: - parsed_data: DocParseData = parse_docs(extracted.doc_string) - if parsed_data is None: - print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") - continue - for class_name, swap_repo in special_classes.items(): - if parsed_data.pipe_class == class_name: - parsed_data.pipe_repo = swap_repo - break - model_class_obj = import_submodules(parsed_data.pipe_class, f"diffusers.pipelines.{extracted.package_name}.{extracted.file_name}") - if not model_class_obj: - continue - extract_init_parameters(model_class_obj) - try: - series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) - except TypeError: - pass # Attempt 1 - if pipe_data.get(series): - if "img2img" in parsed_data.pipe_class.lower(): - continue - pipe_data.setdefault(series, {}).update(comp_data) - special_conditions = special_repos | special_classes - if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): - test = special_conditions.get(parsed_data.pipe_repo) - if test: - staged_repo = test - parsed_data.staged_class = parsed_data.pipe_class - try: - series, comp_data = create_pipe_entry( - staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, - parsed_data.staged_class # - if parsed_data.staged_class - else parsed_data.pipe_class, - ) - except TypeError as error_log: - nfo(series, comp_data) - nfo(error_log) - continue # Attempt 2, - pipe_data.setdefault(series, {}).update(comp_data) - return dict(pipe_data) - - -def transformers_index(): - """Generate LLM model data for MIR index\n - :return: Dictionary ready to be applied to MIR data fields""" - - import os - - from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING_NAMES - - from mir.config.json_io import read_json_file - - root_folder = os.path.dirname(__file__) - params_file = os.path.join(os.path.join(root_folder, "spec", "missing_params.json")) - missing_config_params = read_json_file(params_file) - from mir.inspect.metadata import map_transformers_classes - - mir_data = {} - transformers_data: list[ClassMapEntry] = map_transformers_classes() - for entry in transformers_data: - repo_path = get_repo_from_class_map(entry) - if config := missing_config_params.get(entry.name, {}): - entry.config_params = config.get("params", entry.config_params) - if not repo_path or entry.name == "gpt_oss": - repo_path = config["repo_path"] - if not repo_path: - raise ValueError(f"Unable to determine repo from {entry}") - if entry.config_params: - mir_series, mir_comp, mir_suffix = mir_tag_from_config(entry, repo_path) - # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) - - repo_path = check_migrations(repo_path) - tk_pkg = {} - tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) - if isinstance(tokenizer_classes, str): - tokenizer_classes = [tokenizer_classes] - # mode = modalities.get("mode") - if tokenizer_classes: - index = 0 - for tokenizer in tokenizer_classes: - if tokenizer: - tokenizer_class = import_submodules(tokenizer, "transformers") - tk_pkg.setdefault(index, {"transformers": f"{tokenizer_class.__module__}.{tokenizer_class.__name__}"}) - index += 1 - if tk_pkg: - mir_data.get("info.encoder.tokenizer", mir_data.setdefault("info.encoder.tokenizer", {})).update( - { - mir_suffix: { - "pkg": tk_pkg, - } - }, - ) - mir_data.setdefault( - mir_series, - { - mir_comp: { - "repo": repo_path, - "pkg": { - 0: {"transformers": entry.model_name}, - }, - # "mode": mode, - }, - }, - ) - return mir_data - - -def mlx_repo_capture(base_repo: str = "mlx-community"): - import os - import re - - try: - import mlx_audio # type: ignore - except ImportError: - return {} - result = {} - result_2 = {} - folder_path_named: str = os.path.dirname(mlx_audio.__file__) - for root, dir, file_names in os.walk(folder_path_named): - for file in file_names: - if file.endswith((".py", ".html", ".md", ".ts")): - with open(os.path.join(root, file), "r") as open_file: - content = open_file.read() - if "mlx-community/" in content: - matches = re.findall(base_repo + r'/(.*?)"', content) - for match in matches: - result[match] = f"{base_repo}/{match}" - previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") - class_match = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) - if class_match: - result_2[match] = {f"{base_repo}/{match}": [*class_match]} - else: - if os.path.basename(root) in ["tts", "sts"]: - folder_name = match.partition("-")[0] - file_path = os.path.join(root, "models", folder_name, folder_name + ".py") - if os.path.exists(file_path): - with open(file_path, "r") as model_file: - read_data = model_file.read() # type: ignore # noqa - class_match = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) - - return result_2 - - -# def mlx_repo_capture(base_repo: str = "mlx-community"): -# import os -# import re -# import mlx_audio - -# result = {} -# result_2 = {} -# folder_path_named: str = os.path.dirname(mlx_audio.__file__) -# for root, _, file_names in os.walk(folder_path_named): -# for file in file_names: -# if file.endswith((".py", ".html", ".md", ".ts")): -# with open(os.path.join(root, file), "r") as open_file: -# content = open_file.read() -# if "mlx-community/" in content: -# matches = re.findall(base_repo + r'/(.*?)"', content) -# for match in matches: -# print(file) -# result[match] = f"{base_repo}/{match}" -# previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") -# matches = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) -# if matches: -# result_2[match] = {f"{base_repo}/{match}": [*matches]} -# else: -# result_2[match] = {f"{base_repo}/{match}": None} -# return result_2 - - -# def mlx_audio_scrape(base_repo: str = "mlx-community"): -# import os -# import re -# import mlx_audio - -# result = {} -# result_2 = {} -# folder_path_named: str = os.path.dirname(mlx_audio.__file__) -# for root, _, file_names in os.walk(folder_path_named): -# for file in file_names: -# if file.endswith((".py",)): -# with open(os.path.join(root, file), "r") as open_file: -# content = open_file.read() -# if "mlx-community/" in content: -# matches = re.findall(base_repo + r'/(.*?)"', content) -# for match in matches: -# result[match] = f"{base_repo}/{match}" -# previous_data = content[content.index(match) - 75 : content.index(match)].replace(base_repo, "") -# matches = re.findall(r"(\w+)\.from_pretrained", previous_data, re.MULTILINE) -# if len(matches) > 1: -# result_2[match] = {f"{base_repo}/{match}": [*matches]} -# else: -# if "nn.Module" in content: -# previous_data = content[content.rindex("nn.Module") - 50 : content.rindex("nn.Module")] -# matches = re.search(r"(\w+)\.", previous_data, re.MULTILINE) -# result_2[match] = {f"{base_repo}/{match}": [*matches]} -# return result_2 - - -# @MODE_DATA.decorator -# def add_mode_types(mir_tag: list[str], data: dict | None = None) -> dict[str, list[str] | str]: -# """_summary_\n -# :param mir_tag: _description_ -# :param data: _description_, defaults to None -# :return: _description_""" -# fused_tag = ".".join(mir_tag) - -# mir_details = { -# "mode": data.get(fused_tag, {}).get("pipeline_tag"), -# "pkg_type": data.get(fused_tag, {}).get("library_type"), -# "tags": data.get(fused_tag, {}).get("tags"), -# } -# return mir_details diff --git a/mir/inspect/classes.py b/mir/inspect/classes.py deleted file mode 100644 index 23b955c..0000000 --- a/mir/inspect/classes.py +++ /dev/null @@ -1,91 +0,0 @@ -# ### -# ### - -"""類發現和拆卸""" - -# pylint:disable=protected-access - -from typing import Callable, Dict, List, Optional, Union, Type -from mir.config.conversion import import_submodules -from mir.config.console import nfo - - -def resolve_import_path(code_name: str, pkg_name: str) -> Optional[List[str]]: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n - ### NOTE: in most cases `__module__` makes this redundant - :param code_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - import os - from importlib import import_module - - pkg_paths = { - "diffusers": "pipelines", - "transformers": "models", - } - folder_name = code_name.replace("-", "_") - pkg_name = pkg_name.lower() - folder_path = pkg_paths[pkg_name] - package_obj = import_module(pkg_name) - folder_path_named = [folder_path, folder_name] - pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) - # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) - if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: - import_path = [pkg_name] - import_path.extend(folder_path_named) - return import_path - - -def resolve_code_names(class_name: Optional[Union[str, Type]] = None, pkg_name: Optional[str] = "transformers", path_format: Optional[bool] = False) -> Union[List[str], str]: - """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n - :param class_name: To return only one class, defaults to None - :param pkg_name: optional field for library, defaults to "transformers" - :param path_format: Retrieve just the code name, or the full module path and code name within the package - :return: A list of all code names, or the one corresponding to the provided class""" - - package_map = { - "diffusers": ("_import_structure", "diffusers.pipelines"), - "transformers": ("MODEL_MAPPING_NAMES", "transformers.models.auto.modeling_auto"), - } - pkg_name = pkg_name.lower() - MAPPING_NAMES = import_submodules(*package_map[pkg_name]) - if class_name: - if isinstance(class_name, Type): - class_name = class_name.__name__ - code_name = next(iter(key for key, value in MAPPING_NAMES.items() if class_name in str(value)), "") - return resolve_import_path(code_name, pkg_name) if path_format else code_name.replace("_", "-") - return list(MAPPING_NAMES) - - -def extract_inherited_classes(model_class: Union[Callable, str], pkg_name: Optional[str] = None) -> Optional[Dict[str, List[str]]]: - """Strips tags from module's base classes and extracts inherited class members.\n - If `module` is a string, it requires the `library` argument to convert it into a callable.\n - :param module: A module or string representing a module. - :param library: Library name required if `module` is a string. Defaults to None. - :returns: Mapping indices to class path segments, or None if invalid input.""" - - if isinstance(model_class, str): - if not pkg_name: - nfo("Provide a library type argument to process strings") - return None - model_class = import_submodules(model_class, pkg_name) - signature = model_class.__bases__ - class_names = [] - for index, class_annotation in enumerate(signature): - tag_stripped = str(class_annotation)[8:-2] - module_segments = tag_stripped.split(".") - class_names.append(module_segments) - return class_names - - -# def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: -# from nnll.download.hub_cache import download_hub_file - -# model_file = download_hub_file( -# repo_id=f"{repo_id}/tree/main/{arch}", -# source="huggingface", -# file_name="diffusion_pytorch_model.safetensors.index.json", -# local_dir=".tmp", -# ) diff --git a/mir/inspect/metadata.py b/mir/inspect/metadata.py deleted file mode 100644 index 613afae..0000000 --- a/mir/inspect/metadata.py +++ /dev/null @@ -1,98 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable, Generator - -import diffusers -from mir.config.constants import ClassMapEntry, DocStringEntry, extract_init_parameters -from mir.config.conversion import retrieve_diffusers_docstrings - - -# if code_name and "__" not in code_name: -# tasks = TaskAnalyzer.show_transformers_tasks(code_name=code_name) -# if tasks and isinstance(tasks, list): # Ensure tasks is a list -# task_pipe = next(iter(tasks)) -# if isinstance(task_pipe, tuple): -# task_pipe = task_pipe[0] -# if task_pipe not in exclude_list: -# model_class = getattr(__import__("transformers"), task_pipe) # this is done to get the path to the config -# model_data = extract_init_params(model_class) -# if model_data and ("inspect" not in model_data["config"]) and ("deprecated" not in list(model_data["config"])): -# transformer_data.setdefault(model_class, model_data) -# else: -# model_data = None -# # Reset task_pipe if tasks was None or not a list -# if not tasks or not isinstance(tasks, list): -# task_pipe = None - -# if not model_data and code_name not in second_exclude_list: # second attempt -# if code_name == "donut": -# code_name = "donut-swin" -# if not task_pipe and code_name and MODEL_MAPPING_NAMES.get(code_name.replace("_", "-")): -# model_class = getattr(__import__("transformers"), MODEL_MAPPING_NAMES[code_name.replace("_", "-")], None) -# elif task_pipe: -# model_class = getattr(__import__("transformers"), task_pipe) -# config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("_", "-")) -# if not config_class: -# config_class = CONFIG_MAPPING_NAMES.get(code_name.replace("-", "_")) -# if config_class: -# config_class_obj = getattr(__import__("transformers"), config_class) -# model_data = {"config": str(config_class_obj.__module__ + "." + config_class_obj.__name__).split(".")} -# if model_data and ("inspect" not in model_data) and ("deprecated" not in model_data) and model_class: -# transformer_data.setdefault(model_class, model_data) -# return transformer_data - - -def map_transformers_classes() -> list[ClassMapEntry]: - """Eat the 🤗Transformers classes as a treat, leaving any tasty subclass class morsels neatly arranged as a dictionary.\n - Nom. - :return: Tasty mapping of subclasses to their class references""" - from transformers.models.auto.configuration_auto import CONFIG_MAPPING - from transformers.models.auto.modeling_auto import MODEL_MAPPING # config: model map - - model_data = [] - for config_name, config_obj in CONFIG_MAPPING.items(): - model_params = None - if model_obj := MODEL_MAPPING.get(config_obj, None): - if isinstance(model_obj, Callable): - model_obj = (model_obj,) - assert isinstance(model_obj, tuple) - for model_class in model_obj: - if model_params and ("inspect" not in model_params["config"]) and ("deprecated" not in list(model_params["config"])): - pass - else: - model_params = None - model_name = model_class.__name__ - model_data.append( - ClassMapEntry( - name=config_name, - model_name=model_name.split(".")[-1], - model=model_class, # type: ignore - config=config_obj, - ), - ) - return model_data - - -def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: - """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n - :return: Docstrings for common diffusers models""" - import os - - from diffusers.pipelines import _import_structure - - from mir.config.json_io import read_json_file - - project_root = os.path.dirname(os.path.dirname(__file__)) - pattern_file = os.path.join(project_root, "spec", "docstring_patterns.json") - docstring_patterns = read_json_file(pattern_file) - exclusion_list = docstring_patterns["exclusion_list"] - uncommon_naming = docstring_patterns["uncommon_naming"] - for pipe_name in _import_structure.keys(): - if pipe_name not in exclusion_list: - file_specific = uncommon_naming.get(pipe_name, pipe_name) - if import_name := getattr(diffusers.pipelines, str(pipe_name)): - file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] - yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) - else: - continue diff --git a/mir/inspect/parenting.py b/mir/inspect/parenting.py deleted file mode 100644 index a0bfa26..0000000 --- a/mir/inspect/parenting.py +++ /dev/null @@ -1,32 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import List, Optional - - -def class_parent(code_name: str, pkg_name: str) -> Optional[List[str]]: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n - ### NOTE: in most cases `__module__` makes this redundant - :param code_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - import os - from importlib import import_module - - pkg_paths = { - "diffusers": "pipelines", - "transformers": "models", - } - folder_name = code_name.replace("-", "_") - pkg_name = pkg_name.lower() - folder_path = pkg_paths[pkg_name] - package_obj = import_module(pkg_name) - folder_path_named = [folder_path, folder_name] - pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) - # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) - if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: - import_path = [pkg_name] - import_path.extend(folder_path_named) - return import_path diff --git a/mir/inspect/pipes.py b/mir/inspect/pipes.py deleted file mode 100644 index cdec5f7..0000000 --- a/mir/inspect/pipes.py +++ /dev/null @@ -1,46 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import List, Optional - - -def show_shared_hyperparameters(parameter_filter: Optional[str] = None) -> List[str]: - """Show all config classes in the Transformer package with the specified init annotation\n - :param from_match: Narrow the classes to only those with an exact key inside - :return: A list of all Classes""" - from mir.inspect.metadata import map_transformers_classes - from mir.config.constants import extract_init_parameters - - transformers_data = map_transformers_classes() - config_data = [] - for entry in transformers_data: - if parameter_filter: - segments = extract_init_parameters(module=entry.config, package_name="transformers") - if parameter_filter in list(segments): - config_data.append(entry.config) - else: - config_data.append(entry.config) - return config_data - - -def get_class_parent_folder(class_name: str, pkg_name: str) -> List[str]: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system (formerly seek_class_path)\n - ### NOTE: in most cases `__module__` makes this redundant - :param class_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - from mir.config.console import dbuq - from mir.inspect.classes import resolve_code_names, extract_init_params - - pkg_name = pkg_name.lower() - if pkg_name == "diffusers": - parent_folder: List[str] = resolve_code_names(class_name=class_name, pkg_name=pkg_name, path_format=True) - if not parent_folder or not parent_folder[-1].strip(): - dbuq("Data not found for", " class_name = {class_name},pkg_name = {pkg_name},{parent_folder} = parent_folder") - return None - elif pkg_name == "transformers": - module_path = extract_init_params(class_name, "transformers").get("config") - parent_folder = module_path[:3] - return parent_folder diff --git a/mir/config/json_io.py b/mir/json_io.py similarity index 87% rename from mir/config/json_io.py rename to mir/json_io.py index 92cd60f..6248b11 100644 --- a/mir/config/json_io.py +++ b/mir/json_io.py @@ -1,8 +1,6 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -# pylint: disable=import-outside-toplevel - from typing import Any @@ -17,8 +15,6 @@ def write_json_file(folder_path_named: str, file_name: str, data: Any, mode: str import json import os - from mir.config.console import dbuq - if ".json" not in file_name: file_name += ".json" document = os.path.join(folder_path_named, os.path.basename(file_name)) @@ -26,7 +22,7 @@ def write_json_file(folder_path_named: str, file_name: str, data: Any, mode: str try: os.remove(document) except FileNotFoundError as error_log: - dbuq(f"'File was detected but not found to remove: {document}.'{error_log}", exc_info=True) + print(f"'File was detected but not found to remove: {document}.'{error_log}") with open(document, mode, encoding="UTF-8") as i: json.dump(data, i, ensure_ascii=False, indent=4, sort_keys=False) diff --git a/mir/mir.json b/mir/mir.json deleted file mode 100644 index c897555..0000000 --- a/mir/mir.json +++ /dev/null @@ -1,14941 +0,0 @@ -{ - "info.controlnet.sd-controlnet-canny": { - "*": { - "repo": "lllyasviel/sd-controlnet-canny", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.blipdiffusion-controlnet": { - "*": { - "repo": "Salesforce/blipdiffusion-controlnet", - "pkg": { - "0": { - "diffusers": "BlipDiffusionControlNetPipeline" - } - } - } - }, - "info.controlnet.control-v11p-sd15-inpaint": { - "*": { - "repo": "lllyasviel/control_v11p_sd15_inpaint", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-canny-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-canny-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-depth-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-depth-sdxl-1.0-small", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.stable-diffusion-xl-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLControlNetUnionInpaintPipeline" - } - } - } - }, - "info.controlnet.controlnet-union-sdxl-1": { - "*": { - "repo": "xinsir/controlnet-union-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetUnionModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-canny": { - "*": { - "repo": "InstantX/SD3-Controlnet-Canny", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-inpainting": { - "*": { - "repo": "alimama-creative/SD3-Controlnet-Inpainting", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sd2-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SD2.1-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sdxl-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SDXL-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.unet.marigold-depth-v1-1": { - "*": { - "repo": "prs-eth/marigold-depth-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldDepthPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-depth-v1-1" - ] - } - } - }, - "info.unet.marigold-iid-appearance-v1-1": { - "*": { - "repo": "prs-eth/marigold-iid-appearance-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldIntrinsicsPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-iid-appearance-v1-1" - ] - } - } - }, - "info.unet.marigold-normals-v1-1": { - "*": { - "repo": "prs-eth/marigold-normals-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldNormalsPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-normals-v1-1" - ] - } - } - }, - "info.unet.stable-diffusion-v1-5": { - "*": { - "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", - "pkg": { - "0": { - "diffusers": "StableDiffusionPipeline" - } - }, - "identifiers": [ - "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" - ], - "file_256": [ - "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", - "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", - "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", - "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", - "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", - "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", - "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" - ], - "layer_b3": [ - "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", - "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", - "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", - "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" - ], - "layer_256": [ - "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", - "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", - "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" - ], - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-v1-5" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ] - } - } - }, - "info.unet.stable-unclip-2-1-l": { - "*": { - "repo": "fusing/stable-unclip-2-1-l", - "pkg": { - "0": { - "diffusers": "StableUnCLIPPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "prior_tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "prior_text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "prior": [ - "PriorTransformer" - ], - "prior_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_normalizer": [ - "info.dit.flux1-schnell", - "*" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - } - } - }, - "info.unet.stable-diffusion-2-1-unclip": { - "*": { - "repo": "stabilityai/stable-diffusion-2-1-unclip-small", - "pkg": { - "0": { - "diffusers": "StableUnCLIPImg2ImgPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_normalizer": [ - "info.dit.flux1-schnell", - "*" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-2-1-unclip" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - } - } - }, - "info.unet.stable-diffusion-xl-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "denoising_end": 0.8, - "num_inference_steps": 40, - "output_type": "latent", - "safety_checker": false, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", - "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", - "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", - "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" - ], - "layer_256": [ - "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", - "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", - "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" - ], - "layer_b3": [ - "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", - "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", - "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" - ], - "identifiers": [ - "logit_scale", - "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", - "add_embedding.linear_2.bias" - ], - "pipe_names": {} - }, - "pony-diffusion": { - "file_256": [ - "67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3" - ], - "layer_256": [ - "465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e" - ], - "layer_b3": [ - "bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071" - ] - }, - "pony-diffusion-turbo": { - "file_256": [ - "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", - "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2" - ], - "layer_256": [ - "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", - "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52" - ], - "layer_b3": [ - "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", - "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc" - ] - }, - "animagine-xl-4": { - "repo": "cagliostrolab/animagine-xl-4.0", - "file_256": [ - "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", - "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", - "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", - "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0" - ], - "layer_256": [ - "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", - "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", - "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", - "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65" - ], - "layer_b3": [ - "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", - "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", - "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", - "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447" - ] - }, - "illustrious-xl-v2": { - "repo": "OnomaAIResearch/Illustrious-XL-v2.0", - "file_256": [ - "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", - "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", - "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", - "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", - "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd" - ], - "layer_256": [ - "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", - "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", - "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", - "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", - "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10" - ], - "layer_b3": [ - "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", - "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", - "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", - "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", - "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c" - ] - }, - "playground-v2---aesthetic": { - "repo": "playgroundai/playground-v2.5-1024px-aesthetic", - "pkg": { - "0": { - "diffusers": "DiffusionPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 50, - "guidance_scale": 3 - } - } - }, - "file_256": [ - "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", - "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", - "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", - "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", - "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", - "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a" - ], - "layer_256": [ - "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", - "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", - "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", - "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", - "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c" - ], - "layer_b3": [ - "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", - "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", - "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", - "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", - "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", - "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" - ], - "pipe_names": {} - }, - "segmind-vega": { - "repo": "segmind/Segmind-Vega", - "file_256": [ - "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", - "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", - "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2" - ], - "layer_256": [ - "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", - "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", - "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741" - ], - "layer_b3": [ - "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", - "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", - "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1" - ] - }, - "ssd": { - "repo": "segmind/SSD-1B", - "file_256": [ - "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", - "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", - "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", - "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", - "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a" - ], - "layer_256": [ - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ], - "layer_b3": [ - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ] - } - }, - "info.unet.stable-diffusion-xl-refiner-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-refiner-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLImg2ImgPipeline" - }, - "1": { - "diffusers": "DiffusionPipeline", - "generation": { - "num_inference_steps": 40, - "denoising_end": 0.8 - } - } - }, - "identifiers": [ - "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" - ], - "file_256": [ - "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", - "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", - "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" - ], - "layer_b3": [ - "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", - "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", - "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" - ], - "layer_256": [ - "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", - "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", - "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" - ], - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.sdxl-pix2pix-768": { - "*": { - "repo": "diffusers/sdxl-instructpix2pix-768", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLInstructPix2PixPipeline" - } - }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.allegro": { - "*": { - "repo": "rhymes-ai/Allegro", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "guidance_scale": 7.5, - "max_sequence_length": 512, - "num_inference_steps": 100 - } - } - }, - "file_256": [ - "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" - ], - "layer_b3": [ - "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" - ], - "layer_256": [ - "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" - ] - } - }, - "info.dit.amused-512": { - "*": { - "repo": "amused/amused-512", - "pkg": { - "0": { - "diffusers": "AmusedInpaintPipeline" - } - }, - "pipe_names": { - "vqvae": [ - "VQModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "amused-512" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "UVit2DModel" - ], - "scheduler": [ - "ops.scheduler.amused", - "scheduler" - ] - } - } - }, - "info.lora.animatediff-motion-adapter-v1-5-2": { - "*": { - "repo": "guoyww/animatediff-motion-adapter-v1-5-2", - "pkg": { - "0": { - "diffusers": "AnimateDiffVideoToVideoPipeline" - } - } - } - }, - "info.lora.animatelcm": { - "*": { - "repo": "wangfuyun/AnimateLCM", - "pkg": { - "0": { - "diffusers": "MotionAdapter" - } - } - } - }, - "info.lora.animatediff-motion-adapter-sdxl": { - "*": { - "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", - "pkg": { - "0": { - "diffusers": "AnimateDiffSDXLPipeline" - } - } - } - }, - "info.controlnet.animatediff-sparsectrl-scribble": { - "*": { - "repo": "guoyww/animatediff-sparsectrl-scribble", - "pkg": { - "0": { - "diffusers": "SparseControlNetModel" - } - } - } - }, - "info.controlnet.animatelcm": { - "*": { - "repo": "wangfuyun/AnimateLCM", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.dit.bria-3": { - "*": { - "repo": "briaai/BRIA-3.2", - "pkg": { - "0": { - "diffusers": "BriaPipeline" - } - }, - "pipe_names": { - "transformer": [ - "BriaTransformer2DModel" - ], - "scheduler": [ - [ - "ops.scheduler.euler", - "discrete" - ], - [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "bria-3" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.flux2-dev": { - "*": { - "repo": "black-forest-labs/FLUX.2-dev", - "pkg": { - "0": { - "diffusers": "Flux2Pipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.mistral-3-2503", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux2-dev" - ], - "transformer": [ - "Flux2Transformer2DModel" - ] - } - } - }, - "info.dit.flux1-schnell": { - "*": { - "repo": "black-forest-labs/FLUX.1-schnell", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 0.0, - "num_inference_steps": 4, - "max_sequence_length": 256 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "num_inference_steps": 4 - } - } - }, - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "file_256": [ - "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", - "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" - ], - "layer_b3": [ - "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", - "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", - "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" - ], - "layer_256": [ - "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", - "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", - "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" - ], - "tasks": [ - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - }, - "shuttle-3-aesthetic": { - "repo": "shuttleai/shuttle-3.1-aesthetic", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", - "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" - ], - "layer_256": [ - "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", - "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a" - ], - "layer_b3": [ - "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", - "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c" - ] - }, - "shuttle-3-diffusion": { - "repo": "shuttleai/shuttle-3-diffusion", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", - "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", - "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", - "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8" - ], - "layer_256": [ - "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", - "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", - "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c" - ], - "layer_b3": [ - "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", - "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", - "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd" - ] - }, - "shuttle-jaguar": { - "repo": "shuttleai/shuttle-jaguar", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", - "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f" - ], - "layer_b3": [ - "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", - "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672" - ] - } - }, - "info.controlnet.flux1-canny-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Canny-dev", - "pkg": { - "0": { - "diffusers": "FluxControlPipeline" - } - } - } - }, - "info.controlnet.flux1-depth-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Depth-dev", - "pkg": { - "0": { - "diffusers": "FluxControlInpaintPipeline" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny": { - "*": { - "repo": "InstantX/FLUX.1-dev-controlnet-canny", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny-alpha": { - "*": { - "repo": "InstantX/FLUX.1-dev-Controlnet-Canny-alpha", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.dit.flux1-fill-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Fill-dev", - "pkg": { - "0": { - "diffusers": "FluxFillPipeline" - } - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - } - } - }, - "info.dit.flux1-kontext-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Kontext-dev", - "pkg": { - "0": { - "diffusers": "FluxKontextInpaintPipeline" - } - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.prx-512-t2i-sft": { - "*": { - "repo": "Photoroom/prx-512-t2i-sft", - "pkg": { - "0": { - "diffusers": "PRXPipeline" - } - }, - "pipe_names": { - "transformer": [ - "PRXTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder": [ - "info.stst.t5gemma-prefixlm", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "prx-512-t2i-sft" - ], - "vae": [ - "AutoencoderKL", - [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "NoneType" - ] - } - } - }, - "info.unet.audioldm-s-v2": { - "*": { - "repo": "cvssp/audioldm-s-full-v2", - "pkg": { - "0": { - "diffusers": "AudioLDMPipeline" - } - }, - "file_256": [ - "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clap-htsat-fused", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "info.stst.speecht5-asr", - "*" - ] - } - } - }, - "info.unet.audioldm2": { - "*": { - "repo": "cvssp/audioldm2", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" - ], - "layer_b3": [ - "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" - ], - "layer_256": [ - "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" - ] - } - }, - "info.unet.blipdiffusion": { - "*": { - "repo": "Salesforce/blipdiffusion", - "pkg": { - "0": { - "diffusers": "BlipDiffusionPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "blipdiffusion" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - "ops.scheduler.pndm", - "scheduler" - ], - "qformer": [ - "info.vit.blip2-opt", - "*" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chroma": { - "*": { - "repo": "lodestones/Chroma", - "pkg": { - "0": { - "diffusers": "ChromaPipeline" - }, - "1": { - "generation": { - "neg_text": "", - "num_steps": "28", - "latent_size": [ - 64, - 64 - ] - } - } - }, - "file_256": [ - "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", - "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", - "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", - "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" - ], - "layer_b3": [ - "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" - ], - "layer_256": [ - "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" - ], - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - }, - "chroma1-hd": { - "repo": "lodestones/Chroma1-HD", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 40 - } - } - }, - "file_256": [ - "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", - "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", - "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc" - ] - }, - "chroma1-flash": { - "repo": "lodestones/Chroma1-Flash", - "pkg": { - "0": { - "diffusers": "ChromaPipeline", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.0, - "num_images_per_prompt": 1 - } - } - }, - "file_256": [ - "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", - "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", - "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" - ], - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chroma1-hd": { - "*": { - "repo": "lodestones/Chroma1-HD", - "pkg": { - "0": { - "diffusers": "ChromaImg2ImgPipeline" - } - }, - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma1-hd" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.cogvideox": { - "*": { - "repo": "zai-org/CogVideoX-2b", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_videos_per_prompt": 1, - "num_inference_steps": 50, - "num_frames": 49, - "guidance_scale": 6 - } - } - }, - "file_256": [ - "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" - ], - "layer_b3": [ - "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" - ], - "layer_256": [ - "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" - ] - } - }, - "info.controlnet.cogvideox-fun-v-pose": { - "*": { - "repo": "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", - "pkg": { - "0": { - "diffusers": "CogVideoXFunControlPipeline" - } - } - } - }, - "info.dit.cogvideox-i2v": { - "*": { - "repo": "zai-org/CogVideoX-5b-I2V", - "pkg": { - "0": { - "diffusers": "CogVideoXImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogvideox-i2v" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "info.vae.cogvideox", - "cogvideox-i2v" - ], - "transformer": [ - "CogVideoXTransformer3DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - } - } - }, - "info.dit.cogview3": { - "*": { - "repo": "zai-org/CogView3-Plus-3B", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "guidance_scale": 7.0, - "num_images_per_prompt": 1, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - } - } - } - }, - "info.dit.cogview4": { - "*": { - "repo": "zai-org/CogView4-6B", - "pkg": { - "0": { - "diffusers": "CogView4Pipeline" - } - }, - "tasks": [ - "CogView4ControlPipeline", - "CogView4Pipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogview4" - ], - "text_encoder": [ - "info.stst.glm-4-chat", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "CogView4Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.controlnet.cogview4-control": { - "*": { - "repo": "zai-org/CogView4-6B-Control", - "pkg": { - "0": { - "diffusers": "CogView4ControlPipeline" - } - } - } - }, - "info.dit.pre-trianed": { - "*": { - "repo": "model_id, revision=\"diffusers/base/pre-trianed", - "pkg": { - "0": { - "diffusers": "Cosmos2_5_PredictBasePipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "pre-trianed" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-predict2-text2image": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Text2Image", - "pkg": { - "0": { - "diffusers": "Cosmos2TextToImagePipeline" - } - }, - "file_256": [ - "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", - "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", - "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", - "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", - "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", - "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", - "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", - "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", - "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", - "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", - "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", - "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", - "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" - ], - "layer_b3": [ - "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", - "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", - "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", - "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", - "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", - "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", - "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", - "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", - "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", - "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", - "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", - "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", - "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" - ], - "layer_256": [ - "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", - "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", - "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", - "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", - "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", - "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", - "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", - "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", - "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", - "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", - "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", - "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", - "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" - ], - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-text2image" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-predict2-video2world": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Video2World", - "pkg": { - "0": { - "diffusers": "Cosmos2VideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-text2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Text2World", - "pkg": { - "0": { - "diffusers": "CosmosTextToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-text2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-video2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Video2World", - "pkg": { - "0": { - "diffusers": "CosmosVideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.unet.if-ii-l-v1": { - "*": { - "repo": "DeepFloyd/IF-II-L-v1.0", - "pkg": { - "0": { - "diffusers": "IFSuperResolutionPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "if-ii-l-v1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ], - "image_noising_scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ] - } - } - }, - "info.dit.easyanimatev5-zh": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimatePipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - [ - "info.art.bert-uncased", - "*" - ] - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.controlnet.easyanimatev5-zh-control": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-Control-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateControlPipeline" - } - } - } - }, - "info.dit.easyanimatev5-zh-inp": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-InP-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateInpaintPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - [ - "info.art.bert-uncased", - "*" - ] - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh-inp" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.hidream-i1": { - "*": { - "repo": "HiDream-ai/HiDream-I1-Full", - "pkg": { - "0": { - "diffusers": "HiDreamImagePipeline" - } - }, - "file_256": [ - "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" - ], - "layer_b3": [ - "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" - ], - "layer_256": [ - "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_3": [ - "info.stst.t5", - "*" - ], - "tokenizer_3": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_4": [ - "info.stst.llama-2-hf", - "*" - ], - "tokenizer_4": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuandit-v1": { - "diffusers": { - "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", - "pkg": { - "0": { - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "extra_embedder", - "model.blocks", - "skip_norm.weight" - ], - "file_256": [ - "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", - "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", - "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" - ], - "layer_b3": [ - "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", - "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", - "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" - ], - "layer_256": [ - "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", - "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", - "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" - ] - } - }, - "info.dit.hunyuanvideo": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo", - "pkg": { - "0": { - "diffusers": "HunyuanVideoPipeline" - } - }, - "file_256": [ - "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" - ], - "layer_b3": [ - "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" - ], - "layer_256": [ - "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" - ], - "pipe_names": { - "text_encoder": [ - "info.stst.llama-2-hf", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ] - } - } - }, - "info.dit.hunyuanvideo-i2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-I2V", - "pkg": { - "0": { - "diffusers": "HunyuanVideoImageToVideoPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.llava", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanvideo-1-480p-t2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_t2v", - "pkg": { - "0": { - "diffusers": "HunyuanVideo15Pipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-t2v" - ], - "transformer": [ - "HunyuanVideo15Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-t2v" - ], - "guider": [ - "ClassifierFreeGuidance" - ] - } - } - }, - "info.dit.hunyuanvideo-1-480p-i2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_i2v", - "pkg": { - "0": { - "diffusers": "HunyuanVideo15ImageToVideoPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-i2v" - ], - "transformer": [ - "HunyuanVideo15Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-i2v" - ], - "guider": [ - "ClassifierFreeGuidance" - ], - "image_encoder": [ - "SiglipVisionModel" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanimage-2": { - "diffusers": { - "repo": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", - "pkg": { - "0": { - "diffusers": "HunyuanImagePipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanimage-2" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanimage-2" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanimage-2-refiner": { - "diffusers": { - "repo": "hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", - "pkg": { - "0": { - "diffusers": "HunyuanImageRefinerPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanimage-2-refiner" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.kandinsky-2-1": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-1-prior", - "pkg": { - "0": { - "diffusers": "KandinskyPriorPipeline" - } - }, - "tasks": [ - "Kandinsky3Img2ImgPipeline", - "Kandinsky3Pipeline", - "KandinskyCombinedPipeline", - "KandinskyImg2ImgCombinedPipeline", - "KandinskyImg2ImgPipeline", - "KandinskyInpaintCombinedPipeline", - "KandinskyInpaintPipeline", - "KandinskyPipeline", - "KandinskyV22CombinedPipeline", - "KandinskyV22Img2ImgCombinedPipeline", - "KandinskyV22Img2ImgPipeline", - "KandinskyV22InpaintCombinedPipeline", - "KandinskyV22InpaintPipeline", - "KandinskyV22Pipeline" - ], - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-1" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.kandinsky-2-2": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-2-prior", - "pkg": { - "0": { - "diffusers": "KandinskyV22PriorPipeline" - } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-2" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.latte-1": { - "*": { - "repo": "maxin-cn/Latte-1", - "pkg": { - "0": { - "diffusers": "LattePipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "latte-1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "LatteTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.ltx-video": { - "*": { - "repo": "Lightricks/LTX-Video", - "pkg": { - "0": { - "diffusers": "LTXImageToVideoPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.ltx-video-09": { - "*": { - "repo": "Lightricks/LTX-Video-0.9.5", - "pkg": { - "0": { - "diffusers": "LTXConditionPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video-09" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.lumina-next-sft": { - "diffusers": { - "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", - "pkg": { - "0": { - "precision": " ops.precision.bfloat.B16" - } - }, - "identifiers": [ - "time_caption", - "feed_forward" - ], - "file_256": [ - "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" - ], - "layer_b3": [ - "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", - "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" - ], - "layer_256": [ - "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", - "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" - ] - } - }, - "info.dit.lumina-image-2": { - "*": { - "repo": "Alpha-VLLM/Lumina-Image-2.0", - "pkg": { - "0": { - "diffusers": "Lumina2Pipeline" - } - }, - "file_256": [ - "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", - "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" - ], - "layer_b3": [ - "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" - ], - "layer_256": [ - "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" - ], - "tasks": [ - "Lumina2Pipeline" - ], - "pipe_names": { - "transformer": [ - "Lumina2Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "lumina-image-2" - ] - } - }, - "illustrious-lumina-v3": { - "repo": "OnomaAIResearch/Illustrious-Lumina-v0.03", - "file_256": [ - "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", - "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214" - ], - "layer_256": [ - "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", - "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828" - ], - "layer_b3": [ - "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", - "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c" - ] - } - }, - "info.dit.lucy-edit-dev": { - "*": { - "repo": "decart-ai/Lucy-Edit-Dev", - "pkg": { - "0": { - "diffusers": "LucyEditPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "lucy-edit-dev" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.longcat-image": { - "*": { - "repo": "meituan-longcat/LongCat-Image", - "pkg": { - "0": { - "diffusers": "LongCatImagePipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "longcat-image" - ], - "text_processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.longcat-image-edit": { - "*": { - "repo": "meituan-longcat/LongCat-Image-Edit", - "pkg": { - "0": { - "diffusers": "LongCatImageEditPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "longcat-image-edit" - ], - "text_processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.mochi-1": { - "*": { - "repo": "genmo/mochi-1-preview", - "pkg": { - "0": { - "diffusers": "MochiPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "mochi-1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "mochi-1" - ], - "transformer": [ - "MochiTransformer3DModel" - ] - } - } - }, - "info.unet.musicldm": { - "*": { - "repo": "ucsd-reach/musicldm", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ] - } - }, - "info.dit.omnigen-v1": { - "diffusers": { - "repo": "Shitao/OmniGen-v1-diffusers", - "pkg": { - "0": { - "diffusers": "OmniGenPipeline" - } - }, - "pipe_names": { - "transformer": [ - "OmniGenTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "omnigen-v1" - ] - } - } - }, - "info.dit.ovis-image": { - "*": { - "repo": "AIDC-AI/Ovis-Image-7B", - "pkg": { - "0": { - "diffusers": "OvisImagePipeline" - } - }, - "tasks": [ - "OvisImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.qwen3", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ovis-image" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.visualclozepipeline-384": { - "*": { - "repo": "VisualCloze/VisualClozePipeline-384", - "pkg": { - "0": { - "diffusers": "VisualClozeGenerationPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - } - } - }, - "info.lora.pia-condition-adapter": { - "*": { - "repo": "openmmlab/PIA-condition-adapter", - "pkg": { - "0": { - "diffusers": "PIAPipeline" - } - } - } - }, - "info.dit.pixart-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtAlphaPipeline" - } - }, - "identifiers": [ - "aspect_ratio", - "y_embedding", - "emb.resolution", - "caption_projection" - ], - "file_256": [ - "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" - ], - "layer_b3": [ - "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" - ], - "layer_256": [ - "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" - ], - "tasks": [ - "PixArtAlphaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-xl-2-1024-ms" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } - } - }, - "info.dit.pixart-sigma-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtSigmaPipeline" - } - }, - "identifiers": [ - "adaln_single", - "scale_shift_table" - ], - "file_256": [ - "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", - "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" - ], - "layer_b3": [ - "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", - "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" - ], - "layer_256": [ - "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", - "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" - ], - "tasks": [ - "PixArtAlphaPipeline", - "PixArtSigmaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-sigma-xl-2-1024-ms" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.sana-1024px-bf16": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", - "pkg": { - "0": { - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 4.5, - "num_inference_steps": 20 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" - ], - "layer_b3": [ - "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" - ], - "layer_256": [ - "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" - ] - } - }, - "info.controlnet.sana-1024px-controlnet": { - "diffusers": { - "repo": "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers", - "pkg": { - "0": { - "diffusers": "SanaControlNetPipeline" - } - } - } - }, - "info.dit.sana-sprint-1024px": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", - "pkg": { - "0": { - "diffusers": "SanaSprintPipeline" - } - }, - "tasks": [ - "SanaPAGPipeline", - "SanaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-sprint-1024px" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "vae": [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "transformer": [ - "SanaTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } - } - }, - "info.dit.sana-video": { - "*": { - "repo": "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", - "pkg": { - "0": { - "diffusers": "SanaImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-video" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "vae": [ - [ - "info.vae.dc", - "sana-1024px-bf16" - ], - [ - "info.vae.kl", - "audioldm-s-v2" - ] - ], - "transformer": [ - "SanaVideoTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.unet.shap-e": { - "*": { - "repo": "openai/shap-e", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 64, - "size": 256, - "guidance_scale": 15 - } - } - } - } - }, - "info.dit.stable-audio-open-1": { - "*": { - "repo": "stabilityai/stable-audio-open-1.0", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_end_in_s": 10, - "num_waveforms_per_prompt": 3 - } - } - } - } - }, - "info.unet.stable-cascade": { - "prior": { - "repo": "stabilityai/stable-cascade-prior", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "negative_prompt": "", - "num_images_per_prompt": 1, - "num_inference_steps": 20, - "guidance_scale": 4.0, - "width": 1024, - "height": 1024 - } - } - }, - "file_256": [ - "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", - "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", - "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", - "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", - "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", - "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" - ], - "layer_b3": [ - "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", - "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", - "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", - "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", - "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", - "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" - ], - "layer_256": [ - "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", - "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", - "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", - "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", - "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", - "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" - ], - "identifiers": [ - "down_blocks.0.2.kv_mapper", - "previewer", - "backbone" - ] - }, - "decoder": { - "pkg": { - "0": { - "generation": { - "negative_prompt": "", - "guidance_scale": 0.0, - "output_type": "pil", - "num_inference_steps": 10 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", - "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", - "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", - "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", - "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" - ], - "layer_b3": [ - "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", - "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", - "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", - "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", - "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" - ], - "layer_256": [ - "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", - "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", - "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", - "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", - "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" - ], - "identifiers": [ - "0.2.channelwise", - "clip_mapper.bias", - ".12.self_attn.k_proj.weight" - ] - } - }, - "info.dit.auraflow": { - "*": { - "repo": "fal/AuraFlow", - "pkg": { - "0": { - "diffusers": "AuraFlowPipeline" - } - }, - "identifiers": [ - [ - 8192, - 3072 - ], - "mlpX.c_fc2.weight", - "joint_transformer_blocks.2.ff_context.linear_2.weight" - ], - "file_256": [ - "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", - "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", - "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", - "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" - ], - "layer_b3": [ - "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", - "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", - "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", - "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" - ], - "layer_256": [ - "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", - "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", - "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", - "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" - ], - "tasks": [ - "AuraFlowPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "auraflow" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "AuraFlowTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.stable-diffusion-3": { - "*": { - "repo": "stabilityai/stable-diffusion-3.5-medium", - "pkg": { - "0": { - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "model.diffusion_model.joint_blocks.", - "transformer_blocks.21.norm1_context.linear.weight", - "transformer_blocks.31.norm1_context.linear.weight", - "blocks.11.ff.net.2.weight" - ], - "file_256": [ - "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", - "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" - ], - "layer_b3": [ - "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", - "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" - ], - "layer_256": [ - "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", - "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" - ] - }, - "stable-diffusion-3-turbo": { - "repo": "tensorart/stable-diffusion-3.5-medium-turbo", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.5, - "height": 1024, - "width": 768 - } - } - }, - "file_256": [ - "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", - "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", - "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", - "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e" - ], - "layer_256": [ - "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ], - "layer_b3": [ - "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ] - } - }, - "info.unet.gligen-1-4-inpainting-text-box": { - "*": { - "repo": "masterful/gligen-1-4-inpainting-text-box", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENPipeline" - } - } - } - }, - "info.unet.gligen-inpainting-text-image": { - "*": { - "repo": "anhnct/Gligen_Inpainting_Text_Image", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENTextImagePipeline" - } - } - } - }, - "info.unet.stable-video-diffusion-img2vid-xt": { - "*": { - "repo": "stabilityai/stable-video-diffusion-img2vid-xt", - "pkg": { - "0": { - "diffusers": "StableVideoDiffusionPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "unet": [ - "UNetSpatioTemporalConditionModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.ldm3d-4c": { - "*": { - "repo": "Intel/ldm3d-4c", - "pkg": { - "0": { - "diffusers": "StableDiffusionLDM3DPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ldm3d-4c" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.i2vgen-xl": { - "*": { - "repo": "ali-vilab/i2vgen-xl", - "pkg": { - "0": { - "diffusers": "I2VGenXLPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "i2vgen-xl" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "unet": [ - "I2VGenXLUNet" - ], - "scheduler": [ - "ops.scheduler.ddim", - "scheduler" - ] - } - } - }, - "info.unet.wuerstchen": { - "prior": { - "repo": "warp-ai/wuerstchen-prior", - "pkg": { - "0": { - "diffusers": "WuerstchenPriorPipeline" - } - }, - "tasks": [ - "WuerstchenCombinedPipeline", - "WuerstchenDecoderPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wuerstchen" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "prior": [ - "WuerstchenPrior" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ] - } - } - }, - "info.dit.wan2-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", - "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", - "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", - "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", - "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", - "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", - "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", - "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" - ], - "layer_b3": [ - "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", - "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", - "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", - "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", - "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", - "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", - "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" - ], - "layer_256": [ - "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", - "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", - "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", - "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", - "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", - "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", - "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" - ] - } - }, - "info.dit.wan-animate": { - "diffusers": { - "repo": "Wan-AI/Wan2.2-Animate-14B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanAnimatePipeline" - } - }, - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan-animate" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "WanAnimateTransformer3DModel" - ] - } - } - }, - "info.dit.wan2-i2v-480p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", - "pkg": { - "0": { - "diffusers": "WanImageToVideoPipeline" - } - }, - "file_256": [ - "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", - "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", - "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", - "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", - "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", - "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", - "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", - "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", - "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" - ], - "layer_b3": [ - "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", - "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", - "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", - "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", - "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" - ], - "layer_256": [ - "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", - "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", - "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", - "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", - "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" - ], - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan2-i2v-480p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.wan", - "wan2-i2v-480p" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "WanTransformer3DModel" - ], - "transformer_2": [ - "WanTransformer3DModel" - ] - } - } - }, - "info.dit.wan21-vace": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-VACE-1.3B-diffusers", - "pkg": { - "0": { - "diffusers": "WanVACEPipeline" - } - }, - "file_256": [ - "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", - "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", - "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", - "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", - "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" - ], - "layer_b3": [ - "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", - "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", - "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", - "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" - ], - "layer_256": [ - "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", - "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", - "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", - "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" - ], - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-vace" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "transformer": [ - "WanVACETransformer3DModel" - ], - "transformer_2": [ - "WanVACETransformer3DModel" - ] - } - } - }, - "info.dit.wan21-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-t2v" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-t2v-lite-sft-5s": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5T2VPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-t2v-lite-sft-5s" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-t2v-lite-sft-5s" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-i2i-lite-sft": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5I2IPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-i2i-lite-sft" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-i2i-lite-sft" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-i2v-sft-5s": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5I2VPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-i2v-sft-5s" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-i2v-sft-5s" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-t2i-lite-sft": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5T2IPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-t2i-lite-sft" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-t2i-lite-sft" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.z-image-turbo": { - "*": { - "repo": "Z-a-o/Z-Image-Turbo", - "pkg": { - "0": { - "diffusers": "ZImageOmniPipeline" - } - }, - "tasks": [ - "ZImageControlNetInpaintPipeline", - "ZImageControlNetPipeline", - "ZImageImg2ImgPipeline", - "ZImageOmniPipeline", - "ZImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "PreTrainedModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "z-image-turbo" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ], - "siglip": [ - "info.vit.siglip2-patch16-224", - "*" - ], - "siglip_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.controlnet.z-image-turbo": { - "*": { - "repo": "Tongyi-MAI/Z-Image-Turbo", - "pkg": { - "0": { - "diffusers": "ZImageControlNetInpaintPipeline" - } - } - } - }, - "info.dit.skyreels-v2-t2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2Pipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-t2v-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-df-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-DF-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-df-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-i2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-I2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2ImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-i2v-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_processor": [ - "CLIPProcessor" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.qwen-image": { - "*": { - "repo": "Qwen/Qwen-Image", - "pkg": { - "0": { - "diffusers": "QwenImageInpaintPipeline" - } - }, - "file_256": [ - "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" - ], - "layer_b3": [ - "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" - ], - "layer_256": [ - "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" - ], - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.controlnet.qwen-image-controlnet-union": { - "*": { - "repo": "InstantX/Qwen-Image-ControlNet-Union", - "pkg": { - "0": { - "diffusers": "QwenImageControlNetModel" - } - } - } - }, - "info.controlnet.qwen-image-controlnet-inpainting": { - "*": { - "repo": "InstantX/Qwen-Image-ControlNet-Inpainting", - "pkg": { - "0": { - "diffusers": "QwenImageControlNetModel" - } - } - } - }, - "info.dit.qwen-image-edit": { - "*": { - "repo": "Qwen/Qwen-Image-Edit", - "pkg": { - "0": { - "diffusers": "QwenImageEditInpaintPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-edit" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.qwen-image-edit-2509": { - "*": { - "repo": "Qwen/Qwen-Image-Edit-2509", - "pkg": { - "0": { - "diffusers": "QwenImageEditPlusPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-edit-2509" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.qwen-image-layered": { - "*": { - "repo": "Qwen/Qwen-Image-Layered", - "pkg": { - "0": { - "diffusers": "QwenImageLayeredPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-layered" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chronoedit": { - "diffusers": { - "repo": "nvidia/ChronoEdit-14B-Diffusers", - "pkg": { - "0": { - "diffusers": "ChronoEditPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "chronoedit" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "transformer": [ - "ChronoEditTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.unet.kolors": { - "diffusers": { - "repo": "Kwai-Kolors/Kolors-diffusers", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "negative_prompt": "", - "guidance_scale": 5.0, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" - ], - "layer_b3": [ - "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" - ], - "layer_256": [ - "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" - ], - "identifiers": [ - ".DenseReluDense.wi.weight", - "encoder_hid_proj.weight" - ], - "pipe_names": {} - } - }, - "info.moe.trinity": { - "*": { - "repo": "arcee-ai/Trinity-Mini", - "pkg": { - "0": { - "transformers": "AfmoeModel" - } - }, - "tasks": [ - "AfmoeForCausalLM", - "AfmoeModel", - "AfmoePreTrainedModel" - ] - } - }, - "info.encoder.tokenizer": { - "aimv2-patch14-224-lit": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "albert-xx-v2": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "align": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "afm": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "aria": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "audio-flamingo-3-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "aya-vision": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" - } - } - }, - "bark": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "bart": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "bert-for-seq-generation-l-24-bbc-encoder": { - "pkg": { - "0": { - "transformers": "transformers.models.bert_generation.tokenization_bert_generation.BertGenerationTokenizer" - } - } - }, - "bigbird-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.big_bird.tokenization_big_bird.BigBirdTokenizer" - } - } - }, - "bigbird-pegasus-arxiv": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "biogpt": { - "pkg": { - "0": { - "transformers": "transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer" - } - } - }, - "bitnet-b18-4t": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "blenderbot": { - "pkg": { - "0": { - "transformers": "transformers.models.blenderbot_small.tokenization_blenderbot_small.BlenderbotSmallTokenizer" - } - } - }, - "blip-vqa": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "blip2-opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "bloom": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "blt": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "bridgetower": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "bros-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "camembert": { - "pkg": { - "0": { - "transformers": "transformers.models.camembert.tokenization_camembert.CamembertTokenizer" - } - } - }, - "canine-s": { - "pkg": { - "0": { - "transformers": "transformers.models.canine.tokenization_canine.CanineTokenizer" - } - } - }, - "chameleon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "chinese-clip-vit-patch16": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "clap-htsat-fused": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "clip-vit-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "clipseg-rd64": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "clvp-dev": { - "pkg": { - "0": { - "transformers": "transformers.models.clvp.tokenization_clvp.ClvpTokenizer" - } - } - }, - "llama-2-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "codegen-mono": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "c4ai-command-r-v01": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" - } - } - }, - "conv-bert": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "cpm-ant": { - "pkg": { - "0": { - "transformers": "transformers.models.cpmant.tokenization_cpmant.CpmAntTokenizer" - } - } - }, - "csm": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "ctrl": { - "pkg": { - "0": { - "transformers": "transformers.models.ctrl.tokenization_ctrl.CTRLTokenizer" - } - } - }, - "data2vec-audio-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "data2vec-text": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "dbrx": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "deberta": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta.tokenization_deberta.DebertaTokenizer" - } - } - }, - "deberta-v2-x": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2.DebertaV2Tokenizer" - } - } - }, - "deepseek-v2-lite": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "deepseek-v3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "deepseek-vl-chat": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "dia": { - "pkg": { - "0": { - "transformers": "transformers.models.dia.tokenization_dia.DiaTokenizer" - } - } - }, - "diffllama-handcut": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "distilbert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "dpr-ctx-encoder-single-nq": { - "pkg": { - "0": { - "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" - } - } - }, - "electra-discriminator": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "emu3-chat-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "ernie-3-zh": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "ernie-45-pt": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "ernie-4-a-pt": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "ernie-4-vl-a-pt": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "esm": { - "pkg": { - "0": { - "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" - } - } - }, - "exaone-4": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "falcon": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "falcon-mamba": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "flaubert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" - } - } - }, - "flava": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "flexolmo-7x-1t": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "florence-2": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "fnet": { - "pkg": { - "0": { - "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" - } - } - }, - "wmt19-en-ru": { - "pkg": { - "0": { - "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" - } - } - }, - "funnel": { - "pkg": { - "0": { - "transformers": "transformers.models.funnel.tokenization_funnel.FunnelTokenizer" - } - } - }, - "fuyu": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gemma": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma2": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma-3": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma3-text": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma-3n-e": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "git": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "glm-4-chat": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4-0414": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4-a": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4v-thinking": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4v": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-asr-nano-2512": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "got-ocr-2-hf": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gpt2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-bigcode-santacoder": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-neo": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-neox": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "gpt-neox-japanese": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox_japanese.tokenization_gpt_neox_japanese.GPTNeoXJapaneseTokenizer" - } - } - }, - "gpt-oss": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gpt-j": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "granite": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "powermoe": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "granite-4-h": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "moe-active-shared-experts": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "grounding-dino": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "groupvit-gcc-yfcc": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "helium": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "hubert-ls960": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "ibert-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "idefics": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "idefics2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "idefics3-llama3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "blip-flan-t5": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "internvl3-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "jais-2-chat": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "jamba-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "janus": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "jetmoe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "kosmos-2-patch14-224": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "kosmos-2": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "todo": { - "pkg": { - "0": { - "transformers": "transformers.models.parakeet.tokenization_parakeet_fast.ParakeetTokenizerFast" - } - } - }, - "layoutlm-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "layoutlmv2-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2.LayoutLMv2Tokenizer" - } - } - }, - "layoutlmv3": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" - } - } - }, - "led-16384": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "lfm2-vl": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "lilt-roberta-en": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "llama-4-scout-16e": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-v1-mistral-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-next-video-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-onevision-qwen2-ov-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "longformer-4096": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "long-t5-local": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "luke": { - "pkg": { - "0": { - "transformers": "transformers.models.luke.tokenization_luke.LukeTokenizer" - } - } - }, - "lxmert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "m": { - "pkg": { - "0": { - "transformers": "transformers.models.m2m_100.tokenization_m2m_100.M2M100Tokenizer" - } - } - }, - "mamba": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "mamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "opus-mt-en-de": { - "pkg": { - "0": { - "transformers": "transformers.models.marian.tokenization_marian.MarianTokenizer" - } - } - }, - "mbart-cc25": { - "pkg": { - "0": { - "transformers": "transformers.models.mbart.tokenization_mbart.MBartTokenizer" - } - } - }, - "megatron-bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "metaclip-2-worldwide-huge-quickgelu": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "mgp-str": { - "pkg": { - "0": { - "transformers": "transformers.models.mgp_str.tokenization_mgp_str.MgpstrTokenizer" - } - } - }, - "max-text-01-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "stral-3-2512": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mistral-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mistral-3-2503": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mixtral-8x": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llama-3-vision": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mm-grounding-dino-o365v1-goldg-v3det": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "mobilebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "modernbert": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "moonshine": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "hf-moshiko": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "mpnet": { - "pkg": { - "0": { - "transformers": "transformers.models.mpnet.tokenization_mpnet.MPNetTokenizer" - } - } - }, - "mpt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "mra-512-4": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "mt5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "musicgen": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "musicgen-melody": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "mvp": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "nemotron-3-hf": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "nllb-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.nllb.tokenization_nllb.NllbTokenizer" - } - } - }, - "nystromformer-512": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "olmo-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "olmo2-1124-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "olmo-3-0725": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "olmoe-0924": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "omdet-turbo-swin-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "oneformer-ade-swin": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "openai-gpt": { - "pkg": { - "0": { - "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" - } - } - }, - "opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "ovis2-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "owlv2-patch16": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "owlvit-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "paligemma": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "pegasus": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "pegasus-x": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "language-perceiver": { - "pkg": { - "0": { - "transformers": "transformers.models.perceiver.tokenization_perceiver.PerceiverTokenizer" - } - } - }, - "persimmon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "phi-1": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "phi-3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "phi-3-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "pixtral": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "plbart": { - "pkg": { - "0": { - "transformers": "transformers.models.plbart.tokenization_plbart.PLBartTokenizer" - } - } - }, - "phetnet-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.prophetnet.tokenization_prophetnet.ProphetNetTokenizer" - } - } - }, - "qwen2": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen2-vl": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen15-moe-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-next-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-vl": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-vl-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "recurrentgemma": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "reformer-crime-and-punishment": { - "pkg": { - "0": { - "transformers": "transformers.models.reformer.tokenization_reformer.ReformerTokenizer" - } - } - }, - "rembert": { - "pkg": { - "0": { - "transformers": "transformers.models.rembert.tokenization_rembert.RemBertTokenizer" - } - } - }, - "roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "efficient-mlm-m0-0": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "roc-bert-zh": { - "pkg": { - "0": { - "transformers": "transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer" - } - } - }, - "roformer-chinese": { - "pkg": { - "0": { - "transformers": "transformers.models.roformer.tokenization_roformer.RoFormerTokenizer" - } - } - }, - "rwkv-4-pile": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "hf-seamless-m4t": { - "pkg": { - "0": { - "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" - } - } - }, - "seamless-m4t-v2": { - "pkg": { - "0": { - "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" - } - } - }, - "siglip-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.siglip.tokenization_siglip.SiglipTokenizer" - } - } - }, - "siglip2-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "smollm3": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "s2t-librispeech-asr": { - "pkg": { - "0": { - "transformers": "transformers.models.speech_to_text.tokenization_speech_to_text.Speech2TextTokenizer" - } - } - }, - "speecht5-asr": { - "pkg": { - "0": { - "transformers": "transformers.models.speecht5.tokenization_speecht5.SpeechT5Tokenizer" - } - } - }, - "splinter": { - "pkg": { - "0": { - "transformers": "transformers.models.splinter.tokenization_splinter.SplinterTokenizer" - } - } - }, - "squeezebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "stablelm-4e1t": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "starcoder2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "switch-8": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "t5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "t5gemma-prefixlm": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "tapas-finetuned-sqa": { - "pkg": { - "0": { - "transformers": "transformers.models.tapas.tokenization_tapas.TapasTokenizer" - } - } - }, - "tvp": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "udop": { - "pkg": { - "0": { - "transformers": "transformers.models.udop.tokenization_udop.UdopTokenizer" - } - } - }, - "umt5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "video-llava-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "vilt-b32-mlm": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "vip-llava-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "visualbert-vqa-coco-pre": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "mms-tts-eng": { - "pkg": { - "0": { - "transformers": "transformers.models.vits.tokenization_vits.VitsTokenizer" - } - } - }, - "voxtral-2507": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "wav2vec2-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "wav2vec2-bert-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "wav2vec2-conformer-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "whisper": { - "pkg": { - "0": { - "transformers": "transformers.models.whisper.tokenization_whisper.WhisperTokenizer" - } - } - }, - "xclip-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "xglm": { - "pkg": { - "0": { - "transformers": "transformers.models.xglm.tokenization_xglm.XGLMTokenizer" - } - } - }, - "xlm-mlm-en-2048": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm.tokenization_xlm.XLMTokenizer" - } - } - }, - "xlm-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "xlm-roberta-xl": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "xlnet-cased": { - "pkg": { - "0": { - "transformers": "transformers.models.xlnet.tokenization_xlnet.XLNetTokenizer" - } - } - }, - "xlstm": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "xmod": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "yoso-4096": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "zamba-v1": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "zamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - } - }, - "info.vit.aimv2-patch14-224-lit": { - "*": { - "repo": "apple/aimv2-large-patch14-224-lit", - "pkg": { - "0": { - "transformers": "Aimv2Model" - } - }, - "tasks": [ - "Aimv2VisionModel", - "Aimv2Model", - "Aimv2PreTrainedModel", - "Aimv2TextModel" - ] - } - }, - "info.vit.aimv2-patch14-224": { - "*": { - "repo": "apple/aimv2-large-patch14-224", - "pkg": { - "0": { - "transformers": "Aimv2VisionModel" - } - }, - "tasks": [ - "Aimv2VisionModel", - "Aimv2Model", - "Aimv2PreTrainedModel", - "Aimv2TextModel" - ] - } - }, - "info.art.albert-xx-v2": { - "*": { - "repo": "albert/albert-xxlarge-v2", - "pkg": { - "0": { - "transformers": "AlbertModel" - } - }, - "tasks": [ - "AlbertPreTrainedModel", - "AlbertModel", - "AlbertForPreTraining", - "AlbertForMaskedLM", - "AlbertForSequenceClassification", - "AlbertForTokenClassification", - "AlbertForQuestionAnswering", - "AlbertForMultipleChoice" - ] - } - }, - "info.vit.align": { - "*": { - "repo": "kakaobrain/align-base", - "pkg": { - "0": { - "transformers": "AlignModel" - } - }, - "tasks": [ - "AlignPreTrainedModel", - "AlignTextModel", - "AlignVisionModel", - "AlignModel" - ] - } - }, - "info.vit.altclip": { - "*": { - "repo": "BAAI/AltCLIP", - "pkg": { - "0": { - "transformers": "AltCLIPModel" - } - }, - "tasks": [ - "AltCLIPPreTrainedModel", - "AltCLIPVisionModel", - "AltCLIPTextModel", - "AltCLIPModel" - ] - } - }, - "info.stst.apertus": { - "*": { - "repo": "swiss-ai/Apertus-8B", - "pkg": { - "0": { - "transformers": "ApertusModel" - } - }, - "tasks": [ - "ApertusModel", - "ApertusForCausalLM", - "ApertusForTokenClassification", - "ApertusPreTrainedModel" - ] - } - }, - "info.stst.afm": { - "*": { - "repo": "arcee-ai/AFM-4.5B", - "pkg": { - "0": { - "transformers": "ArceeModel" - } - }, - "tasks": [ - "ArceeForCausalLM", - "ArceeForQuestionAnswering", - "ArceeForSequenceClassification", - "ArceeForTokenClassification", - "ArceeModel", - "ArceePreTrainedModel" - ] - } - }, - "info.vit.aria": { - "*": { - "repo": "rhymes-ai/Aria", - "pkg": { - "0": { - "transformers": "AriaModel" - } - }, - "tasks": [ - "AriaForConditionalGeneration", - "AriaPreTrainedModel", - "AriaTextPreTrainedModel", - "AriaTextModel", - "AriaModel", - "AriaTextForCausalLM" - ] - } - }, - "info.vit.ast-finetuned-audioset-10-10-0593": { - "*": { - "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", - "pkg": { - "0": { - "transformers": "ASTModel" - } - }, - "tasks": [ - "ASTForAudioClassification", - "ASTModel", - "ASTPreTrainedModel" - ] - } - }, - "info.stst.audio-flamingo-3-hf": { - "*": { - "repo": "nvidia/audio-flamingo-3-hf", - "pkg": { - "0": { - "transformers": "AudioFlamingo3ForConditionalGeneration" - } - }, - "tasks": [ - "AudioFlamingo3ForConditionalGeneration", - "AudioFlamingo3PreTrainedModel", - "AudioFlamingo3Encoder" - ] - } - }, - "info.aet.audio-flamingo-3-hf": { - "*": { - "repo": "nvidia/audio-flamingo-3-hf", - "pkg": { - "0": { - "transformers": "AudioFlamingo3Encoder" - } - }, - "tasks": [ - "AudioFlamingo3ForConditionalGeneration", - "AudioFlamingo3PreTrainedModel", - "AudioFlamingo3Encoder" - ] - } - }, - "info.stst.autoformer-tourism-monthly": { - "*": { - "repo": "huggingface/autoformer-tourism-monthly", - "pkg": { - "0": { - "transformers": "AutoformerModel" - } - }, - "tasks": [ - "AutoformerForPrediction", - "AutoformerModel", - "AutoformerPreTrainedModel" - ] - } - }, - "info.vit.aya-vision": { - "*": { - "repo": "CohereForAI/aya-vision-8b", - "pkg": { - "0": { - "transformers": "AyaVisionModel" - } - }, - "tasks": [ - "AyaVisionForConditionalGeneration", - "AyaVisionPreTrainedModel", - "AyaVisionModel" - ] - } - }, - "info.ssm.bamba-t-hf": { - "*": { - "repo": "ibm-fms/Bamba-9.8b-2.2T-hf", - "pkg": { - "0": { - "transformers": "BambaModel" - } - }, - "tasks": [ - "BambaModel", - "BambaForCausalLM", - "BambaPreTrainedModel" - ] - } - }, - "info.art.bark": { - "*": { - "repo": "suno/bark", - "pkg": { - "0": { - "transformers": "BarkModel" - } - }, - "tasks": [ - "BarkFineModel", - "BarkSemanticModel", - "BarkCoarseModel", - "BarkModel", - "BarkPreTrainedModel", - "BarkCausalModel" - ] - } - }, - "info.stst.bart": { - "*": { - "repo": "facebook/bart-large", - "pkg": { - "0": { - "transformers": "BartModel" - } - }, - "tasks": [ - "BartForCausalLM", - "BartForConditionalGeneration", - "BartForQuestionAnswering", - "BartForSequenceClassification", - "BartModel", - "BartPreTrainedModel", - "BartPretrainedModel", - "PretrainedBartModel" - ] - } - }, - "info.vit.beit-patch16-224-pt": { - "*": { - "repo": "microsoft/beit-base-patch16-224-pt22k", - "pkg": { - "0": { - "transformers": "BeitModel" - } - }, - "tasks": [ - "BeitForImageClassification", - "BeitForMaskedImageModeling", - "BeitForSemanticSegmentation", - "BeitModel", - "BeitPreTrainedModel", - "BeitBackbone" - ] - } - }, - "info.art.bert-uncased": { - "*": { - "repo": "google-bert/bert-base-uncased", - "pkg": { - "0": { - "transformers": "BertModel" - } - }, - "file_256": [ - "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" - ], - "layer_b3": [ - "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" - ], - "layer_256": [ - "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" - ], - "tasks": [ - "BertForMaskedLM", - "BertForMultipleChoice", - "BertForNextSentencePrediction", - "BertForPreTraining", - "BertForQuestionAnswering", - "BertForSequenceClassification", - "BertForTokenClassification", - "BertLayer", - "BertLMHeadModel", - "BertModel", - "BertPreTrainedModel" - ] - } - }, - "info.art.bert-for-seq-generation-l-24-bbc-encoder": { - "*": { - "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", - "pkg": { - "0": { - "transformers": "BertGenerationEncoder" - } - }, - "tasks": [ - "BertGenerationDecoder", - "BertGenerationEncoder", - "BertGenerationPreTrainedModel" - ] - } - }, - "info.art.bigbird-roberta": { - "*": { - "repo": "google/bigbird-roberta-base", - "pkg": { - "0": { - "transformers": "BigBirdModel" - } - }, - "tasks": [ - "BigBirdForCausalLM", - "BigBirdForMaskedLM", - "BigBirdForMultipleChoice", - "BigBirdForPreTraining", - "BigBirdForQuestionAnswering", - "BigBirdForSequenceClassification", - "BigBirdForTokenClassification", - "BigBirdLayer", - "BigBirdModel", - "BigBirdPreTrainedModel" - ] - } - }, - "info.stst.bigbird-pegasus-arxiv": { - "*": { - "repo": "google/bigbird-pegasus-large-arxiv", - "pkg": { - "0": { - "transformers": "BigBirdPegasusModel" - } - }, - "tasks": [ - "BigBirdPegasusForCausalLM", - "BigBirdPegasusForConditionalGeneration", - "BigBirdPegasusForQuestionAnswering", - "BigBirdPegasusForSequenceClassification", - "BigBirdPegasusModel", - "BigBirdPegasusPreTrainedModel" - ] - } - }, - "info.art.biogpt": { - "*": { - "repo": "microsoft/biogpt", - "pkg": { - "0": { - "transformers": "BioGptModel" - } - }, - "tasks": [ - "BioGptForCausalLM", - "BioGptForTokenClassification", - "BioGptForSequenceClassification", - "BioGptModel", - "BioGptPreTrainedModel" - ] - } - }, - "info.vit.bit-50": { - "*": { - "repo": "google/bit-50", - "pkg": { - "0": { - "transformers": "BitModel" - } - }, - "tasks": [ - "BitForImageClassification", - "BitModel", - "BitPreTrainedModel", - "BitBackbone" - ] - } - }, - "info.stst.bitnet-b18-4t": { - "*": { - "repo": "microsoft/bitnet-b1.58-2B-4T", - "pkg": { - "0": { - "transformers": "BitNetModel" - } - }, - "tasks": [ - "BitNetForCausalLM", - "BitNetModel", - "BitNetPreTrainedModel" - ] - } - }, - "info.stst.blenderbot": { - "*": { - "repo": "facebook/blenderbot-3B", - "pkg": { - "0": { - "transformers": "BlenderbotModel" - } - }, - "tasks": [ - "BlenderbotForCausalLM", - "BlenderbotForConditionalGeneration", - "BlenderbotModel", - "BlenderbotPreTrainedModel" - ] - } - }, - "info.vit.blip-vqa": { - "*": { - "repo": "Salesforce/blip-vqa-base", - "pkg": { - "0": { - "transformers": "BlipModel" - } - }, - "tasks": [ - "BlipModel", - "BlipPreTrainedModel", - "BlipForConditionalGeneration", - "BlipForQuestionAnswering", - "BlipVisionModel", - "BlipTextModel", - "BlipForImageTextRetrieval" - ] - } - }, - "info.vit.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2Model" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.stst.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2QFormerModel" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.art.bloom": { - "*": { - "repo": "bigscience/bloom", - "pkg": { - "0": { - "transformers": "BloomModel" - } - }, - "tasks": [ - "BloomForCausalLM", - "BloomModel", - "BloomPreTrainedModel", - "BloomForSequenceClassification", - "BloomForTokenClassification", - "BloomForQuestionAnswering" - ] - } - }, - "info.vit.blt": { - "*": { - "repo": "facebook/blt", - "pkg": { - "0": { - "transformers": "BltModel" - } - }, - "tasks": [ - "BltPreTrainedModel", - "BltModel", - "BltPatcher", - "BltForCausalLM" - ] - } - }, - "info.vit.bridgetower": { - "*": { - "repo": "BridgeTower/bridgetower-base", - "pkg": { - "0": { - "transformers": "BridgeTowerModel" - } - }, - "tasks": [ - "BridgeTowerForContrastiveLearning", - "BridgeTowerForImageAndTextRetrieval", - "BridgeTowerForMaskedLM", - "BridgeTowerModel", - "BridgeTowerPreTrainedModel" - ] - } - }, - "info.art.bros-uncased": { - "*": { - "repo": "jinho8345/bros-base-uncased", - "pkg": { - "0": { - "transformers": "BrosModel" - } - }, - "tasks": [ - "BrosPreTrainedModel", - "BrosModel", - "BrosForTokenClassification", - "BrosSpadeEEForTokenClassification", - "BrosSpadeELForTokenClassification" - ] - } - }, - "info.art.camembert": { - "*": { - "repo": "almanach/camembert-base", - "pkg": { - "0": { - "transformers": "CamembertModel" - } - }, - "tasks": [ - "CamembertForCausalLM", - "CamembertForMaskedLM", - "CamembertForMultipleChoice", - "CamembertForQuestionAnswering", - "CamembertForSequenceClassification", - "CamembertForTokenClassification", - "CamembertModel", - "CamembertPreTrainedModel" - ] - } - }, - "info.art.canine-s": { - "*": { - "repo": "google/canine-s", - "pkg": { - "0": { - "transformers": "CanineModel" - } - }, - "tasks": [ - "CanineForMultipleChoice", - "CanineForQuestionAnswering", - "CanineForSequenceClassification", - "CanineForTokenClassification", - "CanineLayer", - "CanineModel", - "CaninePreTrainedModel" - ] - } - }, - "info.stst.chameleon": { - "*": { - "repo": "meta/chameleon-7B", - "pkg": { - "0": { - "transformers": "ChameleonModel" - } - }, - "tasks": [ - "ChameleonForConditionalGeneration", - "ChameleonModel", - "ChameleonPreTrainedModel", - "ChameleonVQVAE" - ] - } - }, - "info.vit.chinese-clip-vit-patch16": { - "*": { - "repo": "OFA-Sys/chinese-clip-vit-base-patch16", - "pkg": { - "0": { - "transformers": "ChineseCLIPModel" - } - }, - "tasks": [ - "ChineseCLIPModel", - "ChineseCLIPPreTrainedModel", - "ChineseCLIPTextModel", - "ChineseCLIPVisionModel" - ] - } - }, - "info.vit.clap-htsat-fused": { - "*": { - "repo": "laion/clap-htsat-fused", - "pkg": { - "0": { - "transformers": "ClapModel" - } - }, - "file_256": [ - "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", - "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" - ], - "layer_b3": [ - "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", - "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" - ], - "layer_256": [ - "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", - "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" - ], - "tasks": [ - "ClapModel", - "ClapPreTrainedModel", - "ClapTextModel", - "ClapTextModelWithProjection", - "ClapAudioModel", - "ClapAudioModelWithProjection" - ] - } - }, - "info.vit.clip-vit-patch32": { - "*": { - "repo": "openai/clip-vit-base-patch32", - "pkg": { - "0": { - "transformers": "CLIPModel" - } - }, - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clipseg-rd64": { - "*": { - "repo": "CIDAS/clipseg-rd64", - "pkg": { - "0": { - "transformers": "CLIPSegModel" - } - }, - "tasks": [ - "CLIPSegModel", - "CLIPSegPreTrainedModel", - "CLIPSegTextModel", - "CLIPSegVisionModel", - "CLIPSegForImageSegmentation" - ] - } - }, - "info.vit.clvp-dev": { - "*": { - "repo": "susnato/clvp_dev", - "pkg": { - "0": { - "transformers": "ClvpModelForConditionalGeneration" - } - }, - "tasks": [ - "ClvpModelForConditionalGeneration", - "ClvpForCausalLM", - "ClvpModel", - "ClvpPreTrainedModel", - "ClvpEncoder", - "ClvpDecoder" - ] - } - }, - "info.stst.llama-2-hf": { - "*": { - "repo": "meta-llama/Llama-2-7b-hf", - "pkg": { - "0": { - "transformers": "LlamaModel" - } - }, - "tasks": [ - "LlamaForCausalLM", - "LlamaModel", - "LlamaPreTrainedModel", - "LlamaForSequenceClassification", - "LlamaForQuestionAnswering", - "LlamaForTokenClassification" - ] - } - }, - "info.art.codegen-mono": { - "*": { - "repo": "Salesforce/codegen-2B-mono", - "pkg": { - "0": { - "transformers": "CodeGenModel" - } - }, - "tasks": [ - "CodeGenForCausalLM", - "CodeGenModel", - "CodeGenPreTrainedModel" - ] - } - }, - "info.stst.c4ai-command-r-v01": { - "*": { - "repo": "CohereForAI/c4ai-command-r-v01", - "pkg": { - "0": { - "transformers": "CohereModel" - } - }, - "tasks": [ - "CohereForCausalLM", - "CohereModel", - "CoherePreTrainedModel" - ] - } - }, - "info.vit.command-a-vision-07-2025": { - "*": { - "repo": "CohereLabs/command-a-vision-07-2025", - "pkg": { - "0": { - "transformers": "Cohere2VisionModel" - } - }, - "tasks": [ - "Cohere2VisionForConditionalGeneration", - "Cohere2VisionPreTrainedModel", - "Cohere2VisionModel" - ] - } - }, - "info.detr.conditional-detr-resnet-50": { - "*": { - "repo": "microsoft/conditional-detr-resnet-50", - "pkg": { - "0": { - "transformers": "ConditionalDetrModel" - } - }, - "tasks": [ - "ConditionalDetrForObjectDetection", - "ConditionalDetrForSegmentation", - "ConditionalDetrModel", - "ConditionalDetrPreTrainedModel" - ] - } - }, - "info.art.conv-bert": { - "*": { - "repo": "YituTech/conv-bert-base", - "pkg": { - "0": { - "transformers": "ConvBertModel" - } - }, - "tasks": [ - "ConvBertForMaskedLM", - "ConvBertForMultipleChoice", - "ConvBertForQuestionAnswering", - "ConvBertForSequenceClassification", - "ConvBertForTokenClassification", - "ConvBertLayer", - "ConvBertModel", - "ConvBertPreTrainedModel" - ] - } - }, - "info.vit.convnext-224": { - "*": { - "repo": "facebook/convnext-tiny-224", - "pkg": { - "0": { - "transformers": "ConvNextModel" - } - }, - "tasks": [ - "ConvNextForImageClassification", - "ConvNextModel", - "ConvNextPreTrainedModel", - "ConvNextBackbone" - ] - } - }, - "info.vit.convnextv2-224": { - "*": { - "repo": "facebook/convnextv2-tiny-1k-224", - "pkg": { - "0": { - "transformers": "ConvNextV2Model" - } - }, - "tasks": [ - "ConvNextV2ForImageClassification", - "ConvNextV2Model", - "ConvNextV2PreTrainedModel", - "ConvNextV2Backbone" - ] - } - }, - "info.stst.cpm-ant": { - "*": { - "repo": "openbmb/cpm-ant-10b", - "pkg": { - "0": { - "transformers": "CpmAntModel" - } - }, - "tasks": [ - "CpmAntForCausalLM", - "CpmAntModel", - "CpmAntPreTrainedModel" - ] - } - }, - "info.stst.csm": { - "*": { - "repo": "sesame/csm-1b", - "pkg": { - "0": { - "transformers": "CsmForConditionalGeneration" - } - }, - "tasks": [ - "CsmPreTrainedModel", - "CsmBackboneModel", - "CsmDepthDecoderModel", - "CsmDepthDecoderForCausalLM", - "CsmForConditionalGeneration" - ] - } - }, - "info.art.ctrl": { - "*": { - "repo": "Salesforce/ctrl", - "pkg": { - "0": { - "transformers": "CTRLModel" - } - }, - "tasks": [ - "CTRLForSequenceClassification", - "CTRLLMHeadModel", - "CTRLModel", - "CTRLPreTrainedModel" - ] - } - }, - "info.vit.cvt-13": { - "*": { - "repo": "microsoft/cvt-13", - "pkg": { - "0": { - "transformers": "CvtModel" - } - }, - "tasks": [ - "CvtForImageClassification", - "CvtModel", - "CvtPreTrainedModel" - ] - } - }, - "info.art.cwm": { - "*": { - "repo": "facebook/cwm", - "pkg": { - "0": { - "transformers": "CwmModel" - } - }, - "tasks": [ - "CwmPreTrainedModel", - "CwmModel", - "CwmForCausalLM" - ] - } - }, - "info.detr.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine-xlarge-coco", - "pkg": { - "0": { - "transformers": "DFineModel" - } - }, - "tasks": [ - "DFineModel", - "DFinePreTrainedModel", - "DFineForObjectDetection" - ] - } - }, - "info.detr.dab-detr": { - "*": { - "repo": "IDEA-Research/dab-detr-resnet-50", - "pkg": { - "0": { - "transformers": "DabDetrModel" - } - }, - "tasks": [ - "DabDetrForObjectDetection", - "DabDetrModel", - "DabDetrPreTrainedModel" - ] - } - }, - "info.gan.dac": { - "*": { - "repo": "descript/dac_16khz", - "pkg": { - "0": { - "transformers": "DacModel" - } - }, - "tasks": [ - "DacModel", - "DacPreTrainedModel" - ] - } - }, - "info.aet.data2vec-audio-960h": { - "*": { - "repo": "facebook/data2vec-audio-base-960h", - "pkg": { - "0": { - "transformers": "Data2VecAudioModel" - } - }, - "tasks": [ - "Data2VecAudioForAudioFrameClassification", - "Data2VecAudioForCTC", - "Data2VecAudioForSequenceClassification", - "Data2VecAudioForXVector", - "Data2VecAudioModel", - "Data2VecAudioPreTrainedModel" - ] - } - }, - "info.art.data2vec-text": { - "*": { - "repo": "facebook/data2vec-text-base", - "pkg": { - "0": { - "transformers": "Data2VecTextModel" - } - }, - "tasks": [ - "Data2VecTextForCausalLM", - "Data2VecTextForMaskedLM", - "Data2VecTextForMultipleChoice", - "Data2VecTextForQuestionAnswering", - "Data2VecTextForSequenceClassification", - "Data2VecTextForTokenClassification", - "Data2VecTextModel", - "Data2VecTextPreTrainedModel" - ] - } - }, - "info.vit.data2vec-vision": { - "*": { - "repo": "facebook/data2vec-vision-base", - "pkg": { - "0": { - "transformers": "Data2VecVisionModel" - } - }, - "tasks": [ - "Data2VecVisionForImageClassification", - "Data2VecVisionForSemanticSegmentation", - "Data2VecVisionModel", - "Data2VecVisionPreTrainedModel" - ] - } - }, - "info.stst.dbrx": { - "*": { - "repo": "databricks/dbrx-instruct", - "pkg": { - "0": { - "transformers": "DbrxModel" - } - }, - "tasks": [ - "DbrxForCausalLM", - "DbrxModel", - "DbrxPreTrainedModel" - ] - } - }, - "info.art.deberta": { - "*": { - "repo": "microsoft/deberta-base", - "pkg": { - "0": { - "transformers": "DebertaModel" - } - }, - "tasks": [ - "DebertaForMaskedLM", - "DebertaForQuestionAnswering", - "DebertaForSequenceClassification", - "DebertaForTokenClassification", - "DebertaModel", - "DebertaPreTrainedModel" - ] - } - }, - "info.art.deberta-v2-x": { - "*": { - "repo": "microsoft/deberta-v2-xlarge", - "pkg": { - "0": { - "transformers": "DebertaV2Model" - } - }, - "tasks": [ - "DebertaV2ForMaskedLM", - "DebertaV2ForMultipleChoice", - "DebertaV2ForQuestionAnswering", - "DebertaV2ForSequenceClassification", - "DebertaV2ForTokenClassification", - "DebertaV2Model", - "DebertaV2PreTrainedModel" - ] - } - }, - "info.art.decision-transformer-gym-hopper": { - "*": { - "repo": "edbeeching/decision-transformer-gym-hopper-medium", - "pkg": { - "0": { - "transformers": "DecisionTransformerModel" - } - }, - "tasks": [ - "DecisionTransformerGPT2Model", - "DecisionTransformerGPT2PreTrainedModel", - "DecisionTransformerModel", - "DecisionTransformerPreTrainedModel" - ] - } - }, - "info.moe.deepseek-v2-lite": { - "*": { - "repo": "deepseek-ai/DeepSeek-V2-Lite", - "pkg": { - "0": { - "transformers": "DeepseekV2Model" - } - }, - "tasks": [ - "DeepseekV2PreTrainedModel", - "DeepseekV2Model", - "DeepseekV2ForCausalLM", - "DeepseekV2ForSequenceClassification" - ] - } - }, - "info.moe.deepseek-v3": { - "*": { - "repo": "bzantium/tiny-deepseek-v3", - "pkg": { - "0": { - "transformers": "DeepseekV3Model" - } - }, - "tasks": [ - "DeepseekV3PreTrainedModel", - "DeepseekV3Model", - "DeepseekV3ForCausalLM", - "DeepseekV3ForSequenceClassification", - "DeepseekV3ForTokenClassification" - ] - } - }, - "info.vit.deepseek-vl-chat": { - "*": { - "repo": "deepseek-community/deepseek-vl-1.3b-chat", - "pkg": { - "0": { - "transformers": "DeepseekVLModel" - } - }, - "tasks": [ - "DeepseekVLPreTrainedModel", - "DeepseekVLModel", - "DeepseekVLForConditionalGeneration" - ] - } - }, - "info.detr.deformable-detr": { - "*": { - "repo": "SenseTime/deformable-detr", - "pkg": { - "0": { - "transformers": "DeformableDetrModel" - } - }, - "tasks": [ - "DeformableDetrForObjectDetection", - "DeformableDetrModel", - "DeformableDetrPreTrainedModel" - ] - } - }, - "info.vit.deit-distilled-patch16-224": { - "*": { - "repo": "facebook/deit-base-distilled-patch16-224", - "pkg": { - "0": { - "transformers": "DeiTModel" - } - }, - "tasks": [ - "DeiTForImageClassification", - "DeiTForImageClassificationWithTeacher", - "DeiTForMaskedImageModeling", - "DeiTModel", - "DeiTPreTrainedModel" - ] - } - }, - "info.vit.depth": { - "*": { - "repo": "apple/DepthPro", - "pkg": { - "0": { - "transformers": "DepthProModel" - } - }, - "tasks": [ - "DepthProPreTrainedModel", - "DepthProModel", - "DepthProForDepthEstimation" - ] - } - }, - "info.detr.detr-resnet-50": { - "*": { - "repo": "facebook/detr-resnet-50", - "pkg": { - "0": { - "transformers": "DetrModel" - } - }, - "tasks": [ - "DetrForObjectDetection", - "DetrForSegmentation", - "DetrModel", - "DetrPreTrainedModel" - ] - } - }, - "info.stst.dia": { - "*": { - "repo": "nari-labs/Dia-1.6B", - "pkg": { - "0": { - "transformers": "DiaModel" - } - }, - "tasks": [ - "DiaModel", - "DiaPreTrainedModel", - "DiaForConditionalGeneration" - ] - } - }, - "info.stst.diffllama-handcut": { - "*": { - "repo": "kajuma/DiffLlama-0.3B-handcut", - "pkg": { - "0": { - "transformers": "DiffLlamaModel" - } - }, - "tasks": [ - "DiffLlamaPreTrainedModel", - "DiffLlamaModel", - "DiffLlamaForCausalLM", - "DiffLlamaForSequenceClassification", - "DiffLlamaForQuestionAnswering", - "DiffLlamaForTokenClassification" - ] - } - }, - "info.gan.dinat-in-224": { - "*": { - "repo": "shi-labs/dinat-mini-in1k-224", - "pkg": { - "0": { - "transformers": "DinatModel" - } - }, - "tasks": [ - "DinatForImageClassification", - "DinatModel", - "DinatPreTrainedModel", - "DinatBackbone" - ] - } - }, - "info.vit.dinov2-patch16-224": { - "*": { - "repo": "google/dinov2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Dinov2Model" - } - }, - "tasks": [ - "Dinov2ForImageClassification", - "Dinov2Model", - "Dinov2PreTrainedModel", - "Dinov2Backbone" - ] - } - }, - "info.vit.dinov2-with-registers": { - "*": { - "repo": "facebook/dinov2-with-registers-base", - "pkg": { - "0": { - "transformers": "Dinov2WithRegistersModel" - } - }, - "tasks": [ - "Dinov2WithRegistersPreTrainedModel", - "Dinov2WithRegistersModel", - "Dinov2WithRegistersForImageClassification", - "Dinov2WithRegistersBackbone" - ] - } - }, - "info.vit.dinov3-convnext-pretrain-lvd": { - "*": { - "repo": "facebook/dinov3-convnext-tiny-pretrain-lvd1689m", - "pkg": { - "0": { - "transformers": "DINOv3ConvNextModel" - } - }, - "tasks": [ - "DINOv3ConvNextModel", - "DINOv3ConvNextPreTrainedModel", - "DINOv3ConvNextBackbone" - ] - } - }, - "info.vit.dinov3-vits16-pretrain-lvd": { - "*": { - "repo": "facebook/dinov3-vits16-pretrain-lvd1689m", - "pkg": { - "0": { - "transformers": "DINOv3ViTModel" - } - }, - "tasks": [ - "DINOv3ViTModel", - "DINOv3ViTPreTrainedModel", - "DINOv3ViTBackbone" - ] - } - }, - "info.art.distilbert-uncased": { - "*": { - "repo": "distilbert-base-uncased", - "pkg": { - "0": { - "transformers": "DistilBertModel" - } - }, - "tasks": [ - "DistilBertForMaskedLM", - "DistilBertForMultipleChoice", - "DistilBertForQuestionAnswering", - "DistilBertForSequenceClassification", - "DistilBertForTokenClassification", - "DistilBertModel", - "DistilBertPreTrainedModel" - ] - } - }, - "info.moe.doge": { - "*": { - "repo": "SmallDoge/Doge-320M", - "pkg": { - "0": { - "transformers": "DogeModel" - } - }, - "tasks": [ - "DogeForCausalLM", - "DogeModel", - "DogePreTrainedModel", - "DogeForSequenceClassification" - ] - } - }, - "info.vit.donut": { - "*": { - "repo": "naver-clova-ix/donut-base", - "pkg": { - "0": { - "transformers": "DonutSwinModel" - } - }, - "tasks": [ - "DonutSwinModel", - "DonutSwinPreTrainedModel", - "DonutSwinForImageClassification" - ] - } - }, - "info.moe.dots-llm1": { - "*": { - "repo": "rednote-hilab/dots.llm1.base", - "pkg": { - "0": { - "transformers": "Dots1Model" - } - }, - "tasks": [ - "Dots1PreTrainedModel", - "Dots1Model", - "Dots1ForCausalLM" - ] - } - }, - "info.vit.dpr-ctx-encoder-single-nq": { - "*": { - "repo": "facebook/dpr-ctx_encoder-single-nq-base", - "pkg": { - "0": { - "transformers": "DPRQuestionEncoder" - } - }, - "tasks": [ - "DPRContextEncoder", - "DPRPretrainedContextEncoder", - "DPRPreTrainedModel", - "DPRPretrainedQuestionEncoder", - "DPRPretrainedReader", - "DPRQuestionEncoder", - "DPRReader" - ] - } - }, - "info.detr.dpt": { - "*": { - "repo": "Intel/dpt-large", - "pkg": { - "0": { - "transformers": "DPTModel" - } - }, - "tasks": [ - "DPTForDepthEstimation", - "DPTForSemanticSegmentation", - "DPTModel", - "DPTPreTrainedModel" - ] - } - }, - "info.vit.edgetam1-hiera": { - "*": { - "repo": "facebook/edgetam.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "EdgeTamModel" - } - }, - "tasks": [ - "EdgeTamModel", - "EdgeTamVisionModel", - "EdgeTamPreTrainedModel" - ] - } - }, - "info.vit.edgetam": { - "*": { - "repo": "facebook/EdgeTAM", - "pkg": { - "0": { - "transformers": "EdgeTamVideoModel" - } - }, - "tasks": [ - "EdgeTamVideoModel", - "EdgeTamVideoInferenceSession", - "EdgeTamVideoPreTrainedModel" - ] - } - }, - "info.vit.efficientloftr": { - "*": { - "repo": "zju-community/efficientloftr", - "pkg": { - "0": { - "transformers": "EfficientLoFTRModel" - } - }, - "tasks": [ - "EfficientLoFTRPreTrainedModel", - "EfficientLoFTRModel", - "EfficientLoFTRForKeypointMatching" - ] - } - }, - "info.vit.efficientnet-b7": { - "*": { - "repo": "google/efficientnet-b7", - "pkg": { - "0": { - "transformers": "EfficientNetModel" - } - }, - "tasks": [ - "EfficientNetForImageClassification", - "EfficientNetModel", - "EfficientNetPreTrainedModel" - ] - } - }, - "info.art.electra-discriminator": { - "*": { - "repo": "google/electra-small-discriminator", - "pkg": { - "0": { - "transformers": "ElectraModel" - } - }, - "tasks": [ - "ElectraForCausalLM", - "ElectraForMaskedLM", - "ElectraForMultipleChoice", - "ElectraForPreTraining", - "ElectraForQuestionAnswering", - "ElectraForSequenceClassification", - "ElectraForTokenClassification", - "ElectraModel", - "ElectraPreTrainedModel" - ] - } - }, - "info.art.emu3-chat-hf": { - "*": { - "repo": "Emu3-community/Emu3-Chat-hf", - "pkg": { - "0": { - "transformers": "Emu3Model" - } - }, - "tasks": [ - "Emu3ForConditionalGeneration", - "Emu3ForCausalLM", - "Emu3TextModel", - "Emu3PreTrainedModel", - "Emu3VQVAE", - "Emu3Model" - ] - } - }, - "info.gan.encodec": { - "*": { - "repo": "facebook/encodec_24khz", - "pkg": { - "0": { - "transformers": "EncodecModel" - } - }, - "tasks": [ - "EncodecModel", - "EncodecPreTrainedModel" - ] - } - }, - "info.art.ernie-3-zh": { - "*": { - "repo": "nghuyong/ernie-3.0-base-zh", - "pkg": { - "0": { - "transformers": "ErnieModel" - } - }, - "tasks": [ - "ErnieForCausalLM", - "ErnieForMaskedLM", - "ErnieForMultipleChoice", - "ErnieForNextSentencePrediction", - "ErnieForPreTraining", - "ErnieForQuestionAnswering", - "ErnieForSequenceClassification", - "ErnieForTokenClassification", - "ErnieModel", - "ErniePreTrainedModel" - ] - } - }, - "info.stst.ernie-45-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-0.3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5Model" - } - }, - "tasks": [ - "Ernie4_5ForCausalLM", - "Ernie4_5Model", - "Ernie4_5PreTrainedModel" - ] - } - }, - "info.moe.ernie-4-a-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-21B-A3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5_MoeModel" - } - }, - "tasks": [ - "Ernie4_5_MoeForCausalLM", - "Ernie4_5_MoeModel", - "Ernie4_5_MoePreTrainedModel" - ] - } - }, - "info.vit.ernie-4-vl-a-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-VL-28B-A3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5_VL_MoeModel" - } - }, - "tasks": [ - "Ernie4_5_VL_MoePreTrainedModel", - "Ernie4_5_VL_MoeForConditionalGeneration", - "Ernie4_5_VL_MoeModel", - "Ernie4_5_VL_MoeTextModel", - "Ernie4_5_VL_MoeVisionTransformerPretrainedModel", - "Ernie4_5_VL_MoeVariableResolutionResamplerModel" - ] - } - }, - "info.aet.esm": { - "*": { - "repo": "facebook/esm-1b", - "pkg": { - "0": { - "transformers": "EsmModel" - } - }, - "tasks": [ - "EsmForMaskedLM", - "EsmForSequenceClassification", - "EsmForTokenClassification", - "EsmModel", - "EsmPreTrainedModel" - ] - } - }, - "info.stst.evolla-hf": { - "*": { - "repo": "westlake-repl/Evolla-10B-hf", - "pkg": { - "0": { - "transformers": "EvollaModel" - } - }, - "tasks": [ - "EvollaForProteinText2Text", - "EvollaModel", - "EvollaPreTrainedModel" - ] - } - }, - "info.stst.exaone-4": { - "*": { - "repo": "LGAI-EXAONE/EXAONE-4.0-32B", - "pkg": { - "0": { - "transformers": "Exaone4Model" - } - }, - "tasks": [ - "Exaone4PreTrainedModel", - "Exaone4Model", - "Exaone4ForCausalLM", - "Exaone4ForSequenceClassification", - "Exaone4ForTokenClassification", - "Exaone4ForQuestionAnswering" - ] - } - }, - "info.ssm.falcon": { - "*": { - "repo": "tiiuae/falcon-7b", - "pkg": { - "0": { - "transformers": "FalconModel" - } - }, - "tasks": [ - "FalconForCausalLM", - "FalconModel", - "FalconPreTrainedModel", - "FalconForSequenceClassification", - "FalconForTokenClassification", - "FalconForQuestionAnswering" - ] - } - }, - "info.ssm.falconh1-t-hf": { - "*": { - "repo": "tiiuae/Falcon-H1-34B-Instruct", - "pkg": { - "0": { - "transformers": "FalconH1Model" - } - }, - "tasks": [ - "FalconH1Model", - "FalconH1ForCausalLM", - "FalconH1PreTrainedModel" - ] - } - }, - "info.ssm.falcon-mamba": { - "*": { - "repo": "tiiuae/falcon-mamba-7b", - "pkg": { - "0": { - "transformers": "FalconMambaModel" - } - }, - "tasks": [ - "FalconMambaForCausalLM", - "FalconMambaModel", - "FalconMambaPreTrainedModel", - "FalconMambaCache" - ] - } - }, - "info.vit.fastvlm": { - "*": { - "repo": "KamilaMila/FastVLM-7B", - "pkg": { - "0": { - "transformers": "FastVlmModel" - } - }, - "tasks": [ - "FastVlmForConditionalGeneration", - "FastVlmModel", - "FastVlmPreTrainedModel" - ] - } - }, - "info.aet.fastspeech2-conformer": { - "*": { - "repo": "espnet/fastspeech2_conformer", - "pkg": { - "0": { - "transformers": "FastSpeech2ConformerModel" - } - }, - "tasks": [ - "FastSpeech2ConformerWithHifiGan", - "FastSpeech2ConformerHifiGan", - "FastSpeech2ConformerModel", - "FastSpeech2ConformerPreTrainedModel" - ] - } - }, - "info.stst.fastspeech2-conformer": { - "*": { - "repo": "espnet/fastspeech2_conformer", - "pkg": { - "0": { - "transformers": "FastSpeech2ConformerWithHifiGan" - } - }, - "tasks": [ - "FastSpeech2ConformerWithHifiGan", - "FastSpeech2ConformerHifiGan", - "FastSpeech2ConformerModel", - "FastSpeech2ConformerPreTrainedModel" - ] - } - }, - "info.art.flaubert-uncased": { - "*": { - "repo": "flaubert/flaubert_base_uncased", - "pkg": { - "0": { - "transformers": "FlaubertModel" - } - }, - "tasks": [ - "FlaubertForMultipleChoice", - "FlaubertForQuestionAnswering", - "FlaubertForQuestionAnsweringSimple", - "FlaubertForSequenceClassification", - "FlaubertForTokenClassification", - "FlaubertModel", - "FlaubertWithLMHeadModel", - "FlaubertPreTrainedModel" - ] - } - }, - "info.vit.flava": { - "*": { - "repo": "facebook/flava-full", - "pkg": { - "0": { - "transformers": "FlavaModel" - } - }, - "tasks": [ - "FlavaForPreTraining", - "FlavaImageCodebook", - "FlavaImageModel", - "FlavaModel", - "FlavaMultimodalModel", - "FlavaPreTrainedModel", - "FlavaTextModel" - ] - } - }, - "info.moe.flexolmo-7x-1t": { - "*": { - "repo": "allenai/FlexOlmo-7x7B-1T", - "pkg": { - "0": { - "transformers": "FlexOlmoModel" - } - }, - "tasks": [ - "FlexOlmoForCausalLM", - "FlexOlmoModel", - "FlexOlmoPreTrainedModel" - ] - } - }, - "info.vit.florence-2": { - "*": { - "repo": "florence-community/Florence-2-base", - "pkg": { - "0": { - "transformers": "Florence2Model" - } - }, - "tasks": [ - "Florence2Model", - "Florence2ForConditionalGeneration", - "Florence2PreTrainedModel", - "Florence2VisionBackbone", - "Florence2VisionPreTrainedModel" - ] - } - }, - "info.art.fnet": { - "*": { - "repo": "google/fnet-base", - "pkg": { - "0": { - "transformers": "FNetModel" - } - }, - "tasks": [ - "FNetForMaskedLM", - "FNetForMultipleChoice", - "FNetForNextSentencePrediction", - "FNetForPreTraining", - "FNetForQuestionAnswering", - "FNetForSequenceClassification", - "FNetForTokenClassification", - "FNetLayer", - "FNetModel", - "FNetPreTrainedModel" - ] - } - }, - "info.vit.focalnet": { - "*": { - "repo": "microsoft/focalnet-tiny", - "pkg": { - "0": { - "transformers": "FocalNetModel" - } - }, - "tasks": [ - "FocalNetForImageClassification", - "FocalNetForMaskedImageModeling", - "FocalNetBackbone", - "FocalNetModel", - "FocalNetPreTrainedModel" - ] - } - }, - "info.stst.wmt19-en-ru": { - "*": { - "repo": "facebook/wmt19-en-ru", - "pkg": { - "0": { - "transformers": "FSMTModel" - } - }, - "tasks": [ - "FSMTForConditionalGeneration", - "FSMTModel", - "PretrainedFSMTModel" - ] - } - }, - "info.aet.funnel": { - "*": { - "repo": "funnel-transformer/small", - "pkg": { - "0": { - "transformers": "FunnelModel" - } - }, - "tasks": [ - "FunnelBaseModel", - "FunnelForMaskedLM", - "FunnelForMultipleChoice", - "FunnelForPreTraining", - "FunnelForQuestionAnswering", - "FunnelForSequenceClassification", - "FunnelForTokenClassification", - "FunnelModel", - "FunnelPreTrainedModel" - ] - } - }, - "info.vit.fuyu": { - "*": { - "repo": "adept/fuyu-8b", - "pkg": { - "0": { - "transformers": "FuyuModel" - } - }, - "tasks": [ - "FuyuForCausalLM", - "FuyuPreTrainedModel", - "FuyuModel" - ] - } - }, - "info.stst.gemma": { - "*": { - "repo": "google/gemma-7b", - "pkg": { - "0": { - "transformers": "GemmaModel" - } - }, - "file_256": [ - "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" - ], - "layer_b3": [ - "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", - "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" - ], - "layer_256": [ - "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", - "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" - ], - "tasks": [ - "GemmaModel", - "GemmaForCausalLM", - "GemmaForSequenceClassification", - "GemmaForTokenClassification", - "GemmaPreTrainedModel" - ] - } - }, - "info.stst.gemma2": { - "*": { - "repo": "google/gemma-2-9b", - "pkg": { - "0": { - "transformers": "Gemma2Model" - } - }, - "file_256": [ - "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", - "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" - ], - "layer_b3": [ - "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", - "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" - ], - "layer_256": [ - "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", - "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" - ], - "tasks": [ - "Gemma2ForCausalLM", - "Gemma2Model", - "Gemma2PreTrainedModel", - "Gemma2ForSequenceClassification", - "Gemma2ForTokenClassification" - ] - } - }, - "info.vit.gemma-3": { - "*": { - "repo": "google/gemma-3-4b-it", - "pkg": { - "0": { - "transformers": "Gemma3Model" - } - }, - "tasks": [ - "Gemma3PreTrainedModel", - "Gemma3TextModel", - "Gemma3ForCausalLM", - "Gemma3ForConditionalGeneration", - "Gemma3Model", - "Gemma3ForSequenceClassification", - "Gemma3TextForSequenceClassification" - ] - } - }, - "info.stst.gemma3-text": { - "*": { - "repo": "google/gemma-3-12b-it", - "pkg": { - "0": { - "transformers": "Gemma3TextModel" - } - }, - "tasks": [ - "Gemma3PreTrainedModel", - "Gemma3TextModel", - "Gemma3ForCausalLM", - "Gemma3ForConditionalGeneration", - "Gemma3Model", - "Gemma3ForSequenceClassification", - "Gemma3TextForSequenceClassification" - ] - } - }, - "info.vit.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nModel" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.art.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nAudioEncoder" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.stst.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nTextModel" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.vit.git": { - "*": { - "repo": "microsoft/git-base", - "pkg": { - "0": { - "transformers": "GitModel" - } - }, - "tasks": [ - "GitForCausalLM", - "GitModel", - "GitPreTrainedModel", - "GitVisionModel" - ] - } - }, - "info.stst.glm-4-chat": { - "*": { - "repo": "zai-org/glm-4-9b-chat", - "pkg": { - "0": { - "transformers": "GlmModel" - } - }, - "tasks": [ - "GlmPreTrainedModel", - "GlmModel", - "GlmForCausalLM", - "GlmForSequenceClassification", - "GlmForTokenClassification" - ] - } - }, - "info.stst.glm-4-0414": { - "*": { - "repo": "zai-org/GLM-4-9B-0414", - "pkg": { - "0": { - "transformers": "Glm4Model" - } - }, - "tasks": [ - "Glm4PreTrainedModel", - "Glm4Model", - "Glm4ForCausalLM", - "Glm4ForSequenceClassification", - "Glm4ForTokenClassification" - ] - } - }, - "info.vit.glm-4v-thinking": { - "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", - "pkg": { - "0": { - "transformers": "Glm46VModel" - } - }, - "tasks": [ - "Glm46VModel", - "Glm46VPreTrainedModel", - "Glm46VForConditionalGeneration" - ] - } - }, - "info.moe.glm-4-a": { - "*": { - "repo": "zai-org/GLM-4.5-Air", - "pkg": { - "0": { - "transformers": "Glm4MoeModel" - } - }, - "tasks": [ - "Glm4MoePreTrainedModel", - "Glm4MoeModel", - "Glm4MoeForCausalLM" - ] - } - }, - "info.vit.glm-4v": { - "*": { - "repo": "zai-org/GLM-4.5V", - "pkg": { - "0": { - "transformers": "Glm4vMoeModel" - } - }, - "tasks": [ - "Glm4vMoeForConditionalGeneration", - "Glm4vMoeModel", - "Glm4vMoePreTrainedModel", - "Glm4vMoeTextModel", - "Glm4vMoeVisionModel" - ] - } - }, - "info.moe.glm-4v": { - "*": { - "repo": "zai-org/GLM-4.5V", - "pkg": { - "0": { - "transformers": "Glm4vMoeTextModel" - } - }, - "tasks": [ - "Glm4vMoeForConditionalGeneration", - "Glm4vMoeModel", - "Glm4vMoePreTrainedModel", - "Glm4vMoeTextModel", - "Glm4vMoeVisionModel" - ] - } - }, - "info.stst.glm-4v-thinking": { - "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", - "pkg": { - "0": { - "transformers": "Glm4vTextModel" - } - }, - "tasks": [ - "Glm4vForConditionalGeneration", - "Glm4vModel", - "Glm4vPreTrainedModel", - "Glm4vTextModel", - "Glm4vVisionModel" - ] - } - }, - "info.stst.glm-asr-nano-2512": { - "*": { - "repo": "zai-org/GLM-ASR-Nano-2512", - "pkg": { - "0": { - "transformers": "GlmAsrForConditionalGeneration" - } - }, - "tasks": [ - "GlmAsrEncoder", - "GlmAsrForConditionalGeneration", - "GlmAsrPreTrainedModel" - ] - } - }, - "info.vit.glpn-kitti": { - "*": { - "repo": "vinvino02/glpn-kitti", - "pkg": { - "0": { - "transformers": "GLPNModel" - } - }, - "tasks": [ - "GLPNForDepthEstimation", - "GLPNLayer", - "GLPNModel", - "GLPNPreTrainedModel" - ] - } - }, - "info.vit.got-ocr-2-hf": { - "*": { - "repo": "stepfun-ai/GOT-OCR-2.0-hf", - "pkg": { - "0": { - "transformers": "GotOcr2Model" - } - }, - "tasks": [ - "GotOcr2PreTrainedModel", - "GotOcr2Model", - "GotOcr2ForConditionalGeneration" - ] - } - }, - "info.art.gpt2": { - "*": { - "repo": "openai-community/gpt2", - "pkg": { - "0": { - "transformers": "GPT2Model" - } - }, - "tasks": [ - "GPT2DoubleHeadsModel", - "GPT2ForQuestionAnswering", - "GPT2ForSequenceClassification", - "GPT2ForTokenClassification", - "GPT2LMHeadModel", - "GPT2Model", - "GPT2PreTrainedModel" - ] - } - }, - "info.art.gpt-bigcode-santacoder": { - "*": { - "repo": "bigcode/gpt_bigcode-santacoder", - "pkg": { - "0": { - "transformers": "GPTBigCodeModel" - } - }, - "tasks": [ - "GPTBigCodeForSequenceClassification", - "GPTBigCodeForTokenClassification", - "GPTBigCodeForCausalLM", - "GPTBigCodeModel", - "GPTBigCodePreTrainedModel" - ] - } - }, - "info.art.gpt-neo": { - "*": { - "repo": "EleutherAI/gpt-neo-1.3B", - "pkg": { - "0": { - "transformers": "GPTNeoModel" - } - }, - "tasks": [ - "GPTNeoForCausalLM", - "GPTNeoForQuestionAnswering", - "GPTNeoForSequenceClassification", - "GPTNeoForTokenClassification", - "GPTNeoModel", - "GPTNeoPreTrainedModel" - ] - } - }, - "info.stst.gpt-neox": { - "*": { - "repo": "EleutherAI/gpt-neox-20b", - "pkg": { - "0": { - "transformers": "GPTNeoXModel" - } - }, - "tasks": [ - "GPTNeoXForCausalLM", - "GPTNeoXForQuestionAnswering", - "GPTNeoXForSequenceClassification", - "GPTNeoXForTokenClassification", - "GPTNeoXLayer", - "GPTNeoXModel", - "GPTNeoXPreTrainedModel" - ] - } - }, - "info.stst.gpt-neox-japanese": { - "*": { - "repo": "abeja/gpt-neox-japanese-2.7b", - "pkg": { - "0": { - "transformers": "GPTNeoXJapaneseModel" - } - }, - "tasks": [ - "GPTNeoXJapaneseForCausalLM", - "GPTNeoXJapaneseLayer", - "GPTNeoXJapaneseModel", - "GPTNeoXJapanesePreTrainedModel" - ] - } - }, - "info.moe.gpt-oss": { - "*": { - "repo": "openai/gpt-oss-120b", - "pkg": { - "0": { - "transformers": "GptOssModel" - } - }, - "file_256": [ - "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", - "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" - ], - "layer_b3": [ - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", - "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" - ], - "layer_256": [ - "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", - "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" - ], - "tasks": [ - "GptOssForCausalLM", - "GptOssForSequenceClassification", - "GptOssForTokenClassification", - "GptOssModel", - "GptOssPreTrainedModel" - ] - } - }, - "info.art.gpt-j": { - "*": { - "repo": "EleutherAI/gpt-j-6B", - "pkg": { - "0": { - "transformers": "GPTJModel" - } - }, - "tasks": [ - "GPTJForCausalLM", - "GPTJForQuestionAnswering", - "GPTJForSequenceClassification", - "GPTJModel", - "GPTJPreTrainedModel" - ] - } - }, - "info.stst.granite": { - "*": { - "repo": "ibm-granite/granite-3.3-2b-base", - "pkg": { - "0": { - "transformers": "GraniteModel" - } - }, - "tasks": [ - "GraniteForCausalLM", - "GraniteModel", - "GranitePreTrainedModel" - ] - } - }, - "info.moe.powermoe": { - "*": { - "repo": "ibm-research/PowerMoE-3b", - "pkg": { - "0": { - "transformers": "GraniteMoeModel" - } - }, - "tasks": [ - "GraniteMoeForCausalLM", - "GraniteMoeModel", - "GraniteMoePreTrainedModel" - ] - } - }, - "info.ssm.granite-4-h": { - "*": { - "repo": "ibm-granite/granite-4.0-h-small", - "pkg": { - "0": { - "transformers": "GraniteMoeHybridModel" - } - }, - "tasks": [ - "GraniteMoeHybridForCausalLM", - "GraniteMoeHybridModel", - "GraniteMoeHybridPreTrainedModel" - ] - } - }, - "info.moe.moe-active-shared-experts": { - "*": { - "repo": "ibm-research/moe-7b-1b-active-shared-experts", - "pkg": { - "0": { - "transformers": "GraniteMoeSharedModel" - } - }, - "tasks": [ - "GraniteMoeSharedForCausalLM", - "GraniteMoeSharedModel", - "GraniteMoeSharedPreTrainedModel" - ] - } - }, - "info.vit.llava-v1-mistral-hf": { - "*": { - "repo": "llava-hf/llava-v1.6-mistral-7b-hf", - "pkg": { - "0": { - "transformers": "LlavaNextModel" - } - }, - "tasks": [ - "LlavaNextForConditionalGeneration", - "LlavaNextPreTrainedModel", - "LlavaNextModel" - ] - } - }, - "info.detr.grounding-dino": { - "*": { - "repo": "IDEA-Research/grounding-dino-tiny", - "pkg": { - "0": { - "transformers": "GroundingDinoModel" - } - }, - "tasks": [ - "GroundingDinoForObjectDetection", - "GroundingDinoModel", - "GroundingDinoPreTrainedModel" - ] - } - }, - "info.vit.groupvit-gcc-yfcc": { - "*": { - "repo": "nvidia/groupvit-gcc-yfcc", - "pkg": { - "0": { - "transformers": "GroupViTModel" - } - }, - "tasks": [ - "GroupViTModel", - "GroupViTPreTrainedModel", - "GroupViTTextModel", - "GroupViTVisionModel" - ] - } - }, - "info.stst.helium": { - "*": { - "repo": "kyutai/helium-1-2b", - "pkg": { - "0": { - "transformers": "HeliumModel" - } - }, - "tasks": [ - "HeliumPreTrainedModel", - "HeliumModel", - "HeliumForCausalLM", - "HeliumForSequenceClassification", - "HeliumForTokenClassification" - ] - } - }, - "info.vit.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine_x_coco", - "pkg": { - "0": { - "transformers": "HGNetV2Backbone" - } - }, - "tasks": [ - "HGNetV2Backbone", - "HGNetV2PreTrainedModel", - "HGNetV2ForImageClassification" - ] - } - }, - "info.vit.hiera-224": { - "*": { - "repo": "facebook/hiera-base-224-hf", - "pkg": { - "0": { - "transformers": "HieraModel" - } - }, - "tasks": [ - "HieraForImageClassification", - "HieraForPreTraining", - "HieraBackbone", - "HieraModel", - "HieraPreTrainedModel" - ] - } - }, - "info.aet.hubert-ls960": { - "*": { - "repo": "facebook/hubert-base-ls960", - "pkg": { - "0": { - "transformers": "HubertModel" - } - }, - "tasks": [ - "HubertForCTC", - "HubertForSequenceClassification", - "HubertModel", - "HubertPreTrainedModel" - ] - } - }, - "info.stst.hunyuan": { - "*": { - "repo": "tencent/Hunyuan-7B-Instruct", - "pkg": { - "0": { - "transformers": "HunYuanDenseV1Model" - } - }, - "tasks": [ - "HunYuanDenseV1ForCausalLM", - "HunYuanDenseV1Model", - "HunYuanDenseV1PreTrainedModel", - "HunYuanDenseV1ForSequenceClassification" - ] - } - }, - "info.moe.hunyuan-a": { - "*": { - "repo": "tencent/Hunyuan-A13B-Instruct", - "pkg": { - "0": { - "transformers": "HunYuanMoEV1Model" - } - }, - "tasks": [ - "HunYuanMoEV1ForCausalLM", - "HunYuanMoEV1Model", - "HunYuanMoEV1PreTrainedModel", - "HunYuanMoEV1ForSequenceClassification" - ] - } - }, - "info.art.ibert-roberta": { - "*": { - "repo": "kssteven/ibert-roberta-base", - "pkg": { - "0": { - "transformers": "IBertModel" - } - }, - "tasks": [ - "IBertForMaskedLM", - "IBertForMultipleChoice", - "IBertForQuestionAnswering", - "IBertForSequenceClassification", - "IBertForTokenClassification", - "IBertModel", - "IBertPreTrainedModel" - ] - } - }, - "info.vit.idefics": { - "*": { - "repo": "HuggingFaceM4/idefics-9b", - "pkg": { - "0": { - "transformers": "IdeficsModel" - } - }, - "tasks": [ - "IdeficsForVisionText2Text", - "IdeficsModel", - "IdeficsPreTrainedModel" - ] - } - }, - "info.vit.idefics2": { - "*": { - "repo": "HuggingFaceM4/idefics2-8b", - "pkg": { - "0": { - "transformers": "Idefics2Model" - } - }, - "tasks": [ - "Idefics2ForConditionalGeneration", - "Idefics2PreTrainedModel", - "Idefics2Model" - ] - } - }, - "info.vit.idefics3-llama3": { - "*": { - "repo": "HuggingFaceM4/Idefics3-8B-Llama3", - "pkg": { - "0": { - "transformers": "Idefics3Model" - } - }, - "tasks": [ - "Idefics3ForConditionalGeneration", - "Idefics3PreTrainedModel", - "Idefics3Model", - "Idefics3VisionTransformer" - ] - } - }, - "info.vit.siglip-patch16-224": { - "*": { - "repo": "google/siglip-base-patch16-224", - "pkg": { - "0": { - "transformers": "Idefics3VisionTransformer" - } - }, - "tasks": [ - "Idefics3ForConditionalGeneration", - "Idefics3PreTrainedModel", - "Idefics3Model", - "Idefics3VisionTransformer" - ] - } - }, - "info.vit.ijepa-vith14": { - "*": { - "repo": "facebook/ijepa_vith14_1k", - "pkg": { - "0": { - "transformers": "IJepaModel" - } - }, - "tasks": [ - "IJepaPreTrainedModel", - "IJepaModel", - "IJepaForImageClassification" - ] - } - }, - "info.art.imagegpt": { - "*": { - "repo": "openai/imagegpt-small", - "pkg": { - "0": { - "transformers": "ImageGPTModel" - } - }, - "tasks": [ - "ImageGPTForCausalImageModeling", - "ImageGPTForImageClassification", - "ImageGPTModel", - "ImageGPTPreTrainedModel" - ] - } - }, - "info.stst.informer-tourism-monthly": { - "*": { - "repo": "huggingface/informer-tourism-monthly", - "pkg": { - "0": { - "transformers": "InformerModel" - } - }, - "tasks": [ - "InformerForPrediction", - "InformerModel", - "InformerPreTrainedModel" - ] - } - }, - "info.vit.blip-flan-t5": { - "*": { - "repo": "Salesforce/instructblip-flan-t5-xl", - "pkg": { - "0": { - "transformers": "InstructBlipModel" - } - }, - "tasks": [ - "InstructBlipQFormerModel", - "InstructBlipPreTrainedModel", - "InstructBlipModel", - "InstructBlipForConditionalGeneration", - "InstructBlipVisionModel" - ] - } - }, - "info.vit.internvl3-hf": { - "*": { - "repo": "OpenGVLab/InternVL3-1B-hf", - "pkg": { - "0": { - "transformers": "InternVLModel" - } - }, - "tasks": [ - "InternVLVisionPreTrainedModel", - "InternVLVisionModel", - "InternVLPreTrainedModel", - "InternVLModel", - "InternVLForConditionalGeneration" - ] - } - }, - "info.stst.jais-2-chat": { - "*": { - "repo": "inceptionai/Jais-2-8B-Chat", - "pkg": { - "0": { - "transformers": "Jais2Model" - } - }, - "tasks": [ - "Jais2Model", - "Jais2ForCausalLM", - "Jais2PreTrainedModel" - ] - } - }, - "info.ssm.jamba-v0": { - "*": { - "repo": "ai21labs/Jamba-v0.1", - "pkg": { - "0": { - "transformers": "JambaModel" - } - }, - "tasks": [ - "JambaForCausalLM", - "JambaForSequenceClassification", - "JambaModel", - "JambaPreTrainedModel" - ] - } - }, - "info.vit.janus": { - "*": { - "repo": "deepseek-community/Janus-Pro-1B", - "pkg": { - "0": { - "transformers": "JanusModel" - } - }, - "tasks": [ - "JanusPreTrainedModel", - "JanusForConditionalGeneration", - "JanusModel", - "JanusVQVAE", - "JanusVisionModel" - ] - } - }, - "info.moe.jetmoe": { - "*": { - "repo": "jetmoe/jetmoe-8b", - "pkg": { - "0": { - "transformers": "JetMoeModel" - } - }, - "tasks": [ - "JetMoeForCausalLM", - "JetMoeModel", - "JetMoePreTrainedModel", - "JetMoeForSequenceClassification" - ] - } - }, - "info.vit.kosmos-2-patch14-224": { - "*": { - "repo": "microsoft/kosmos-2-patch14-224", - "pkg": { - "0": { - "transformers": "Kosmos2Model" - } - }, - "tasks": [ - "Kosmos2ForConditionalGeneration", - "Kosmos2Model", - "Kosmos2PreTrainedModel" - ] - } - }, - "info.vit.kosmos-2": { - "*": { - "repo": "microsoft/kosmos-2.5", - "pkg": { - "0": { - "transformers": "Kosmos2_5Model" - } - }, - "tasks": [ - "Kosmos2_5ForConditionalGeneration", - "Kosmos2_5Model", - "Kosmos2_5PreTrainedModel" - ] - } - }, - "info.stst.stt-en-trfs": { - "*": { - "repo": "kyutai/stt-2.6b-en-trfs", - "pkg": { - "0": { - "transformers": "KyutaiSpeechToTextModel" - } - }, - "tasks": [ - "KyutaiSpeechToTextPreTrainedModel", - "KyutaiSpeechToTextModel", - "KyutaiSpeechToTextForConditionalGeneration" - ] - } - }, - "info.aet.todo": { - "*": { - "repo": "TODO/TODO", - "pkg": { - "0": { - "transformers": "LasrForCTC" - } - }, - "tasks": [ - "LasrForCTC", - "LasrEncoder", - "LasrPreTrainedModel" - ] - } - }, - "info.stst.todo": { - "*": { - "repo": "TODO/TODO", - "pkg": { - "0": { - "transformers": "LasrEncoder" - } - }, - "tasks": [ - "LasrForCTC", - "LasrEncoder", - "LasrPreTrainedModel" - ] - } - }, - "info.art.layoutlm-uncased": { - "*": { - "repo": "microsoft/layoutlm-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMModel" - } - }, - "tasks": [ - "LayoutLMForMaskedLM", - "LayoutLMForSequenceClassification", - "LayoutLMForTokenClassification", - "LayoutLMForQuestionAnswering", - "LayoutLMModel", - "LayoutLMPreTrainedModel" - ] - } - }, - "info.art.layoutlmv2-uncased": { - "*": { - "repo": "microsoft/layoutlmv2-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMv2Model" - } - }, - "tasks": [ - "LayoutLMv2ForQuestionAnswering", - "LayoutLMv2ForSequenceClassification", - "LayoutLMv2ForTokenClassification", - "LayoutLMv2Layer", - "LayoutLMv2Model", - "LayoutLMv2PreTrainedModel" - ] - } - }, - "info.vit.layoutlmv3": { - "*": { - "repo": "microsoft/layoutlmv3-base", - "pkg": { - "0": { - "transformers": "LayoutLMv3Model" - } - }, - "tasks": [ - "LayoutLMv3ForQuestionAnswering", - "LayoutLMv3ForSequenceClassification", - "LayoutLMv3ForTokenClassification", - "LayoutLMv3Model", - "LayoutLMv3PreTrainedModel" - ] - } - }, - "info.stst.led-16384": { - "*": { - "repo": "allenai/led-base-16384", - "pkg": { - "0": { - "transformers": "LEDModel" - } - }, - "tasks": [ - "LEDForConditionalGeneration", - "LEDForQuestionAnswering", - "LEDForSequenceClassification", - "LEDModel", - "LEDPreTrainedModel" - ] - } - }, - "info.gan.levit-128s": { - "*": { - "repo": "facebook/levit-128S", - "pkg": { - "0": { - "transformers": "LevitModel" - } - }, - "tasks": [ - "LevitForImageClassification", - "LevitForImageClassificationWithTeacher", - "LevitModel", - "LevitPreTrainedModel" - ] - } - }, - "info.stst.lfm": { - "*": { - "repo": "LiquidAI/LFM2-1.2B", - "pkg": { - "0": { - "transformers": "Lfm2Model" - } - }, - "tasks": [ - "Lfm2ForCausalLM", - "Lfm2Model", - "Lfm2PreTrainedModel" - ] - } - }, - "info.moe.lfm2-a": { - "*": { - "repo": "LiquidAI/LFM2-8B-A1B", - "pkg": { - "0": { - "transformers": "Lfm2MoeModel" - } - }, - "tasks": [ - "Lfm2MoeForCausalLM", - "Lfm2MoeModel", - "Lfm2MoePreTrainedModel" - ] - } - }, - "info.vit.lfm2-vl": { - "*": { - "repo": "LiquidAI/LFM2-VL-1.6B", - "pkg": { - "0": { - "transformers": "Lfm2VlModel" - } - }, - "tasks": [ - "Lfm2VlForConditionalGeneration", - "Lfm2VlPreTrainedModel", - "Lfm2VlModel" - ] - } - }, - "info.aet.lightglue-superpoint": { - "*": { - "repo": "ETH-CVG/lightglue_superpoint", - "pkg": { - "0": { - "transformers": "LightGlueForKeypointMatching" - } - }, - "tasks": [ - "LightGluePreTrainedModel", - "LightGlueForKeypointMatching" - ] - } - }, - "info.art.lilt-roberta-en": { - "*": { - "repo": "SCUT-DLVCLab/lilt-roberta-en-base", - "pkg": { - "0": { - "transformers": "LiltModel" - } - }, - "tasks": [ - "LiltForQuestionAnswering", - "LiltForSequenceClassification", - "LiltForTokenClassification", - "LiltModel", - "LiltPreTrainedModel" - ] - } - }, - "info.vit.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4ForConditionalGeneration" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.moe.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4TextModel" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.vit.llava": { - "*": { - "repo": "llava-hf/llava-9b", - "pkg": { - "0": { - "transformers": "LlavaModel" - } - }, - "file_256": [ - "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" - ], - "layer_b3": [ - "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" - ], - "layer_256": [ - "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" - ], - "tasks": [ - "LlavaForConditionalGeneration", - "LlavaPreTrainedModel", - "LlavaModel" - ] - } - }, - "info.vit.llava-next-video-hf": { - "*": { - "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", - "pkg": { - "0": { - "transformers": "LlavaNextVideoModel" - } - }, - "tasks": [ - "LlavaNextVideoForConditionalGeneration", - "LlavaNextVideoModel", - "LlavaNextVideoPreTrainedModel" - ] - } - }, - "info.vit.llava-onevision-qwen2-ov-hf": { - "*": { - "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", - "pkg": { - "0": { - "transformers": "LlavaOnevisionModel" - } - }, - "tasks": [ - "LlavaOnevisionModel", - "LlavaOnevisionForConditionalGeneration", - "LlavaOnevisionPreTrainedModel" - ] - } - }, - "info.stst.longcat-flash-chat": { - "*": { - "repo": "meituan-longcat/LongCat-Flash-Chat", - "pkg": { - "0": { - "transformers": "LongcatFlashModel" - } - }, - "tasks": [ - "LongcatFlashPreTrainedModel", - "LongcatFlashModel", - "LongcatFlashForCausalLM" - ] - } - }, - "info.art.longformer-4096": { - "*": { - "repo": "allenai/longformer-base-4096", - "pkg": { - "0": { - "transformers": "LongformerModel" - } - }, - "tasks": [ - "LongformerForMaskedLM", - "LongformerForMultipleChoice", - "LongformerForQuestionAnswering", - "LongformerForSequenceClassification", - "LongformerForTokenClassification", - "LongformerModel", - "LongformerPreTrainedModel", - "LongformerSelfAttention" - ] - } - }, - "info.stst.long-t5-local": { - "*": { - "repo": "google/long-t5-local-base", - "pkg": { - "0": { - "transformers": "LongT5Model" - } - }, - "tasks": [ - "LongT5EncoderModel", - "LongT5ForConditionalGeneration", - "LongT5Model", - "LongT5PreTrainedModel" - ] - } - }, - "info.art.luke": { - "*": { - "repo": "studio-ousia/luke-base", - "pkg": { - "0": { - "transformers": "LukeModel" - } - }, - "tasks": [ - "LukeForEntityClassification", - "LukeForEntityPairClassification", - "LukeForEntitySpanClassification", - "LukeForMultipleChoice", - "LukeForQuestionAnswering", - "LukeForSequenceClassification", - "LukeForTokenClassification", - "LukeForMaskedLM", - "LukeModel", - "LukePreTrainedModel" - ] - } - }, - "info.art.lxmert-uncased": { - "*": { - "repo": "unc-nlp/lxmert-base-uncased", - "pkg": { - "0": { - "transformers": "LxmertModel" - } - }, - "tasks": [ - "LxmertEncoder", - "LxmertForPreTraining", - "LxmertForQuestionAnswering", - "LxmertModel", - "LxmertPreTrainedModel", - "LxmertVisualFeatureEncoder", - "LxmertXLayer" - ] - } - }, - "info.stst.m": { - "*": { - "repo": "facebook/m2m100_418M", - "pkg": { - "0": { - "transformers": "M2M100Model" - } - }, - "tasks": [ - "M2M100ForConditionalGeneration", - "M2M100Model", - "M2M100PreTrainedModel" - ] - } - }, - "info.ssm.mamba": { - "*": { - "repo": "state-spaces/mamba-2.8b", - "pkg": { - "0": { - "transformers": "MambaModel" - } - }, - "tasks": [ - "MambaForCausalLM", - "MambaModel", - "MambaPreTrainedModel", - "MambaCache" - ] - } - }, - "info.ssm.mamba2": { - "*": { - "repo": "AntonV/mamba2-2.7b-hf", - "pkg": { - "0": { - "transformers": "Mamba2Model" - } - }, - "tasks": [ - "Mamba2ForCausalLM", - "Mamba2Model", - "Mamba2PreTrainedModel" - ] - } - }, - "info.stst.opus-mt-en-de": { - "*": { - "repo": "Helsinki-NLP/opus-mt-en-de", - "pkg": { - "0": { - "transformers": "MarianModel" - } - }, - "tasks": [ - "MarianForCausalLM", - "MarianModel", - "MarianMTModel", - "MarianPreTrainedModel" - ] - } - }, - "info.art.markuplm": { - "*": { - "repo": "microsoft/markuplm-base", - "pkg": { - "0": { - "transformers": "MarkupLMModel" - } - }, - "tasks": [ - "MarkupLMForQuestionAnswering", - "MarkupLMForSequenceClassification", - "MarkupLMForTokenClassification", - "MarkupLMModel", - "MarkupLMPreTrainedModel" - ] - } - }, - "info.detr.mask2former-swin-coco-instance": { - "*": { - "repo": "facebook/mask2former-swin-small-coco-instance", - "pkg": { - "0": { - "transformers": "Mask2FormerModel" - } - }, - "tasks": [ - "Mask2FormerForUniversalSegmentation", - "Mask2FormerModel", - "Mask2FormerPreTrainedModel" - ] - } - }, - "info.detr.maskformer-swin-ade": { - "*": { - "repo": "facebook/maskformer-swin-base-ade", - "pkg": { - "0": { - "transformers": "MaskFormerModel" - } - }, - "tasks": [ - "MaskFormerForInstanceSegmentation", - "MaskFormerModel", - "MaskFormerPreTrainedModel" - ] - } - }, - "info.vit.swin-patch4-window7-224": { - "*": { - "repo": "microsoft/swin-tiny-patch4-window7-224", - "pkg": { - "0": { - "transformers": "MaskFormerSwinModel" - } - }, - "tasks": [ - "MaskFormerSwinBackbone", - "MaskFormerSwinModel", - "MaskFormerSwinPreTrainedModel" - ] - } - }, - "info.stst.mbart-cc25": { - "*": { - "repo": "facebook/mbart-large-cc25", - "pkg": { - "0": { - "transformers": "MBartModel" - } - }, - "tasks": [ - "MBartForCausalLM", - "MBartForConditionalGeneration", - "MBartForQuestionAnswering", - "MBartForSequenceClassification", - "MBartModel", - "MBartPreTrainedModel" - ] - } - }, - "info.art.megatron-bert-uncased": { - "*": { - "repo": "nvidia/megatron-bert-uncased-345m", - "pkg": { - "0": { - "transformers": "MegatronBertModel" - } - }, - "tasks": [ - "MegatronBertForCausalLM", - "MegatronBertForMaskedLM", - "MegatronBertForMultipleChoice", - "MegatronBertForNextSentencePrediction", - "MegatronBertForPreTraining", - "MegatronBertForQuestionAnswering", - "MegatronBertForSequenceClassification", - "MegatronBertForTokenClassification", - "MegatronBertModel", - "MegatronBertPreTrainedModel" - ] - } - }, - "info.vit.metaclip-2-worldwide-huge-quickgelu": { - "*": { - "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", - "pkg": { - "0": { - "transformers": "MetaClip2Model" - } - }, - "tasks": [ - "MetaClip2Model", - "MetaClip2PreTrainedModel", - "MetaClip2TextModel", - "MetaClip2TextModelWithProjection", - "MetaClip2VisionModel", - "MetaClip2VisionModelWithProjection", - "MetaClip2ForImageClassification" - ] - } - }, - "info.vit.mgp-str": { - "*": { - "repo": "alibaba-damo/mgp-str-base", - "pkg": { - "0": { - "transformers": "MgpstrForSceneTextRecognition" - } - }, - "tasks": [ - "MgpstrModel", - "MgpstrPreTrainedModel", - "MgpstrForSceneTextRecognition" - ] - } - }, - "info.gan.mimi": { - "*": { - "repo": "kyutai/mimi", - "pkg": { - "0": { - "transformers": "MimiModel" - } - }, - "tasks": [ - "MimiModel", - "MimiPreTrainedModel" - ] - } - }, - "info.moe.max-text-01-hf": { - "*": { - "repo": "MiniMaxAI/MiniMax-Text-01-hf", - "pkg": { - "0": { - "transformers": "MiniMaxModel" - } - }, - "tasks": [ - "MiniMaxPreTrainedModel", - "MiniMaxModel", - "MiniMaxForCausalLM", - "MiniMaxForSequenceClassification", - "MiniMaxForTokenClassification", - "MiniMaxForQuestionAnswering" - ] - } - }, - "info.stst.stral-2410": { - "*": { - "repo": "mistralai/Ministral-8B-Instruct-2410", - "pkg": { - "0": { - "transformers": "MinistralModel" - } - }, - "tasks": [ - "MinistralPreTrainedModel", - "MinistralModel", - "MinistralForCausalLM", - "MinistralForSequenceClassification", - "MinistralForTokenClassification", - "MinistralForQuestionAnswering" - ] - } - }, - "info.stst.stral-3-2512": { - "*": { - "repo": "mistralai/Ministral-3-8B-Base-2512", - "pkg": { - "0": { - "transformers": "Ministral3Model" - } - }, - "tasks": [ - "Ministral3ForCausalLM", - "Ministral3ForQuestionAnswering", - "Ministral3Model", - "Ministral3PreTrainedModel", - "Ministral3ForSequenceClassification", - "Ministral3ForTokenClassification" - ] - } - }, - "info.stst.mistral-v0": { - "*": { - "repo": "mistralai/Mistral-7B-v0.1", - "pkg": { - "0": { - "transformers": "MistralModel" - } - }, - "tasks": [ - "MistralForCausalLM", - "MistralForQuestionAnswering", - "MistralModel", - "MistralPreTrainedModel", - "MistralForSequenceClassification", - "MistralForTokenClassification" - ] - } - }, - "info.vit.mistral-3-2503": { - "*": { - "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", - "pkg": { - "0": { - "transformers": "Mistral3Model" - } - }, - "tasks": [ - "Mistral3Model", - "Mistral3PreTrainedModel", - "Mistral3ForConditionalGeneration" - ] - } - }, - "info.moe.mixtral-8x": { - "*": { - "repo": "mistralai/Mixtral-8x7B-v0.1", - "pkg": { - "0": { - "transformers": "MixtralModel" - } - }, - "tasks": [ - "MixtralForCausalLM", - "MixtralForQuestionAnswering", - "MixtralModel", - "MixtralPreTrainedModel", - "MixtralForSequenceClassification", - "MixtralForTokenClassification" - ] - } - }, - "info.vit.mlcd-vit-bigg-patch14-336": { - "*": { - "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", - "pkg": { - "0": { - "transformers": "MLCDVisionModel" - } - }, - "tasks": [ - "MLCDPreTrainedModel", - "MLCDVisionModel" - ] - } - }, - "info.vit.llama-3-vision": { - "*": { - "repo": "meta-llama/Llama-3.2-11B-Vision", - "pkg": { - "0": { - "transformers": "MllamaModel" - } - }, - "tasks": [ - "MllamaForConditionalGeneration", - "MllamaForCausalLM", - "MllamaTextModel", - "MllamaVisionModel", - "MllamaPreTrainedModel", - "MllamaModel" - ] - } - }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { - "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", - "pkg": { - "0": { - "transformers": "MMGroundingDinoModel" - } - }, - "tasks": [ - "MMGroundingDinoForObjectDetection", - "MMGroundingDinoModel", - "MMGroundingDinoPreTrainedModel" - ] - } - }, - "info.art.mobilebert-uncased": { - "*": { - "repo": "google/mobilebert-uncased", - "pkg": { - "0": { - "transformers": "MobileBertModel" - } - }, - "tasks": [ - "MobileBertForMaskedLM", - "MobileBertForMultipleChoice", - "MobileBertForNextSentencePrediction", - "MobileBertForPreTraining", - "MobileBertForQuestionAnswering", - "MobileBertForSequenceClassification", - "MobileBertForTokenClassification", - "MobileBertLayer", - "MobileBertModel", - "MobileBertPreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v1-1--224": { - "*": { - "repo": "google/mobilenet_v1_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV1Model" - } - }, - "tasks": [ - "MobileNetV1ForImageClassification", - "MobileNetV1Model", - "MobileNetV1PreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v2-1--224": { - "*": { - "repo": "google/mobilenet_v2_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV2Model" - } - }, - "tasks": [ - "MobileNetV2ForImageClassification", - "MobileNetV2ForSemanticSegmentation", - "MobileNetV2Model", - "MobileNetV2PreTrainedModel" - ] - } - }, - "info.vit.mobilevit": { - "*": { - "repo": "apple/mobilevit-small", - "pkg": { - "0": { - "transformers": "MobileViTModel" - } - }, - "tasks": [ - "MobileViTForImageClassification", - "MobileViTForSemanticSegmentation", - "MobileViTModel", - "MobileViTPreTrainedModel" - ] - } - }, - "info.vit.mobilevitv2-1": { - "*": { - "repo": "apple/mobilevitv2-1.0-imagenet1k-256", - "pkg": { - "0": { - "transformers": "MobileViTV2Model" - } - }, - "tasks": [ - "MobileViTV2ForImageClassification", - "MobileViTV2ForSemanticSegmentation", - "MobileViTV2Model", - "MobileViTV2PreTrainedModel" - ] - } - }, - "info.aet.modernbert": { - "*": { - "repo": "answerdotai/ModernBERT-base", - "pkg": { - "0": { - "transformers": "ModernBertModel" - } - }, - "tasks": [ - "ModernBertModel", - "ModernBertPreTrainedModel", - "ModernBertForMaskedLM", - "ModernBertForSequenceClassification", - "ModernBertForTokenClassification", - "ModernBertForQuestionAnswering", - "ModernBertForMultipleChoice" - ] - } - }, - "info.aet.test-dec": { - "*": { - "repo": "blab-jhu/test-32m-dec", - "pkg": { - "0": { - "transformers": "ModernBertDecoderModel" - } - }, - "tasks": [ - "ModernBertDecoderModel", - "ModernBertDecoderPreTrainedModel", - "ModernBertDecoderForCausalLM", - "ModernBertDecoderForSequenceClassification" - ] - } - }, - "info.stst.moonshine": { - "*": { - "repo": "UsefulSensors/moonshine-tiny", - "pkg": { - "0": { - "transformers": "MoonshineModel" - } - }, - "tasks": [ - "MoonshineModel", - "MoonshinePreTrainedModel", - "MoonshineForConditionalGeneration" - ] - } - }, - "info.stst.hf-moshiko": { - "*": { - "repo": "kmhf/hf-moshiko", - "pkg": { - "0": { - "transformers": "MoshiModel" - } - }, - "tasks": [ - "MoshiForCausalLM", - "MoshiForConditionalGeneration", - "MoshiModel", - "MoshiPreTrainedModel" - ] - } - }, - "info.art.mpnet": { - "*": { - "repo": "microsoft/mpnet-base", - "pkg": { - "0": { - "transformers": "MPNetModel" - } - }, - "tasks": [ - "MPNetForMaskedLM", - "MPNetForMultipleChoice", - "MPNetForQuestionAnswering", - "MPNetForSequenceClassification", - "MPNetForTokenClassification", - "MPNetLayer", - "MPNetModel", - "MPNetPreTrainedModel" - ] - } - }, - "info.art.mpt": { - "*": { - "repo": "mosaicml/mpt-7b", - "pkg": { - "0": { - "transformers": "MptModel" - } - }, - "tasks": [ - "MptForCausalLM", - "MptModel", - "MptPreTrainedModel", - "MptForSequenceClassification", - "MptForTokenClassification", - "MptForQuestionAnswering" - ] - } - }, - "info.art.mra-512-4": { - "*": { - "repo": "uw-madison/mra-base-512-4", - "pkg": { - "0": { - "transformers": "MraModel" - } - }, - "tasks": [ - "MraForMaskedLM", - "MraForMultipleChoice", - "MraForQuestionAnswering", - "MraForSequenceClassification", - "MraForTokenClassification", - "MraLayer", - "MraModel", - "MraPreTrainedModel" - ] - } - }, - "info.stst.mt5": { - "*": { - "repo": "google/mt5-small", - "pkg": { - "0": { - "transformers": "MT5Model" - } - }, - "identifiers": [ - [ - 250112, - 2048 - ], - "text_encoders.mt5xl.transformer.shared.weight" - ], - "file_256": [ - "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", - "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" - ], - "layer_b3": [ - "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51" - ], - "layer_256": [ - "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", - "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" - ], - "tasks": [ - "MT5EncoderModel", - "MT5ForConditionalGeneration", - "MT5ForQuestionAnswering", - "MT5ForSequenceClassification", - "MT5ForTokenClassification", - "MT5Model", - "MT5PreTrainedModel" - ] - } - }, - "info.art.musicgen": { - "*": { - "repo": "facebook/musicgen-small", - "pkg": { - "0": { - "transformers": "MusicgenModel" - } - }, - "tasks": [ - "MusicgenForConditionalGeneration", - "MusicgenForCausalLM", - "MusicgenModel", - "MusicgenPreTrainedModel" - ] - } - }, - "info.art.musicgen-melody": { - "*": { - "repo": "facebook/musicgen-melody", - "pkg": { - "0": { - "transformers": "MusicgenMelodyModel" - } - }, - "tasks": [ - "MusicgenMelodyForConditionalGeneration", - "MusicgenMelodyForCausalLM", - "MusicgenMelodyModel", - "MusicgenMelodyPreTrainedModel" - ] - } - }, - "info.stst.mvp": { - "*": { - "repo": "RUCAIBox/mvp", - "pkg": { - "0": { - "transformers": "MvpModel" - } - }, - "tasks": [ - "MvpForCausalLM", - "MvpForConditionalGeneration", - "MvpForQuestionAnswering", - "MvpForSequenceClassification", - "MvpModel", - "MvpPreTrainedModel" - ] - } - }, - "info.stst.nanochat-d32": { - "*": { - "repo": "karpathy/nanochat-d32", - "pkg": { - "0": { - "transformers": "NanoChatModel" - } - }, - "tasks": [ - "NanoChatPreTrainedModel", - "NanoChatModel", - "NanoChatForCausalLM" - ] - } - }, - "info.stst.nemotron-3-hf": { - "*": { - "repo": "mgoin/nemotron-3-8b-chat-4k-sft-hf", - "pkg": { - "0": { - "transformers": "NemotronModel" - } - }, - "tasks": [ - "NemotronForQuestionAnswering", - "NemotronForCausalLM", - "NemotronModel", - "NemotronPreTrainedModel", - "NemotronForSequenceClassification", - "NemotronForTokenClassification" - ] - } - }, - "info.moe.nllb-moe": { - "*": { - "repo": "facebook/nllb-moe-54b", - "pkg": { - "0": { - "transformers": "NllbMoeModel" - } - }, - "tasks": [ - "NllbMoeForConditionalGeneration", - "NllbMoeModel", - "NllbMoePreTrainedModel", - "NllbMoeTop2Router", - "NllbMoeSparseMLP" - ] - } - }, - "info.art.nystromformer-512": { - "*": { - "repo": "uw-madison/nystromformer-512", - "pkg": { - "0": { - "transformers": "NystromformerModel" - } - }, - "tasks": [ - "NystromformerForMaskedLM", - "NystromformerForMultipleChoice", - "NystromformerForQuestionAnswering", - "NystromformerForSequenceClassification", - "NystromformerForTokenClassification", - "NystromformerLayer", - "NystromformerModel", - "NystromformerPreTrainedModel" - ] - } - }, - "info.stst.olmo-hf": { - "*": { - "repo": "allenai/OLMo-7B-hf", - "pkg": { - "0": { - "transformers": "OlmoModel" - } - }, - "tasks": [ - "OlmoForCausalLM", - "OlmoModel", - "OlmoPreTrainedModel" - ] - } - }, - "info.stst.olmo2-1124-hf": { - "*": { - "repo": "allenai/Olmo-2-1124-7B", - "pkg": { - "0": { - "transformers": "Olmo2Model" - } - }, - "tasks": [ - "Olmo2ForCausalLM", - "Olmo2Model", - "Olmo2PreTrainedModel" - ] - } - }, - "info.stst.olmo-3-0725": { - "*": { - "repo": "allenai/OLMo-3-0725-1B", - "pkg": { - "0": { - "transformers": "Olmo3Model" - } - }, - "tasks": [ - "Olmo3ForCausalLM", - "Olmo3Model", - "Olmo3PreTrainedModel" - ] - } - }, - "info.moe.olmoe-0924": { - "*": { - "repo": "allenai/OLMoE-1B-7B-0924", - "pkg": { - "0": { - "transformers": "OlmoeModel" - } - }, - "tasks": [ - "OlmoeForCausalLM", - "OlmoeModel", - "OlmoePreTrainedModel" - ] - } - }, - "info.detr.omdet-turbo-swin-hf": { - "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", - "pkg": { - "0": { - "transformers": "OmDetTurboForObjectDetection" - } - }, - "tasks": [ - "OmDetTurboForObjectDetection", - "OmDetTurboPreTrainedModel" - ] - } - }, - "info.detr.oneformer-ade-swin": { - "*": { - "repo": "shi-labs/oneformer_ade20k_swin_tiny", - "pkg": { - "0": { - "transformers": "OneFormerModel" - } - }, - "tasks": [ - "OneFormerForUniversalSegmentation", - "OneFormerModel", - "OneFormerPreTrainedModel" - ] - } - }, - "info.art.openai-gpt": { - "*": { - "repo": "openai-community/openai-gpt", - "pkg": { - "0": { - "transformers": "OpenAIGPTModel" - } - }, - "tasks": [ - "OpenAIGPTDoubleHeadsModel", - "OpenAIGPTForSequenceClassification", - "OpenAIGPTLMHeadModel", - "OpenAIGPTModel", - "OpenAIGPTPreTrainedModel" - ] - } - }, - "info.art.opt": { - "*": { - "repo": "facebook/opt-350m", - "pkg": { - "0": { - "transformers": "OPTModel" - } - }, - "tasks": [ - "OPTForCausalLM", - "OPTModel", - "OPTPreTrainedModel", - "OPTForSequenceClassification", - "OPTForQuestionAnswering" - ] - } - }, - "info.vit.ovis2-hf": { - "*": { - "repo": "thisisiron/Ovis2-1B-hf", - "pkg": { - "0": { - "transformers": "Ovis2Model" - } - }, - "tasks": [ - "Ovis2PreTrainedModel", - "Ovis2Model", - "Ovis2ForConditionalGeneration" - ] - } - }, - "info.vit.owlv2-patch16": { - "*": { - "repo": "google/owlv2-base-patch16", - "pkg": { - "0": { - "transformers": "Owlv2Model" - } - }, - "tasks": [ - "Owlv2Model", - "Owlv2PreTrainedModel", - "Owlv2TextModel", - "Owlv2VisionModel", - "Owlv2ForObjectDetection" - ] - } - }, - "info.vit.owlvit-patch32": { - "*": { - "repo": "google/owlvit-base-patch32", - "pkg": { - "0": { - "transformers": "OwlViTModel" - } - }, - "tasks": [ - "OwlViTModel", - "OwlViTPreTrainedModel", - "OwlViTTextModel", - "OwlViTVisionModel", - "OwlViTForObjectDetection" - ] - } - }, - "info.vit.paligemma": { - "*": { - "repo": "google/paligemma2-3b-mix-224", - "pkg": { - "0": { - "transformers": "PaliGemmaModel" - } - }, - "tasks": [ - "PaliGemmaForConditionalGeneration", - "PaliGemmaPreTrainedModel", - "PaliGemmaModel" - ] - } - }, - "info.aet.parakeet-ctc-b": { - "*": { - "repo": "nvidia/parakeet-ctc-1.1b", - "pkg": { - "0": { - "transformers": "ParakeetForCTC" - } - }, - "tasks": [ - "ParakeetForCTC", - "ParakeetEncoder", - "ParakeetPreTrainedModel" - ] - } - }, - "info.stst.parakeet-ctc-b": { - "*": { - "repo": "nvidia/parakeet-ctc-1.1b", - "pkg": { - "0": { - "transformers": "ParakeetEncoder" - } - }, - "tasks": [ - "ParakeetForCTC", - "ParakeetEncoder", - "ParakeetPreTrainedModel" - ] - } - }, - "info.mlp.patchtsmixer-etth1-pretrain": { - "*": { - "repo": "ibm/patchtsmixer-etth1-pretrain", - "pkg": { - "0": { - "transformers": "PatchTSMixerModel" - } - }, - "tasks": [ - "PatchTSMixerPreTrainedModel", - "PatchTSMixerModel", - "PatchTSMixerForPretraining", - "PatchTSMixerForPrediction", - "PatchTSMixerForTimeSeriesClassification", - "PatchTSMixerForRegression" - ] - } - }, - "info.art.patchtst": { - "*": { - "repo": "ibm/patchtst", - "pkg": { - "0": { - "transformers": "PatchTSTModel" - } - }, - "tasks": [ - "PatchTSTModel", - "PatchTSTPreTrainedModel", - "PatchTSTForPrediction", - "PatchTSTForPretraining", - "PatchTSTForRegression", - "PatchTSTForClassification" - ] - } - }, - "info.stst.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeAudioModel" - } - }, - "tasks": [ - "PeAudioFrameLevelModel", - "PeAudioModel", - "PeAudioEncoder" - ] - } - }, - "info.aet.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeAudioVideoModel" - } - }, - "tasks": [ - "PeAudioVideoModel", - "PeAudioVideoEncoder" - ] - } - }, - "info.vit.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeVideoEncoder" - } - }, - "tasks": [ - "PeVideoEncoder", - "PeVideoModel" - ] - } - }, - "info.stst.pegasus": { - "*": { - "repo": "google/pegasus-large", - "pkg": { - "0": { - "transformers": "PegasusModel" - } - }, - "tasks": [ - "PegasusForCausalLM", - "PegasusForConditionalGeneration", - "PegasusModel", - "PegasusPreTrainedModel" - ] - } - }, - "info.stst.pegasus-x": { - "*": { - "repo": "google/pegasus-x-large", - "pkg": { - "0": { - "transformers": "PegasusXModel" - } - }, - "tasks": [ - "PegasusXForConditionalGeneration", - "PegasusXModel", - "PegasusXPreTrainedModel" - ] - } - }, - "info.vit.language-perceiver": { - "*": { - "repo": "deepmind/language-perceiver", - "pkg": { - "0": { - "transformers": "PerceiverModel" - } - }, - "tasks": [ - "PerceiverForImageClassificationConvProcessing", - "PerceiverForImageClassificationFourier", - "PerceiverForImageClassificationLearned", - "PerceiverForMaskedLM", - "PerceiverForMultimodalAutoencoding", - "PerceiverForOpticalFlow", - "PerceiverForSequenceClassification", - "PerceiverLayer", - "PerceiverModel", - "PerceiverPreTrainedModel" - ] - } - }, - "info.vit.perception-lm": { - "*": { - "repo": "facebook/Perception-LM-1B", - "pkg": { - "0": { - "transformers": "PerceptionLMModel" - } - }, - "tasks": [ - "PerceptionLMForConditionalGeneration", - "PerceptionLMPreTrainedModel", - "PerceptionLMModel" - ] - } - }, - "info.stst.persimmon": { - "*": { - "repo": "adept/persimmon-8b-base", - "pkg": { - "0": { - "transformers": "PersimmonModel" - } - }, - "tasks": [ - "PersimmonForCausalLM", - "PersimmonModel", - "PersimmonPreTrainedModel", - "PersimmonForSequenceClassification", - "PersimmonForTokenClassification" - ] - } - }, - "info.stst.phi-1": { - "*": { - "repo": "microsoft/phi-1", - "pkg": { - "0": { - "transformers": "PhiModel" - } - }, - "tasks": [ - "PhiPreTrainedModel", - "PhiModel", - "PhiForCausalLM", - "PhiForSequenceClassification", - "PhiForTokenClassification" - ] - } - }, - "info.stst.phi-3": { - "*": { - "repo": "microsoft/Phi-3-mini-4k-instruct", - "pkg": { - "0": { - "transformers": "Phi3Model" - } - }, - "tasks": [ - "Phi3PreTrainedModel", - "Phi3Model", - "Phi3ForCausalLM", - "Phi3ForSequenceClassification", - "Phi3ForTokenClassification" - ] - } - }, - "info.vit.phi-4": { - "*": { - "repo": "microsoft/Phi-4-multimodal-instruct", - "pkg": { - "0": { - "transformers": "Phi4MultimodalModel" - } - }, - "file_256": [ - "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" - ], - "layer_b3": [ - "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" - ], - "layer_256": [ - "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" - ], - "tasks": [ - "Phi4MultimodalAudioPreTrainedModel", - "Phi4MultimodalAudioModel", - "Phi4MultimodalVisionPreTrainedModel", - "Phi4MultimodalVisionModel", - "Phi4MultimodalPreTrainedModel", - "Phi4MultimodalModel", - "Phi4MultimodalForCausalLM" - ] - } - }, - "info.moe.phi-3-moe": { - "*": { - "repo": "microsoft/Phi-3.5-MoE-instruct", - "pkg": { - "0": { - "transformers": "PhimoeModel" - } - }, - "tasks": [ - "PhimoePreTrainedModel", - "PhimoeModel", - "PhimoeForCausalLM", - "PhimoeForSequenceClassification" - ] - } - }, - "info.vit.pixio-huge": { - "*": { - "repo": "facebook/pixio-huge", - "pkg": { - "0": { - "transformers": "PixioModel" - } - }, - "tasks": [ - "PixioModel", - "PixioPreTrainedModel", - "PixioBackbone" - ] - } - }, - "info.vit.pixtral": { - "*": { - "repo": "mistralai/Pixtral-12B-Base-2409", - "pkg": { - "0": { - "transformers": "PixtralVisionModel" - } - }, - "tasks": [ - "PixtralVisionModel", - "PixtralPreTrainedModel" - ] - } - }, - "info.stst.plbart": { - "*": { - "repo": "uclanlp/plbart-base", - "pkg": { - "0": { - "transformers": "PLBartModel" - } - }, - "tasks": [ - "PLBartForCausalLM", - "PLBartForConditionalGeneration", - "PLBartForSequenceClassification", - "PLBartModel", - "PLBartPreTrainedModel" - ] - } - }, - "info.vit.poolformer-s12": { - "*": { - "repo": "sail/poolformer_s12", - "pkg": { - "0": { - "transformers": "PoolFormerModel" - } - }, - "tasks": [ - "PoolFormerForImageClassification", - "PoolFormerModel", - "PoolFormerPreTrainedModel" - ] - } - }, - "info.stst.phetnet-uncased": { - "*": { - "repo": "microsoft/prophetnet-large-uncased", - "pkg": { - "0": { - "transformers": "ProphetNetModel" - } - }, - "tasks": [ - "ProphetNetDecoder", - "ProphetNetEncoder", - "ProphetNetForCausalLM", - "ProphetNetForConditionalGeneration", - "ProphetNetModel", - "ProphetNetPreTrainedModel" - ] - } - }, - "info.vit.pvt-224": { - "*": { - "repo": "Xrenya/pvt-tiny-224", - "pkg": { - "0": { - "transformers": "PvtModel" - } - }, - "tasks": [ - "PvtForImageClassification", - "PvtModel", - "PvtPreTrainedModel" - ] - } - }, - "info.vit.pvt-v2-b0": { - "*": { - "repo": "OpenGVLab/pvt_v2_b0", - "pkg": { - "0": { - "transformers": "PvtV2Model" - } - }, - "tasks": [ - "PvtV2ForImageClassification", - "PvtV2Model", - "PvtV2PreTrainedModel", - "PvtV2Backbone" - ] - } - }, - "info.stst.qwen2": { - "*": { - "repo": "Qwen/Qwen2-7B", - "pkg": { - "0": { - "transformers": "Qwen2Model" - } - }, - "tasks": [ - "Qwen2PreTrainedModel", - "Qwen2Model", - "Qwen2ForCausalLM", - "Qwen2RMSNorm", - "Qwen2ForSequenceClassification", - "Qwen2ForTokenClassification", - "Qwen2ForQuestionAnswering" - ] - } - }, - "info.vit.qwen2-vl": { - "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen2_5_VLModel" - } - }, - "tasks": [ - "Qwen2_5_VLForConditionalGeneration", - "Qwen2_5_VLModel", - "Qwen2_5_VLPreTrainedModel", - "Qwen2_5_VLTextModel" - ] - } - }, - "info.stst.qwen2-vl": { - "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen2_5_VLTextModel" - } - }, - "file_256": [ - "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", - "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", - "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", - "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" - ], - "layer_b3": [ - "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", - "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", - "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", - "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" - ], - "layer_256": [ - "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", - "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", - "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", - "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" - ], - "tasks": [ - "Qwen2_5_VLForConditionalGeneration", - "Qwen2_5_VLModel", - "Qwen2_5_VLPreTrainedModel", - "Qwen2_5_VLTextModel" - ] - } - }, - "info.aet.qwen2-audio": { - "*": { - "repo": "Qwen/Qwen2-Audio-7B", - "pkg": { - "0": { - "transformers": "Qwen2AudioEncoder" - } - }, - "tasks": [ - "Qwen2AudioForConditionalGeneration", - "Qwen2AudioPreTrainedModel", - "Qwen2AudioEncoder" - ] - } - }, - "info.moe.qwen15-moe-a": { - "*": { - "repo": "Qwen/Qwen1.5-MoE-A2.7B", - "pkg": { - "0": { - "transformers": "Qwen2MoeModel" - } - }, - "tasks": [ - "Qwen2MoeForCausalLM", - "Qwen2MoeForQuestionAnswering", - "Qwen2MoeModel", - "Qwen2MoePreTrainedModel", - "Qwen2MoeForSequenceClassification", - "Qwen2MoeForTokenClassification" - ] - } - }, - "info.stst.qwen3": { - "*": { - "repo": "Qwen/Qwen3-8B", - "pkg": { - "0": { - "transformers": "Qwen3Model" - } - }, - "tasks": [ - "Qwen3ForCausalLM", - "Qwen3ForQuestionAnswering", - "Qwen3PreTrainedModel", - "Qwen3Model", - "Qwen3ForSequenceClassification", - "Qwen3ForTokenClassification" - ] - } - }, - "info.moe.qwen3-a": { - "*": { - "repo": "Qwen/Qwen3-30B-A3B", - "pkg": { - "0": { - "transformers": "Qwen3MoeModel" - } - }, - "file_256": [ - "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" - ], - "layer_b3": [ - "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" - ], - "layer_256": [ - "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" - ], - "tasks": [ - "Qwen3MoeForCausalLM", - "Qwen3MoeForQuestionAnswering", - "Qwen3MoeModel", - "Qwen3MoePreTrainedModel", - "Qwen3MoeForSequenceClassification", - "Qwen3MoeForTokenClassification" - ] - } - }, - "info.moe.qwen3-next-a": { - "*": { - "repo": "Qwen/Qwen3-Next-80B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3NextModel" - } - }, - "tasks": [ - "Qwen3NextForCausalLM", - "Qwen3NextForQuestionAnswering", - "Qwen3NextModel", - "Qwen3NextPreTrainedModel", - "Qwen3NextForSequenceClassification", - "Qwen3NextForTokenClassification" - ] - } - }, - "info.vit.qwen3-vl": { - "*": { - "repo": "Qwen/Qwen3-VL-4B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLModel" - } - }, - "tasks": [ - "Qwen3VLVisionModel", - "Qwen3VLForConditionalGeneration", - "Qwen3VLModel", - "Qwen3VLPreTrainedModel", - "Qwen3VLTextModel" - ] - } - }, - "info.vit.qwen3-vl-a": { - "*": { - "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLMoeModel" - } - }, - "tasks": [ - "Qwen3VLMoeVisionModel", - "Qwen3VLMoeForConditionalGeneration", - "Qwen3VLMoeModel", - "Qwen3VLMoePreTrainedModel", - "Qwen3VLMoeTextModel" - ] - } - }, - "info.moe.qwen3-vl-a": { - "*": { - "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLMoeTextModel" - } - }, - "tasks": [ - "Qwen3VLMoeVisionModel", - "Qwen3VLMoeForConditionalGeneration", - "Qwen3VLMoeModel", - "Qwen3VLMoePreTrainedModel", - "Qwen3VLMoeTextModel" - ] - } - }, - "info.stst.qwen3-vl": { - "*": { - "repo": "Qwen/Qwen3-VL-4B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLTextModel" - } - }, - "tasks": [ - "Qwen3VLVisionModel", - "Qwen3VLForConditionalGeneration", - "Qwen3VLModel", - "Qwen3VLPreTrainedModel", - "Qwen3VLTextModel" - ] - } - }, - "info.rnn.recurrentgemma": { - "*": { - "repo": "google/recurrentgemma-2b", - "pkg": { - "0": { - "transformers": "RecurrentGemmaModel" - } - }, - "tasks": [ - "RecurrentGemmaForCausalLM", - "RecurrentGemmaModel", - "RecurrentGemmaPreTrainedModel" - ] - } - }, - "info.art.reformer-crime-and-punishment": { - "*": { - "repo": "google/reformer-crime-and-punishment", - "pkg": { - "0": { - "transformers": "ReformerModel" - } - }, - "tasks": [ - "ReformerAttention", - "ReformerForMaskedLM", - "ReformerForQuestionAnswering", - "ReformerForSequenceClassification", - "ReformerLayer", - "ReformerModel", - "ReformerModelWithLMHead", - "ReformerPreTrainedModel" - ] - } - }, - "info.vit.regnet-y-040": { - "*": { - "repo": "facebook/regnet-y-040", - "pkg": { - "0": { - "transformers": "RegNetModel" - } - }, - "tasks": [ - "RegNetForImageClassification", - "RegNetModel", - "RegNetPreTrainedModel" - ] - } - }, - "info.art.rembert": { - "*": { - "repo": "google/rembert", - "pkg": { - "0": { - "transformers": "RemBertModel" - } - }, - "tasks": [ - "RemBertForCausalLM", - "RemBertForMaskedLM", - "RemBertForMultipleChoice", - "RemBertForQuestionAnswering", - "RemBertForSequenceClassification", - "RemBertForTokenClassification", - "RemBertLayer", - "RemBertModel", - "RemBertPreTrainedModel" - ] - } - }, - "info.vit.resnet-50": { - "*": { - "repo": "microsoft/resnet-50", - "pkg": { - "0": { - "transformers": "ResNetModel" - } - }, - "tasks": [ - "ResNetForImageClassification", - "ResNetModel", - "ResNetPreTrainedModel", - "ResNetBackbone" - ] - } - }, - "info.art.roberta": { - "*": { - "repo": "FacebookAI/roberta-base", - "pkg": { - "0": { - "transformers": "RobertaModel" - } - }, - "tasks": [ - "RobertaForCausalLM", - "RobertaForMaskedLM", - "RobertaForMultipleChoice", - "RobertaForQuestionAnswering", - "RobertaForSequenceClassification", - "RobertaForTokenClassification", - "RobertaModel", - "RobertaPreTrainedModel" - ] - } - }, - "info.art.efficient-mlm-m0-0": { - "*": { - "repo": "andreasmadsen/efficient_mlm_m0.40", - "pkg": { - "0": { - "transformers": "RobertaPreLayerNormModel" - } - }, - "tasks": [ - "RobertaPreLayerNormForCausalLM", - "RobertaPreLayerNormForMaskedLM", - "RobertaPreLayerNormForMultipleChoice", - "RobertaPreLayerNormForQuestionAnswering", - "RobertaPreLayerNormForSequenceClassification", - "RobertaPreLayerNormForTokenClassification", - "RobertaPreLayerNormModel", - "RobertaPreLayerNormPreTrainedModel" - ] - } - }, - "info.art.roc-bert-zh": { - "*": { - "repo": "weiweishi/roc-bert-base-zh", - "pkg": { - "0": { - "transformers": "RoCBertModel" - } - }, - "tasks": [ - "RoCBertForCausalLM", - "RoCBertForMaskedLM", - "RoCBertForMultipleChoice", - "RoCBertForPreTraining", - "RoCBertForQuestionAnswering", - "RoCBertForSequenceClassification", - "RoCBertForTokenClassification", - "RoCBertLayer", - "RoCBertModel", - "RoCBertPreTrainedModel" - ] - } - }, - "info.art.roformer-chinese": { - "*": { - "repo": "junnyu/roformer_chinese_base", - "pkg": { - "0": { - "transformers": "RoFormerModel" - } - }, - "tasks": [ - "RoFormerForCausalLM", - "RoFormerForMaskedLM", - "RoFormerForMultipleChoice", - "RoFormerForQuestionAnswering", - "RoFormerForSequenceClassification", - "RoFormerForTokenClassification", - "RoFormerLayer", - "RoFormerModel", - "RoFormerPreTrainedModel" - ] - } - }, - "info.detr.rtdetr-r50vd": { - "*": { - "repo": "PekingU/rtdetr_r50vd", - "pkg": { - "0": { - "transformers": "RTDetrModel" - } - }, - "tasks": [ - "RTDetrForObjectDetection", - "RTDetrModel", - "RTDetrPreTrainedModel" - ] - } - }, - "info.detr.rtdetr-r18vd": { - "*": { - "repo": "PekingU/rtdetr_r18vd", - "pkg": { - "0": { - "transformers": "RTDetrV2Model" - } - }, - "tasks": [ - "RTDetrV2Model", - "RTDetrV2PreTrainedModel", - "RTDetrV2ForObjectDetection" - ] - } - }, - "info.rnn.rwkv-4-pile": { - "*": { - "repo": "RWKV/rwkv-4-169m-pile", - "pkg": { - "0": { - "transformers": "RwkvModel" - } - }, - "tasks": [ - "RwkvForCausalLM", - "RwkvModel", - "RwkvPreTrainedModel" - ] - } - }, - "info.vit.sam-vit-huge": { - "*": { - "repo": "facebook/sam-vit-huge", - "pkg": { - "0": { - "transformers": "SamModel" - } - }, - "tasks": [ - "SamVisionModel", - "SamModel", - "SamPreTrainedModel" - ] - } - }, - "info.vit.sam2-hiera": { - "*": { - "repo": "facebook/sam2.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "Sam2Model" - } - }, - "tasks": [ - "Sam2Model", - "Sam2VisionModel", - "Sam2PreTrainedModel", - "Sam2HieraDetModel" - ] - } - }, - "info.vit.sam3": { - "*": { - "repo": "facebook/sam3", - "pkg": { - "0": { - "transformers": "Sam3Model" - } - }, - "tasks": [ - "Sam3Model", - "Sam3VisionModel", - "Sam3ViTModel", - "Sam3PreTrainedModel" - ] - } - }, - "info.vit.sam3-tracker1-hiera": { - "*": { - "repo": "facebook/sam3_tracker.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "Sam3TrackerModel" - } - }, - "tasks": [ - "Sam3TrackerModel", - "Sam3TrackerPreTrainedModel" - ] - } - }, - "info.stst.sam3": { - "*": { - "repo": "facebook/sam3", - "pkg": { - "0": { - "transformers": "Sam3VideoModel" - } - }, - "tasks": [ - "Sam3VideoModel", - "Sam3VideoPreTrainedModel", - "Sam3VideoInferenceSession", - "Sam3VideoSegmentationOutput" - ] - } - }, - "info.vit.sam-hq-vit-h": { - "*": { - "repo": "sushmanth/sam_hq_vit_h", - "pkg": { - "0": { - "transformers": "SamHQModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.vit.sam-hq-vit-huge": { - "*": { - "repo": "syscv-community/sam-hq-vit-huge", - "pkg": { - "0": { - "transformers": "SamHQVisionModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.aet.hf-seamless-m4t": { - "*": { - "repo": "facebook/hf-seamless-m4t-medium", - "pkg": { - "0": { - "transformers": "SeamlessM4TModel" - } - }, - "tasks": [ - "SeamlessM4TForTextToSpeech", - "SeamlessM4TForSpeechToSpeech", - "SeamlessM4TForTextToText", - "SeamlessM4TForSpeechToText", - "SeamlessM4TModel", - "SeamlessM4TPreTrainedModel", - "SeamlessM4TCodeHifiGan", - "SeamlessM4THifiGan", - "SeamlessM4TTextToUnitForConditionalGeneration", - "SeamlessM4TTextToUnitModel" - ] - } - }, - "info.stst.seamless-m4t-v2": { - "*": { - "repo": "facebook/seamless-m4t-v2-large", - "pkg": { - "0": { - "transformers": "SeamlessM4Tv2Model" - } - }, - "tasks": [ - "SeamlessM4Tv2ForTextToSpeech", - "SeamlessM4Tv2ForSpeechToSpeech", - "SeamlessM4Tv2ForTextToText", - "SeamlessM4Tv2ForSpeechToText", - "SeamlessM4Tv2Model", - "SeamlessM4Tv2PreTrainedModel" - ] - } - }, - "info.stst.seedoss": { - "*": { - "repo": "ByteDance-Seed/SeedOss-36B", - "pkg": { - "0": { - "transformers": "SeedOssModel" - } - }, - "tasks": [ - "SeedOssForCausalLM", - "SeedOssForQuestionAnswering", - "SeedOssPreTrainedModel", - "SeedOssModel", - "SeedOssForSequenceClassification", - "SeedOssForTokenClassification" - ] - } - }, - "info.vit.segformer-b0-finetuned-ade-512-512": { - "*": { - "repo": "nvidia/segformer-b0-finetuned-ade-512-512", - "pkg": { - "0": { - "transformers": "SegformerModel" - } - }, - "tasks": [ - "SegformerDecodeHead", - "SegformerForImageClassification", - "SegformerForSemanticSegmentation", - "SegformerLayer", - "SegformerModel", - "SegformerPreTrainedModel" - ] - } - }, - "info.vit.seggpt-vit": { - "*": { - "repo": "BAAI/seggpt-vit-large", - "pkg": { - "0": { - "transformers": "SegGptModel" - } - }, - "tasks": [ - "SegGptModel", - "SegGptPreTrainedModel", - "SegGptForImageSegmentation" - ] - } - }, - "info.aet.sew": { - "*": { - "repo": "asapp/sew-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWModel" - } - }, - "tasks": [ - "SEWForCTC", - "SEWForSequenceClassification", - "SEWModel", - "SEWPreTrainedModel" - ] - } - }, - "info.aet.sew-d": { - "*": { - "repo": "asapp/sew-d-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWDModel" - } - }, - "tasks": [ - "SEWDForCTC", - "SEWDForSequenceClassification", - "SEWDModel", - "SEWDPreTrainedModel" - ] - } - }, - "info.vit.siglip2-patch16-224": { - "*": { - "repo": "google/siglip2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Siglip2Model" - } - }, - "tasks": [ - "Siglip2Model", - "Siglip2PreTrainedModel", - "Siglip2TextModel", - "Siglip2VisionModel", - "Siglip2ForImageClassification" - ] - } - }, - "info.vit.siglip2-patch16-naflex": { - "*": { - "repo": "google/siglip2-base-patch16-naflex", - "pkg": { - "0": { - "transformers": "Siglip2VisionModel" - } - }, - "tasks": [ - "Siglip2Model", - "Siglip2PreTrainedModel", - "Siglip2TextModel", - "Siglip2VisionModel", - "Siglip2ForImageClassification" - ] - } - }, - "info.stst.smollm3": { - "*": { - "repo": "HuggingFaceTB/SmolLM3-3B", - "pkg": { - "0": { - "transformers": "SmolLM3Model" - } - }, - "tasks": [ - "SmolLM3PreTrainedModel", - "SmolLM3Model", - "SmolLM3ForCausalLM", - "SmolLM3ForSequenceClassification", - "SmolLM3ForTokenClassification", - "SmolLM3ForQuestionAnswering" - ] - } - }, - "info.vit.smolvlm": { - "*": { - "repo": "HuggingFaceTB/SmolVLM2-2.2B-Instruct", - "pkg": { - "0": { - "transformers": "SmolVLMModel" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.vit.siglip-so-patch14-384": { - "*": { - "repo": "google/siglip-so400m-patch14-384", - "pkg": { - "0": { - "transformers": "SmolVLMVisionTransformer" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.aet.s2t-librispeech-asr": { - "*": { - "repo": "facebook/s2t-small-librispeech-asr", - "pkg": { - "0": { - "transformers": "Speech2TextModel" - } - }, - "tasks": [ - "Speech2TextForConditionalGeneration", - "Speech2TextModel", - "Speech2TextPreTrainedModel" - ] - } - }, - "info.stst.speecht5-asr": { - "*": { - "repo": "microsoft/speecht5_asr", - "pkg": { - "0": { - "transformers": "SpeechT5Model" - } - }, - "tasks": [ - "SpeechT5ForSpeechToText", - "SpeechT5ForSpeechToSpeech", - "SpeechT5ForTextToSpeech", - "SpeechT5Model", - "SpeechT5PreTrainedModel", - "SpeechT5HifiGan" - ] - } - }, - "info.art.splinter": { - "*": { - "repo": "tau/splinter-base", - "pkg": { - "0": { - "transformers": "SplinterModel" - } - }, - "tasks": [ - "SplinterForQuestionAnswering", - "SplinterForPreTraining", - "SplinterLayer", - "SplinterModel", - "SplinterPreTrainedModel" - ] - } - }, - "info.art.squeezebert-uncased": { - "*": { - "repo": "squeezebert/squeezebert-uncased", - "pkg": { - "0": { - "transformers": "SqueezeBertModel" - } - }, - "tasks": [ - "SqueezeBertForMaskedLM", - "SqueezeBertForMultipleChoice", - "SqueezeBertForQuestionAnswering", - "SqueezeBertForSequenceClassification", - "SqueezeBertForTokenClassification", - "SqueezeBertModel", - "SqueezeBertModule", - "SqueezeBertPreTrainedModel" - ] - } - }, - "info.stst.stablelm-4e1t": { - "*": { - "repo": "stabilityai/stablelm-3b-4e1t", - "pkg": { - "0": { - "transformers": "StableLmModel" - } - }, - "tasks": [ - "StableLmForCausalLM", - "StableLmModel", - "StableLmPreTrainedModel", - "StableLmForSequenceClassification", - "StableLmForTokenClassification" - ] - } - }, - "info.stst.starcoder2": { - "*": { - "repo": "bigcode/starcoder2-7b", - "pkg": { - "0": { - "transformers": "Starcoder2Model" - } - }, - "tasks": [ - "Starcoder2ForCausalLM", - "Starcoder2Model", - "Starcoder2PreTrainedModel", - "Starcoder2ForSequenceClassification", - "Starcoder2ForTokenClassification" - ] - } - }, - "info.vit.swiftformer-xs": { - "*": { - "repo": "MBZUAI/swiftformer-xs", - "pkg": { - "0": { - "transformers": "SwiftFormerModel" - } - }, - "tasks": [ - "SwiftFormerForImageClassification", - "SwiftFormerModel", - "SwiftFormerPreTrainedModel" - ] - } - }, - "info.vit.swin2sr-classicalsr-x2-64": { - "*": { - "repo": "caidas/swin2sr-classicalsr-x2-64", - "pkg": { - "0": { - "transformers": "Swin2SRModel" - } - }, - "tasks": [ - "Swin2SRForImageSuperResolution", - "Swin2SRModel", - "Swin2SRPreTrainedModel" - ] - } - }, - "info.vit.swinv2-patch4-window8-256": { - "*": { - "repo": "microsoft/swinv2-tiny-patch4-window8-256", - "pkg": { - "0": { - "transformers": "Swinv2Model" - } - }, - "tasks": [ - "Swinv2ForImageClassification", - "Swinv2ForMaskedImageModeling", - "Swinv2Model", - "Swinv2PreTrainedModel", - "Swinv2Backbone" - ] - } - }, - "info.moe.switch-8": { - "*": { - "repo": "google/switch-base-8", - "pkg": { - "0": { - "transformers": "SwitchTransformersModel" - } - }, - "tasks": [ - "SwitchTransformersEncoderModel", - "SwitchTransformersForConditionalGeneration", - "SwitchTransformersModel", - "SwitchTransformersPreTrainedModel", - "SwitchTransformersTop1Router", - "SwitchTransformersSparseMLP" - ] - } - }, - "info.stst.t5": { - "*": { - "repo": "google-t5/t5-small", - "pkg": { - "0": { - "transformers": "T5Model" - } - }, - "identifiers": [ - [ - 4096 - ], - "encoder.embed_tokens.weight", - "text_encoders.t5xxl.transformer.shared.weight", - "t5xxl", - "encoder.block.0.layer.1.DenseReluDense.wi.weight" - ], - "file_256": [ - "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", - "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", - "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", - "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", - "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", - "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", - "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", - "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", - "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", - "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", - "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", - "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", - "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", - "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", - "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", - "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", - "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", - "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", - "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", - "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", - "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", - "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", - "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", - "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", - "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", - "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", - "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" - ], - "layer_b3": [ - "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", - "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", - "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", - "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", - "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", - "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", - "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", - "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", - "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", - "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", - "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", - "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", - "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", - "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", - "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", - "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", - "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", - "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", - "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", - "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", - "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", - "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", - "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", - "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", - "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", - "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", - "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", - "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", - "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", - "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" - ], - "layer_256": [ - "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", - "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", - "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", - "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", - "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", - "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", - "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", - "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", - "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", - "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", - "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", - "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", - "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", - "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", - "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", - "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", - "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", - "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", - "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", - "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", - "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", - "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", - "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", - "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", - "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", - "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", - "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", - "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" - ], - "tasks": [ - "T5EncoderModel", - "T5ForConditionalGeneration", - "T5Model", - "T5PreTrainedModel", - "T5ForQuestionAnswering", - "T5ForSequenceClassification", - "T5ForTokenClassification" - ] - } - }, - "info.stst.t5gemma-prefixlm": { - "*": { - "repo": "google/t5gemma-2b-2b-prefixlm-it", - "pkg": { - "0": { - "transformers": "T5GemmaModel" - } - }, - "tasks": [ - "T5GemmaForConditionalGeneration", - "T5GemmaModel", - "T5GemmaEncoderModel", - "T5GemmaPreTrainedModel", - "T5GemmaForSequenceClassification", - "T5GemmaForTokenClassification" - ] - } - }, - "info.stst.t5gemma-2": { - "*": { - "repo": "google/t5gemma-2-270m-270m", - "pkg": { - "0": { - "transformers": "T5Gemma2Model" - } - }, - "tasks": [ - "T5Gemma2ForConditionalGeneration", - "T5Gemma2Model", - "T5Gemma2PreTrainedModel", - "T5Gemma2ForSequenceClassification", - "T5Gemma2ForTokenClassification" - ] - } - }, - "info.detr.table-transformer-detection": { - "*": { - "repo": "microsoft/table-transformer-detection", - "pkg": { - "0": { - "transformers": "TableTransformerModel" - } - }, - "tasks": [ - "TableTransformerForObjectDetection", - "TableTransformerModel", - "TableTransformerPreTrainedModel" - ] - } - }, - "info.art.tapas-finetuned-sqa": { - "*": { - "repo": "google/tapas-base-finetuned-sqa", - "pkg": { - "0": { - "transformers": "TapasModel" - } - }, - "tasks": [ - "TapasForMaskedLM", - "TapasForQuestionAnswering", - "TapasForSequenceClassification", - "TapasModel", - "TapasPreTrainedModel" - ] - } - }, - "info.vit.textnet": { - "*": { - "repo": "czczup/textnet-base", - "pkg": { - "0": { - "transformers": "TextNetModel" - } - }, - "tasks": [ - "TextNetBackbone", - "TextNetModel", - "TextNetPreTrainedModel", - "TextNetForImageClassification" - ] - } - }, - "info.stst.time-series-transformer-tourism-monthly": { - "*": { - "repo": "huggingface/time-series-transformer-tourism-monthly", - "pkg": { - "0": { - "transformers": "TimeSeriesTransformerModel" - } - }, - "tasks": [ - "TimeSeriesTransformerForPrediction", - "TimeSeriesTransformerModel", - "TimeSeriesTransformerPreTrainedModel" - ] - } - }, - "info.art.timesfm-2-pytorch": { - "*": { - "repo": "google/timesfm-2.0-500m-pytorch", - "pkg": { - "0": { - "transformers": "TimesFmModel" - } - }, - "tasks": [ - "TimesFmModelForPrediction", - "TimesFmPreTrainedModel", - "TimesFmModel" - ] - } - }, - "info.vit.timesformer-finetuned-k600": { - "*": { - "repo": "facebook/timesformer-base-finetuned-k600", - "pkg": { - "0": { - "transformers": "TimesformerModel" - } - }, - "tasks": [ - "TimesformerModel", - "TimesformerForVideoClassification", - "TimesformerPreTrainedModel" - ] - } - }, - "info.detr.resnet18-a1-in": { - "*": { - "repo": "timm/resnet18.a1_in1k", - "pkg": { - "0": { - "transformers": "TimmWrapperModel" - } - }, - "tasks": [ - "TimmWrapperPreTrainedModel", - "TimmWrapperModel", - "TimmWrapperForImageClassification" - ] - } - }, - "info.detr.tvp": { - "*": { - "repo": "Intel/tvp-base", - "pkg": { - "0": { - "transformers": "TvpModel" - } - }, - "tasks": [ - "TvpModel", - "TvpPreTrainedModel", - "TvpForVideoGrounding" - ] - } - }, - "info.vit.udop": { - "*": { - "repo": "microsoft/udop-large", - "pkg": { - "0": { - "transformers": "UdopModel" - } - }, - "tasks": [ - "UdopForConditionalGeneration", - "UdopPreTrainedModel", - "UdopModel", - "UdopEncoderModel" - ] - } - }, - "info.stst.umt5": { - "*": { - "repo": "google/umt5-small", - "pkg": { - "0": { - "transformers": "UMT5Model" - } - }, - "identifiers": [ - "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" - ], - "file_256": [ - "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", - "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", - "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", - "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", - "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", - "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", - "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", - "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", - "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", - "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", - "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", - "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", - "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", - "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", - "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", - "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" - ], - "layer_b3": [ - "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", - "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", - "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", - "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", - "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", - "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", - "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", - "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", - "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", - "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", - "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", - "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", - "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", - "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", - "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", - "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", - "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", - "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" - ], - "layer_256": [ - "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", - "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", - "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", - "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", - "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", - "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", - "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", - "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", - "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", - "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", - "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", - "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", - "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", - "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", - "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", - "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", - "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", - "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" - ], - "tasks": [ - "UMT5EncoderModel", - "UMT5ForConditionalGeneration", - "UMT5ForQuestionAnswering", - "UMT5ForSequenceClassification", - "UMT5ForTokenClassification", - "UMT5Model", - "UMT5PreTrainedModel" - ] - } - }, - "info.aet.unispeech-1500h-cv": { - "*": { - "repo": "microsoft/unispeech-large-1500h-cv", - "pkg": { - "0": { - "transformers": "UniSpeechModel" - } - }, - "tasks": [ - "UniSpeechForCTC", - "UniSpeechForPreTraining", - "UniSpeechForSequenceClassification", - "UniSpeechModel", - "UniSpeechPreTrainedModel" - ] - } - }, - "info.aet.unispeech-sat-100h-libri-ft": { - "*": { - "repo": "microsoft/unispeech-sat-base-100h-libri-ft", - "pkg": { - "0": { - "transformers": "UniSpeechSatModel" - } - }, - "tasks": [ - "UniSpeechSatForAudioFrameClassification", - "UniSpeechSatForCTC", - "UniSpeechSatForPreTraining", - "UniSpeechSatForSequenceClassification", - "UniSpeechSatForXVector", - "UniSpeechSatModel", - "UniSpeechSatPreTrainedModel" - ] - } - }, - "info.gan.univnet-dev": { - "*": { - "repo": "dg845/univnet-dev", - "pkg": { - "0": { - "transformers": "UnivNetModel" - } - }, - "tasks": [ - "UnivNetModel" - ] - } - }, - "info.stst.vaultgemma": { - "*": { - "repo": "google/vaultgemma-7b", - "pkg": { - "0": { - "transformers": "VaultGemmaModel" - } - }, - "tasks": [ - "VaultGemmaForCausalLM", - "VaultGemmaModel", - "VaultGemmaPreTrainedModel" - ] - } - }, - "info.vit.videollama3-image-hf": { - "*": { - "repo": "lkhl/VideoLLaMA3-2B-Image-HF", - "pkg": { - "0": { - "transformers": "VideoLlama3Model" - } - }, - "tasks": [ - "VideoLlama3VisionModel", - "VideoLlama3PreTrainedModel", - "VideoLlama3Model", - "VideoLlama3ForConditionalGeneration" - ] - } - }, - "info.vit.video-llava-hf": { - "*": { - "repo": "LanguageBind/Video-LLaVA-7B-hf", - "pkg": { - "0": { - "transformers": "VideoLlavaModel" - } - }, - "tasks": [ - "VideoLlavaPreTrainedModel", - "VideoLlavaModel", - "VideoLlavaForConditionalGeneration" - ] - } - }, - "info.vit.videomae": { - "*": { - "repo": "MCG-NJU/videomae-base", - "pkg": { - "0": { - "transformers": "VideoMAEModel" - } - }, - "tasks": [ - "VideoMAEForPreTraining", - "VideoMAEModel", - "VideoMAEPreTrainedModel", - "VideoMAEForVideoClassification" - ] - } - }, - "info.vit.vilt-b32-mlm": { - "*": { - "repo": "dandelin/vilt-b32-mlm", - "pkg": { - "0": { - "transformers": "ViltModel" - } - }, - "tasks": [ - "ViltForImageAndTextRetrieval", - "ViltForImagesAndTextClassification", - "ViltForTokenClassification", - "ViltForMaskedLM", - "ViltForQuestionAnswering", - "ViltLayer", - "ViltModel", - "ViltPreTrainedModel" - ] - } - }, - "info.vit.vip-llava-hf": { - "*": { - "repo": "ybelkada/vip-llava-7b-hf", - "pkg": { - "0": { - "transformers": "VipLlavaModel" - } - }, - "tasks": [ - "VipLlavaModel", - "VipLlavaForConditionalGeneration", - "VipLlavaPreTrainedModel" - ] - } - }, - "info.vit.japanese-clip-vit-h-14-bert-wider": { - "*": { - "repo": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", - "pkg": { - "0": { - "transformers": "VisionTextDualEncoderModel" - } - }, - "tasks": [ - "VisionTextDualEncoderModel" - ] - } - }, - "info.art.visualbert-vqa-coco-pre": { - "*": { - "repo": "uclanlp/visualbert-vqa-coco-pre", - "pkg": { - "0": { - "transformers": "VisualBertModel" - } - }, - "tasks": [ - "VisualBertForMultipleChoice", - "VisualBertForPreTraining", - "VisualBertForQuestionAnswering", - "VisualBertForRegionToPhraseAlignment", - "VisualBertForVisualReasoning", - "VisualBertLayer", - "VisualBertModel", - "VisualBertPreTrainedModel" - ] - } - }, - "info.vit.vit-patch16-224": { - "*": { - "repo": "google/vit-base-patch16-224", - "pkg": { - "0": { - "transformers": "ViTModel" - } - }, - "tasks": [ - "ViTForImageClassification", - "ViTForMaskedImageModeling", - "ViTModel", - "ViTPreTrainedModel" - ] - } - }, - "info.vit.vit-mae": { - "*": { - "repo": "facebook/vit-mae-base", - "pkg": { - "0": { - "transformers": "ViTMAEModel" - } - }, - "tasks": [ - "ViTMAEForPreTraining", - "ViTMAELayer", - "ViTMAEModel", - "ViTMAEPreTrainedModel" - ] - } - }, - "info.vit.vit-msn": { - "*": { - "repo": "facebook/vit-msn-base", - "pkg": { - "0": { - "transformers": "ViTMSNModel" - } - }, - "tasks": [ - "ViTMSNModel", - "ViTMSNForImageClassification", - "ViTMSNPreTrainedModel" - ] - } - }, - "info.vit.vitdet-patch16-224": { - "*": { - "repo": "google/vitdet-base-patch16-224", - "pkg": { - "0": { - "transformers": "VitDetModel" - } - }, - "tasks": [ - "VitDetModel", - "VitDetPreTrainedModel", - "VitDetBackbone" - ] - } - }, - "info.art.mms-tts-eng": { - "*": { - "repo": "facebook/mms-tts-eng", - "pkg": { - "0": { - "transformers": "VitsModel" - } - }, - "tasks": [ - "VitsModel", - "VitsPreTrainedModel" - ] - } - }, - "info.vit.vivit16x2-kinetics400": { - "*": { - "repo": "google/vivit-b-16x2-kinetics400", - "pkg": { - "0": { - "transformers": "VivitModel" - } - }, - "tasks": [ - "VivitModel", - "VivitPreTrainedModel", - "VivitForVideoClassification" - ] - } - }, - "info.vit.vjepa2-vitl-fpc64-256": { - "*": { - "repo": "facebook/vjepa2-vitl-fpc64-256", - "pkg": { - "0": { - "transformers": "VJEPA2Model" - } - }, - "tasks": [ - "VJEPA2Model", - "VJEPA2PreTrainedModel", - "VJEPA2ForVideoClassification" - ] - } - }, - "info.stst.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralForConditionalGeneration" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.aet.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralEncoder" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.aet.wav2vec2-960h": { - "*": { - "repo": "facebook/wav2vec2-base-960h", - "pkg": { - "0": { - "transformers": "Wav2Vec2Model" - } - }, - "tasks": [ - "Wav2Vec2ForAudioFrameClassification", - "Wav2Vec2ForCTC", - "Wav2Vec2ForMaskedLM", - "Wav2Vec2ForPreTraining", - "Wav2Vec2ForSequenceClassification", - "Wav2Vec2ForXVector", - "Wav2Vec2Model", - "Wav2Vec2PreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-bert-rel-pos": { - "*": { - "repo": "facebook/w2v-bert-2.0", - "pkg": { - "0": { - "transformers": "Wav2Vec2BertModel" - } - }, - "tasks": [ - "Wav2Vec2BertForAudioFrameClassification", - "Wav2Vec2BertForCTC", - "Wav2Vec2BertForSequenceClassification", - "Wav2Vec2BertForXVector", - "Wav2Vec2BertModel", - "Wav2Vec2BertPreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-conformer-rel-pos": { - "*": { - "repo": "facebook/wav2vec2-conformer-rel-pos-large", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerModel" - } - }, - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.aet.wavlm": { - "*": { - "repo": "microsoft/wavlm-base", - "pkg": { - "0": { - "transformers": "WavLMModel" - } - }, - "tasks": [ - "WavLMForAudioFrameClassification", - "WavLMForCTC", - "WavLMForSequenceClassification", - "WavLMForXVector", - "WavLMModel", - "WavLMPreTrainedModel" - ] - } - }, - "info.aet.whisper": { - "*": { - "repo": "openai/whisper-tiny", - "pkg": { - "0": { - "transformers": "WhisperModel" - } - }, - "tasks": [ - "WhisperForCausalLM", - "WhisperForConditionalGeneration", - "WhisperModel", - "WhisperPreTrainedModel", - "WhisperForAudioClassification" - ] - } - }, - "info.vit.xclip-patch32": { - "*": { - "repo": "microsoft/xclip-base-patch32", - "pkg": { - "0": { - "transformers": "XCLIPModel" - } - }, - "tasks": [ - "XCLIPModel", - "XCLIPPreTrainedModel", - "XCLIPTextModel", - "XCLIPVisionModel" - ] - } - }, - "info.gan.x-codec": { - "*": { - "repo": "Manel/X-Codec", - "pkg": { - "0": { - "transformers": "XcodecModel" - } - }, - "tasks": [ - "XcodecModel", - "XcodecPreTrainedModel" - ] - } - }, - "info.art.xglm": { - "*": { - "repo": "facebook/xglm-564M", - "pkg": { - "0": { - "transformers": "XGLMModel" - } - }, - "tasks": [ - "XGLMForCausalLM", - "XGLMModel", - "XGLMPreTrainedModel" - ] - } - }, - "info.art.xlm-mlm-en-2048": { - "*": { - "repo": "FacebookAI/xlm-mlm-en-2048", - "pkg": { - "0": { - "transformers": "XLMModel" - } - }, - "tasks": [ - "XLMForMultipleChoice", - "XLMForQuestionAnswering", - "XLMForQuestionAnsweringSimple", - "XLMForSequenceClassification", - "XLMForTokenClassification", - "XLMModel", - "XLMPreTrainedModel", - "XLMWithLMHeadModel" - ] - } - }, - "info.art.xlm-roberta": { - "*": { - "repo": "FacebookAI/xlm-roberta-base", - "pkg": { - "0": { - "transformers": "XLMRobertaModel" - } - }, - "tasks": [ - "XLMRobertaForCausalLM", - "XLMRobertaForMaskedLM", - "XLMRobertaForMultipleChoice", - "XLMRobertaForQuestionAnswering", - "XLMRobertaForSequenceClassification", - "XLMRobertaForTokenClassification", - "XLMRobertaModel", - "XLMRobertaPreTrainedModel" - ] - } - }, - "info.art.xlm-roberta-xl": { - "*": { - "repo": "facebook/xlm-roberta-xl", - "pkg": { - "0": { - "transformers": "XLMRobertaXLModel" - } - }, - "tasks": [ - "XLMRobertaXLForCausalLM", - "XLMRobertaXLForMaskedLM", - "XLMRobertaXLForMultipleChoice", - "XLMRobertaXLForQuestionAnswering", - "XLMRobertaXLForSequenceClassification", - "XLMRobertaXLForTokenClassification", - "XLMRobertaXLModel", - "XLMRobertaXLPreTrainedModel" - ] - } - }, - "info.art.xlnet-cased": { - "*": { - "repo": "xlnet/xlnet-large-cased", - "pkg": { - "0": { - "transformers": "XLNetModel" - } - }, - "tasks": [ - "XLNetForMultipleChoice", - "XLNetForQuestionAnswering", - "XLNetForQuestionAnsweringSimple", - "XLNetForSequenceClassification", - "XLNetForTokenClassification", - "XLNetLMHeadModel", - "XLNetModel", - "XLNetPreTrainedModel" - ] - } - }, - "info.lstm.xlstm": { - "*": { - "repo": "NX-AI/xLSTM-7b", - "pkg": { - "0": { - "transformers": "xLSTMModel" - } - }, - "tasks": [ - "xLSTMForCausalLM", - "xLSTMModel", - "xLSTMPreTrainedModel" - ] - } - }, - "info.art.xmod": { - "*": { - "repo": "facebook/xmod-base", - "pkg": { - "0": { - "transformers": "XmodModel" - } - }, - "tasks": [ - "XmodForCausalLM", - "XmodForMaskedLM", - "XmodForMultipleChoice", - "XmodForQuestionAnswering", - "XmodForSequenceClassification", - "XmodForTokenClassification", - "XmodModel", - "XmodPreTrainedModel" - ] - } - }, - "info.cnn.yolos": { - "*": { - "repo": "hustvl/yolos-base", - "pkg": { - "0": { - "transformers": "YolosModel" - } - }, - "tasks": [ - "YolosForObjectDetection", - "YolosModel", - "YolosPreTrainedModel" - ] - } - }, - "info.art.yoso-4096": { - "*": { - "repo": "uw-madison/yoso-4096", - "pkg": { - "0": { - "transformers": "YosoModel" - } - }, - "tasks": [ - "YosoForMaskedLM", - "YosoForMultipleChoice", - "YosoForQuestionAnswering", - "YosoForSequenceClassification", - "YosoForTokenClassification", - "YosoLayer", - "YosoModel", - "YosoPreTrainedModel" - ] - } - }, - "info.ssm.zamba-v1": { - "*": { - "repo": "Zyphra/Zamba-7B-v1", - "pkg": { - "0": { - "transformers": "ZambaModel" - } - }, - "tasks": [ - "ZambaForCausalLM", - "ZambaForSequenceClassification", - "ZambaModel", - "ZambaPreTrainedModel" - ] - } - }, - "info.ssm.zamba2": { - "*": { - "repo": "Zyphra/Zamba2-2.7B", - "pkg": { - "0": { - "transformers": "Zamba2Model" - } - }, - "tasks": [ - "Zamba2ForCausalLM", - "Zamba2ForSequenceClassification", - "Zamba2Model", - "Zamba2PreTrainedModel" - ] - } - }, - "ops.precision.uint": { - "U8": { - "pkg": { - "0": { - "torch": { - "uint8": { - "variant": "uint8" - } - } - } - } - }, - "U16": { - "pkg": { - "0": { - "torch": { - "uint16": { - "variant": "uint16" - } - } - } - } - }, - "U32": { - "pkg": { - "0": { - "torch": { - "uint32": { - "variant": "uint32" - } - } - } - } - }, - "U64": { - "pkg": { - "0": { - "torch": { - "uint64": { - "variant": "uint64" - } - } - } - } - }, - "U1": { - "pkg": { - "0": { - "torch": { - "uint1": { - "variant": "uint1" - } - } - } - } - }, - "U2": { - "pkg": { - "0": { - "torch": { - "uint2": { - "variant": "uint2" - } - } - } - } - }, - "U3": { - "pkg": { - "0": { - "torch": { - "uint3": { - "variant": "uint3" - } - } - } - } - }, - "U4": { - "pkg": { - "0": { - "torch": { - "uint4": { - "variant": "uint4" - } - } - } - } - }, - "U5": { - "pkg": { - "0": { - "torch": { - "uint5": { - "variant": "uint5" - } - } - } - } - }, - "U6": { - "pkg": { - "0": { - "torch": { - "uint6": { - "variant": "uint6" - } - } - } - } - }, - "U7": { - "pkg": { - "0": { - "torch": { - "uint7": { - "variant": "uint7" - } - } - } - } - } - }, - "ops.precision.int": { - "I8": { - "pkg": { - "0": { - "torch": { - "int8": { - "variant": "int8" - } - } - } - } - }, - "I16": { - "pkg": { - "0": { - "torch": { - "int16": { - "variant": "int16" - } - } - } - } - }, - "I32": { - "pkg": { - "0": { - "torch": { - "int32": { - "variant": "int32" - } - } - } - } - }, - "I64": { - "pkg": { - "0": { - "torch": { - "int64": { - "variant": "int64" - } - } - } - } - }, - "Q8": { - "pkg": { - "0": { - "torch": { - "qint8": { - "variant": "qint8" - } - } - } - } - }, - "Q32": { - "pkg": { - "0": { - "torch": { - "qint32": { - "variant": "qint32" - } - } - } - } - }, - "I1": { - "pkg": { - "0": { - "torch": { - "int1": { - "variant": "int1" - } - } - } - } - }, - "I2": { - "pkg": { - "0": { - "torch": { - "int2": { - "variant": "int2" - } - } - } - } - }, - "I3": { - "pkg": { - "0": { - "torch": { - "int3": { - "variant": "int3" - } - } - } - } - }, - "I4": { - "pkg": { - "0": { - "torch": { - "int4": { - "variant": "int4" - } - } - } - } - }, - "I5": { - "pkg": { - "0": { - "torch": { - "int5": { - "variant": "int5" - } - } - } - } - }, - "I6": { - "pkg": { - "0": { - "torch": { - "int6": { - "variant": "int6" - } - } - } - } - }, - "I7": { - "pkg": { - "0": { - "torch": { - "int7": { - "variant": "int7" - } - } - } - } - } - }, - "ops.precision.float": { - "F16": { - "pkg": { - "0": { - "torch": { - "float16": { - "variant": "fp16" - } - } - } - } - }, - "F32": { - "pkg": { - "0": { - "torch": { - "float32": { - "variant": "fp32" - } - } - } - } - }, - "F64": { - "pkg": { - "0": { - "torch": { - "float64": { - "variant": "fp64" - } - } - } - } - }, - "F8_E5M2": { - "pkg": { - "0": { - "torch": { - "float8_e5m2": { - "variant": "fp8_e5m2" - } - } - } - } - }, - "F8_E4M3": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fn": { - "variant": "fp8_e4m3fn" - } - } - } - } - }, - "F8_E5M2FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e5m2fnuz": { - "variant": "fp8_e5m2fnuz" - } - } - } - } - }, - "F8_E4M3FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fnuz": { - "variant": "fp8_e4m3fnuz" - } - } - } - } - }, - "F8_E8M0FNU": { - "pkg": { - "0": { - "torch": { - "float8_e8m0fnu": { - "variant": "fp8_e8m0fnu" - } - } - } - } - }, - "F8_E2M1": { - "pkg": { - "0": { - "torch": { - "float4_e2m1fn_x2": { - "variant": "fp4_e2m1fn_x2" - } - } - } - } - } - }, - "ops.precision.complex": { - "C32": { - "pkg": { - "0": { - "torch": { - "complex32": { - "variant": "complex32" - } - } - } - } - }, - "C64": { - "pkg": { - "0": { - "torch": { - "complex64": { - "variant": "complex64" - } - } - } - } - }, - "C128": { - "pkg": { - "0": { - "torch": { - "complex128": { - "variant": "complex128" - } - } - } - } - } - }, - "ops.precision.bool": { - "Bbool": { - "pkg": { - "0": { - "torch": { - "bool": { - "variant": "bool" - } - } - } - } - } - }, - "ops.precision.quint": { - "Q8": { - "pkg": { - "0": { - "torch": { - "quint8": { - "variant": "quint8" - } - } - } - } - }, - "Q4x2": { - "pkg": { - "0": { - "torch": { - "quint4x2": { - "variant": "quint4x2" - } - } - } - } - }, - "Q2x4": { - "pkg": { - "0": { - "torch": { - "quint2x4": { - "variant": "quint2x4" - } - } - } - } - } - }, - "ops.precision.bfloat": { - "B16": { - "pkg": { - "0": { - "torch": { - "bfloat16": { - "variant": "bf16" - } - } - } - } - } - }, - "ops.precision.bits": { - "B1x8": { - "pkg": { - "0": { - "torch": { - "bits1x8": { - "variant": "bits1x8" - } - } - } - } - }, - "B2x4": { - "pkg": { - "0": { - "torch": { - "bits2x4": { - "variant": "bits2x4" - } - } - } - } - }, - "B4x2": { - "pkg": { - "0": { - "torch": { - "bits4x2": { - "variant": "bits4x2" - } - } - } - } - }, - "B8": { - "pkg": { - "0": { - "torch": { - "bits8": { - "variant": "bits8" - } - } - } - } - }, - "B16": { - "pkg": { - "0": { - "torch": { - "bits16": { - "variant": "bits16" - } - } - } - } - } - }, - "ops.scheduler.amused": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "AmusedScheduler", - "module_path": "diffusers.schedulers.scheduling_amused" - } - } - } - }, - "ops.scheduler.cmstochasticiterative": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CMStochasticIterativeScheduler", - "module_path": "diffusers.schedulers.scheduling_consistency_models" - } - } - } - }, - "ops.scheduler.cogvideoxddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_cogvideox" - } - } - } - }, - "ops.scheduler.cogvideoxdpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_dpm_cogvideox" - } - } - } - }, - "ops.scheduler.ddiminverse": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_inverse" - } - } - } - }, - "ops.scheduler.ddimparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_parallel" - } - } - } - }, - "ops.scheduler.ddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim" - } - } - } - }, - "ops.scheduler.ddpmparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_parallel" - } - } - } - }, - "ops.scheduler.ddpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm" - } - } - } - }, - "ops.scheduler.ddpmwuerstchen": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMWuerstchenScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_wuerstchen" - } - } - } - }, - "ops.scheduler.deis": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DEISMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_deis_multistep" - } - } - } - }, - "ops.scheduler.dpminverse": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep_inverse" - } - } - } - }, - "ops.scheduler.dpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.dpmsinglestep": { - "solver": { - "pkg": { - "0": { - "diffusers": "DPMSolverSinglestepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_singlestep" - } - } - } - }, - "ops.scheduler.edmdpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "EDMDPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.edmeuler": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "EDMEulerScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_euler" - } - } - } - }, - "ops.scheduler.eulerancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerAncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_ancestral_discrete" - } - } - } - }, - "ops.scheduler.euler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatcheuler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchEulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatchheun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchHeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_heun_discrete" - } - } - } - }, - "ops.scheduler.flowmatchlcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "FlowMatchLCMScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_lcm" - } - } - } - }, - "ops.scheduler.heun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "HeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_heun_discrete" - } - } - } - }, - "ops.scheduler.ipndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "IPNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_ipndm" - } - } - } - }, - "ops.scheduler.karrasve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "KarrasVeScheduler", - "module_path": "diffusers.schedulers.deprecated.scheduling_karras_ve" - } - } - } - }, - "ops.scheduler.kdpm2ancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2AncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete" - } - } - } - }, - "ops.scheduler.kdpm2": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2DiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_discrete" - } - } - } - }, - "ops.scheduler.lcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "LCMScheduler", - "module_path": "diffusers.schedulers.scheduling_lcm" - } - } - } - }, - "ops.scheduler.pndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "PNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_pndm" - } - } - } - }, - "ops.scheduler.repaint": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "RePaintScheduler", - "module_path": "diffusers.schedulers.scheduling_repaint" - } - } - } - }, - "ops.scheduler.sa": { - "solver": { - "pkg": { - "0": { - "diffusers": "SASolverScheduler", - "module_path": "diffusers.schedulers.scheduling_sasolver" - } - } - } - }, - "ops.scheduler.scm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "SCMScheduler", - "module_path": "diffusers.schedulers.scheduling_scm" - } - } - } - }, - "ops.scheduler.scoresdeve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "ScoreSdeVeScheduler", - "module_path": "diffusers.schedulers.scheduling_sde_ve" - } - } - } - }, - "ops.scheduler.tcd": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "TCDScheduler", - "module_path": "diffusers.schedulers.scheduling_tcd" - } - } - } - }, - "ops.scheduler.unclip": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "UnCLIPScheduler", - "module_path": "diffusers.schedulers.scheduling_unclip" - } - } - } - }, - "ops.scheduler.unipc": { - "multistep": { - "pkg": { - "0": { - "diffusers": "UniPCMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_unipc_multistep" - } - } - } - }, - "ops.scheduler.vqdiffusion": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "VQDiffusionScheduler", - "module_path": "diffusers.schedulers.scheduling_vq_diffusion" - } - } - } - }, - "ops.scheduler.karrasdiffusion": { - "schedulers": { - "pkg": { - "0": { - "diffusers": "KarrasDiffusionSchedulers", - "module_path": "diffusers.schedulers.scheduling_utils" - } - } - } - }, - "info.lora.dmd": { - "stable-diffusion-xl-1": { - "repo": "tianweiy/DMD2", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "timesteps": [ - 999, - 749, - 499, - 249 - ] - }, - "scheduler": { - "ops.scheduler.lcm": "" - } - } - }, - "file_256": [ - "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", - "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb" - ] - } - }, - "info.lora.dpo": { - "stable-diffusion-xl-1": { - "repo": "radames/sdxl-DPO-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5, - "num_inference_steps": 4 - }, - "scheduler": { - "ops.scheduler.dpm": { - "algorithm_type": "sde-dpmsolver++", - "use_karras_sigmas": true, - "order": 2 - } - } - } - }, - "file_256": [ - "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", - "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad" - ] - } - }, - "info.lora.flash": { - "stable-diffusion-xl-1": { - "repo": "jasperai/flash-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": "ops.scheduler.lcm" - } - }, - "file_256": [ - "afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7" - ] - }, - "pixart-alpha": { - "repo": "jasperai/flash-pixart", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b" - ] - }, - "stable-diffusion-3": { - "repo": "jasperai/flash-sd3", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15" - ] - }, - "stable-diffusion-v1-5": { - "repo": "jasperai/flash-sd", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - }, - "file_256": [ - "99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f" - ] - } - }, - "info.lora.hyper": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - } - } - }, - "file_256": { - "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": { - "num_inference_steps": 12 - }, - "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": { - "num_inference_steps": 8 - }, - "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "flux1-dev": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": { - "num_inference_steps": 16 - }, - "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": { - "num_inference_steps": 4 - }, - "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": { - "num_inference_steps": 8 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": { - "num_inference_steps": 12 - }, - "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": { - "num_inference_steps": 8 - }, - "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - } - }, - "info.lora.lcm": { - "stable-diffusion-xl-1": { - "repo": "latent-consistency/lcm-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141" - ] - }, - "ssd": { - "repo": "latent-consistency/lcm-lora-ssd-1b", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b" - ] - }, - "segmind-vega": { - "repo": "segmind/Segmind-VegaRT", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "gen_kwargs": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb" - ] - }, - "stable-diffusion-v1-5": { - "repo": "latent-consistency/lcm-lora-sdv1-5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4" - ] - } - }, - "info.lora.lightning": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/SDXL-Lightning", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - } - } - }, - "info.lora.pcm": { - "stable-diffusion-xl-1": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": { - "num_inference_steps": 16 - }, - "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": { - "num_inference_steps": 16 - }, - "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": { - "num_inference_steps": 4 - }, - "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": { - "num_inference_steps": 4 - }, - "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": { - "num_inference_steps": 8 - }, - "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": { - "num_inference_steps": 8 - }, - "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - }, - "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": { - "num_inference_steps": 16 - }, - "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": { - "num_inference_steps": 4 - }, - "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": { - "num_inference_steps": 8 - }, - "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": { - "num_inference_steps": 2, - "guidance_scale": 1.2 - }, - "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - } - } - } - }, - "info.lora.slam": { - "stable-diffusion-xl-1": { - "repo": "alimama-creative/slam-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 1 - } - } - }, - "file_256": [ - "22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91" - ] - }, - "stable-diffusion-v1-5": { - "repo": "alimama-creative/slam-sd1.5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - } - } - }, - "info.lora.spo": { - "stable-diffusion-xl-1": { - "repo": "SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df" - ] - }, - "stable-diffusion-v1-5": { - "repo": "SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5 - } - } - }, - "file_256": [ - "1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4" - ] - } - }, - "info.lora.tcd": { - "stable-diffusion-xl-1": { - "repo": "h1t/TCD-SDXL-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "eta": 0.3 - }, - "scheduler": { - "ops.scheduler.tcd": {} - } - } - }, - "file_256": [ - "2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba" - ] - }, - "stable-diffusion-v1-5": { - "repo": "h1t/TCD-SD15-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232" - ], - "layer_256": [ - "e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75" - ], - "layer_b3": [ - "90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b" - ] - } - }, - "info.lora.turbo": { - "stable-diffusion-xl-1": { - "file_256": [ - "a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69" - ] - }, - "flux1-dev": { - "repo": "alimama-creative/FLUX.1-Turbo-Alpha", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - }, - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 8, - "max_sequence_length": 512 - } - } - }, - "file_256": [ - "77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff" - ] - }, - "stable-diffusion-3": { - "repo": "tensorart/stable-diffusion-3.5-large-TurboX", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.flow-match": { - "shift": 5 - } - } - } - }, - "file_256": { - "fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": { - "num_inference_steps": "8" - } - } - } - }, - "info.art.audiogen": { - "*": { - "repo": "facebook/audiogen-medium", - "pkg": { - "0": { - "audiocraft": "models.AudioGen", - "generation": { - "duration": 5 - }, - "stage_2": { - "audiocraft": ".data.audioaudio_write", - "generation": { - "strategy": "loudness", - "loudness_compressor": true - } - } - } - } - } - }, - "info.art.parler-tts-v1": { - "*": { - "repo": "parler-tts/parler-tts-large-v1", - "pkg": { - "0": { - "parler_tts": "ParlerTTSForConditionalGeneration", - "generation": { - "return_tensors": "pt" - } - } - } - } - }, - "info.gan.snac-st": { - "*": { - "repo": "Zuellni/snac-24khz-ST", - "pkg": { - "0": { - "snac": "SNAC" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio" - } - }, - "file_256": [ - "e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", - "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d" - ], - "layer_256": [ - "35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", - "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841" - ], - "layer_b3": [ - "18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", - "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119" - ] - } - }, - "info.gan.kokoro": { - "*": { - "repo": "hexgrad/Kokoro-82M", - "pkg": { - "0": { - "kokoro": "KPipeline" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", - "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4" - ], - "layer_256": [ - "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", - "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b" - ], - "layer_b3": [ - "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", - "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", - "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e932dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92" - ] - } - }, - "info.stst.silero-vad": { - "*": { - "repo": "freddyaboulton/silero-vad", - "pkg": { - "0": { - "onnx": "onnx" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9" - ], - "layer_256": [ - "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd" - ], - "layer_b3": [ - "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", - "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", - "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", - "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e" - ] - } - }, - "info.stst.wav2vec2-conformer-rope-960h-ft": { - "*": { - "repo": "facebook/wav2vec2-conformer-rope-large-960h-ft", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerForCTC" - } - }, - "file_256": [ - "97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d" - ], - "layer_256": [ - "1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d" - ], - "layer_b3": [ - "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" - ], - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.art.orpheus-0-ft": { - "*": { - "repo": "canopylabs/orpheus-3b-0.1-ft", - "pkg": { - "0": { - "orpheus_tts": "OrpheusModel", - "generation": { - "max_model_len": 2048 - } - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.art.outetts-0": { - "*": { - "repo": "OuteAI/OuteTTS-0.3-1B", - "pkg": { - "0": { - "outetts": "InterfaceHF" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.gan.speecht5-hifigan": { - "*": { - "file_256": [ - "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c" - ], - "layer_256": [ - "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770" - ], - "layer_b3": [ - "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956" - ] - } - }, - "info.dit.flux1-dev": { - "mystic": { - "repo": "enhanceaiteam/Mystic", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 16, - "guidance_scale": 7.5, - "width": 768, - "height": 1024 - } - } - }, - "file_256": [ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" - ], - "layer_256": [ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" - ], - "layer_b3": [ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" - ] - }, - "flux1-lite": { - "repo": "freepik/flux.1-lite-8b", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 28 - } - } - }, - "file_256": [ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" - ], - "layer_256": [ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" - ], - "layer_b3": [ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" - ] - }, - "f-lite": { - "repo": "freepik/f-lite", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "f-lite-texture": { - "repo": "freepik/f-lite-texture", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "flux": { - "repo": "TencentARC/flux-mini", - "file_256": [ - "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" - ], - "layer_256": [ - "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" - ], - "layer_b3": [ - "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" - ] - }, - "flex2": { - "repo": "ostris/Flex.2-preview", - "file_256": [ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" - ], - "layer_256": [ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" - ], - "layer_b3": [ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" - ] - }, - "flex1-alpha": { - "repo": "ostris/Flex.1-alpha", - "file_256": [ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" - ], - "layer_256": [ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" - ], - "layer_b3": [ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" - ] - }, - "*": { - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 3.5, - "num_inference_steps": 50, - "max_sequence_length": 512 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "gudance": 3.5, - "num_inference_steps": 25 - } - } - }, - "file_256": [ - "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", - "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", - "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", - "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", - "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" - ], - "layer_b3": [ - "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", - "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", - "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" - ], - "layer_256": [ - "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", - "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", - "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" - ], - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "tasks": [ - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - } - }, - "info.dit.wan2-flf2v-720p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", - "file_256": [ - "", - "" - ], - "layer_256": [ - "" - ], - "layer_b3": [ - "" - ] - } - }, - "ops.patch.hidiffusion": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "hidiffusion": { - "apply_hidiffusion": { - "timesteps": "StableDiffusionXLTimesteps" - } - }, - "generation": { - "height": 2048, - "width": 2048, - "eta": 1.0, - "guidance_scale": 7.5, - "num_inference_steps": 10 - } - } - } - } - }, - "ops.scheduler.align-your-steps": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "diffusers": "schedulers.scheduling_utils.AysSchedules", - "generation": { - "timesteps": "StableDiffusionXLTimesteps", - "num_inference_steps": 10 - } - } - } - } - }, - "info.art.chameleon": { - "lumina-mgpt-1024": { - "repo": "Alpha-VLLM/Lumina-mGPT-7B-1024", - "pkg": { - "0": { - "inference_solver": { - "FlexARInferenceSolver": { - "precision": "bf16", - "target_size": 768 - } - }, - "generation": { - "images": [], - "qas": [ - [ - "q1", - null - ] - ], - "max_gen_len": 8192, - "temperature": 1.0 - } - }, - "1": { - "inference_solver": "ChameleonXLLMXForConditionalGeneration" - } - }, - "file_256": [ - "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", - "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", - "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", - "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b" - ], - "layer_256": [ - "eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25" - ], - "layer_b3": [ - "6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656" - ] - } - }, - "info.vit.clip-vit-patch14": { - "*": { - "repo": "openai/clip-vit-large-patch14", - "pkg": { - "0": { - "transformers": "CLIPTextModel" - } - }, - "file_256": [ - "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", - "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", - "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", - "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", - "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", - "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", - "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", - "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", - "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", - "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", - "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", - "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", - "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", - "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", - "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", - "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", - "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1" - ], - "layer_256": [ - "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", - "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", - "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", - "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", - "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", - "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", - "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", - "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", - "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", - "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", - "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", - "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", - "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3" - ], - "layer_b3": [ - "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", - "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", - "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", - "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", - "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", - "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", - "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", - "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", - "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", - "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", - "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", - "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", - "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", - "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", - "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", - "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-g-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-g-14-laion2B-s12B-b42K", - "pkg": { - "0": { - "transformers": "CLIPTextModelWithProjection" - } - }, - "file_256": [ - "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", - "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", - "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", - "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", - "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", - "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", - "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", - "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", - "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", - "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b" - ], - "layer_256": [ - "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", - "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", - "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", - "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", - "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", - "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", - "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46" - ], - "layer_b3": [ - "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", - "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", - "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", - "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", - "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", - "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", - "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-h-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K", - "pkg": { - "0": { - "transformers": "CLIPModel" - } - }, - "file_256": [ - "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", - "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", - "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161" - ], - "layer_256": [ - "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", - "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", - "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c" - ], - "layer_b3": [ - "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", - "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", - "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.aet.chatglm3": { - "*": { - "repo": "zai-org/chatglm3-6b", - "pkg": { - "0": { - "transformers": "AutoModel" - } - }, - "file_256": [ - "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", - "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d" - ], - "layer_256": [ - "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44" - ], - "layer_b3": [ - "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481" - ] - } - }, - "info.art.qwen2": { - "bagel-mot": { - "repo": "ByteDance-Seed/BAGEL-7B-MoT", - "pkg": { - "0": { - "Bagel": "app" - } - } - } - }, - "info.vae.tae": { - "stable-diffusion-3": { - "repo": "madebyollin/taesd3", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399" - ] - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/taesdxl", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f" - ] - }, - "stable-diffusion-v1-5": { - "repo": "madebyollin/taesd", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549" - ] - }, - "flux1-dev": { - "repo": "madebyollin/taef1", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449" - ] - } - }, - "info.vae.kl": { - "qwen-image": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLQwenImage" - } - }, - "file_256": [ - "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344" - ], - "layer_256": [ - "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc" - ], - "layer_b3": [ - "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b" - ] - }, - "ltx-video": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLLTXVideo" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "allegro": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLAllegro" - } - }, - "file_256": [ - "47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a" - ], - "layer_256": [ - "bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f" - ], - "layer_b3": [ - "93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0" - ] - }, - "cosmos-1-diffusion-video2world": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCosmos" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "easyanimatev5-zh": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMagvit" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "hunyuanvideo-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLHunyuanVideo" - } - }, - "file_256": [ - "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", - "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", - "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", - "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0" - ] - }, - "mochi-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMochi" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "audioldm-s-v2": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5" - ], - "layer_256": [ - "54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6" - ], - "layer_b3": [ - "00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de" - ] - }, - "stable-video-diffusion-img2vid-xt": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLTemporalDecoder" - } - } - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/sdxl-vae-fp16-fix", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", - "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", - "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", - "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", - "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", - "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", - "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", - "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0" - ] - }, - "stable-diffusion-xl-1*": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", - "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", - "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74" - ] - }, - "shuttle-jaguar": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904" - ], - "layer_256": [ - "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b" - ], - "layer_b3": [ - "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", - "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0" - ] - }, - "flux1-dev": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", - "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", - "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", - "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc" - ], - "layer_256": [ - "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", - "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", - "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", - "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80" - ], - "layer_b3": [ - "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", - "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903" - ] - }, - "musicldm": { - "file_256": [ - "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4" - ], - "layer_256": [ - "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f" - ], - "layer_b3": [ - "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0" - ] - }, - "stable-diffusion-v1-5": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", - "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", - "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", - "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", - "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", - "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", - "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", - "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c" - ], - "layer_256": [ - "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", - "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3" - ], - "layer_b3": [ - "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", - "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833" - ] - } - }, - "info.vae.wan": { - "wan2-i2v-480p": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLWan", - "precision": "ops.precision.float.F32" - } - }, - "file_256": [ - "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", - "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b" - ], - "layer_256": [ - "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", - "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e" - ], - "layer_b3": [ - "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", - "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433" - ] - }, - "skyreels-v2-t2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "skyreels-v2-i2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.cogvideox": { - "cogvideox-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCogVideoX" - } - }, - "file_256": [ - "a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e" - ], - "layer_256": [ - "43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e" - ], - "layer_b3": [ - "246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb" - ] - }, - "cogvideox-fun-v-pose": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "consisid": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.dc": { - "sana-1024px-bf16": { - "pkg": { - "0": { - "diffusers": "AutoencoderDC" - } - }, - "file_256": [ - "15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f" - ], - "layer_256": [ - "abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde" - ], - "layer_b3": [ - "cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0" - ] - } - }, - "info.vae.oobleck": { - "stable-audio-open-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderOobleck" - } - } - } - }, - "info.vae.eq": { - "stable-diffusion-xl-1": { - "repo": "KBlueLeaf/EQ-SDXL-VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - }, - "info.vae.ms-lc-eq": { - "stable-diffusion-xl-1": { - "repo": "Anzhc/MS-LC-EQ-D-VR_VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - } -} \ No newline at end of file diff --git a/mir/spec/__init__.py b/mir/spec/__init__.py index 618a5cc..4e29e96 100644 --- a/mir/spec/__init__.py +++ b/mir/spec/__init__.py @@ -1,18 +1,14 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # - import urllib.parse from collections import defaultdict from dataclasses import dataclass -from logging import INFO, Logger from pathlib import Path from typing import Any, Callable, Dict, List, Optional, TypeVar, Union from pydantic import BaseModel, create_model -nfo_obj = Logger(INFO) -nfo = nfo_obj.info T = TypeVar("T") @@ -188,7 +184,7 @@ def __init__(self, series: str) -> None: self.compatibility = defaultdict(dict) self.flat_dict = defaultdict(dict) - def add_compat(self, compat_label: str, compat_obj: Dict[str, int | float | list | str]) -> None: + def add_compat(self, compat_label: str, compat_obj: Dict[str, Any]) -> None: """Add compatibility: Attribute an object to a sub-class of the Series""" self.compatibility[compat_label] = compat_obj @@ -278,7 +274,7 @@ def to_dict(self) -> Dict[str, Any]: return self.flat_dict -def mir_entry(domain: str, arch: str, series: str, comp: str, **kwargs) -> None: +def mir_entry(domain: str, arch: str, series: str, comp: str, **kwargs) -> dict[str, Any]: """Define a new Machine Intelligence Resource\n :param domain: Broad name of the type of data (model/ops/info/dev) :param arch: Common name of the neural network structure being referenced @@ -297,18 +293,10 @@ def mir_entry(domain: str, arch: str, series: str, comp: str, **kwargs) -> None: return domain_inst.to_dict() -# def create_model_tag(model_header,metadata_dict): -# parse_file = parse_model_header(model_header) -# reconstructed_file_path = os.path.join(disk_path,each_file) -# attribute_dict = metadata_dict | {"disk_path": reconstructed_file_path} -# file_metadata = parse_file | attribute_dict -# index_tag = create_model_tag(file_metadata) -# - - def main(): """Add a single entry to MIR database\n""" import argparse + from mir.maid import MIRDatabase parser = argparse.ArgumentParser( @@ -337,15 +325,19 @@ def main(): parser.add_argument("-a", "--arch", type=str, help=" Common name of the neural network structure being referenced") parser.add_argument("-s", "--series", type=str, help="Specific release title or technique") parser.add_argument("-c", "--comp", "--compatibility", type=str, help="Details about purpose, tasks") - parser.add_argument( - "-k", "--kwargs", "--keyword-arguments", type=dict[str | int, str | int | dict | list], help="Keyword arguments to pass to function constructors (default: NOne)" - ) + parser.add_argument("-k", "--kwargs", "--keyword-arguments", help="Keyword arguments to pass to function constructors (default: None)") args = parser.parse_args() mir_db = MIRDatabase() mir_db.add( - mir_entry(domain=args.domain, arch=args.arch, series=args.series, comp=args.compatibility, **args.kwargs), + mir_entry( + domain=args.domain, + arch=args.arch, + series=args.series, + comp=args.compatibility, + **args.kwargs, + ), ) mir_db.write_to_disk() diff --git a/mir/spec/versions.json b/mir/spec/regex.json similarity index 68% rename from mir/spec/versions.json rename to mir/spec/regex.json index 0fe7908..4430d31 100644 --- a/mir/spec/versions.json +++ b/mir/spec/regex.json @@ -1,4 +1,7 @@ { + "breaking": ".*(?:-)(prior)$|.*(?:-)(diffusers)$|.*[_-](\\d{3,4}px|-T2V$|-I2V$)", + "search": "\\d+[._-]?\\d+[BbMmKk](it)?|[._-]\\d+[BbMmKk](it)?", + "parameters": "(\\d{1,4}[KkMmBb]|[._-]\\d+[\\._-]\\d+[Bb][._-]).*?$", "semantic": [ "-?\\d+[bBmMkK]", "-?v\\d+", @@ -8,7 +11,7 @@ "-large$", "-medium$" ], - "suffixes": [ + "suffix": [ "-\\d{1,2}[bBmMkK]", "-\\d[1-9][bBmMkK]", "-v\\d{1,2}", diff --git a/mir/tag.py b/mir/tag.py index 3c1fec4..6cb4d16 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -2,7 +2,7 @@ # from typing import Any -from mir.config.constants import PARAMETERS_SUFFIX, BREAKING_SUFFIX, ClassMapEntry +from mir import PARAMETERS, BREAKING, SEARCH def tag_model_from_repo(repo_title: str, decoder=False, data: dict | None = None) -> tuple[str, Any]: @@ -28,14 +28,14 @@ def tag_model_from_repo(repo_title: str, decoder=False, data: dict | None = None parts = repo_title.split("_") subtraction_prefixes = r"\d.b-|\-rl|tiny|large|mlx|onnx|gguf|medium|base|multimodal|mini|instruct|full|:latest|preview|small|pro|beta|hybrid|plus|dpo|community" - pattern_2 = re.compile(PARAMETERS_SUFFIX) + pattern_2 = re.compile(PARAMETERS) clean_parts = [re.sub(pattern_2, "", segment.lower()) for segment in parts] cleaned_string = "-".join([x for x in clean_parts if x]) cleaned_string = re.sub(subtraction_prefixes, "", cleaned_string) cleaned_string = re.sub("-it", "", cleaned_string.replace("-bit", "")).replace("--", "-") cleaned_string = cleaned_string.replace("-b-", "") # print(cleaned_string) - suffix_match = re.findall(BREAKING_SUFFIX, cleaned_string) # Check for breaking suffixes first + suffix_match = re.findall(BREAKING, cleaned_string) # Check for breaking suffixes first if suffix_match: suffix = next(iter(suffix for suffix in suffix_match[0] if suffix)) cleaned_string = re.sub(suffix.lower(), "-", cleaned_string).rstrip("-,") @@ -43,116 +43,3 @@ def tag_model_from_repo(repo_title: str, decoder=False, data: dict | None = None suffix = root cleaned_string = re.sub(r"[._]+", "-", cleaned_string.lower()).strip("-_") return (cleaned_string, suffix) - - -def tag_scheduler(series_name: str) -> tuple[str, str]: - """Create a mir label from a scheduler operation\n - :param class_name: Known period-separated prefix and model type - :return: The assembled mir tag with compatibility pre-separated""" - - import re - - comp_name = None - patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] - for scheduler in patterns: - compiled = re.compile(scheduler) - match = re.search(compiled, series_name) - if match: - comp_name = match.group() - comp_name = comp_name.lower() - break - for pattern in patterns: - series_name = re.sub(pattern, "", series_name) - series_name.lower() - assert series_name is not None - assert comp_name is not None - return series_name, comp_name - - -def mir_prefix_from_forward_pass(transformers: bool = False, **kwargs): - """Set type of MIR prefix depending on model type\n - :param transformers: Use transformers data instead of diffusers data, defaults to False - :raises ValueError: Model type not detected - :return: MIR prefix based on model configuration""" - from mir.config.json_io import read_json_file - - data = read_json_file("mir/spec/template.json") - - if transformers: - flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object - else: - flags = data["arch"]["diffuser"] # pylint:disable=unsubscriptable-object - for mir_prefix, key_match in flags.items(): - if any(kwargs.get(param, None) for param in key_match): - return mir_prefix - return None - - -def tag_base_model(repo_path: str, class_name: str, addendum: dict | None = None) -> tuple[str, str, str | dict[str, dict]]: - """Convert model repo paths to MIR tags, classifying by feature\n - :param name: Repo path - :param class_name: The HF transformers class for the model - :return: A segmented MIR tag useful for appending index entries""" - - from mir.config.constants import extract_init_parameters - - annotations = extract_init_parameters(class_name.replace("Model", "Config"), "transformers") - if not annotations: - class_name = class_name.replace("Config", "Model") - annotations = extract_init_parameters(class_name, "transformers") - if not annotations: - raise TypeError("No mode type returned") - mir_prefix = mir_prefix_from_forward_pass(True, **annotations) - base_series, base_comp = tag_model_from_repo(repo_path) - if not addendum: - return mir_prefix, base_series, base_comp - else: - mir_prefix = f"info.{mir_prefix}" - return mir_prefix, base_series, {base_comp: addendum} - - -def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: - """Convert model repo pipes to MIR tags, classifying by feature\n - :param name: Repo path - :param class_name: The HF Diffusers class for the model - :return: A segmented MIR tag useful for appending index entries""" - - from mir.indexers import create_pipe_entry - - mir_series, mir_data = create_pipe_entry(repo_path=repo_path, class_name=class_name) - mir_prefix, mir_series = mir_series.rsplit(".", 1) - mir_comp = list(mir_data)[0] - return mir_prefix, mir_series, {mir_comp: addendum} - - -def mir_tag_from_config(class_map: ClassMapEntry, repo_path: str) -> tuple[str, str, str]: - """Change a transformers config class into a MIR series and comp - :param class_map: Transformers class information extracted from dependency""" - - mir_prefix = mir_prefix_from_forward_pass(transformers=True, **class_map.config_params) - if not mir_prefix: - if class_map.model_params: - if mir_prefix := mir_prefix_from_forward_pass(transformers=True, **class_map.model_params): - pass - else: - raise ValueError(f"Unable to determine MIR prefix from {class_map, repo_path}") - else: - raise ValueError(f"Unrecognized model type, no tag matched {class_map.name} with {class_map.config_params} or {class_map.model_params}") - mir_prefix = "info." + mir_prefix - if class_map.name != "funnel": - mir_suffix, mir_comp = tag_model_from_repo(repo_path) - else: - mir_suffix, mir_comp = ["funnel", "*"] - mir_series = mir_prefix + "." + mir_suffix - return mir_series, mir_comp, mir_suffix - - -# def tag_mlx_model(repo_path: str, class_name: str, addendum: dict) -> tuple[str]: -# dev_series, dev_comp = make_mir_tag("black-forest-labs/FLUX.1-dev") -# schnell_series, schnell_comp = make_mir_tag("black-forest-labs/FLUX.1-schnell") -# series, comp = make_mir_tag(repo_path) -# if class_name == "Flux1": -# mir_prefix = "info.dit" -# base_series = dev_series -# mir_comp = series -# return mir_prefix, base_series, {base_comp: addendum} diff --git a/pyproject.toml b/pyproject.toml index 580736e..4c33193 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -39,7 +39,7 @@ Homepage = "https://github.com/darkshapes/MIR" Documentation = "https://github.com/darkshapes/sdbx/wiki" [project.scripts] -mir = "mir.__init__:main" +mir = "mir.generate.__main__:main" [tool.setuptools_scm] version_scheme = "guess-next-dev" diff --git a/tests/test_deconstructors_root.py b/tests/test_deconstructors_root.py index c8e01ad..67a0bed 100644 --- a/tests/test_deconstructors_root.py +++ b/tests/test_deconstructors_root.py @@ -2,17 +2,17 @@ # # # import pytest -from mir.inspect.classes import extract_init_params +from mir.config.constants import extract_init_parameters def test_root_class_with_builtin_types(): class DummyInitModule: - def __init__(self, flag: bool, count: int): + def __init__(self): pass expected_output = {} - result = extract_init_params(DummyInitModule) + result = extract_init_parameters(DummyInitModule) assert result == expected_output diff --git a/tests/test_seek_class.py b/tests/test_seek_class.py index 28f847c..4d3a1de 100644 --- a/tests/test_seek_class.py +++ b/tests/test_seek_class.py @@ -10,7 +10,8 @@ def test_seek_diffusers_path(): def test_seek_transformers_path(): - assert get_class_parent_folder(import_submodules("AlbertModel", "transformers"), "transformers") == ["transformers", "models", "albert"] + module = import_submodules("AlbertModel", "transformers") + assert get_class_parent_folder(module, "transformers") == ["transformers", "models", "albert"] def test_seek_class_attention(): diff --git a/tests/test_taskanalyzer.py b/tests/test_taskanalyzer.py index 4161da7..77adb96 100644 --- a/tests/test_taskanalyzer.py +++ b/tests/test_taskanalyzer.py @@ -10,17 +10,16 @@ from mir.inspect.tasks import TaskAnalyzer - def test_show_transformers_tasks_by_code_name(): """Test that show_transformers_tasks returns a list of class names when code_name is provided.""" tasks = TaskAnalyzer.show_transformers_tasks(code_name="bert") - + # Should return a list (not a type object) - assert isinstance(tasks, list), f"Expected list, got {type(tasks)}" - + assert isinstance(tasks, list), f"Expected list, got {tasks} type {type(tasks)}" + # Should contain string class names if tasks: - assert all(isinstance(task, str) for task in tasks), f"Expected list of strings, got {tasks}" + assert all(isinstance(task, str) for task in tasks), f"Expected list of strings, got {tasks} type {type(tasks)}" print(f"show_transformers_tasks('bert') returned: {tasks}") @@ -178,6 +177,7 @@ def test_show_diffusers_tasks(): # assert tasks == ["DummyClass"] + @pytest.mark.asyncio async def test_trace_finds_map_with_code_name(): ap = TaskAnalyzer() From 5143276a2c59f80a7122c9fc55a4ab0b4aaf2e13 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Tue, 13 Jan 2026 22:03:55 -0500 Subject: [PATCH 06/16] -rewrite --- MIR.egg-info/PKG-INFO | 7 +- MIR.egg-info/SOURCES.txt | 53 +- MIR.egg-info/entry_points.txt | 2 +- MIR.egg-info/requires.txt | 1 + mir.json | 14941 ---------------- mir/__init__.py | 1 + {data => mir/data}/__init__.py | 2 +- {data => mir/data}/diffusers_adds.json | 2 +- {data => mir/data}/exclusions.json | 0 {data => mir/data}/migrations.json | 34 +- {data => mir/data}/nn_filter.json | 0 {data => mir/data}/parameters.json | 10 +- .../data/pipe_markers.json | 0 {data => mir/data}/tag_scrape.json | 0 {data => mir/data}/transformers_adds.json | 0 mir/generate/.notes.txt | 66 - mir/generate/__main__.py | 118 + mir/generate/diffusers/doc_parse.py | 33 +- mir/generate/from_module.py | 41 +- mir/generate/indexers.py | 29 +- mir/generate/transformers/__init__.py | 25 +- mir/generate/transformers/index.py | 324 +- mir/generate/transformers/raw_data.py | 66 + mir/generate/transformers/tokenizers.py | 24 + mir/generate/write_to_mir.py | 31 - mir/maid.py | 153 +- {data => mir}/mir.json | 0 mir/spec/docstring_patterns.json | 41 - mir/spec/missing_params.json | 73 - mir/spec/repo_migrations.json | 29 - mir/tag.py | 6 +- pyproject.toml | 1 + uv.lock | 25 + 33 files changed, 504 insertions(+), 15634 deletions(-) delete mode 100644 mir.json rename {data => mir/data}/__init__.py (90%) rename {data => mir/data}/diffusers_adds.json (99%) rename {data => mir/data}/exclusions.json (100%) rename {data => mir/data}/migrations.json (68%) rename {data => mir/data}/nn_filter.json (100%) rename {data => mir/data}/parameters.json (74%) rename data/prefixes.json => mir/data/pipe_markers.json (100%) rename {data => mir/data}/tag_scrape.json (100%) rename {data => mir/data}/transformers_adds.json (100%) delete mode 100644 mir/generate/.notes.txt create mode 100644 mir/generate/transformers/raw_data.py create mode 100644 mir/generate/transformers/tokenizers.py delete mode 100644 mir/generate/write_to_mir.py rename {data => mir}/mir.json (100%) delete mode 100644 mir/spec/docstring_patterns.json delete mode 100644 mir/spec/missing_params.json delete mode 100644 mir/spec/repo_migrations.json diff --git a/MIR.egg-info/PKG-INFO b/MIR.egg-info/PKG-INFO index d98b3d3..ba67201 100644 --- a/MIR.egg-info/PKG-INFO +++ b/MIR.egg-info/PKG-INFO @@ -33,6 +33,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence Requires-Python: >=3.11 Description-Content-Type: text/markdown License-File: LICENSE +Requires-Dist: chanfig>=0.0.114 Requires-Dist: diffusers>=0.35.2 Requires-Dist: ftfy>=6.3.1 Requires-Dist: huggingface-hub[hf-xet]>=1.1.7 @@ -139,14 +140,14 @@ Meant to be created by standards community, derived from code and file analysis |
ART
| Autoregressive Transformer | |
BRNN
| Bi-directional Recurrent Neural Network | |
CNN
| Convolutional Neural Network | -|
CONTROLNET
| Controlnet | +|
CONTROLNET
| ControlNet | |
DETR
| Detection Transformer | |
GAN
| Generative Adversarial Model | -|
GRU
| Gated recurrent unit | +|
GRU
| Gated Recurrent Unit | |
LORA
| Low-Rank Adaptation | |
LSTM
| Long Short-Term Memory | |
MOE
| Mixture of Experts | -|
RBM
| Restricted Boltzmann machine | +|
RBM
| Restricted Boltzmann Machine | |
RCNN
| Region-based Convolutional Neural Network | |
RESNET
| Residual Network | |
RNN
| Recurrent Neural Network | diff --git a/MIR.egg-info/SOURCES.txt b/MIR.egg-info/SOURCES.txt index dea9843..e7d1cc2 100644 --- a/MIR.egg-info/SOURCES.txt +++ b/MIR.egg-info/SOURCES.txt @@ -13,29 +13,42 @@ MIR.egg-info/entry_points.txt MIR.egg-info/requires.txt MIR.egg-info/top_level.txt mir/__init__.py -mir/__main__.py -mir/automata.py -mir/doc_parser.py -mir/indexers.py +mir/json_io.py mir/maid.py mir/mir.json mir/tag.py -mir/config/__init__.py -mir/config/console.py -mir/config/constants.py -mir/config/conversion.py -mir/config/json_io.py -mir/inspect/__init__.py -mir/inspect/classes.py -mir/inspect/metadata.py -mir/inspect/parenting.py -mir/inspect/pipes.py -mir/inspect/tasks.py -mir/spec/docstring_patterns.json -mir/spec/mir.py -mir/spec/modes.json -mir/spec/template.json -mir/spec/versions.json +mir/data/__init__.py +mir/data/diffusers_adds.json +mir/data/exclusions.json +mir/data/migrations.json +mir/data/nn_filter.json +mir/data/parameters.json +mir/data/pipe_markers.json +mir/data/tag_scrape.json +mir/data/transformers_adds.json +mir/generate/__init__.py +mir/generate/__main__.py +mir/generate/_extras.py +mir/generate/automata.py +mir/generate/from_module.py +mir/generate/indexers.py +mir/generate/tasks.py +mir/generate/diffusers/__init__.py +mir/generate/diffusers/attention.py +mir/generate/diffusers/doc_parse.py +mir/generate/diffusers/guiders.py +mir/generate/diffusers/index.py +mir/generate/diffusers/schedulers.py +mir/generate/mlx/__init__.py +mir/generate/mlx/index.py +mir/generate/torch/__init__.py +mir/generate/torch/dtypes.py +mir/generate/transformers/__init__.py +mir/generate/transformers/index.py +mir/generate/transformers/raw_data.py +mir/generate/transformers/tokenizers.py +mir/spec/__init__.py +mir/spec/regex.json tests/test_class_parent.py tests/test_deconstructors_root.py tests/test_doc_parser.py diff --git a/MIR.egg-info/entry_points.txt b/MIR.egg-info/entry_points.txt index e057fe6..cf321fe 100644 --- a/MIR.egg-info/entry_points.txt +++ b/MIR.egg-info/entry_points.txt @@ -1,2 +1,2 @@ [console_scripts] -mir = mir.__init__:main +mir = mir.generate.__main__:main diff --git a/MIR.egg-info/requires.txt b/MIR.egg-info/requires.txt index 089ac9c..5f1d4be 100644 --- a/MIR.egg-info/requires.txt +++ b/MIR.egg-info/requires.txt @@ -1,3 +1,4 @@ +chanfig>=0.0.114 diffusers>=0.35.2 ftfy>=6.3.1 huggingface-hub[hf-xet]>=1.1.7 diff --git a/mir.json b/mir.json deleted file mode 100644 index c897555..0000000 --- a/mir.json +++ /dev/null @@ -1,14941 +0,0 @@ -{ - "info.controlnet.sd-controlnet-canny": { - "*": { - "repo": "lllyasviel/sd-controlnet-canny", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.blipdiffusion-controlnet": { - "*": { - "repo": "Salesforce/blipdiffusion-controlnet", - "pkg": { - "0": { - "diffusers": "BlipDiffusionControlNetPipeline" - } - } - } - }, - "info.controlnet.control-v11p-sd15-inpaint": { - "*": { - "repo": "lllyasviel/control_v11p_sd15_inpaint", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-canny-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-canny-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.controlnet-depth-sdxl-1": { - "*": { - "repo": "diffusers/controlnet-depth-sdxl-1.0-small", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.controlnet.stable-diffusion-xl-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLControlNetUnionInpaintPipeline" - } - } - } - }, - "info.controlnet.controlnet-union-sdxl-1": { - "*": { - "repo": "xinsir/controlnet-union-sdxl-1.0", - "pkg": { - "0": { - "diffusers": "ControlNetUnionModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-canny": { - "*": { - "repo": "InstantX/SD3-Controlnet-Canny", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.sd3-controlnet-inpainting": { - "*": { - "repo": "alimama-creative/SD3-Controlnet-Inpainting", - "pkg": { - "0": { - "diffusers": "SD3ControlNetModel" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sd2-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SD2.1-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.controlnet.testing-conrolnetxs-sdxl-canny": { - "*": { - "repo": "UmerHA/Testing-ConrolNetXS-SDXL-canny", - "pkg": { - "0": { - "diffusers": "ControlNetXSAdapter" - } - } - } - }, - "info.unet.marigold-depth-v1-1": { - "*": { - "repo": "prs-eth/marigold-depth-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldDepthPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-depth-v1-1" - ] - } - } - }, - "info.unet.marigold-iid-appearance-v1-1": { - "*": { - "repo": "prs-eth/marigold-iid-appearance-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldIntrinsicsPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-iid-appearance-v1-1" - ] - } - } - }, - "info.unet.marigold-normals-v1-1": { - "*": { - "repo": "prs-eth/marigold-normals-v1-1", - "pkg": { - "0": { - "diffusers": "MarigoldNormalsPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - [ - "ops.scheduler.ddim", - "scheduler" - ], - [ - "ops.scheduler.lcm", - "scheduler" - ] - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "marigold-normals-v1-1" - ] - } - } - }, - "info.unet.stable-diffusion-v1-5": { - "*": { - "repo": "stable-diffusion-v1-5/stable-diffusion-v1-5", - "pkg": { - "0": { - "diffusers": "StableDiffusionPipeline" - } - }, - "identifiers": [ - "up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight" - ], - "file_256": [ - "6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa", - "1a189f0be69d6106a48548e7626207dddd7042a418dbf372cefd05e0cdba61b6", - "e1441589a6f3c5a53f5f54d0975a18a7feb7cdf0b0dee276dfc3331ae376a053", - "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", - "19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1", - "cd1b6db09a81cb1d39fbd245a89c1e3db9da9fe8eba5e8f9098ea6c4994221d3", - "c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21" - ], - "layer_b3": [ - "909c6ff3192ab2767e789a6125865bc23163db467ab78b1c633bad46a4293fad", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "d31382d71a1044b636d80d861a2b4dbca51826bed34d34b5c14608b7679ccefd", - "5fd8b28013b7e5a64c7c235f0a93d93e48bc19a0e5dde7b646a87b429219643a", - "731f552f29edcb4f86112cc94d296377f3533a9633ccf83e202d9e1785d94a00", - "2d2f97574a161cf01a6f6d476b141c7be06f940d94b695ffc12c4e74eca2de1c" - ], - "layer_256": [ - "ece771354ad470a82d56eda413ae3dd6c00d2de28ab3c56a88201d08d4424b4b", - "65b084dada803461ab9ca9be9b892d211870a121dd6c555a111eea470b951c54", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91", - "92565dec90f7c8412dc872e820f66cd0c56263bbbc392439645b6fee270f41bb" - ], - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-v1-5" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ] - } - } - }, - "info.unet.stable-unclip-2-1-l": { - "*": { - "repo": "fusing/stable-unclip-2-1-l", - "pkg": { - "0": { - "diffusers": "StableUnCLIPPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "prior_tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "prior_text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "prior": [ - "PriorTransformer" - ], - "prior_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_normalizer": [ - "info.dit.flux1-schnell", - "*" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-unclip-2-1-l" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - } - } - }, - "info.unet.stable-diffusion-2-1-unclip": { - "*": { - "repo": "stabilityai/stable-diffusion-2-1-unclip-small", - "pkg": { - "0": { - "diffusers": "StableUnCLIPImg2ImgPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_normalizer": [ - "info.dit.flux1-schnell", - "*" - ], - "image_noising_scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-2-1-unclip" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vae": [ - "AutoencoderKL" - ] - } - } - }, - "info.unet.stable-diffusion-xl-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "denoising_end": 0.8, - "num_inference_steps": 40, - "output_type": "latent", - "safety_checker": false, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a", - "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139", - "31e35c80fc4829d14f90153f4c74cd59c90b779f6afe05a74cd6120b893f7e5b", - "6f001c090fb13c0d0f8b0a5916da814712a94400b99471fabe77c1c4a51ecaaf" - ], - "layer_256": [ - "62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef", - "34dff8d98898baa0f10e71943e56b588cc114253b0d2f1051f3ce7a8a45fee0b", - "56b1ccd89b0d6ab658048aa34d659788b6ed663f13ef566f4b11bccef590b9da" - ], - "layer_b3": [ - "8be44fa13c1efa60f8bcadaa57f1d718473f9660f03c4f0e65dc037960d8cba1", - "c9ab95ed1851418b65ef99651c1eb6bbdd2e3b0715e0e435d6d1e56ce310fac3", - "adfa260098d87616d748e3cf9c10bb2c90ff8890a84abbb2853d4aa69664070b" - ], - "identifiers": [ - "logit_scale", - "conditioner.embedders.0.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight", - "add_embedding.linear_2.bias" - ], - "pipe_names": {} - }, - "pony-diffusion": { - "file_256": [ - "67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3" - ], - "layer_256": [ - "465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e" - ], - "layer_b3": [ - "bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071" - ] - }, - "pony-diffusion-turbo": { - "file_256": [ - "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", - "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2" - ], - "layer_256": [ - "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", - "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52" - ], - "layer_b3": [ - "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", - "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc" - ] - }, - "animagine-xl-4": { - "repo": "cagliostrolab/animagine-xl-4.0", - "file_256": [ - "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", - "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", - "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", - "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0" - ], - "layer_256": [ - "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", - "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", - "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", - "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65" - ], - "layer_b3": [ - "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", - "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", - "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", - "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447" - ] - }, - "illustrious-xl-v2": { - "repo": "OnomaAIResearch/Illustrious-XL-v2.0", - "file_256": [ - "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", - "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", - "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", - "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", - "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd" - ], - "layer_256": [ - "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", - "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", - "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", - "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", - "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10" - ], - "layer_b3": [ - "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", - "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", - "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", - "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", - "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c" - ] - }, - "playground-v2---aesthetic": { - "repo": "playgroundai/playground-v2.5-1024px-aesthetic", - "pkg": { - "0": { - "diffusers": "DiffusionPipeline", - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 50, - "guidance_scale": 3 - } - } - }, - "file_256": [ - "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", - "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", - "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", - "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", - "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", - "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a" - ], - "layer_256": [ - "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", - "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", - "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", - "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", - "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c" - ], - "layer_b3": [ - "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", - "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", - "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", - "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", - "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", - "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd" - ], - "pipe_names": {} - }, - "segmind-vega": { - "repo": "segmind/Segmind-Vega", - "file_256": [ - "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", - "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", - "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2" - ], - "layer_256": [ - "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", - "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", - "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741" - ], - "layer_b3": [ - "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", - "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", - "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1" - ] - }, - "ssd": { - "repo": "segmind/SSD-1B", - "file_256": [ - "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", - "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", - "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", - "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", - "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a" - ], - "layer_256": [ - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ], - "layer_b3": [ - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6" - ] - } - }, - "info.unet.stable-diffusion-xl-refiner-1": { - "*": { - "repo": "stabilityai/stable-diffusion-xl-refiner-1.0", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLImg2ImgPipeline" - }, - "1": { - "diffusers": "DiffusionPipeline", - "generation": { - "num_inference_steps": 40, - "denoising_end": 0.8 - } - } - }, - "identifiers": [ - "conditioner.embedders.0.model.transformer.resblocks.9.mlp.c_proj.bias" - ], - "file_256": [ - "54f9cd2f2daf3aeec0b2708fa3dbc0e84e4f8ddd1ddead42e5bc60c6572c989f", - "7440042bbdc8a24813002c09b6b69b64dc90fded4472613437b7f55f9b7d9c5f", - "3ea0376dcf065eaefd27806394a90e310001b1a71d4f1cf1f655e86c0e566ffe" - ], - "layer_b3": [ - "6281355dbb37e5769c9460ae0ac75506d89932e2f97b09d9ade32ecf191e75ba", - "afb0639aae2eb65577c12d4a30cf7c9b3620ae63ba64a8fa632b58608c8a7a2e", - "669046014b69d98ab0f6fbb59547644436e0275f8b638f467ce2a873c3313683" - ], - "layer_256": [ - "bb9eadbfabb52c0d8645783525a3fa70b59e9d7d09d5290d742a303262e793a2", - "c5adb56fe51343af2c3d493eb9f41515c204bd91eb9f40b983d45f70a1fa3b6d", - "1f838e39ed6e916258aee6990b72c09b34aa8eb3b5342234a497b8852b3df1c6" - ], - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "stable-diffusion-xl-refiner-1" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.sdxl-pix2pix-768": { - "*": { - "repo": "diffusers/sdxl-instructpix2pix-768", - "pkg": { - "0": { - "diffusers": "StableDiffusionXLInstructPix2PixPipeline" - } - }, - "tasks": [ - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "sdxl-pix2pix-768" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.allegro": { - "*": { - "repo": "rhymes-ai/Allegro", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "guidance_scale": 7.5, - "max_sequence_length": 512, - "num_inference_steps": 100 - } - } - }, - "file_256": [ - "6927dcc812841c1da549bf11c97ddf30532aee0e708a6642fa64cf8e0dfcdef7" - ], - "layer_b3": [ - "8b20714a6af89ea4bf4ada1f805c5b9d529ef136c229e9b75392242d62d80c3e" - ], - "layer_256": [ - "9e44e6c919dc71c24a193641e6265cd9983a2a773b9bbaf527c10ac4837b29fd" - ] - } - }, - "info.dit.amused-512": { - "*": { - "repo": "amused/amused-512", - "pkg": { - "0": { - "diffusers": "AmusedInpaintPipeline" - } - }, - "pipe_names": { - "vqvae": [ - "VQModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "amused-512" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "UVit2DModel" - ], - "scheduler": [ - "ops.scheduler.amused", - "scheduler" - ] - } - } - }, - "info.lora.animatediff-motion-adapter-v1-5-2": { - "*": { - "repo": "guoyww/animatediff-motion-adapter-v1-5-2", - "pkg": { - "0": { - "diffusers": "AnimateDiffVideoToVideoPipeline" - } - } - } - }, - "info.lora.animatelcm": { - "*": { - "repo": "wangfuyun/AnimateLCM", - "pkg": { - "0": { - "diffusers": "MotionAdapter" - } - } - } - }, - "info.lora.animatediff-motion-adapter-sdxl": { - "*": { - "repo": "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", - "pkg": { - "0": { - "diffusers": "AnimateDiffSDXLPipeline" - } - } - } - }, - "info.controlnet.animatediff-sparsectrl-scribble": { - "*": { - "repo": "guoyww/animatediff-sparsectrl-scribble", - "pkg": { - "0": { - "diffusers": "SparseControlNetModel" - } - } - } - }, - "info.controlnet.animatelcm": { - "*": { - "repo": "wangfuyun/AnimateLCM", - "pkg": { - "0": { - "diffusers": "ControlNetModel" - } - } - } - }, - "info.dit.bria-3": { - "*": { - "repo": "briaai/BRIA-3.2", - "pkg": { - "0": { - "diffusers": "BriaPipeline" - } - }, - "pipe_names": { - "transformer": [ - "BriaTransformer2DModel" - ], - "scheduler": [ - [ - "ops.scheduler.euler", - "discrete" - ], - [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "bria-3" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.flux2-dev": { - "*": { - "repo": "black-forest-labs/FLUX.2-dev", - "pkg": { - "0": { - "diffusers": "Flux2Pipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.mistral-3-2503", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux2-dev" - ], - "transformer": [ - "Flux2Transformer2DModel" - ] - } - } - }, - "info.dit.flux1-schnell": { - "*": { - "repo": "black-forest-labs/FLUX.1-schnell", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 0.0, - "num_inference_steps": 4, - "max_sequence_length": 256 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "num_inference_steps": 4 - } - } - }, - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "file_256": [ - "9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a", - "9b633dbe87316385c5b1c262bd4b5a01e3d955170661d63dcec8a01e89c0d820" - ], - "layer_b3": [ - "c65ba812ce3ce056eb1585673f62fb896afe6ec049faaf00a97bc35c9a398c44", - "03049273329fc7db2da10de6d3eb27cb03f190e379c0556cc97b3f0f29001d0c", - "483c4be8ef031c56bc8450d1a3cfbe54445ed317bcd801be5abe89f1d3c48790" - ], - "layer_256": [ - "79c07e339865fe9e22c80f723d728c778130acd07a330339c68218b92bb7b3b8", - "ef5c9cd1ebe6e3be5e8b1347eca0a6f0b138986c71220a7f1c2c14f29d01beed", - "27bc71eca2d2ff7459165acc12010230911db7709a4f6a5c255befedfa6b1649" - ], - "tasks": [ - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - }, - "shuttle-3-aesthetic": { - "repo": "shuttleai/shuttle-3.1-aesthetic", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", - "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42" - ], - "layer_256": [ - "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", - "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a" - ], - "layer_b3": [ - "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", - "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c" - ] - }, - "shuttle-3-diffusion": { - "repo": "shuttleai/shuttle-3-diffusion", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", - "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", - "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", - "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8" - ], - "layer_256": [ - "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", - "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", - "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c" - ], - "layer_b3": [ - "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", - "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", - "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd" - ] - }, - "shuttle-jaguar": { - "repo": "shuttleai/shuttle-jaguar", - "pkg": { - "2": { - "diffusers": "DiffusionPipeline", - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 4 - } - } - }, - "file_256": [ - "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", - "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f" - ], - "layer_b3": [ - "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", - "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672" - ] - } - }, - "info.controlnet.flux1-canny-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Canny-dev", - "pkg": { - "0": { - "diffusers": "FluxControlPipeline" - } - } - } - }, - "info.controlnet.flux1-depth-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Depth-dev", - "pkg": { - "0": { - "diffusers": "FluxControlInpaintPipeline" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny": { - "*": { - "repo": "InstantX/FLUX.1-dev-controlnet-canny", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.controlnet.flux1-dev-controlnet-canny-alpha": { - "*": { - "repo": "InstantX/FLUX.1-dev-Controlnet-Canny-alpha", - "pkg": { - "0": { - "diffusers": "FluxControlNetModel" - } - } - } - }, - "info.dit.flux1-fill-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Fill-dev", - "pkg": { - "0": { - "diffusers": "FluxFillPipeline" - } - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-fill-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - } - } - }, - "info.dit.flux1-kontext-dev": { - "*": { - "repo": "black-forest-labs/FLUX.1-Kontext-dev", - "pkg": { - "0": { - "diffusers": "FluxKontextInpaintPipeline" - } - }, - "tasks": [ - "FluxControlImg2ImgPipeline", - "FluxControlInpaintPipeline", - "FluxControlNetImg2ImgPipeline", - "FluxControlNetInpaintPipeline", - "FluxControlNetPipeline", - "FluxControlPipeline", - "FluxImg2ImgPipeline", - "FluxInpaintPipeline", - "FluxKontextPipeline", - "FluxPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "flux1-kontext-dev" - ], - "transformer": [ - "FluxTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.prx-512-t2i-sft": { - "*": { - "repo": "Photoroom/prx-512-t2i-sft", - "pkg": { - "0": { - "diffusers": "PRXPipeline" - } - }, - "pipe_names": { - "transformer": [ - "PRXTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder": [ - "info.stst.t5gemma-prefixlm", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "prx-512-t2i-sft" - ], - "vae": [ - "AutoencoderKL", - [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "NoneType" - ] - } - } - }, - "info.unet.audioldm-s-v2": { - "*": { - "repo": "cvssp/audioldm-s-full-v2", - "pkg": { - "0": { - "diffusers": "AudioLDMPipeline" - } - }, - "file_256": [ - "fc30d5b5a3bb8d08672736efb1fff10755ba7024dace39b2dcb579a105aa2a5a" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clap-htsat-fused", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "vocoder": [ - "info.stst.speecht5-asr", - "*" - ] - } - } - }, - "info.unet.audioldm2": { - "*": { - "repo": "cvssp/audioldm2", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "359a5ffb89a844beb2fcfac584aae2cd7cd6e87c3ab1ec4e892ef45d91db77c2" - ], - "layer_b3": [ - "eac241273f9f30982fc04aa88b4dc1c38b533430956a55b9ed4d3e5c717ec962" - ], - "layer_256": [ - "ab109d01b43788063802f00c6ecab024c830ea58d668f5c2df9e3ae5b87d86cb" - ] - } - }, - "info.unet.blipdiffusion": { - "*": { - "repo": "Salesforce/blipdiffusion", - "pkg": { - "0": { - "diffusers": "BlipDiffusionPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "blipdiffusion" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "scheduler": [ - "ops.scheduler.pndm", - "scheduler" - ], - "qformer": [ - "info.vit.blip2-opt", - "*" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chroma": { - "*": { - "repo": "lodestones/Chroma", - "pkg": { - "0": { - "diffusers": "ChromaPipeline" - }, - "1": { - "generation": { - "neg_text": "", - "num_steps": "28", - "latent_size": [ - 64, - 64 - ] - } - } - }, - "file_256": [ - "53adcb3b6b6005758d40e2d8058b044ed4892bc8616efb7a62cc2dd384be07de", - "2c41e8a9831f3be1eaff2c2ed590abb62e4534e814f7ec58a5fd74ff71dc2036", - "0a7b2d9699dbd22b3744ee2692900cabcfb731a43dac13729c33807f2bb7c9f6", - "6ddc9e2bbe3376ab5ee9f10b2d947f127b6bf6f879f06f316a2208bb0da357b8" - ], - "layer_b3": [ - "15e227ced8a89c41abaa9cc44f84dfffdf5ead0c626035e5a2dde2bbb0935479" - ], - "layer_256": [ - "a4daa6ff6f45ca70c738adb8c19bc3b6f228df931e6bf2a3394463e4dd7ec882" - ], - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - }, - "chroma1-hd": { - "repo": "lodestones/Chroma1-HD", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 40 - } - } - }, - "file_256": [ - "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", - "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", - "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc" - ] - }, - "chroma1-flash": { - "repo": "lodestones/Chroma1-Flash", - "pkg": { - "0": { - "diffusers": "ChromaPipeline", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.0, - "num_images_per_prompt": 1 - } - } - }, - "file_256": [ - "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", - "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", - "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db" - ], - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chroma1-hd": { - "*": { - "repo": "lodestones/Chroma1-HD", - "pkg": { - "0": { - "diffusers": "ChromaImg2ImgPipeline" - } - }, - "tasks": [ - "ChromaPipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "chroma1-hd" - ], - "transformer": [ - "ChromaTransformer2DModel" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.cogvideox": { - "*": { - "repo": "zai-org/CogVideoX-2b", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_videos_per_prompt": 1, - "num_inference_steps": 50, - "num_frames": 49, - "guidance_scale": 6 - } - } - }, - "file_256": [ - "8fbb6a5e67c70885a8ed8e33df144ac61253e45977be5035fa18cfdf77d386c7" - ], - "layer_b3": [ - "1db3439649b5362448455fb2ed6ebde0c3b973655a206832731149757ad165bb" - ], - "layer_256": [ - "edd6bd51f1236f528ff8d32dc754f0b86cfac901b800642ea497358156dc00bd" - ] - } - }, - "info.controlnet.cogvideox-fun-v-pose": { - "*": { - "repo": "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", - "pkg": { - "0": { - "diffusers": "CogVideoXFunControlPipeline" - } - } - } - }, - "info.dit.cogvideox-i2v": { - "*": { - "repo": "zai-org/CogVideoX-5b-I2V", - "pkg": { - "0": { - "diffusers": "CogVideoXImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogvideox-i2v" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "info.vae.cogvideox", - "cogvideox-i2v" - ], - "transformer": [ - "CogVideoXTransformer3DModel" - ], - "scheduler": [ - [ - "ops.scheduler.cogvideoxddim", - "scheduler" - ], - [ - "ops.scheduler.cogvideoxdpm", - "scheduler" - ] - ] - } - } - }, - "info.dit.cogview3": { - "*": { - "repo": "zai-org/CogView3-Plus-3B", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "guidance_scale": 7.0, - "num_images_per_prompt": 1, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - } - } - } - }, - "info.dit.cogview4": { - "*": { - "repo": "zai-org/CogView4-6B", - "pkg": { - "0": { - "diffusers": "CogView4Pipeline" - } - }, - "tasks": [ - "CogView4ControlPipeline", - "CogView4Pipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "cogview4" - ], - "text_encoder": [ - "info.stst.glm-4-chat", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "CogView4Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.controlnet.cogview4-control": { - "*": { - "repo": "zai-org/CogView4-6B-Control", - "pkg": { - "0": { - "diffusers": "CogView4ControlPipeline" - } - } - } - }, - "info.dit.pre-trianed": { - "*": { - "repo": "model_id, revision=\"diffusers/base/pre-trianed", - "pkg": { - "0": { - "diffusers": "Cosmos2_5_PredictBasePipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "pre-trianed" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-predict2-text2image": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Text2Image", - "pkg": { - "0": { - "diffusers": "Cosmos2TextToImagePipeline" - } - }, - "file_256": [ - "7fbd20dae97cc26a55c7aff3024bc84e554cff8f69966c725a24c8238c5431ec", - "6d211f1c14cd793156da3a840dd5462ae072046fcd6f1dc64c613a5343bfe896", - "95a2b32ad31a271eb64d35985c7ea46f1448528af70932eb1f35d57f90c27be2", - "344e67faf333b7849fa94290c9028bdd5e40eb19700754c833cda0423bc10ad0", - "ce15ef565cbb9ef414a6f7a396c455d82d5f762d2174493da87fe009c5fee75b", - "94aa9f2b59330b88e97b6b439e2f206a51c86e6b154fb66d43ed149bfac23cf8", - "636de5388da249130d51752991a1792b90af31cbf43f021ae07f75756ee2d79a", - "472c5e4cf5056a1a59085addb5a86d801de39bf5e000d253f206a7f63c710029", - "663266ace67c22529c3b6bfa0e8bd69f0ba6e683f5f02b8e3da50881057ba142", - "21a674b314c1364d0dbb3712f5ed702996a7b7403c452835cac22709e01c2f77", - "3bf2df806c6472e039efc9e8d3181163d7faa7b385e61519b7d17d5e9c993a49", - "1de35e1603c4c30bc80b132ccea15fc0503369caf68290708f17e679e98cd41f", - "0738e559bbd71f7351ccba34b2b47362a3f829b92f3dbcffeaf1e44b0d52f42c" - ], - "layer_b3": [ - "5a18ba14c41c6601dcc1195ca180ac7744357eb15ace39272788bda1a7151e9b", - "67cc3eaf7987c89cd7ccff13de6bc03e3eec59d260d44486e2367cd946ce6f20", - "3c6fefa107742488d2e6856714198a762f2fd35c67edd50d4657eaf4b59c7ca3", - "4e1f90ee1e8959d334c9b1ea2cc5e58d0b8340e271c35f81c8a5ec26e16d9d76", - "f8171071e828524fcc2806126ad100a2198e450c82c0864c8fe8b358c5cbbfbd", - "8126101a0207ecfbd741394fd59f306bcb4c492b2a921e0921c426ca7bd38985", - "c942c5a85ff7cb602d8ca894f5d180c2224e91f0b62c3a21f6a425f9e0e8554b", - "c8c500de74da879a547875fe1046f62ab18bdfd09c09eb3da723cbc2319cb4e3", - "c0ac3f67501004e9e9a55d1658402ad97e42bf8a266edf81f6f3bb835ee476b9", - "84f5926eb4e11d826815682b076ed7d3bba4c86520859be80aa1ef92c72b26a4", - "1d4375aab5548708559b0fde150754a2163cd211eb20a5471e17afaeeb26e082", - "68bd8982f59c60d69c301d16dfb5a60f5d43d66c0b60138d48a22f5ded598e7b", - "c3e9a10cad7aebf979072092008be6e2815d03d28cbf316c15e8daf22116bd7d" - ], - "layer_256": [ - "38f2a75eab667c0cc85f3946a23ca6dc2278438c25a9f93aaaa9f79c3808e180", - "ee8434a5e9bc6fa07199de2d0c69fb87f7922c31792bafd13f527c9d92fecb0c", - "2f8382657babb4d0ae4f8e425ae33b21ad71deb6ba457fd6734f05208d52e06a", - "34b181a8291b571857cdbf67ac0081fea594a2f223bf20bd2fc8b0c889e9602d", - "d198c412b972e381acfb812304fa98ed0d97a2f072ddc195cd9a1eb83b1d8146", - "79580a13aff9859e67b0a9f4f8893236cdcfa58c3d43770641aaac8daee55a94", - "cfd48c7ad71c913fa8768167ed0c2ee8c207311b22b1e5a8761369b5a780e8d6", - "da91362ad85d4d2e80a2cb7a55e4ae0e52c9eef8b437a95894ce5ab75d36568c", - "15f84001f5205b6dd8c6f1334cb51c46f6171c7795fb2a557ea16b874f0c71e5", - "5d29179ad15a15d2561defcdda66f1d1e4d065c1e0738f9cba4db5b68b93d2ea", - "7ec489d1e461f5fb2af627b68034ca57f19c516aeccbc5d188b3bd27e3353a15", - "c8dc42fe7b411d746ebdf86286b91cd6893c5f028076b8fe4103f7ea8e1d8833", - "86df7c095aee01588e961438f322b85ca0100a9e440b8a2b6c724e00f748d8b5" - ], - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-text2image" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-predict2-video2world": { - "*": { - "repo": "nvidia/Cosmos-Predict2-2B-Video2World", - "pkg": { - "0": { - "diffusers": "Cosmos2VideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-predict2-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-text2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Text2World", - "pkg": { - "0": { - "diffusers": "CosmosTextToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-text2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.dit.cosmos-1-diffusion-video2world": { - "*": { - "repo": "nvidia/Cosmos-1.0-Diffusion-7B-Video2World", - "pkg": { - "0": { - "diffusers": "CosmosVideoToWorldPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "cosmos-1-diffusion-video2world" - ], - "transformer": [ - "CosmosTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "cosmos-1-diffusion-video2world" - ], - "scheduler": [ - "ops.scheduler.edmeuler", - "scheduler" - ], - "safety_checker": [ - "CosmosSafetyChecker" - ] - } - } - }, - "info.unet.if-ii-l-v1": { - "*": { - "repo": "DeepFloyd/IF-II-L-v1.0", - "pkg": { - "0": { - "diffusers": "IFSuperResolutionPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "if-ii-l-v1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ], - "image_noising_scheduler": [ - "ops.scheduler.ddpm", - "scheduler" - ] - } - } - }, - "info.dit.easyanimatev5-zh": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimatePipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - [ - "info.art.bert-uncased", - "*" - ] - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.controlnet.easyanimatev5-zh-control": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-Control-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateControlPipeline" - } - } - } - }, - "info.dit.easyanimatev5-zh-inp": { - "diffusers": { - "repo": "alibaba-pai/EasyAnimateV5.1-12b-zh-InP-diffusers", - "pkg": { - "0": { - "diffusers": "EasyAnimateInpaintPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "easyanimatev5-zh" - ], - "text_encoder": [ - "Qwen2VLForConditionalGeneration", - [ - "info.art.bert-uncased", - "*" - ] - ], - "tokenizer": [ - "info.encoder.tokenizer", - "easyanimatev5-zh-inp" - ], - "transformer": [ - "EasyAnimateTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.hidream-i1": { - "*": { - "repo": "HiDream-ai/HiDream-I1-Full", - "pkg": { - "0": { - "diffusers": "HiDreamImagePipeline" - } - }, - "file_256": [ - "3cb3f6d77a3fce19b90fa7f66da0cbe997b0785a38a788b559290d3062f6fd26" - ], - "layer_b3": [ - "612eb9b2676a3e7b28b10aae045a97a95de2a399fe3801c8f6369589c3a832a6" - ], - "layer_256": [ - "78fbfb7fddb9ccbdf91f22b0c3d304cbf0cc7305dbccb216982233849ec727df" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_3": [ - "info.stst.t5", - "*" - ], - "tokenizer_3": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "text_encoder_4": [ - "info.stst.llama-2-hf", - "*" - ], - "tokenizer_4": [ - "info.encoder.tokenizer", - "hidream-i1" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuandit-v1": { - "diffusers": { - "repo": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", - "pkg": { - "0": { - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "extra_embedder", - "model.blocks", - "skip_norm.weight" - ], - "file_256": [ - "4fb84f84079cda457d171b3c6b15d1be95b5a3e5d9825703951a99ddf92d1787", - "e01db5e129e8ca1117e9cf473fc5a2b096949f03ab90048aeabbc328de7ec800", - "8af691cadb78047d55721259355d708e87ddbba1b7845df9377d9a5ae917b45d" - ], - "layer_b3": [ - "aead6b61b17ebc77c4c186a4b82c193f11ec267b20d909726422ee9852e2e0b2", - "885a056b94f6f9844c0660be489844d63bb74cc13316f441d10968fff3dd3120", - "390d951cbdda6e2cffb690031b60f02921624651534c2effaaa7d68ab476c700" - ], - "layer_256": [ - "d4842ce2b7f927203326b25ff4d6738ec9a8b95327f06791c387e4a351ed6ed0", - "5af943f96f5dc9fecb1e92fe2b1fa17c94dd6947690201f4a5ee1a4a2721a68e", - "4a1f2b8234fa4336e263842e042d42e8d64d8a4d3941d9c0c78366b50303950c" - ] - } - }, - "info.dit.hunyuanvideo": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo", - "pkg": { - "0": { - "diffusers": "HunyuanVideoPipeline" - } - }, - "file_256": [ - "bdb957b35585ea74ae42ca92865a68fa1bf1ebc6c5b7e686a889e5c977dc24c7" - ], - "layer_b3": [ - "d31c56b4c9444d4c2f1b10120fe964e0956f6b8c7e7c1e4cc5a1f37406fc49f5" - ], - "layer_256": [ - "fe741fdfd163bcb1e0ed81d80f79ac3576dbf6e6740674efadfeff782a48bed4" - ], - "pipe_names": { - "text_encoder": [ - "info.stst.llama-2-hf", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo" - ] - } - } - }, - "info.dit.hunyuanvideo-i2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-I2V", - "pkg": { - "0": { - "diffusers": "HunyuanVideoImageToVideoPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.llava", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "transformer": [ - "HunyuanVideoTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-i2v" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanvideo-1-480p-t2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_t2v", - "pkg": { - "0": { - "diffusers": "HunyuanVideo15Pipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-t2v" - ], - "transformer": [ - "HunyuanVideo15Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-t2v" - ], - "guider": [ - "ClassifierFreeGuidance" - ] - } - } - }, - "info.dit.hunyuanvideo-1-480p-i2v": { - "*": { - "repo": "hunyuanvideo-community/HunyuanVideo-1.5-480p_i2v", - "pkg": { - "0": { - "diffusers": "HunyuanVideo15ImageToVideoPipeline" - } - }, - "pipe_names": { - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-i2v" - ], - "transformer": [ - "HunyuanVideo15Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanvideo-1-480p-i2v" - ], - "guider": [ - "ClassifierFreeGuidance" - ], - "image_encoder": [ - "SiglipVisionModel" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanimage-2": { - "diffusers": { - "repo": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", - "pkg": { - "0": { - "diffusers": "HunyuanImagePipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanimage-2" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "hunyuanimage-2" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.hunyuanimage-2-refiner": { - "diffusers": { - "repo": "hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", - "pkg": { - "0": { - "diffusers": "HunyuanImageRefinerPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "hunyuanimage-2-refiner" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.kandinsky-2-1": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-1-prior", - "pkg": { - "0": { - "diffusers": "KandinskyPriorPipeline" - } - }, - "tasks": [ - "Kandinsky3Img2ImgPipeline", - "Kandinsky3Pipeline", - "KandinskyCombinedPipeline", - "KandinskyImg2ImgCombinedPipeline", - "KandinskyImg2ImgPipeline", - "KandinskyInpaintCombinedPipeline", - "KandinskyInpaintPipeline", - "KandinskyPipeline", - "KandinskyV22CombinedPipeline", - "KandinskyV22Img2ImgCombinedPipeline", - "KandinskyV22Img2ImgPipeline", - "KandinskyV22InpaintCombinedPipeline", - "KandinskyV22InpaintPipeline", - "KandinskyV22Pipeline" - ], - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-1" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.kandinsky-2-2": { - "prior": { - "repo": "kandinsky-community/kandinsky-2-2-prior", - "pkg": { - "0": { - "diffusers": "KandinskyV22PriorPipeline" - } - }, - "pipe_names": { - "prior": [ - "PriorTransformer" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-2-2" - ], - "scheduler": [ - "ops.scheduler.unclip", - "scheduler" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.latte-1": { - "*": { - "repo": "maxin-cn/Latte-1", - "pkg": { - "0": { - "diffusers": "LattePipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "latte-1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "LatteTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.ltx-video": { - "*": { - "repo": "Lightricks/LTX-Video", - "pkg": { - "0": { - "diffusers": "LTXImageToVideoPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.ltx-video-09": { - "*": { - "repo": "Lightricks/LTX-Video-0.9.5", - "pkg": { - "0": { - "diffusers": "LTXConditionPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "ltx-video" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ltx-video-09" - ], - "transformer": [ - "LTXVideoTransformer3DModel" - ] - } - } - }, - "info.dit.lumina-next-sft": { - "diffusers": { - "repo": "Alpha-VLLM/Lumina-Next-SFT-diffusers", - "pkg": { - "0": { - "precision": " ops.precision.bfloat.B16" - } - }, - "identifiers": [ - "time_caption", - "feed_forward" - ], - "file_256": [ - "371153b7c7b7a64899d4016970c7cc472039f9c9b21ebe073adf0b8525cdf1bd" - ], - "layer_b3": [ - "fa134efd6e9672e7de2965e4895fc58879bd0a6c4fdf9165c278f2748254675f", - "4d960ec35c53f72f065b94b836bcd923ea6074d38ad49881061f315d62e3c839" - ], - "layer_256": [ - "3938a85568d9df186923edf04391d79e89e6199123bc175afb520e0948d1ae05", - "c0ca51fdea051fcd042bf4b56d32e1e8bb9525a921f2e197f370f101e90527f0" - ] - } - }, - "info.dit.lumina-image-2": { - "*": { - "repo": "Alpha-VLLM/Lumina-Image-2.0", - "pkg": { - "0": { - "diffusers": "Lumina2Pipeline" - } - }, - "file_256": [ - "132b4d213fdd3cfc14333746fc3eb8bbe6358cd73c3bc95ac4ccec230b97dca3", - "a7c09ebae62996a8289782161338a3cdba58c11d2d849c50b2d6502e152b0d6d" - ], - "layer_b3": [ - "198bde52f09736f1fc650dcdbd0e6b0f6a5ce186582554c1d9ee8ab16ac0feb2", - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa" - ], - "layer_256": [ - "982893c99860aac8198c2e435cf85f782fce8f10732daf1f2881a26864400a4e", - "dc937b59892604f5a86ac96936cd7ff09e25f18ae6b758e8014a24c7fa039e91" - ], - "tasks": [ - "Lumina2Pipeline" - ], - "pipe_names": { - "transformer": [ - "Lumina2Transformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "lumina-image-2" - ] - } - }, - "illustrious-lumina-v3": { - "repo": "OnomaAIResearch/Illustrious-Lumina-v0.03", - "file_256": [ - "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", - "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214" - ], - "layer_256": [ - "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", - "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828" - ], - "layer_b3": [ - "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", - "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c" - ] - } - }, - "info.dit.lucy-edit-dev": { - "*": { - "repo": "decart-ai/Lucy-Edit-Dev", - "pkg": { - "0": { - "diffusers": "LucyEditPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "lucy-edit-dev" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.longcat-image": { - "*": { - "repo": "meituan-longcat/LongCat-Image", - "pkg": { - "0": { - "diffusers": "LongCatImagePipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "longcat-image" - ], - "text_processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.longcat-image-edit": { - "*": { - "repo": "meituan-longcat/LongCat-Image-Edit", - "pkg": { - "0": { - "diffusers": "LongCatImageEditPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "longcat-image-edit" - ], - "text_processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.mochi-1": { - "*": { - "repo": "genmo/mochi-1-preview", - "pkg": { - "0": { - "diffusers": "MochiPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "mochi-1" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "mochi-1" - ], - "transformer": [ - "MochiTransformer3DModel" - ] - } - } - }, - "info.unet.musicldm": { - "*": { - "repo": "ucsd-reach/musicldm", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 200, - "audio_length_in_s": 10.0 - } - } - }, - "file_256": [ - "853d0ef1d61cbf5d682872322ea8b761ba3d2f85bfbccd58363bd6b2f837268f" - ], - "layer_b3": [ - "82fbcc553c1ad770d28fd1866b935249c5ebfbf75f3166ae823e1bc6ef39a95a" - ], - "layer_256": [ - "d076446a58a36bf436e37444679d62bcf2f45689d4aa3d799b3fe801c71ed2c8" - ] - } - }, - "info.dit.omnigen-v1": { - "diffusers": { - "repo": "Shitao/OmniGen-v1-diffusers", - "pkg": { - "0": { - "diffusers": "OmniGenPipeline" - } - }, - "pipe_names": { - "transformer": [ - "OmniGenTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "omnigen-v1" - ] - } - } - }, - "info.dit.ovis-image": { - "*": { - "repo": "AIDC-AI/Ovis-Image-7B", - "pkg": { - "0": { - "diffusers": "OvisImagePipeline" - } - }, - "tasks": [ - "OvisImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.stst.qwen3", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ovis-image" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.visualclozepipeline-384": { - "*": { - "repo": "VisualCloze/VisualClozePipeline-384", - "pkg": { - "0": { - "diffusers": "VisualClozeGenerationPipeline" - } - }, - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "text_encoder_2": [ - "info.stst.t5", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "visualclozepipeline-384" - ], - "transformer": [ - "FluxTransformer2DModel" - ] - } - } - }, - "info.lora.pia-condition-adapter": { - "*": { - "repo": "openmmlab/PIA-condition-adapter", - "pkg": { - "0": { - "diffusers": "PIAPipeline" - } - } - } - }, - "info.dit.pixart-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtAlphaPipeline" - } - }, - "identifiers": [ - "aspect_ratio", - "y_embedding", - "emb.resolution", - "caption_projection" - ], - "file_256": [ - "809a92d52a4a228f381a4b4f4b76051294b73285fb0cbb02f0ad24f9372217a8" - ], - "layer_b3": [ - "c5be83545ce9dbc564bcc9fd8fe4157d131347ccfc8f62adc877ec205b20acee" - ], - "layer_256": [ - "117225c0e91423746114b23d3e409708ad55c90ff52b21fa7a1c5105d2e935a5" - ], - "tasks": [ - "PixArtAlphaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-xl-2-1024-ms" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } - } - }, - "info.dit.pixart-sigma-xl-2-1024-ms": { - "*": { - "repo": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", - "pkg": { - "0": { - "diffusers": "PixArtSigmaPipeline" - } - }, - "identifiers": [ - "adaln_single", - "scale_shift_table" - ], - "file_256": [ - "c34b520ef473329b945c2a21083cdf1337c5a468d23b3215b65576789bfd0305", - "2fa4dee9229c02b03163f57bdb8e80c7a5ee364b7161796abe9c05e8dd13f239" - ], - "layer_b3": [ - "a199930ff537994872da77391955f0dd52eddd22ab9105388f0c5852f1b8021f", - "ee6f980c32e98da6885f3e97d3f88d9158031e362cd3a49b20d1e23924b251e3" - ], - "layer_256": [ - "e0afd203aff5a1d192e325d0f59361373273d85d138b51768c3f10a75c154dc0", - "987f3c2ff5d399191e5fd7dd7b1f1f285c197dc8124ad77f05cde7f2fb677a3c" - ], - "tasks": [ - "PixArtAlphaPipeline", - "PixArtSigmaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "pixart-sigma-xl-2-1024-ms" - ], - "text_encoder": [ - "info.stst.t5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "PixArtTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ] - } - } - }, - "info.dit.sana-1024px-bf16": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", - "pkg": { - "0": { - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 4.5, - "num_inference_steps": 20 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "b0b50c33be8758713459aa3c760feef6315d4bea31521fb5b8c3e8fdd9841ffe" - ], - "layer_b3": [ - "461e3d83dfa7e075ef21e2138ef153922ecfadde3db464b03dff92819f3e86dd" - ], - "layer_256": [ - "b928bbcc2ce99d55d21c189e2b1c57498bc313ef5b1457036e356107d567fc4e" - ] - } - }, - "info.controlnet.sana-1024px-controlnet": { - "diffusers": { - "repo": "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers", - "pkg": { - "0": { - "diffusers": "SanaControlNetPipeline" - } - } - } - }, - "info.dit.sana-sprint-1024px": { - "diffusers": { - "repo": "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", - "pkg": { - "0": { - "diffusers": "SanaSprintPipeline" - } - }, - "tasks": [ - "SanaPAGPipeline", - "SanaPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-sprint-1024px" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "vae": [ - "info.vae.dc", - "sana-1024px-bf16" - ], - "transformer": [ - "SanaTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.dpm", - "multistep" - ] - } - } - }, - "info.dit.sana-video": { - "*": { - "repo": "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", - "pkg": { - "0": { - "diffusers": "SanaImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "sana-video" - ], - "text_encoder": [ - "info.stst.gemma2", - "*" - ], - "vae": [ - [ - "info.vae.dc", - "sana-1024px-bf16" - ], - [ - "info.vae.kl", - "audioldm-s-v2" - ] - ], - "transformer": [ - "SanaVideoTransformer3DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.unet.shap-e": { - "*": { - "repo": "openai/shap-e", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 64, - "size": 256, - "guidance_scale": 15 - } - } - } - } - }, - "info.dit.stable-audio-open-1": { - "*": { - "repo": "stabilityai/stable-audio-open-1.0", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "num_inference_steps": 200, - "audio_end_in_s": 10, - "num_waveforms_per_prompt": 3 - } - } - } - } - }, - "info.unet.stable-cascade": { - "prior": { - "repo": "stabilityai/stable-cascade-prior", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "negative_prompt": "", - "num_images_per_prompt": 1, - "num_inference_steps": 20, - "guidance_scale": 4.0, - "width": 1024, - "height": 1024 - } - } - }, - "file_256": [ - "673b3173b037fb5f65b14fde37267390641a36726683de75dcf9df76fce2b866", - "45c1eb5ce9b69efac891ad459b15c215cd90a986adbbfaf3effd3a89578cbcaf", - "088ddf1e444abf399007b2da2bac87791df165c69f477994f6b3c745a20904b0", - "39cec96c7212607f9e526db719bf1df507166d09f4748676c13b0d31cd4adb07", - "31ffe2f1a3e2351d658fc7d3002a4eca22466a680f7fb3715b1e3768476f9633", - "dfe24009fc881011f350d08d9d13be13a1a3b3cbfed667435efe0fd419aca099" - ], - "layer_b3": [ - "c55c83fa435ed128457f605bf1312e54727996d1c94413fc5ab5b49e9933857c", - "6fb07ed9fc6ee636e50783802754b3a37bbecfc67037813b616223aeaf6fe877", - "2ea194240e105c8962923e2baca88cb6a0c826794afc2ef82474301694711d68", - "3412c8a184805621e4595d57268ced0b5c3c1974cd221bf67b2c908eec4fd61c", - "53abfb013cfb0e41d0bc7b96bb83e42a4d4c67cb7325f9acf645b02d90efd8fe", - "34556558f680c183adc2accd493cb9888a98ba853226bbecb07d95eb2055ff4f" - ], - "layer_256": [ - "4f5e0a738b963d3d4f8413387a0966ac1ce51f0f985bcbcc124fa221a2fff467", - "8aa77e732a398b7d0dcd9a35d5682c2b5ab090ae90e915c7c91878abff0284d8", - "4bbd46ded0916de3108f0da7145a80f5c7acea26ed35b0aaa29af12008352453", - "415d1f3ecd06416708c1b83ab21e50b39c9d88d19dc33e60b977b7b7061880b9", - "f678c32815c238e14091f690c8a83c3375c8f7738dc7abff79ff086ed9b59204", - "17c8da803df7b9bbc8b1d7cc0c44916fea5b5ac0891330c4fdf0326fcd4496cb" - ], - "identifiers": [ - "down_blocks.0.2.kv_mapper", - "previewer", - "backbone" - ] - }, - "decoder": { - "pkg": { - "0": { - "generation": { - "negative_prompt": "", - "guidance_scale": 0.0, - "output_type": "pil", - "num_inference_steps": 10 - }, - "precision": "ops.precision.bfloat.B16" - } - }, - "file_256": [ - "fe92687deefcfb33bb3ec181254b55fe4e434c5084ce9d38815eaa32487ad376", - "2c8d58b267678aecfa6705a0a0375c88613065a8a8d32ad3a4c3867f5461cb3a", - "6c218dc948575e3b14b03dffe2014d7870ac505005770ce3abdc28e920a03c05", - "a6c3d534a9be308e95d2c3224af94a854bebd9b503f620f1ae3c8e6ba4a341bf", - "7b431ea7d0f10e72b3eaece353bf6bf2f6bc717b6f4207411be186b40dec1f43" - ], - "layer_b3": [ - "9506d989de0226018de214f7ced4670eb5aad4a0c399a9229488ceccdf9a3ceb", - "6c09dcb83e0cd7ad735eb763c5e3721c579d796853f0b9d31ba74fb13cad4f94", - "e07025965cee925e31f1d617ea8baa575e7db910d40cc0482fd83df317c0812b", - "d9a42e4226fb2778aaeaf0d6bda173a4ff95aa574c6d9e27e41542aa469e40a3", - "8dcd87dc7a9b877e8e2a00abac44c4da9eadf2b8df4ae68f27415bb791381a96" - ], - "layer_256": [ - "630ec0f3adf97145316c034139836f9df952060d0237ac4e478c55d9a3a50bc8", - "80904f707c192ddd06be2cebeb2ebbec3eb0e9c99076d50824d391ef3ac67bf2", - "8ccedbe1e8cc4093f05b5f8d90e6103e688ae1ac71e0d6261fb17c42ff7c25e4", - "3524e7fa9ca6f7ef695bc2d3410934eabd5272946a05c8cacd7f329e0bd9f1dd", - "40499a8f45ae28558ed2fe4fc549a4cb469bd237434b331ccc0b1910310ed733" - ], - "identifiers": [ - "0.2.channelwise", - "clip_mapper.bias", - ".12.self_attn.k_proj.weight" - ] - } - }, - "info.dit.auraflow": { - "*": { - "repo": "fal/AuraFlow", - "pkg": { - "0": { - "diffusers": "AuraFlowPipeline" - } - }, - "identifiers": [ - [ - 8192, - 3072 - ], - "mlpX.c_fc2.weight", - "joint_transformer_blocks.2.ff_context.linear_2.weight" - ], - "file_256": [ - "ce3e475246258b94ee9dcb8b83292cb34edfffc2bbde46c74604d9c6cd7c585c", - "526be97cf581c89ad87c6b19c1f7c2378851137698f7ec436596d061a382d37b", - "6a40b011f287452dbca80face78e667055904c5ad97eb2097ade3200259b2203", - "05e5493018333d947bb5940083dbc2f071093027ff414bc5b1b1229e4836e5cb" - ], - "layer_b3": [ - "cc6d383576c35a9709798d2e2b9e3eb31ba8c608040cf3712bc37871cfd14e21", - "ddd54c44fa28fbddecf7cfae91cfa04917fd2f2fa94fc78c528cef2356a4ec3a", - "90c694e7d1e20e6da49b571e9954338d384775419790be315304103227b1051b", - "9e85aec1bdb616f52f88c80ddc7ab1eae8c16c0b5fbfcdb61a71ac02c325003d" - ], - "layer_256": [ - "3c13e6a965d03a49227d8b1606ba6a343a23772d8768407cc78d4ddb9102bc80", - "b356cc84a23bc93bda4cc0fce1d0ba1b8e3d5a521e659ffc72e9e4a2d2c7f204", - "270df7317fe01abf06333acbbd4f15f8fc7a7c56053219f42efb598454a3af24", - "7ab6aa4514dd09f3cf589587d51a81734193ce45dd51bda9db0bd62fe48ef7d5" - ], - "tasks": [ - "AuraFlowPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "auraflow" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "AutoencoderKL" - ], - "transformer": [ - "AuraFlowTransformer2DModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.stable-diffusion-3": { - "*": { - "repo": "stabilityai/stable-diffusion-3.5-medium", - "pkg": { - "0": { - "precision": "ops.precision.float.F16" - } - }, - "identifiers": [ - "model.diffusion_model.joint_blocks.", - "transformer_blocks.21.norm1_context.linear.weight", - "transformer_blocks.31.norm1_context.linear.weight", - "blocks.11.ff.net.2.weight" - ], - "file_256": [ - "ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93", - "11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de" - ], - "layer_b3": [ - "e411016545785046810b29cc3999f40bc6392be134a1318386c6f1c48f98726a", - "a81e07ee67bc627e8b3c5e292ec1ca239009517a2106e8249d670ced0a88f746" - ], - "layer_256": [ - "13c982a6dc82d21c9f459e837d8c6f6d4696fd6e7e7b5783bdd2250b1f4fec61", - "6ee79050373337bf63ac20916596df778bb22022bb38af986128a7459eda1463" - ] - }, - "stable-diffusion-3-turbo": { - "repo": "tensorart/stable-diffusion-3.5-medium-turbo", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.5, - "height": 1024, - "width": 768 - } - } - }, - "file_256": [ - "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", - "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", - "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", - "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e" - ], - "layer_256": [ - "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ], - "layer_b3": [ - "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6" - ] - } - }, - "info.unet.gligen-1-4-inpainting-text-box": { - "*": { - "repo": "masterful/gligen-1-4-inpainting-text-box", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENPipeline" - } - } - } - }, - "info.unet.gligen-inpainting-text-image": { - "*": { - "repo": "anhnct/Gligen_Inpainting_Text_Image", - "pkg": { - "0": { - "diffusers": "StableDiffusionGLIGENTextImagePipeline" - } - } - } - }, - "info.unet.stable-video-diffusion-img2vid-xt": { - "*": { - "repo": "stabilityai/stable-video-diffusion-img2vid-xt", - "pkg": { - "0": { - "diffusers": "StableVideoDiffusionPipeline" - } - }, - "pipe_names": { - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "unet": [ - "UNetSpatioTemporalConditionModel" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.ldm3d-4c": { - "*": { - "repo": "Intel/ldm3d-4c", - "pkg": { - "0": { - "diffusers": "StableDiffusionLDM3DPipeline" - } - }, - "tasks": [ - "StableDiffusion3ControlNetInpaintingPipeline", - "StableDiffusion3ControlNetPipeline", - "StableDiffusion3Img2ImgPipeline", - "StableDiffusion3InpaintPipeline", - "StableDiffusion3PAGImg2ImgPipeline", - "StableDiffusion3PAGPipeline", - "StableDiffusion3Pipeline", - "StableDiffusionControlNetImg2ImgPipeline", - "StableDiffusionControlNetInpaintPipeline", - "StableDiffusionControlNetPAGInpaintPipeline", - "StableDiffusionControlNetPAGPipeline", - "StableDiffusionControlNetPipeline", - "StableDiffusionImg2ImgPipeline", - "StableDiffusionInpaintPipeline", - "StableDiffusionPAGImg2ImgPipeline", - "StableDiffusionPAGInpaintPipeline", - "StableDiffusionPAGPipeline", - "StableDiffusionPipeline", - "StableDiffusionXLControlNetImg2ImgPipeline", - "StableDiffusionXLControlNetInpaintPipeline", - "StableDiffusionXLControlNetPAGImg2ImgPipeline", - "StableDiffusionXLControlNetPAGPipeline", - "StableDiffusionXLControlNetPipeline", - "StableDiffusionXLControlNetUnionImg2ImgPipeline", - "StableDiffusionXLControlNetUnionInpaintPipeline", - "StableDiffusionXLControlNetUnionPipeline", - "StableDiffusionXLImg2ImgPipeline", - "StableDiffusionXLInpaintPipeline", - "StableDiffusionXLPAGImg2ImgPipeline", - "StableDiffusionXLPAGInpaintPipeline", - "StableDiffusionXLPAGPipeline", - "StableDiffusionXLPipeline" - ], - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "ldm3d-4c" - ], - "scheduler": [ - "ops.scheduler.karrasdiffusion", - "schedulers" - ], - "safety_checker": [ - "StableDiffusionSafetyChecker" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.unet.i2vgen-xl": { - "*": { - "repo": "ali-vilab/i2vgen-xl", - "pkg": { - "0": { - "diffusers": "I2VGenXLPipeline" - } - }, - "pipe_names": { - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "i2vgen-xl" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "feature_extractor": [ - "info.dit.flux1-schnell", - "*" - ], - "unet": [ - "I2VGenXLUNet" - ], - "scheduler": [ - "ops.scheduler.ddim", - "scheduler" - ] - } - } - }, - "info.unet.wuerstchen": { - "prior": { - "repo": "warp-ai/wuerstchen-prior", - "pkg": { - "0": { - "diffusers": "WuerstchenPriorPipeline" - } - }, - "tasks": [ - "WuerstchenCombinedPipeline", - "WuerstchenDecoderPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wuerstchen" - ], - "text_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "prior": [ - "WuerstchenPrior" - ], - "scheduler": [ - "ops.scheduler.ddpmwuerstchen", - "scheduler" - ] - } - } - }, - "info.dit.wan2-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-14B-Diffusers", - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "299e6304544f2783896372fa919e755a8bb9ab8caf898ce08a678dae391e1179", - "a9278e6e9c82d174e6c67b3c97d8b97fef30af51dcf59160f2fc241f6819f5dc", - "be531024cd9018cb5b48c40cfbb6a6191645b1c792eb8bf4f8c1c6e10f924dc5", - "6f999b0d6cb9a72b3d98ac386ed96f57f8cecae13994a69232514ea4974ad5fd", - "2e39adde59c5e0e90edbb35873126b0d67928b5c11c501e384e976d6dc597cce", - "2ee88ab18d7ed7691c5b7f8bdc3d0a9815e6efe75499287564830fd209d3cdfb", - "46c27d3693bf2475990a912e08bf67fc6e6cd5396eab87b5e8dd1fcd3651364a", - "193535c6450045f718df5f011de6d94d49bd9b13f37ca0412500f050dbbb01a8" - ], - "layer_b3": [ - "32266d1c79b518adb9d21837e6a427f6ae55b68cfdd673a7dadb38820fddeb48", - "3b6989856f4f05368524c1852d8660b73c84cfbe44460af017d7139c2a4641b8", - "f4d6cee3c112db93b3c9137ad102ec0e79ec7ab68b9bbc59004fbc268ccd5ddb", - "e627144f41055619eb5407699c46e69ac0d87cf8873721e3e48c9e842656abf8", - "6c00f3fadedacb841c4b9b4321b94a11ef85a08c9dd9253e5f9ba95856715579", - "a0c339253c714b05877c8fbab649ed631cf021930978f3696a46f685a07c9092", - "6435da89a870fd0e88680d31de75b9a40c408a4768eff384ce9b9e99481e8e66" - ], - "layer_256": [ - "52493c23c5fc1d087a283bc4eabb151421b7ae09affa12a5bb059d62656c5766", - "058dedb3d2683a9a5b671c6302690e22722c93f6ed92281d5fa74ab190e632a1", - "5fbed4b95e7196d3626003ea9e0fbbffd074b4297ca406e01b5b6c5d881a6080", - "3a2335c8e7a4359c071b50333b5c00eef6f42a1d5206915e2ee99464a8c5eae7", - "0542780670dd75d4cd9deda123d2e150730646c0a1a8d34582460991498a77a6", - "e925b8222774905c8fbf10af77811fde7870e563eedcde2c94bd5c727e952d49", - "3d915854976284347efa7aa0a117c0fc3b415c4208e1a6c94beb4ccb9720743d" - ] - } - }, - "info.dit.wan-animate": { - "diffusers": { - "repo": "Wan-AI/Wan2.2-Animate-14B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanAnimatePipeline" - } - }, - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan-animate" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "WanAnimateTransformer3DModel" - ] - } - } - }, - "info.dit.wan2-i2v-480p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", - "pkg": { - "0": { - "diffusers": "WanImageToVideoPipeline" - } - }, - "file_256": [ - "b4602c35fa0519750a42c03e3f296c02d542291e344c4d702522cddbd1711f13", - "6d7a34b63b70eb608324e546d979167a5e787ac6bca3528e63f54a11572d66aa", - "b2051cd29d6b2f0c924fa7a3e78a4772f0134d7b059f21590dcce416f4f6cbe8", - "7664fe075b3c82dcecf89012ad3429eee41ee9f10d476f60bc2d2ae3c4ca986c", - "8ef7ea5bf9eea636b9b3ebd84c40671b4a18ae2704cb4c8595cb5b25c1d8e8b9", - "b2de21b99b2e72cb0ff15253b07e926f26e7cf1b7e229efc32f94ad1f1ed9395", - "0ca75338e7a47ca7cacddb7e626647e65829c497387f718ecb6ea0bae456944a", - "c058a4ac5363c35d1ab4dd3bdec788c23b267fa42a0d7c68aba599f2f74600c9", - "27988f6b510eb8d5fdd7485671b54897f8683f2bba7a772c5671be21d3491253" - ], - "layer_b3": [ - "4b6c3354c9ee5694e00a78f5658fdf14129f159c3b78a57f82fb18e0f265a83d", - "c36c783559a40d22504f6c4bfb4f5aae760f3f46bbb3a595be79880935122175", - "ac62f7d5583fd2e85b738fafaf233e2cde6e2857e04351135bb9ded45f9082ce", - "215e89e855b5e9456af9aa68bc67567dc2269002aaa6b01d849ffec425fc628d", - "324b8b6c2d512547a2c31bafa12e20acf313fd3aad587b293334f9f629edeec6" - ], - "layer_256": [ - "137881dad8c00063bc8bf05f93067736e419173cd171acc22f77b730db688a19", - "8c5952fd3d333d3a4b719bf7d8ce6b12d1d2e78caaa7e42d713788cfdcadd244", - "86c58bc4864c97f394ea6bccb2ecedc4aab7166f5b9bfeb313edfdcb2918164a", - "cac45f7d8f1a0628cb0738bd308689e439b1cc6206e5f887d60d5b37d30138f2", - "60e4f71a0961b1346b6f6b5ebe4c8cc93219239c5e13b4c0f1e19e9b8e1324d5" - ], - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan2-i2v-480p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.wan", - "wan2-i2v-480p" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "transformer": [ - "WanTransformer3DModel" - ], - "transformer_2": [ - "WanTransformer3DModel" - ] - } - } - }, - "info.dit.wan21-vace": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-VACE-1.3B-diffusers", - "pkg": { - "0": { - "diffusers": "WanVACEPipeline" - } - }, - "file_256": [ - "bd8bbb8834a274525ab65cbb063f21aa58973a054bfd1638bfe395504c9d9b99", - "192804a4e10b5bb0a13f5c224bc4ec9707b3b8cc0def8eea005dbce7c9d6752a", - "f202a5c59b8a91ada1862c46a038214f1f7f216c61ec8350d25f69b919da4307", - "654693bf2a93a27cd67c3bcee238bc1d0cbb0dd9a74928ed7155fb21a2a1900a", - "640ccc0577e6a5d4bb15cd91b11b699ef914fc55f126c5a1c544e152130784f2" - ], - "layer_b3": [ - "5357d78799a61cd2d72a8a2824c919d63f718eb3fba624af63689e9c657db032", - "7ae67b7ccf79d1c3f4531ae138e1eb63d52dd97a66b3fcbe1d68fded8df4d5b1", - "ee63ecdfb3da6901853a59ec950f3e7c3f6595ac46347a03881a4a9c71425377", - "82762df3539021d3c0342e0da04137ddbe95ef37ea933cd0a68c09c2c650f2ac" - ], - "layer_256": [ - "2684413479030170fb3f08c1069c02957ffc386a59168d23b55d579d5c675269", - "d527680fa735e5f30ef8852aabf8a49f02a094bc4718f0787c5b85710a13c026", - "9677492a107b3ed827c7285db3393f5321d451cc6d922a4d0488d2a67e939446", - "aaef66a4f65ecf852888d160b2122753fe4c6d642b5d41db29e4ce9e6855b5a0" - ], - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-vace" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "transformer": [ - "WanVACETransformer3DModel" - ], - "transformer_2": [ - "WanVACETransformer3DModel" - ] - } - } - }, - "info.dit.wan21-t2v": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", - "pkg": { - "0": { - "diffusers": "WanPipeline", - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 480, - "width": 832, - "num_frames": 81, - "guidance_scale": 5.0 - } - } - }, - "tasks": [ - "WanImageToVideoPipeline", - "WanPipeline", - "WanVideoToVideoPipeline" - ], - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "wan21-t2v" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-t2v-lite-sft-5s": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5T2VPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-t2v-lite-sft-5s" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-t2v-lite-sft-5s" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-i2i-lite-sft": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5I2IPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-i2i-lite-sft" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-i2i-lite-sft" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-i2v-sft-5s": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5I2VPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "hunyuanvideo-i2v" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-i2v-sft-5s" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-i2v-sft-5s" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.kandinsky-5-t2i-lite-sft": { - "diffusers": { - "repo": "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers", - "pkg": { - "0": { - "diffusers": "Kandinsky5T2IPipeline" - } - }, - "pipe_names": { - "transformer": [ - "Kandinsky5Transformer3DModel" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "kandinsky-5-t2i-lite-sft" - ], - "text_encoder_2": [ - "info.vit.clip-vit-patch32", - "*" - ], - "tokenizer_2": [ - "info.encoder.tokenizer", - "kandinsky-5-t2i-lite-sft" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.dit.z-image-turbo": { - "*": { - "repo": "Z-a-o/Z-Image-Turbo", - "pkg": { - "0": { - "diffusers": "ZImageOmniPipeline" - } - }, - "tasks": [ - "ZImageControlNetInpaintPipeline", - "ZImageControlNetPipeline", - "ZImageImg2ImgPipeline", - "ZImageOmniPipeline", - "ZImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "AutoencoderKL" - ], - "text_encoder": [ - "PreTrainedModel" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "z-image-turbo" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ], - "siglip": [ - "info.vit.siglip2-patch16-224", - "*" - ], - "siglip_processor": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.controlnet.z-image-turbo": { - "*": { - "repo": "Tongyi-MAI/Z-Image-Turbo", - "pkg": { - "0": { - "diffusers": "ZImageControlNetInpaintPipeline" - } - } - } - }, - "info.dit.skyreels-v2-t2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-T2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2Pipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-t2v-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-df-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-DF-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2DiffusionForcingVideoToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-df-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.skyreels-v2-i2v-720p": { - "diffusers": { - "repo": "Skywork/SkyReels-V2-I2V-14B-720P-Diffusers", - "pkg": { - "0": { - "diffusers": "SkyReelsV2ImageToVideoPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "skyreels-v2-i2v-720p" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_processor": [ - "CLIPProcessor" - ], - "transformer": [ - "SkyReelsV2Transformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.unipc", - "multistep" - ] - } - } - }, - "info.dit.qwen-image": { - "*": { - "repo": "Qwen/Qwen-Image", - "pkg": { - "0": { - "diffusers": "QwenImageInpaintPipeline" - } - }, - "file_256": [ - "9f33a59093af3abcc2836d4cf4b7bd122c238ca70a26c70f34fdde64646b3bcd" - ], - "layer_b3": [ - "c87eedda853c12844a8deb3592a90bbcbd4dff2f7a850c28755e4aa171432150" - ], - "layer_256": [ - "fda2472d8ef6587a4c979021a2390eeb7c8fc2bcf565330ab8dc6b22f5348ec9" - ], - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.controlnet.qwen-image-controlnet-union": { - "*": { - "repo": "InstantX/Qwen-Image-ControlNet-Union", - "pkg": { - "0": { - "diffusers": "QwenImageControlNetModel" - } - } - } - }, - "info.controlnet.qwen-image-controlnet-inpainting": { - "*": { - "repo": "InstantX/Qwen-Image-ControlNet-Inpainting", - "pkg": { - "0": { - "diffusers": "QwenImageControlNetModel" - } - } - } - }, - "info.dit.qwen-image-edit": { - "*": { - "repo": "Qwen/Qwen-Image-Edit", - "pkg": { - "0": { - "diffusers": "QwenImageEditInpaintPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-edit" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.qwen-image-edit-2509": { - "*": { - "repo": "Qwen/Qwen-Image-Edit-2509", - "pkg": { - "0": { - "diffusers": "QwenImageEditPlusPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-edit-2509" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.qwen-image-layered": { - "*": { - "repo": "Qwen/Qwen-Image-Layered", - "pkg": { - "0": { - "diffusers": "QwenImageLayeredPipeline" - } - }, - "tasks": [ - "QwenImageControlNetPipeline", - "QwenImageEditInpaintPipeline", - "QwenImageEditPipeline", - "QwenImageEditPlusPipeline", - "QwenImageImg2ImgPipeline", - "QwenImageInpaintPipeline", - "QwenImagePipeline" - ], - "pipe_names": { - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ], - "vae": [ - "info.vae.kl", - "qwen-image" - ], - "text_encoder": [ - "info.vit.qwen2-vl", - "*" - ], - "tokenizer": [ - "info.encoder.tokenizer", - "qwen-image-layered" - ], - "processor": [ - "Qwen2VLProcessor" - ], - "transformer": [ - "info.dit.flux1-schnell", - "*" - ] - } - } - }, - "info.dit.chronoedit": { - "diffusers": { - "repo": "nvidia/ChronoEdit-14B-Diffusers", - "pkg": { - "0": { - "diffusers": "ChronoEditPipeline" - } - }, - "pipe_names": { - "tokenizer": [ - "info.encoder.tokenizer", - "chronoedit" - ], - "text_encoder": [ - "info.stst.mt5", - "*" - ], - "image_encoder": [ - "info.vit.clip-vit-patch32", - "*" - ], - "image_processor": [ - "info.dit.flux1-schnell", - "*" - ], - "transformer": [ - "ChronoEditTransformer3DModel" - ], - "vae": [ - "info.vae.kl", - "audioldm-s-v2" - ], - "scheduler": [ - "ops.scheduler.euler", - "discrete" - ] - } - } - }, - "info.unet.kolors": { - "diffusers": { - "repo": "Kwai-Kolors/Kolors-diffusers", - "pkg": { - "0": { - "precision": "ops.precision.float.F16", - "generation": { - "negative_prompt": "", - "guidance_scale": 5.0, - "num_inference_steps": 50, - "width": 1024, - "height": 1024 - } - }, - "1": { - "diffusers": "DiffusionPipeline" - } - }, - "file_256": [ - "425ff1dcbe3a70ac13d3afdd69bd4e3176b0c3260722527c80b210f11d2d966c" - ], - "layer_b3": [ - "6eb15506fa38b4cbb26391ab1b6c9ead05f86c711e46583bfbe8fc4421571414" - ], - "layer_256": [ - "04e3c17170b8a200481f6941b370fdc5056a00fe5a16956de01790f8a93c0dcd" - ], - "identifiers": [ - ".DenseReluDense.wi.weight", - "encoder_hid_proj.weight" - ], - "pipe_names": {} - } - }, - "info.moe.trinity": { - "*": { - "repo": "arcee-ai/Trinity-Mini", - "pkg": { - "0": { - "transformers": "AfmoeModel" - } - }, - "tasks": [ - "AfmoeForCausalLM", - "AfmoeModel", - "AfmoePreTrainedModel" - ] - } - }, - "info.encoder.tokenizer": { - "aimv2-patch14-224-lit": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "albert-xx-v2": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "align": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "afm": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "aria": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "audio-flamingo-3-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "aya-vision": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" - } - } - }, - "bark": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "bart": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "bert-for-seq-generation-l-24-bbc-encoder": { - "pkg": { - "0": { - "transformers": "transformers.models.bert_generation.tokenization_bert_generation.BertGenerationTokenizer" - } - } - }, - "bigbird-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.big_bird.tokenization_big_bird.BigBirdTokenizer" - } - } - }, - "bigbird-pegasus-arxiv": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "biogpt": { - "pkg": { - "0": { - "transformers": "transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer" - } - } - }, - "bitnet-b18-4t": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "blenderbot": { - "pkg": { - "0": { - "transformers": "transformers.models.blenderbot_small.tokenization_blenderbot_small.BlenderbotSmallTokenizer" - } - } - }, - "blip-vqa": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "blip2-opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "bloom": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "blt": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "bridgetower": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "bros-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "camembert": { - "pkg": { - "0": { - "transformers": "transformers.models.camembert.tokenization_camembert.CamembertTokenizer" - } - } - }, - "canine-s": { - "pkg": { - "0": { - "transformers": "transformers.models.canine.tokenization_canine.CanineTokenizer" - } - } - }, - "chameleon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "chinese-clip-vit-patch16": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "clap-htsat-fused": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "clip-vit-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "clipseg-rd64": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "clvp-dev": { - "pkg": { - "0": { - "transformers": "transformers.models.clvp.tokenization_clvp.ClvpTokenizer" - } - } - }, - "llama-2-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "codegen-mono": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "c4ai-command-r-v01": { - "pkg": { - "0": { - "transformers": "transformers.models.cohere.tokenization_cohere.CohereTokenizer" - } - } - }, - "conv-bert": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "cpm-ant": { - "pkg": { - "0": { - "transformers": "transformers.models.cpmant.tokenization_cpmant.CpmAntTokenizer" - } - } - }, - "csm": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "ctrl": { - "pkg": { - "0": { - "transformers": "transformers.models.ctrl.tokenization_ctrl.CTRLTokenizer" - } - } - }, - "data2vec-audio-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "data2vec-text": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "dbrx": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "deberta": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta.tokenization_deberta.DebertaTokenizer" - } - } - }, - "deberta-v2-x": { - "pkg": { - "0": { - "transformers": "transformers.models.deberta_v2.tokenization_deberta_v2.DebertaV2Tokenizer" - } - } - }, - "deepseek-v2-lite": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "deepseek-v3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "deepseek-vl-chat": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "dia": { - "pkg": { - "0": { - "transformers": "transformers.models.dia.tokenization_dia.DiaTokenizer" - } - } - }, - "diffllama-handcut": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "distilbert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "dpr-ctx-encoder-single-nq": { - "pkg": { - "0": { - "transformers": "transformers.models.dpr.tokenization_dpr_fast.DPRQuestionEncoderTokenizerFast" - } - } - }, - "electra-discriminator": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "emu3-chat-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "ernie-3-zh": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "ernie-45-pt": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "ernie-4-a-pt": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "ernie-4-vl-a-pt": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "esm": { - "pkg": { - "0": { - "transformers": "transformers.models.esm.tokenization_esm.EsmTokenizer" - } - } - }, - "exaone-4": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "falcon": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "falcon-mamba": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "flaubert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.flaubert.tokenization_flaubert.FlaubertTokenizer" - } - } - }, - "flava": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "flexolmo-7x-1t": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "florence-2": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "fnet": { - "pkg": { - "0": { - "transformers": "transformers.models.fnet.tokenization_fnet.FNetTokenizer" - } - } - }, - "wmt19-en-ru": { - "pkg": { - "0": { - "transformers": "transformers.models.fsmt.tokenization_fsmt.FSMTTokenizer" - } - } - }, - "funnel": { - "pkg": { - "0": { - "transformers": "transformers.models.funnel.tokenization_funnel.FunnelTokenizer" - } - } - }, - "fuyu": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gemma": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma2": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma-3": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma3-text": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "gemma-3n-e": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "git": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "glm-4-chat": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4-0414": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4-a": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4v-thinking": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-4v": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "glm-asr-nano-2512": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "got-ocr-2-hf": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gpt2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-bigcode-santacoder": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-neo": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "gpt-neox": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "gpt-neox-japanese": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox_japanese.tokenization_gpt_neox_japanese.GPTNeoXJapaneseTokenizer" - } - } - }, - "gpt-oss": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "gpt-j": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "granite": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "powermoe": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "granite-4-h": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "moe-active-shared-experts": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "grounding-dino": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "groupvit-gcc-yfcc": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "helium": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "hubert-ls960": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "ibert-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "idefics": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "idefics2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "idefics3-llama3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "blip-flan-t5": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "internvl3-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "jais-2-chat": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "jamba-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "janus": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "jetmoe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "kosmos-2-patch14-224": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "kosmos-2": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "todo": { - "pkg": { - "0": { - "transformers": "transformers.models.parakeet.tokenization_parakeet_fast.ParakeetTokenizerFast" - } - } - }, - "layoutlm-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "layoutlmv2-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv2.tokenization_layoutlmv2.LayoutLMv2Tokenizer" - } - } - }, - "layoutlmv3": { - "pkg": { - "0": { - "transformers": "transformers.models.layoutlmv3.tokenization_layoutlmv3.LayoutLMv3Tokenizer" - } - } - }, - "led-16384": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "lfm2-vl": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "lilt-roberta-en": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "llama-4-scout-16e": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-v1-mistral-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-next-video-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llava-onevision-qwen2-ov-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "longformer-4096": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "long-t5-local": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "luke": { - "pkg": { - "0": { - "transformers": "transformers.models.luke.tokenization_luke.LukeTokenizer" - } - } - }, - "lxmert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "m": { - "pkg": { - "0": { - "transformers": "transformers.models.m2m_100.tokenization_m2m_100.M2M100Tokenizer" - } - } - }, - "mamba": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "mamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "opus-mt-en-de": { - "pkg": { - "0": { - "transformers": "transformers.models.marian.tokenization_marian.MarianTokenizer" - } - } - }, - "mbart-cc25": { - "pkg": { - "0": { - "transformers": "transformers.models.mbart.tokenization_mbart.MBartTokenizer" - } - } - }, - "megatron-bert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "metaclip-2-worldwide-huge-quickgelu": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "mgp-str": { - "pkg": { - "0": { - "transformers": "transformers.models.mgp_str.tokenization_mgp_str.MgpstrTokenizer" - } - } - }, - "max-text-01-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "stral-3-2512": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mistral-v0": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mistral-3-2503": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mixtral-8x": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "llama-3-vision": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "mm-grounding-dino-o365v1-goldg-v3det": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "mobilebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "modernbert": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "moonshine": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "hf-moshiko": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "mpnet": { - "pkg": { - "0": { - "transformers": "transformers.models.mpnet.tokenization_mpnet.MPNetTokenizer" - } - } - }, - "mpt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "mra-512-4": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "mt5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "musicgen": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "musicgen-melody": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "mvp": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "nemotron-3-hf": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "nllb-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.nllb.tokenization_nllb.NllbTokenizer" - } - } - }, - "nystromformer-512": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "olmo-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "olmo2-1124-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "olmo-3-0725": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "olmoe-0924": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "omdet-turbo-swin-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "oneformer-ade-swin": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "openai-gpt": { - "pkg": { - "0": { - "transformers": "transformers.models.openai.tokenization_openai.OpenAIGPTTokenizer" - } - } - }, - "opt": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "ovis2-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "owlv2-patch16": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "owlvit-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "paligemma": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "pegasus": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "pegasus-x": { - "pkg": { - "0": { - "transformers": "transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer" - } - } - }, - "language-perceiver": { - "pkg": { - "0": { - "transformers": "transformers.models.perceiver.tokenization_perceiver.PerceiverTokenizer" - } - } - }, - "persimmon": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "phi-1": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "phi-3": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "phi-3-moe": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "pixtral": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "plbart": { - "pkg": { - "0": { - "transformers": "transformers.models.plbart.tokenization_plbart.PLBartTokenizer" - } - } - }, - "phetnet-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.prophetnet.tokenization_prophetnet.ProphetNetTokenizer" - } - } - }, - "qwen2": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen2-vl": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen15-moe-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-next-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-vl": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "qwen3-vl-a": { - "pkg": { - "0": { - "transformers": "transformers.models.qwen2.tokenization_qwen2.Qwen2Tokenizer" - } - } - }, - "recurrentgemma": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "reformer-crime-and-punishment": { - "pkg": { - "0": { - "transformers": "transformers.models.reformer.tokenization_reformer.ReformerTokenizer" - } - } - }, - "rembert": { - "pkg": { - "0": { - "transformers": "transformers.models.rembert.tokenization_rembert.RemBertTokenizer" - } - } - }, - "roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "efficient-mlm-m0-0": { - "pkg": { - "0": { - "transformers": "transformers.models.roberta.tokenization_roberta.RobertaTokenizer" - } - } - }, - "roc-bert-zh": { - "pkg": { - "0": { - "transformers": "transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer" - } - } - }, - "roformer-chinese": { - "pkg": { - "0": { - "transformers": "transformers.models.roformer.tokenization_roformer.RoFormerTokenizer" - } - } - }, - "rwkv-4-pile": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "hf-seamless-m4t": { - "pkg": { - "0": { - "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" - } - } - }, - "seamless-m4t-v2": { - "pkg": { - "0": { - "transformers": "transformers.models.seamless_m4t.tokenization_seamless_m4t.SeamlessM4TTokenizer" - } - } - }, - "siglip-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.siglip.tokenization_siglip.SiglipTokenizer" - } - } - }, - "siglip2-patch16-224": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "smollm3": { - "pkg": { - "0": { - "transformers": "transformers.tokenization_utils_tokenizers.TokenizersBackend" - } - } - }, - "s2t-librispeech-asr": { - "pkg": { - "0": { - "transformers": "transformers.models.speech_to_text.tokenization_speech_to_text.Speech2TextTokenizer" - } - } - }, - "speecht5-asr": { - "pkg": { - "0": { - "transformers": "transformers.models.speecht5.tokenization_speecht5.SpeechT5Tokenizer" - } - } - }, - "splinter": { - "pkg": { - "0": { - "transformers": "transformers.models.splinter.tokenization_splinter.SplinterTokenizer" - } - } - }, - "squeezebert-uncased": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "stablelm-4e1t": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "starcoder2": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer" - } - } - }, - "switch-8": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "t5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "t5gemma-prefixlm": { - "pkg": { - "0": { - "transformers": "transformers.models.gemma.tokenization_gemma.GemmaTokenizer" - } - } - }, - "tapas-finetuned-sqa": { - "pkg": { - "0": { - "transformers": "transformers.models.tapas.tokenization_tapas.TapasTokenizer" - } - } - }, - "tvp": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "udop": { - "pkg": { - "0": { - "transformers": "transformers.models.udop.tokenization_udop.UdopTokenizer" - } - } - }, - "umt5": { - "pkg": { - "0": { - "transformers": "transformers.models.t5.tokenization_t5.T5Tokenizer" - } - } - }, - "video-llava-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "vilt-b32-mlm": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "vip-llava-hf": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "visualbert-vqa-coco-pre": { - "pkg": { - "0": { - "transformers": "transformers.models.bert.tokenization_bert.BertTokenizer" - } - } - }, - "mms-tts-eng": { - "pkg": { - "0": { - "transformers": "transformers.models.vits.tokenization_vits.VitsTokenizer" - } - } - }, - "voxtral-2507": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "wav2vec2-960h": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "wav2vec2-bert-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "wav2vec2-conformer-rel-pos": { - "pkg": { - "0": { - "transformers": "transformers.models.wav2vec2.tokenization_wav2vec2.Wav2Vec2CTCTokenizer" - } - } - }, - "whisper": { - "pkg": { - "0": { - "transformers": "transformers.models.whisper.tokenization_whisper.WhisperTokenizer" - } - } - }, - "xclip-patch32": { - "pkg": { - "0": { - "transformers": "transformers.models.clip.tokenization_clip.CLIPTokenizer" - } - } - }, - "xglm": { - "pkg": { - "0": { - "transformers": "transformers.models.xglm.tokenization_xglm.XGLMTokenizer" - } - } - }, - "xlm-mlm-en-2048": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm.tokenization_xlm.XLMTokenizer" - } - } - }, - "xlm-roberta": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "xlm-roberta-xl": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "xlnet-cased": { - "pkg": { - "0": { - "transformers": "transformers.models.xlnet.tokenization_xlnet.XLNetTokenizer" - } - } - }, - "xlstm": { - "pkg": { - "0": { - "transformers": "transformers.models.gpt_neox.tokenization_gpt_neox.GPTNeoXTokenizer" - } - } - }, - "xmod": { - "pkg": { - "0": { - "transformers": "transformers.models.xlm_roberta.tokenization_xlm_roberta.XLMRobertaTokenizer" - } - } - }, - "yoso-4096": { - "pkg": { - "0": { - "transformers": "transformers.models.albert.tokenization_albert.AlbertTokenizer" - } - } - }, - "zamba-v1": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - }, - "zamba2": { - "pkg": { - "0": { - "transformers": "transformers.models.llama.tokenization_llama.LlamaTokenizer" - } - } - } - }, - "info.vit.aimv2-patch14-224-lit": { - "*": { - "repo": "apple/aimv2-large-patch14-224-lit", - "pkg": { - "0": { - "transformers": "Aimv2Model" - } - }, - "tasks": [ - "Aimv2VisionModel", - "Aimv2Model", - "Aimv2PreTrainedModel", - "Aimv2TextModel" - ] - } - }, - "info.vit.aimv2-patch14-224": { - "*": { - "repo": "apple/aimv2-large-patch14-224", - "pkg": { - "0": { - "transformers": "Aimv2VisionModel" - } - }, - "tasks": [ - "Aimv2VisionModel", - "Aimv2Model", - "Aimv2PreTrainedModel", - "Aimv2TextModel" - ] - } - }, - "info.art.albert-xx-v2": { - "*": { - "repo": "albert/albert-xxlarge-v2", - "pkg": { - "0": { - "transformers": "AlbertModel" - } - }, - "tasks": [ - "AlbertPreTrainedModel", - "AlbertModel", - "AlbertForPreTraining", - "AlbertForMaskedLM", - "AlbertForSequenceClassification", - "AlbertForTokenClassification", - "AlbertForQuestionAnswering", - "AlbertForMultipleChoice" - ] - } - }, - "info.vit.align": { - "*": { - "repo": "kakaobrain/align-base", - "pkg": { - "0": { - "transformers": "AlignModel" - } - }, - "tasks": [ - "AlignPreTrainedModel", - "AlignTextModel", - "AlignVisionModel", - "AlignModel" - ] - } - }, - "info.vit.altclip": { - "*": { - "repo": "BAAI/AltCLIP", - "pkg": { - "0": { - "transformers": "AltCLIPModel" - } - }, - "tasks": [ - "AltCLIPPreTrainedModel", - "AltCLIPVisionModel", - "AltCLIPTextModel", - "AltCLIPModel" - ] - } - }, - "info.stst.apertus": { - "*": { - "repo": "swiss-ai/Apertus-8B", - "pkg": { - "0": { - "transformers": "ApertusModel" - } - }, - "tasks": [ - "ApertusModel", - "ApertusForCausalLM", - "ApertusForTokenClassification", - "ApertusPreTrainedModel" - ] - } - }, - "info.stst.afm": { - "*": { - "repo": "arcee-ai/AFM-4.5B", - "pkg": { - "0": { - "transformers": "ArceeModel" - } - }, - "tasks": [ - "ArceeForCausalLM", - "ArceeForQuestionAnswering", - "ArceeForSequenceClassification", - "ArceeForTokenClassification", - "ArceeModel", - "ArceePreTrainedModel" - ] - } - }, - "info.vit.aria": { - "*": { - "repo": "rhymes-ai/Aria", - "pkg": { - "0": { - "transformers": "AriaModel" - } - }, - "tasks": [ - "AriaForConditionalGeneration", - "AriaPreTrainedModel", - "AriaTextPreTrainedModel", - "AriaTextModel", - "AriaModel", - "AriaTextForCausalLM" - ] - } - }, - "info.vit.ast-finetuned-audioset-10-10-0593": { - "*": { - "repo": "MIT/ast-finetuned-audioset-10-10-0.4593", - "pkg": { - "0": { - "transformers": "ASTModel" - } - }, - "tasks": [ - "ASTForAudioClassification", - "ASTModel", - "ASTPreTrainedModel" - ] - } - }, - "info.stst.audio-flamingo-3-hf": { - "*": { - "repo": "nvidia/audio-flamingo-3-hf", - "pkg": { - "0": { - "transformers": "AudioFlamingo3ForConditionalGeneration" - } - }, - "tasks": [ - "AudioFlamingo3ForConditionalGeneration", - "AudioFlamingo3PreTrainedModel", - "AudioFlamingo3Encoder" - ] - } - }, - "info.aet.audio-flamingo-3-hf": { - "*": { - "repo": "nvidia/audio-flamingo-3-hf", - "pkg": { - "0": { - "transformers": "AudioFlamingo3Encoder" - } - }, - "tasks": [ - "AudioFlamingo3ForConditionalGeneration", - "AudioFlamingo3PreTrainedModel", - "AudioFlamingo3Encoder" - ] - } - }, - "info.stst.autoformer-tourism-monthly": { - "*": { - "repo": "huggingface/autoformer-tourism-monthly", - "pkg": { - "0": { - "transformers": "AutoformerModel" - } - }, - "tasks": [ - "AutoformerForPrediction", - "AutoformerModel", - "AutoformerPreTrainedModel" - ] - } - }, - "info.vit.aya-vision": { - "*": { - "repo": "CohereForAI/aya-vision-8b", - "pkg": { - "0": { - "transformers": "AyaVisionModel" - } - }, - "tasks": [ - "AyaVisionForConditionalGeneration", - "AyaVisionPreTrainedModel", - "AyaVisionModel" - ] - } - }, - "info.ssm.bamba-t-hf": { - "*": { - "repo": "ibm-fms/Bamba-9.8b-2.2T-hf", - "pkg": { - "0": { - "transformers": "BambaModel" - } - }, - "tasks": [ - "BambaModel", - "BambaForCausalLM", - "BambaPreTrainedModel" - ] - } - }, - "info.art.bark": { - "*": { - "repo": "suno/bark", - "pkg": { - "0": { - "transformers": "BarkModel" - } - }, - "tasks": [ - "BarkFineModel", - "BarkSemanticModel", - "BarkCoarseModel", - "BarkModel", - "BarkPreTrainedModel", - "BarkCausalModel" - ] - } - }, - "info.stst.bart": { - "*": { - "repo": "facebook/bart-large", - "pkg": { - "0": { - "transformers": "BartModel" - } - }, - "tasks": [ - "BartForCausalLM", - "BartForConditionalGeneration", - "BartForQuestionAnswering", - "BartForSequenceClassification", - "BartModel", - "BartPreTrainedModel", - "BartPretrainedModel", - "PretrainedBartModel" - ] - } - }, - "info.vit.beit-patch16-224-pt": { - "*": { - "repo": "microsoft/beit-base-patch16-224-pt22k", - "pkg": { - "0": { - "transformers": "BeitModel" - } - }, - "tasks": [ - "BeitForImageClassification", - "BeitForMaskedImageModeling", - "BeitForSemanticSegmentation", - "BeitModel", - "BeitPreTrainedModel", - "BeitBackbone" - ] - } - }, - "info.art.bert-uncased": { - "*": { - "repo": "google-bert/bert-base-uncased", - "pkg": { - "0": { - "transformers": "BertModel" - } - }, - "file_256": [ - "c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914" - ], - "layer_b3": [ - "30d7d2cc3ec9e4ba45844e005d0bbcb5887b6a0976042f73da916237dc5c4c12" - ], - "layer_256": [ - "94fd2508680ff684eff57e4a5a8ca46bf338fc356a9cf6fe8db2b84543dd7971" - ], - "tasks": [ - "BertForMaskedLM", - "BertForMultipleChoice", - "BertForNextSentencePrediction", - "BertForPreTraining", - "BertForQuestionAnswering", - "BertForSequenceClassification", - "BertForTokenClassification", - "BertLayer", - "BertLMHeadModel", - "BertModel", - "BertPreTrainedModel" - ] - } - }, - "info.art.bert-for-seq-generation-l-24-bbc-encoder": { - "*": { - "repo": "google/bert_for_seq_generation_L-24_bbc_encoder", - "pkg": { - "0": { - "transformers": "BertGenerationEncoder" - } - }, - "tasks": [ - "BertGenerationDecoder", - "BertGenerationEncoder", - "BertGenerationPreTrainedModel" - ] - } - }, - "info.art.bigbird-roberta": { - "*": { - "repo": "google/bigbird-roberta-base", - "pkg": { - "0": { - "transformers": "BigBirdModel" - } - }, - "tasks": [ - "BigBirdForCausalLM", - "BigBirdForMaskedLM", - "BigBirdForMultipleChoice", - "BigBirdForPreTraining", - "BigBirdForQuestionAnswering", - "BigBirdForSequenceClassification", - "BigBirdForTokenClassification", - "BigBirdLayer", - "BigBirdModel", - "BigBirdPreTrainedModel" - ] - } - }, - "info.stst.bigbird-pegasus-arxiv": { - "*": { - "repo": "google/bigbird-pegasus-large-arxiv", - "pkg": { - "0": { - "transformers": "BigBirdPegasusModel" - } - }, - "tasks": [ - "BigBirdPegasusForCausalLM", - "BigBirdPegasusForConditionalGeneration", - "BigBirdPegasusForQuestionAnswering", - "BigBirdPegasusForSequenceClassification", - "BigBirdPegasusModel", - "BigBirdPegasusPreTrainedModel" - ] - } - }, - "info.art.biogpt": { - "*": { - "repo": "microsoft/biogpt", - "pkg": { - "0": { - "transformers": "BioGptModel" - } - }, - "tasks": [ - "BioGptForCausalLM", - "BioGptForTokenClassification", - "BioGptForSequenceClassification", - "BioGptModel", - "BioGptPreTrainedModel" - ] - } - }, - "info.vit.bit-50": { - "*": { - "repo": "google/bit-50", - "pkg": { - "0": { - "transformers": "BitModel" - } - }, - "tasks": [ - "BitForImageClassification", - "BitModel", - "BitPreTrainedModel", - "BitBackbone" - ] - } - }, - "info.stst.bitnet-b18-4t": { - "*": { - "repo": "microsoft/bitnet-b1.58-2B-4T", - "pkg": { - "0": { - "transformers": "BitNetModel" - } - }, - "tasks": [ - "BitNetForCausalLM", - "BitNetModel", - "BitNetPreTrainedModel" - ] - } - }, - "info.stst.blenderbot": { - "*": { - "repo": "facebook/blenderbot-3B", - "pkg": { - "0": { - "transformers": "BlenderbotModel" - } - }, - "tasks": [ - "BlenderbotForCausalLM", - "BlenderbotForConditionalGeneration", - "BlenderbotModel", - "BlenderbotPreTrainedModel" - ] - } - }, - "info.vit.blip-vqa": { - "*": { - "repo": "Salesforce/blip-vqa-base", - "pkg": { - "0": { - "transformers": "BlipModel" - } - }, - "tasks": [ - "BlipModel", - "BlipPreTrainedModel", - "BlipForConditionalGeneration", - "BlipForQuestionAnswering", - "BlipVisionModel", - "BlipTextModel", - "BlipForImageTextRetrieval" - ] - } - }, - "info.vit.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2Model" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.stst.blip2-opt": { - "*": { - "repo": "Salesforce/blip2-opt-2.7b", - "pkg": { - "0": { - "transformers": "Blip2QFormerModel" - } - }, - "tasks": [ - "Blip2Model", - "Blip2VisionModelWithProjection", - "Blip2QFormerModel", - "Blip2PreTrainedModel", - "Blip2ForConditionalGeneration", - "Blip2ForImageTextRetrieval", - "Blip2VisionModel", - "Blip2TextModelWithProjection" - ] - } - }, - "info.art.bloom": { - "*": { - "repo": "bigscience/bloom", - "pkg": { - "0": { - "transformers": "BloomModel" - } - }, - "tasks": [ - "BloomForCausalLM", - "BloomModel", - "BloomPreTrainedModel", - "BloomForSequenceClassification", - "BloomForTokenClassification", - "BloomForQuestionAnswering" - ] - } - }, - "info.vit.blt": { - "*": { - "repo": "facebook/blt", - "pkg": { - "0": { - "transformers": "BltModel" - } - }, - "tasks": [ - "BltPreTrainedModel", - "BltModel", - "BltPatcher", - "BltForCausalLM" - ] - } - }, - "info.vit.bridgetower": { - "*": { - "repo": "BridgeTower/bridgetower-base", - "pkg": { - "0": { - "transformers": "BridgeTowerModel" - } - }, - "tasks": [ - "BridgeTowerForContrastiveLearning", - "BridgeTowerForImageAndTextRetrieval", - "BridgeTowerForMaskedLM", - "BridgeTowerModel", - "BridgeTowerPreTrainedModel" - ] - } - }, - "info.art.bros-uncased": { - "*": { - "repo": "jinho8345/bros-base-uncased", - "pkg": { - "0": { - "transformers": "BrosModel" - } - }, - "tasks": [ - "BrosPreTrainedModel", - "BrosModel", - "BrosForTokenClassification", - "BrosSpadeEEForTokenClassification", - "BrosSpadeELForTokenClassification" - ] - } - }, - "info.art.camembert": { - "*": { - "repo": "almanach/camembert-base", - "pkg": { - "0": { - "transformers": "CamembertModel" - } - }, - "tasks": [ - "CamembertForCausalLM", - "CamembertForMaskedLM", - "CamembertForMultipleChoice", - "CamembertForQuestionAnswering", - "CamembertForSequenceClassification", - "CamembertForTokenClassification", - "CamembertModel", - "CamembertPreTrainedModel" - ] - } - }, - "info.art.canine-s": { - "*": { - "repo": "google/canine-s", - "pkg": { - "0": { - "transformers": "CanineModel" - } - }, - "tasks": [ - "CanineForMultipleChoice", - "CanineForQuestionAnswering", - "CanineForSequenceClassification", - "CanineForTokenClassification", - "CanineLayer", - "CanineModel", - "CaninePreTrainedModel" - ] - } - }, - "info.stst.chameleon": { - "*": { - "repo": "meta/chameleon-7B", - "pkg": { - "0": { - "transformers": "ChameleonModel" - } - }, - "tasks": [ - "ChameleonForConditionalGeneration", - "ChameleonModel", - "ChameleonPreTrainedModel", - "ChameleonVQVAE" - ] - } - }, - "info.vit.chinese-clip-vit-patch16": { - "*": { - "repo": "OFA-Sys/chinese-clip-vit-base-patch16", - "pkg": { - "0": { - "transformers": "ChineseCLIPModel" - } - }, - "tasks": [ - "ChineseCLIPModel", - "ChineseCLIPPreTrainedModel", - "ChineseCLIPTextModel", - "ChineseCLIPVisionModel" - ] - } - }, - "info.vit.clap-htsat-fused": { - "*": { - "repo": "laion/clap-htsat-fused", - "pkg": { - "0": { - "transformers": "ClapModel" - } - }, - "file_256": [ - "c92b5a2bee69ff5dd05820d9e0a5cddbc9c9b9dd19a6cb3214f0cf4f29a4d1b0", - "ae69f555e7f1a2333b8e684c9fa8233f44a47bbadf76d484f941b74f74d2753d" - ], - "layer_b3": [ - "a4d26450ac399d51b9abbe37859615bb02a5cbf63521da4c7cdc549d04a2872c", - "ddf310d8eb2d4e3f61e605978675a9d3a748cad9406b9aee8335eae013e77573" - ], - "layer_256": [ - "843ba86000971d6067bfc4f3ed6dd01bd6f6726188aaa15d86b05554f4fe8481", - "27529e30442d030a28badf9d62710f4b74e38e9c4424ed169c7e0ac072f5a771" - ], - "tasks": [ - "ClapModel", - "ClapPreTrainedModel", - "ClapTextModel", - "ClapTextModelWithProjection", - "ClapAudioModel", - "ClapAudioModelWithProjection" - ] - } - }, - "info.vit.clip-vit-patch32": { - "*": { - "repo": "openai/clip-vit-base-patch32", - "pkg": { - "0": { - "transformers": "CLIPModel" - } - }, - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clipseg-rd64": { - "*": { - "repo": "CIDAS/clipseg-rd64", - "pkg": { - "0": { - "transformers": "CLIPSegModel" - } - }, - "tasks": [ - "CLIPSegModel", - "CLIPSegPreTrainedModel", - "CLIPSegTextModel", - "CLIPSegVisionModel", - "CLIPSegForImageSegmentation" - ] - } - }, - "info.vit.clvp-dev": { - "*": { - "repo": "susnato/clvp_dev", - "pkg": { - "0": { - "transformers": "ClvpModelForConditionalGeneration" - } - }, - "tasks": [ - "ClvpModelForConditionalGeneration", - "ClvpForCausalLM", - "ClvpModel", - "ClvpPreTrainedModel", - "ClvpEncoder", - "ClvpDecoder" - ] - } - }, - "info.stst.llama-2-hf": { - "*": { - "repo": "meta-llama/Llama-2-7b-hf", - "pkg": { - "0": { - "transformers": "LlamaModel" - } - }, - "tasks": [ - "LlamaForCausalLM", - "LlamaModel", - "LlamaPreTrainedModel", - "LlamaForSequenceClassification", - "LlamaForQuestionAnswering", - "LlamaForTokenClassification" - ] - } - }, - "info.art.codegen-mono": { - "*": { - "repo": "Salesforce/codegen-2B-mono", - "pkg": { - "0": { - "transformers": "CodeGenModel" - } - }, - "tasks": [ - "CodeGenForCausalLM", - "CodeGenModel", - "CodeGenPreTrainedModel" - ] - } - }, - "info.stst.c4ai-command-r-v01": { - "*": { - "repo": "CohereForAI/c4ai-command-r-v01", - "pkg": { - "0": { - "transformers": "CohereModel" - } - }, - "tasks": [ - "CohereForCausalLM", - "CohereModel", - "CoherePreTrainedModel" - ] - } - }, - "info.vit.command-a-vision-07-2025": { - "*": { - "repo": "CohereLabs/command-a-vision-07-2025", - "pkg": { - "0": { - "transformers": "Cohere2VisionModel" - } - }, - "tasks": [ - "Cohere2VisionForConditionalGeneration", - "Cohere2VisionPreTrainedModel", - "Cohere2VisionModel" - ] - } - }, - "info.detr.conditional-detr-resnet-50": { - "*": { - "repo": "microsoft/conditional-detr-resnet-50", - "pkg": { - "0": { - "transformers": "ConditionalDetrModel" - } - }, - "tasks": [ - "ConditionalDetrForObjectDetection", - "ConditionalDetrForSegmentation", - "ConditionalDetrModel", - "ConditionalDetrPreTrainedModel" - ] - } - }, - "info.art.conv-bert": { - "*": { - "repo": "YituTech/conv-bert-base", - "pkg": { - "0": { - "transformers": "ConvBertModel" - } - }, - "tasks": [ - "ConvBertForMaskedLM", - "ConvBertForMultipleChoice", - "ConvBertForQuestionAnswering", - "ConvBertForSequenceClassification", - "ConvBertForTokenClassification", - "ConvBertLayer", - "ConvBertModel", - "ConvBertPreTrainedModel" - ] - } - }, - "info.vit.convnext-224": { - "*": { - "repo": "facebook/convnext-tiny-224", - "pkg": { - "0": { - "transformers": "ConvNextModel" - } - }, - "tasks": [ - "ConvNextForImageClassification", - "ConvNextModel", - "ConvNextPreTrainedModel", - "ConvNextBackbone" - ] - } - }, - "info.vit.convnextv2-224": { - "*": { - "repo": "facebook/convnextv2-tiny-1k-224", - "pkg": { - "0": { - "transformers": "ConvNextV2Model" - } - }, - "tasks": [ - "ConvNextV2ForImageClassification", - "ConvNextV2Model", - "ConvNextV2PreTrainedModel", - "ConvNextV2Backbone" - ] - } - }, - "info.stst.cpm-ant": { - "*": { - "repo": "openbmb/cpm-ant-10b", - "pkg": { - "0": { - "transformers": "CpmAntModel" - } - }, - "tasks": [ - "CpmAntForCausalLM", - "CpmAntModel", - "CpmAntPreTrainedModel" - ] - } - }, - "info.stst.csm": { - "*": { - "repo": "sesame/csm-1b", - "pkg": { - "0": { - "transformers": "CsmForConditionalGeneration" - } - }, - "tasks": [ - "CsmPreTrainedModel", - "CsmBackboneModel", - "CsmDepthDecoderModel", - "CsmDepthDecoderForCausalLM", - "CsmForConditionalGeneration" - ] - } - }, - "info.art.ctrl": { - "*": { - "repo": "Salesforce/ctrl", - "pkg": { - "0": { - "transformers": "CTRLModel" - } - }, - "tasks": [ - "CTRLForSequenceClassification", - "CTRLLMHeadModel", - "CTRLModel", - "CTRLPreTrainedModel" - ] - } - }, - "info.vit.cvt-13": { - "*": { - "repo": "microsoft/cvt-13", - "pkg": { - "0": { - "transformers": "CvtModel" - } - }, - "tasks": [ - "CvtForImageClassification", - "CvtModel", - "CvtPreTrainedModel" - ] - } - }, - "info.art.cwm": { - "*": { - "repo": "facebook/cwm", - "pkg": { - "0": { - "transformers": "CwmModel" - } - }, - "tasks": [ - "CwmPreTrainedModel", - "CwmModel", - "CwmForCausalLM" - ] - } - }, - "info.detr.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine-xlarge-coco", - "pkg": { - "0": { - "transformers": "DFineModel" - } - }, - "tasks": [ - "DFineModel", - "DFinePreTrainedModel", - "DFineForObjectDetection" - ] - } - }, - "info.detr.dab-detr": { - "*": { - "repo": "IDEA-Research/dab-detr-resnet-50", - "pkg": { - "0": { - "transformers": "DabDetrModel" - } - }, - "tasks": [ - "DabDetrForObjectDetection", - "DabDetrModel", - "DabDetrPreTrainedModel" - ] - } - }, - "info.gan.dac": { - "*": { - "repo": "descript/dac_16khz", - "pkg": { - "0": { - "transformers": "DacModel" - } - }, - "tasks": [ - "DacModel", - "DacPreTrainedModel" - ] - } - }, - "info.aet.data2vec-audio-960h": { - "*": { - "repo": "facebook/data2vec-audio-base-960h", - "pkg": { - "0": { - "transformers": "Data2VecAudioModel" - } - }, - "tasks": [ - "Data2VecAudioForAudioFrameClassification", - "Data2VecAudioForCTC", - "Data2VecAudioForSequenceClassification", - "Data2VecAudioForXVector", - "Data2VecAudioModel", - "Data2VecAudioPreTrainedModel" - ] - } - }, - "info.art.data2vec-text": { - "*": { - "repo": "facebook/data2vec-text-base", - "pkg": { - "0": { - "transformers": "Data2VecTextModel" - } - }, - "tasks": [ - "Data2VecTextForCausalLM", - "Data2VecTextForMaskedLM", - "Data2VecTextForMultipleChoice", - "Data2VecTextForQuestionAnswering", - "Data2VecTextForSequenceClassification", - "Data2VecTextForTokenClassification", - "Data2VecTextModel", - "Data2VecTextPreTrainedModel" - ] - } - }, - "info.vit.data2vec-vision": { - "*": { - "repo": "facebook/data2vec-vision-base", - "pkg": { - "0": { - "transformers": "Data2VecVisionModel" - } - }, - "tasks": [ - "Data2VecVisionForImageClassification", - "Data2VecVisionForSemanticSegmentation", - "Data2VecVisionModel", - "Data2VecVisionPreTrainedModel" - ] - } - }, - "info.stst.dbrx": { - "*": { - "repo": "databricks/dbrx-instruct", - "pkg": { - "0": { - "transformers": "DbrxModel" - } - }, - "tasks": [ - "DbrxForCausalLM", - "DbrxModel", - "DbrxPreTrainedModel" - ] - } - }, - "info.art.deberta": { - "*": { - "repo": "microsoft/deberta-base", - "pkg": { - "0": { - "transformers": "DebertaModel" - } - }, - "tasks": [ - "DebertaForMaskedLM", - "DebertaForQuestionAnswering", - "DebertaForSequenceClassification", - "DebertaForTokenClassification", - "DebertaModel", - "DebertaPreTrainedModel" - ] - } - }, - "info.art.deberta-v2-x": { - "*": { - "repo": "microsoft/deberta-v2-xlarge", - "pkg": { - "0": { - "transformers": "DebertaV2Model" - } - }, - "tasks": [ - "DebertaV2ForMaskedLM", - "DebertaV2ForMultipleChoice", - "DebertaV2ForQuestionAnswering", - "DebertaV2ForSequenceClassification", - "DebertaV2ForTokenClassification", - "DebertaV2Model", - "DebertaV2PreTrainedModel" - ] - } - }, - "info.art.decision-transformer-gym-hopper": { - "*": { - "repo": "edbeeching/decision-transformer-gym-hopper-medium", - "pkg": { - "0": { - "transformers": "DecisionTransformerModel" - } - }, - "tasks": [ - "DecisionTransformerGPT2Model", - "DecisionTransformerGPT2PreTrainedModel", - "DecisionTransformerModel", - "DecisionTransformerPreTrainedModel" - ] - } - }, - "info.moe.deepseek-v2-lite": { - "*": { - "repo": "deepseek-ai/DeepSeek-V2-Lite", - "pkg": { - "0": { - "transformers": "DeepseekV2Model" - } - }, - "tasks": [ - "DeepseekV2PreTrainedModel", - "DeepseekV2Model", - "DeepseekV2ForCausalLM", - "DeepseekV2ForSequenceClassification" - ] - } - }, - "info.moe.deepseek-v3": { - "*": { - "repo": "bzantium/tiny-deepseek-v3", - "pkg": { - "0": { - "transformers": "DeepseekV3Model" - } - }, - "tasks": [ - "DeepseekV3PreTrainedModel", - "DeepseekV3Model", - "DeepseekV3ForCausalLM", - "DeepseekV3ForSequenceClassification", - "DeepseekV3ForTokenClassification" - ] - } - }, - "info.vit.deepseek-vl-chat": { - "*": { - "repo": "deepseek-community/deepseek-vl-1.3b-chat", - "pkg": { - "0": { - "transformers": "DeepseekVLModel" - } - }, - "tasks": [ - "DeepseekVLPreTrainedModel", - "DeepseekVLModel", - "DeepseekVLForConditionalGeneration" - ] - } - }, - "info.detr.deformable-detr": { - "*": { - "repo": "SenseTime/deformable-detr", - "pkg": { - "0": { - "transformers": "DeformableDetrModel" - } - }, - "tasks": [ - "DeformableDetrForObjectDetection", - "DeformableDetrModel", - "DeformableDetrPreTrainedModel" - ] - } - }, - "info.vit.deit-distilled-patch16-224": { - "*": { - "repo": "facebook/deit-base-distilled-patch16-224", - "pkg": { - "0": { - "transformers": "DeiTModel" - } - }, - "tasks": [ - "DeiTForImageClassification", - "DeiTForImageClassificationWithTeacher", - "DeiTForMaskedImageModeling", - "DeiTModel", - "DeiTPreTrainedModel" - ] - } - }, - "info.vit.depth": { - "*": { - "repo": "apple/DepthPro", - "pkg": { - "0": { - "transformers": "DepthProModel" - } - }, - "tasks": [ - "DepthProPreTrainedModel", - "DepthProModel", - "DepthProForDepthEstimation" - ] - } - }, - "info.detr.detr-resnet-50": { - "*": { - "repo": "facebook/detr-resnet-50", - "pkg": { - "0": { - "transformers": "DetrModel" - } - }, - "tasks": [ - "DetrForObjectDetection", - "DetrForSegmentation", - "DetrModel", - "DetrPreTrainedModel" - ] - } - }, - "info.stst.dia": { - "*": { - "repo": "nari-labs/Dia-1.6B", - "pkg": { - "0": { - "transformers": "DiaModel" - } - }, - "tasks": [ - "DiaModel", - "DiaPreTrainedModel", - "DiaForConditionalGeneration" - ] - } - }, - "info.stst.diffllama-handcut": { - "*": { - "repo": "kajuma/DiffLlama-0.3B-handcut", - "pkg": { - "0": { - "transformers": "DiffLlamaModel" - } - }, - "tasks": [ - "DiffLlamaPreTrainedModel", - "DiffLlamaModel", - "DiffLlamaForCausalLM", - "DiffLlamaForSequenceClassification", - "DiffLlamaForQuestionAnswering", - "DiffLlamaForTokenClassification" - ] - } - }, - "info.gan.dinat-in-224": { - "*": { - "repo": "shi-labs/dinat-mini-in1k-224", - "pkg": { - "0": { - "transformers": "DinatModel" - } - }, - "tasks": [ - "DinatForImageClassification", - "DinatModel", - "DinatPreTrainedModel", - "DinatBackbone" - ] - } - }, - "info.vit.dinov2-patch16-224": { - "*": { - "repo": "google/dinov2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Dinov2Model" - } - }, - "tasks": [ - "Dinov2ForImageClassification", - "Dinov2Model", - "Dinov2PreTrainedModel", - "Dinov2Backbone" - ] - } - }, - "info.vit.dinov2-with-registers": { - "*": { - "repo": "facebook/dinov2-with-registers-base", - "pkg": { - "0": { - "transformers": "Dinov2WithRegistersModel" - } - }, - "tasks": [ - "Dinov2WithRegistersPreTrainedModel", - "Dinov2WithRegistersModel", - "Dinov2WithRegistersForImageClassification", - "Dinov2WithRegistersBackbone" - ] - } - }, - "info.vit.dinov3-convnext-pretrain-lvd": { - "*": { - "repo": "facebook/dinov3-convnext-tiny-pretrain-lvd1689m", - "pkg": { - "0": { - "transformers": "DINOv3ConvNextModel" - } - }, - "tasks": [ - "DINOv3ConvNextModel", - "DINOv3ConvNextPreTrainedModel", - "DINOv3ConvNextBackbone" - ] - } - }, - "info.vit.dinov3-vits16-pretrain-lvd": { - "*": { - "repo": "facebook/dinov3-vits16-pretrain-lvd1689m", - "pkg": { - "0": { - "transformers": "DINOv3ViTModel" - } - }, - "tasks": [ - "DINOv3ViTModel", - "DINOv3ViTPreTrainedModel", - "DINOv3ViTBackbone" - ] - } - }, - "info.art.distilbert-uncased": { - "*": { - "repo": "distilbert-base-uncased", - "pkg": { - "0": { - "transformers": "DistilBertModel" - } - }, - "tasks": [ - "DistilBertForMaskedLM", - "DistilBertForMultipleChoice", - "DistilBertForQuestionAnswering", - "DistilBertForSequenceClassification", - "DistilBertForTokenClassification", - "DistilBertModel", - "DistilBertPreTrainedModel" - ] - } - }, - "info.moe.doge": { - "*": { - "repo": "SmallDoge/Doge-320M", - "pkg": { - "0": { - "transformers": "DogeModel" - } - }, - "tasks": [ - "DogeForCausalLM", - "DogeModel", - "DogePreTrainedModel", - "DogeForSequenceClassification" - ] - } - }, - "info.vit.donut": { - "*": { - "repo": "naver-clova-ix/donut-base", - "pkg": { - "0": { - "transformers": "DonutSwinModel" - } - }, - "tasks": [ - "DonutSwinModel", - "DonutSwinPreTrainedModel", - "DonutSwinForImageClassification" - ] - } - }, - "info.moe.dots-llm1": { - "*": { - "repo": "rednote-hilab/dots.llm1.base", - "pkg": { - "0": { - "transformers": "Dots1Model" - } - }, - "tasks": [ - "Dots1PreTrainedModel", - "Dots1Model", - "Dots1ForCausalLM" - ] - } - }, - "info.vit.dpr-ctx-encoder-single-nq": { - "*": { - "repo": "facebook/dpr-ctx_encoder-single-nq-base", - "pkg": { - "0": { - "transformers": "DPRQuestionEncoder" - } - }, - "tasks": [ - "DPRContextEncoder", - "DPRPretrainedContextEncoder", - "DPRPreTrainedModel", - "DPRPretrainedQuestionEncoder", - "DPRPretrainedReader", - "DPRQuestionEncoder", - "DPRReader" - ] - } - }, - "info.detr.dpt": { - "*": { - "repo": "Intel/dpt-large", - "pkg": { - "0": { - "transformers": "DPTModel" - } - }, - "tasks": [ - "DPTForDepthEstimation", - "DPTForSemanticSegmentation", - "DPTModel", - "DPTPreTrainedModel" - ] - } - }, - "info.vit.edgetam1-hiera": { - "*": { - "repo": "facebook/edgetam.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "EdgeTamModel" - } - }, - "tasks": [ - "EdgeTamModel", - "EdgeTamVisionModel", - "EdgeTamPreTrainedModel" - ] - } - }, - "info.vit.edgetam": { - "*": { - "repo": "facebook/EdgeTAM", - "pkg": { - "0": { - "transformers": "EdgeTamVideoModel" - } - }, - "tasks": [ - "EdgeTamVideoModel", - "EdgeTamVideoInferenceSession", - "EdgeTamVideoPreTrainedModel" - ] - } - }, - "info.vit.efficientloftr": { - "*": { - "repo": "zju-community/efficientloftr", - "pkg": { - "0": { - "transformers": "EfficientLoFTRModel" - } - }, - "tasks": [ - "EfficientLoFTRPreTrainedModel", - "EfficientLoFTRModel", - "EfficientLoFTRForKeypointMatching" - ] - } - }, - "info.vit.efficientnet-b7": { - "*": { - "repo": "google/efficientnet-b7", - "pkg": { - "0": { - "transformers": "EfficientNetModel" - } - }, - "tasks": [ - "EfficientNetForImageClassification", - "EfficientNetModel", - "EfficientNetPreTrainedModel" - ] - } - }, - "info.art.electra-discriminator": { - "*": { - "repo": "google/electra-small-discriminator", - "pkg": { - "0": { - "transformers": "ElectraModel" - } - }, - "tasks": [ - "ElectraForCausalLM", - "ElectraForMaskedLM", - "ElectraForMultipleChoice", - "ElectraForPreTraining", - "ElectraForQuestionAnswering", - "ElectraForSequenceClassification", - "ElectraForTokenClassification", - "ElectraModel", - "ElectraPreTrainedModel" - ] - } - }, - "info.art.emu3-chat-hf": { - "*": { - "repo": "Emu3-community/Emu3-Chat-hf", - "pkg": { - "0": { - "transformers": "Emu3Model" - } - }, - "tasks": [ - "Emu3ForConditionalGeneration", - "Emu3ForCausalLM", - "Emu3TextModel", - "Emu3PreTrainedModel", - "Emu3VQVAE", - "Emu3Model" - ] - } - }, - "info.gan.encodec": { - "*": { - "repo": "facebook/encodec_24khz", - "pkg": { - "0": { - "transformers": "EncodecModel" - } - }, - "tasks": [ - "EncodecModel", - "EncodecPreTrainedModel" - ] - } - }, - "info.art.ernie-3-zh": { - "*": { - "repo": "nghuyong/ernie-3.0-base-zh", - "pkg": { - "0": { - "transformers": "ErnieModel" - } - }, - "tasks": [ - "ErnieForCausalLM", - "ErnieForMaskedLM", - "ErnieForMultipleChoice", - "ErnieForNextSentencePrediction", - "ErnieForPreTraining", - "ErnieForQuestionAnswering", - "ErnieForSequenceClassification", - "ErnieForTokenClassification", - "ErnieModel", - "ErniePreTrainedModel" - ] - } - }, - "info.stst.ernie-45-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-0.3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5Model" - } - }, - "tasks": [ - "Ernie4_5ForCausalLM", - "Ernie4_5Model", - "Ernie4_5PreTrainedModel" - ] - } - }, - "info.moe.ernie-4-a-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-21B-A3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5_MoeModel" - } - }, - "tasks": [ - "Ernie4_5_MoeForCausalLM", - "Ernie4_5_MoeModel", - "Ernie4_5_MoePreTrainedModel" - ] - } - }, - "info.vit.ernie-4-vl-a-pt": { - "*": { - "repo": "baidu/ERNIE-4.5-VL-28B-A3B-PT", - "pkg": { - "0": { - "transformers": "Ernie4_5_VL_MoeModel" - } - }, - "tasks": [ - "Ernie4_5_VL_MoePreTrainedModel", - "Ernie4_5_VL_MoeForConditionalGeneration", - "Ernie4_5_VL_MoeModel", - "Ernie4_5_VL_MoeTextModel", - "Ernie4_5_VL_MoeVisionTransformerPretrainedModel", - "Ernie4_5_VL_MoeVariableResolutionResamplerModel" - ] - } - }, - "info.aet.esm": { - "*": { - "repo": "facebook/esm-1b", - "pkg": { - "0": { - "transformers": "EsmModel" - } - }, - "tasks": [ - "EsmForMaskedLM", - "EsmForSequenceClassification", - "EsmForTokenClassification", - "EsmModel", - "EsmPreTrainedModel" - ] - } - }, - "info.stst.evolla-hf": { - "*": { - "repo": "westlake-repl/Evolla-10B-hf", - "pkg": { - "0": { - "transformers": "EvollaModel" - } - }, - "tasks": [ - "EvollaForProteinText2Text", - "EvollaModel", - "EvollaPreTrainedModel" - ] - } - }, - "info.stst.exaone-4": { - "*": { - "repo": "LGAI-EXAONE/EXAONE-4.0-32B", - "pkg": { - "0": { - "transformers": "Exaone4Model" - } - }, - "tasks": [ - "Exaone4PreTrainedModel", - "Exaone4Model", - "Exaone4ForCausalLM", - "Exaone4ForSequenceClassification", - "Exaone4ForTokenClassification", - "Exaone4ForQuestionAnswering" - ] - } - }, - "info.ssm.falcon": { - "*": { - "repo": "tiiuae/falcon-7b", - "pkg": { - "0": { - "transformers": "FalconModel" - } - }, - "tasks": [ - "FalconForCausalLM", - "FalconModel", - "FalconPreTrainedModel", - "FalconForSequenceClassification", - "FalconForTokenClassification", - "FalconForQuestionAnswering" - ] - } - }, - "info.ssm.falconh1-t-hf": { - "*": { - "repo": "tiiuae/Falcon-H1-34B-Instruct", - "pkg": { - "0": { - "transformers": "FalconH1Model" - } - }, - "tasks": [ - "FalconH1Model", - "FalconH1ForCausalLM", - "FalconH1PreTrainedModel" - ] - } - }, - "info.ssm.falcon-mamba": { - "*": { - "repo": "tiiuae/falcon-mamba-7b", - "pkg": { - "0": { - "transformers": "FalconMambaModel" - } - }, - "tasks": [ - "FalconMambaForCausalLM", - "FalconMambaModel", - "FalconMambaPreTrainedModel", - "FalconMambaCache" - ] - } - }, - "info.vit.fastvlm": { - "*": { - "repo": "KamilaMila/FastVLM-7B", - "pkg": { - "0": { - "transformers": "FastVlmModel" - } - }, - "tasks": [ - "FastVlmForConditionalGeneration", - "FastVlmModel", - "FastVlmPreTrainedModel" - ] - } - }, - "info.aet.fastspeech2-conformer": { - "*": { - "repo": "espnet/fastspeech2_conformer", - "pkg": { - "0": { - "transformers": "FastSpeech2ConformerModel" - } - }, - "tasks": [ - "FastSpeech2ConformerWithHifiGan", - "FastSpeech2ConformerHifiGan", - "FastSpeech2ConformerModel", - "FastSpeech2ConformerPreTrainedModel" - ] - } - }, - "info.stst.fastspeech2-conformer": { - "*": { - "repo": "espnet/fastspeech2_conformer", - "pkg": { - "0": { - "transformers": "FastSpeech2ConformerWithHifiGan" - } - }, - "tasks": [ - "FastSpeech2ConformerWithHifiGan", - "FastSpeech2ConformerHifiGan", - "FastSpeech2ConformerModel", - "FastSpeech2ConformerPreTrainedModel" - ] - } - }, - "info.art.flaubert-uncased": { - "*": { - "repo": "flaubert/flaubert_base_uncased", - "pkg": { - "0": { - "transformers": "FlaubertModel" - } - }, - "tasks": [ - "FlaubertForMultipleChoice", - "FlaubertForQuestionAnswering", - "FlaubertForQuestionAnsweringSimple", - "FlaubertForSequenceClassification", - "FlaubertForTokenClassification", - "FlaubertModel", - "FlaubertWithLMHeadModel", - "FlaubertPreTrainedModel" - ] - } - }, - "info.vit.flava": { - "*": { - "repo": "facebook/flava-full", - "pkg": { - "0": { - "transformers": "FlavaModel" - } - }, - "tasks": [ - "FlavaForPreTraining", - "FlavaImageCodebook", - "FlavaImageModel", - "FlavaModel", - "FlavaMultimodalModel", - "FlavaPreTrainedModel", - "FlavaTextModel" - ] - } - }, - "info.moe.flexolmo-7x-1t": { - "*": { - "repo": "allenai/FlexOlmo-7x7B-1T", - "pkg": { - "0": { - "transformers": "FlexOlmoModel" - } - }, - "tasks": [ - "FlexOlmoForCausalLM", - "FlexOlmoModel", - "FlexOlmoPreTrainedModel" - ] - } - }, - "info.vit.florence-2": { - "*": { - "repo": "florence-community/Florence-2-base", - "pkg": { - "0": { - "transformers": "Florence2Model" - } - }, - "tasks": [ - "Florence2Model", - "Florence2ForConditionalGeneration", - "Florence2PreTrainedModel", - "Florence2VisionBackbone", - "Florence2VisionPreTrainedModel" - ] - } - }, - "info.art.fnet": { - "*": { - "repo": "google/fnet-base", - "pkg": { - "0": { - "transformers": "FNetModel" - } - }, - "tasks": [ - "FNetForMaskedLM", - "FNetForMultipleChoice", - "FNetForNextSentencePrediction", - "FNetForPreTraining", - "FNetForQuestionAnswering", - "FNetForSequenceClassification", - "FNetForTokenClassification", - "FNetLayer", - "FNetModel", - "FNetPreTrainedModel" - ] - } - }, - "info.vit.focalnet": { - "*": { - "repo": "microsoft/focalnet-tiny", - "pkg": { - "0": { - "transformers": "FocalNetModel" - } - }, - "tasks": [ - "FocalNetForImageClassification", - "FocalNetForMaskedImageModeling", - "FocalNetBackbone", - "FocalNetModel", - "FocalNetPreTrainedModel" - ] - } - }, - "info.stst.wmt19-en-ru": { - "*": { - "repo": "facebook/wmt19-en-ru", - "pkg": { - "0": { - "transformers": "FSMTModel" - } - }, - "tasks": [ - "FSMTForConditionalGeneration", - "FSMTModel", - "PretrainedFSMTModel" - ] - } - }, - "info.aet.funnel": { - "*": { - "repo": "funnel-transformer/small", - "pkg": { - "0": { - "transformers": "FunnelModel" - } - }, - "tasks": [ - "FunnelBaseModel", - "FunnelForMaskedLM", - "FunnelForMultipleChoice", - "FunnelForPreTraining", - "FunnelForQuestionAnswering", - "FunnelForSequenceClassification", - "FunnelForTokenClassification", - "FunnelModel", - "FunnelPreTrainedModel" - ] - } - }, - "info.vit.fuyu": { - "*": { - "repo": "adept/fuyu-8b", - "pkg": { - "0": { - "transformers": "FuyuModel" - } - }, - "tasks": [ - "FuyuForCausalLM", - "FuyuPreTrainedModel", - "FuyuModel" - ] - } - }, - "info.stst.gemma": { - "*": { - "repo": "google/gemma-7b", - "pkg": { - "0": { - "transformers": "GemmaModel" - } - }, - "file_256": [ - "01676b4c6e765f737a5e9854a315de3887e939c370cae116d505777729099a68" - ], - "layer_b3": [ - "438d82c867240f194a4e15798eef2886a911c8f57fa2d9f4ffad1d56e7bd1ccf", - "1de38e09f5f2c5345de48b8cd4dddcfff3e341cc0059752446e186b3863f0981" - ], - "layer_256": [ - "e4835a72d582b4ae066d6ff0519f2ee9f8b21fb02e8c28d8eaa317f8d1e9ea75", - "1657c7180b48672004f4463308dfdd56d92eedeb23d1408ea766985ca208e5aa" - ], - "tasks": [ - "GemmaModel", - "GemmaForCausalLM", - "GemmaForSequenceClassification", - "GemmaForTokenClassification", - "GemmaPreTrainedModel" - ] - } - }, - "info.stst.gemma2": { - "*": { - "repo": "google/gemma-2-9b", - "pkg": { - "0": { - "transformers": "Gemma2Model" - } - }, - "file_256": [ - "e909230aabafad02d097c7dc02f2ae062b4e6b0593477c1f07679d277e09ce71", - "d61628bc793240439e608c5ae744f55ec8770f684abb63602648a24cb6da60bc" - ], - "layer_b3": [ - "55a3c812ac0832d154867f5927365bcc776926e48e65f7f35a81fc11f4bb81da", - "543572889beb25cad83a43ce70cdd255d2c82951d6595e8c97ff62fd05871c99" - ], - "layer_256": [ - "a0d820c39578cf888f398579d9a00d69b31c81e049795ba70008dad8fe5b3a33", - "abc83b04a04467579ea1952a7efbdd252b8641ac0e2a6a9be2a5a73e371111d6" - ], - "tasks": [ - "Gemma2ForCausalLM", - "Gemma2Model", - "Gemma2PreTrainedModel", - "Gemma2ForSequenceClassification", - "Gemma2ForTokenClassification" - ] - } - }, - "info.vit.gemma-3": { - "*": { - "repo": "google/gemma-3-4b-it", - "pkg": { - "0": { - "transformers": "Gemma3Model" - } - }, - "tasks": [ - "Gemma3PreTrainedModel", - "Gemma3TextModel", - "Gemma3ForCausalLM", - "Gemma3ForConditionalGeneration", - "Gemma3Model", - "Gemma3ForSequenceClassification", - "Gemma3TextForSequenceClassification" - ] - } - }, - "info.stst.gemma3-text": { - "*": { - "repo": "google/gemma-3-12b-it", - "pkg": { - "0": { - "transformers": "Gemma3TextModel" - } - }, - "tasks": [ - "Gemma3PreTrainedModel", - "Gemma3TextModel", - "Gemma3ForCausalLM", - "Gemma3ForConditionalGeneration", - "Gemma3Model", - "Gemma3ForSequenceClassification", - "Gemma3TextForSequenceClassification" - ] - } - }, - "info.vit.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nModel" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.art.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nAudioEncoder" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.stst.gemma-3n-e": { - "*": { - "repo": "google/gemma-3n-E4B", - "pkg": { - "0": { - "transformers": "Gemma3nTextModel" - } - }, - "tasks": [ - "Gemma3nAudioEncoder", - "Gemma3nForCausalLM", - "Gemma3nForConditionalGeneration", - "Gemma3nModel", - "Gemma3nPreTrainedModel", - "Gemma3nTextModel" - ] - } - }, - "info.vit.git": { - "*": { - "repo": "microsoft/git-base", - "pkg": { - "0": { - "transformers": "GitModel" - } - }, - "tasks": [ - "GitForCausalLM", - "GitModel", - "GitPreTrainedModel", - "GitVisionModel" - ] - } - }, - "info.stst.glm-4-chat": { - "*": { - "repo": "zai-org/glm-4-9b-chat", - "pkg": { - "0": { - "transformers": "GlmModel" - } - }, - "tasks": [ - "GlmPreTrainedModel", - "GlmModel", - "GlmForCausalLM", - "GlmForSequenceClassification", - "GlmForTokenClassification" - ] - } - }, - "info.stst.glm-4-0414": { - "*": { - "repo": "zai-org/GLM-4-9B-0414", - "pkg": { - "0": { - "transformers": "Glm4Model" - } - }, - "tasks": [ - "Glm4PreTrainedModel", - "Glm4Model", - "Glm4ForCausalLM", - "Glm4ForSequenceClassification", - "Glm4ForTokenClassification" - ] - } - }, - "info.vit.glm-4v-thinking": { - "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", - "pkg": { - "0": { - "transformers": "Glm46VModel" - } - }, - "tasks": [ - "Glm46VModel", - "Glm46VPreTrainedModel", - "Glm46VForConditionalGeneration" - ] - } - }, - "info.moe.glm-4-a": { - "*": { - "repo": "zai-org/GLM-4.5-Air", - "pkg": { - "0": { - "transformers": "Glm4MoeModel" - } - }, - "tasks": [ - "Glm4MoePreTrainedModel", - "Glm4MoeModel", - "Glm4MoeForCausalLM" - ] - } - }, - "info.vit.glm-4v": { - "*": { - "repo": "zai-org/GLM-4.5V", - "pkg": { - "0": { - "transformers": "Glm4vMoeModel" - } - }, - "tasks": [ - "Glm4vMoeForConditionalGeneration", - "Glm4vMoeModel", - "Glm4vMoePreTrainedModel", - "Glm4vMoeTextModel", - "Glm4vMoeVisionModel" - ] - } - }, - "info.moe.glm-4v": { - "*": { - "repo": "zai-org/GLM-4.5V", - "pkg": { - "0": { - "transformers": "Glm4vMoeTextModel" - } - }, - "tasks": [ - "Glm4vMoeForConditionalGeneration", - "Glm4vMoeModel", - "Glm4vMoePreTrainedModel", - "Glm4vMoeTextModel", - "Glm4vMoeVisionModel" - ] - } - }, - "info.stst.glm-4v-thinking": { - "*": { - "repo": "zai-org/GLM-4.1V-9B-Thinking", - "pkg": { - "0": { - "transformers": "Glm4vTextModel" - } - }, - "tasks": [ - "Glm4vForConditionalGeneration", - "Glm4vModel", - "Glm4vPreTrainedModel", - "Glm4vTextModel", - "Glm4vVisionModel" - ] - } - }, - "info.stst.glm-asr-nano-2512": { - "*": { - "repo": "zai-org/GLM-ASR-Nano-2512", - "pkg": { - "0": { - "transformers": "GlmAsrForConditionalGeneration" - } - }, - "tasks": [ - "GlmAsrEncoder", - "GlmAsrForConditionalGeneration", - "GlmAsrPreTrainedModel" - ] - } - }, - "info.vit.glpn-kitti": { - "*": { - "repo": "vinvino02/glpn-kitti", - "pkg": { - "0": { - "transformers": "GLPNModel" - } - }, - "tasks": [ - "GLPNForDepthEstimation", - "GLPNLayer", - "GLPNModel", - "GLPNPreTrainedModel" - ] - } - }, - "info.vit.got-ocr-2-hf": { - "*": { - "repo": "stepfun-ai/GOT-OCR-2.0-hf", - "pkg": { - "0": { - "transformers": "GotOcr2Model" - } - }, - "tasks": [ - "GotOcr2PreTrainedModel", - "GotOcr2Model", - "GotOcr2ForConditionalGeneration" - ] - } - }, - "info.art.gpt2": { - "*": { - "repo": "openai-community/gpt2", - "pkg": { - "0": { - "transformers": "GPT2Model" - } - }, - "tasks": [ - "GPT2DoubleHeadsModel", - "GPT2ForQuestionAnswering", - "GPT2ForSequenceClassification", - "GPT2ForTokenClassification", - "GPT2LMHeadModel", - "GPT2Model", - "GPT2PreTrainedModel" - ] - } - }, - "info.art.gpt-bigcode-santacoder": { - "*": { - "repo": "bigcode/gpt_bigcode-santacoder", - "pkg": { - "0": { - "transformers": "GPTBigCodeModel" - } - }, - "tasks": [ - "GPTBigCodeForSequenceClassification", - "GPTBigCodeForTokenClassification", - "GPTBigCodeForCausalLM", - "GPTBigCodeModel", - "GPTBigCodePreTrainedModel" - ] - } - }, - "info.art.gpt-neo": { - "*": { - "repo": "EleutherAI/gpt-neo-1.3B", - "pkg": { - "0": { - "transformers": "GPTNeoModel" - } - }, - "tasks": [ - "GPTNeoForCausalLM", - "GPTNeoForQuestionAnswering", - "GPTNeoForSequenceClassification", - "GPTNeoForTokenClassification", - "GPTNeoModel", - "GPTNeoPreTrainedModel" - ] - } - }, - "info.stst.gpt-neox": { - "*": { - "repo": "EleutherAI/gpt-neox-20b", - "pkg": { - "0": { - "transformers": "GPTNeoXModel" - } - }, - "tasks": [ - "GPTNeoXForCausalLM", - "GPTNeoXForQuestionAnswering", - "GPTNeoXForSequenceClassification", - "GPTNeoXForTokenClassification", - "GPTNeoXLayer", - "GPTNeoXModel", - "GPTNeoXPreTrainedModel" - ] - } - }, - "info.stst.gpt-neox-japanese": { - "*": { - "repo": "abeja/gpt-neox-japanese-2.7b", - "pkg": { - "0": { - "transformers": "GPTNeoXJapaneseModel" - } - }, - "tasks": [ - "GPTNeoXJapaneseForCausalLM", - "GPTNeoXJapaneseLayer", - "GPTNeoXJapaneseModel", - "GPTNeoXJapanesePreTrainedModel" - ] - } - }, - "info.moe.gpt-oss": { - "*": { - "repo": "openai/gpt-oss-120b", - "pkg": { - "0": { - "transformers": "GptOssModel" - } - }, - "file_256": [ - "68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3", - "a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a" - ], - "layer_b3": [ - "b52807536902cabbf84f99e4fa2f8713fb4ef77e739f06367ee0d486e3222faa", - "43c618018db1fd6e915dead610652da261d9058b73bc5355c85c6ac69af4d913", - "ab27ce7391b7fbd6ce3c319faa119afdac68f746af6a0ce2c3400a132f36f6ac" - ], - "layer_256": [ - "de5dcad822be5ed6196f0f3f6965739993118d14db97b33a94a269f4f1b7a363", - "575f1977ed42d95a050e13dadaafc05a6d94c8aadca8364dca8a62aa4f2b146c" - ], - "tasks": [ - "GptOssForCausalLM", - "GptOssForSequenceClassification", - "GptOssForTokenClassification", - "GptOssModel", - "GptOssPreTrainedModel" - ] - } - }, - "info.art.gpt-j": { - "*": { - "repo": "EleutherAI/gpt-j-6B", - "pkg": { - "0": { - "transformers": "GPTJModel" - } - }, - "tasks": [ - "GPTJForCausalLM", - "GPTJForQuestionAnswering", - "GPTJForSequenceClassification", - "GPTJModel", - "GPTJPreTrainedModel" - ] - } - }, - "info.stst.granite": { - "*": { - "repo": "ibm-granite/granite-3.3-2b-base", - "pkg": { - "0": { - "transformers": "GraniteModel" - } - }, - "tasks": [ - "GraniteForCausalLM", - "GraniteModel", - "GranitePreTrainedModel" - ] - } - }, - "info.moe.powermoe": { - "*": { - "repo": "ibm-research/PowerMoE-3b", - "pkg": { - "0": { - "transformers": "GraniteMoeModel" - } - }, - "tasks": [ - "GraniteMoeForCausalLM", - "GraniteMoeModel", - "GraniteMoePreTrainedModel" - ] - } - }, - "info.ssm.granite-4-h": { - "*": { - "repo": "ibm-granite/granite-4.0-h-small", - "pkg": { - "0": { - "transformers": "GraniteMoeHybridModel" - } - }, - "tasks": [ - "GraniteMoeHybridForCausalLM", - "GraniteMoeHybridModel", - "GraniteMoeHybridPreTrainedModel" - ] - } - }, - "info.moe.moe-active-shared-experts": { - "*": { - "repo": "ibm-research/moe-7b-1b-active-shared-experts", - "pkg": { - "0": { - "transformers": "GraniteMoeSharedModel" - } - }, - "tasks": [ - "GraniteMoeSharedForCausalLM", - "GraniteMoeSharedModel", - "GraniteMoeSharedPreTrainedModel" - ] - } - }, - "info.vit.llava-v1-mistral-hf": { - "*": { - "repo": "llava-hf/llava-v1.6-mistral-7b-hf", - "pkg": { - "0": { - "transformers": "LlavaNextModel" - } - }, - "tasks": [ - "LlavaNextForConditionalGeneration", - "LlavaNextPreTrainedModel", - "LlavaNextModel" - ] - } - }, - "info.detr.grounding-dino": { - "*": { - "repo": "IDEA-Research/grounding-dino-tiny", - "pkg": { - "0": { - "transformers": "GroundingDinoModel" - } - }, - "tasks": [ - "GroundingDinoForObjectDetection", - "GroundingDinoModel", - "GroundingDinoPreTrainedModel" - ] - } - }, - "info.vit.groupvit-gcc-yfcc": { - "*": { - "repo": "nvidia/groupvit-gcc-yfcc", - "pkg": { - "0": { - "transformers": "GroupViTModel" - } - }, - "tasks": [ - "GroupViTModel", - "GroupViTPreTrainedModel", - "GroupViTTextModel", - "GroupViTVisionModel" - ] - } - }, - "info.stst.helium": { - "*": { - "repo": "kyutai/helium-1-2b", - "pkg": { - "0": { - "transformers": "HeliumModel" - } - }, - "tasks": [ - "HeliumPreTrainedModel", - "HeliumModel", - "HeliumForCausalLM", - "HeliumForSequenceClassification", - "HeliumForTokenClassification" - ] - } - }, - "info.vit.dfine-x-coco": { - "*": { - "repo": "ustc-community/dfine_x_coco", - "pkg": { - "0": { - "transformers": "HGNetV2Backbone" - } - }, - "tasks": [ - "HGNetV2Backbone", - "HGNetV2PreTrainedModel", - "HGNetV2ForImageClassification" - ] - } - }, - "info.vit.hiera-224": { - "*": { - "repo": "facebook/hiera-base-224-hf", - "pkg": { - "0": { - "transformers": "HieraModel" - } - }, - "tasks": [ - "HieraForImageClassification", - "HieraForPreTraining", - "HieraBackbone", - "HieraModel", - "HieraPreTrainedModel" - ] - } - }, - "info.aet.hubert-ls960": { - "*": { - "repo": "facebook/hubert-base-ls960", - "pkg": { - "0": { - "transformers": "HubertModel" - } - }, - "tasks": [ - "HubertForCTC", - "HubertForSequenceClassification", - "HubertModel", - "HubertPreTrainedModel" - ] - } - }, - "info.stst.hunyuan": { - "*": { - "repo": "tencent/Hunyuan-7B-Instruct", - "pkg": { - "0": { - "transformers": "HunYuanDenseV1Model" - } - }, - "tasks": [ - "HunYuanDenseV1ForCausalLM", - "HunYuanDenseV1Model", - "HunYuanDenseV1PreTrainedModel", - "HunYuanDenseV1ForSequenceClassification" - ] - } - }, - "info.moe.hunyuan-a": { - "*": { - "repo": "tencent/Hunyuan-A13B-Instruct", - "pkg": { - "0": { - "transformers": "HunYuanMoEV1Model" - } - }, - "tasks": [ - "HunYuanMoEV1ForCausalLM", - "HunYuanMoEV1Model", - "HunYuanMoEV1PreTrainedModel", - "HunYuanMoEV1ForSequenceClassification" - ] - } - }, - "info.art.ibert-roberta": { - "*": { - "repo": "kssteven/ibert-roberta-base", - "pkg": { - "0": { - "transformers": "IBertModel" - } - }, - "tasks": [ - "IBertForMaskedLM", - "IBertForMultipleChoice", - "IBertForQuestionAnswering", - "IBertForSequenceClassification", - "IBertForTokenClassification", - "IBertModel", - "IBertPreTrainedModel" - ] - } - }, - "info.vit.idefics": { - "*": { - "repo": "HuggingFaceM4/idefics-9b", - "pkg": { - "0": { - "transformers": "IdeficsModel" - } - }, - "tasks": [ - "IdeficsForVisionText2Text", - "IdeficsModel", - "IdeficsPreTrainedModel" - ] - } - }, - "info.vit.idefics2": { - "*": { - "repo": "HuggingFaceM4/idefics2-8b", - "pkg": { - "0": { - "transformers": "Idefics2Model" - } - }, - "tasks": [ - "Idefics2ForConditionalGeneration", - "Idefics2PreTrainedModel", - "Idefics2Model" - ] - } - }, - "info.vit.idefics3-llama3": { - "*": { - "repo": "HuggingFaceM4/Idefics3-8B-Llama3", - "pkg": { - "0": { - "transformers": "Idefics3Model" - } - }, - "tasks": [ - "Idefics3ForConditionalGeneration", - "Idefics3PreTrainedModel", - "Idefics3Model", - "Idefics3VisionTransformer" - ] - } - }, - "info.vit.siglip-patch16-224": { - "*": { - "repo": "google/siglip-base-patch16-224", - "pkg": { - "0": { - "transformers": "Idefics3VisionTransformer" - } - }, - "tasks": [ - "Idefics3ForConditionalGeneration", - "Idefics3PreTrainedModel", - "Idefics3Model", - "Idefics3VisionTransformer" - ] - } - }, - "info.vit.ijepa-vith14": { - "*": { - "repo": "facebook/ijepa_vith14_1k", - "pkg": { - "0": { - "transformers": "IJepaModel" - } - }, - "tasks": [ - "IJepaPreTrainedModel", - "IJepaModel", - "IJepaForImageClassification" - ] - } - }, - "info.art.imagegpt": { - "*": { - "repo": "openai/imagegpt-small", - "pkg": { - "0": { - "transformers": "ImageGPTModel" - } - }, - "tasks": [ - "ImageGPTForCausalImageModeling", - "ImageGPTForImageClassification", - "ImageGPTModel", - "ImageGPTPreTrainedModel" - ] - } - }, - "info.stst.informer-tourism-monthly": { - "*": { - "repo": "huggingface/informer-tourism-monthly", - "pkg": { - "0": { - "transformers": "InformerModel" - } - }, - "tasks": [ - "InformerForPrediction", - "InformerModel", - "InformerPreTrainedModel" - ] - } - }, - "info.vit.blip-flan-t5": { - "*": { - "repo": "Salesforce/instructblip-flan-t5-xl", - "pkg": { - "0": { - "transformers": "InstructBlipModel" - } - }, - "tasks": [ - "InstructBlipQFormerModel", - "InstructBlipPreTrainedModel", - "InstructBlipModel", - "InstructBlipForConditionalGeneration", - "InstructBlipVisionModel" - ] - } - }, - "info.vit.internvl3-hf": { - "*": { - "repo": "OpenGVLab/InternVL3-1B-hf", - "pkg": { - "0": { - "transformers": "InternVLModel" - } - }, - "tasks": [ - "InternVLVisionPreTrainedModel", - "InternVLVisionModel", - "InternVLPreTrainedModel", - "InternVLModel", - "InternVLForConditionalGeneration" - ] - } - }, - "info.stst.jais-2-chat": { - "*": { - "repo": "inceptionai/Jais-2-8B-Chat", - "pkg": { - "0": { - "transformers": "Jais2Model" - } - }, - "tasks": [ - "Jais2Model", - "Jais2ForCausalLM", - "Jais2PreTrainedModel" - ] - } - }, - "info.ssm.jamba-v0": { - "*": { - "repo": "ai21labs/Jamba-v0.1", - "pkg": { - "0": { - "transformers": "JambaModel" - } - }, - "tasks": [ - "JambaForCausalLM", - "JambaForSequenceClassification", - "JambaModel", - "JambaPreTrainedModel" - ] - } - }, - "info.vit.janus": { - "*": { - "repo": "deepseek-community/Janus-Pro-1B", - "pkg": { - "0": { - "transformers": "JanusModel" - } - }, - "tasks": [ - "JanusPreTrainedModel", - "JanusForConditionalGeneration", - "JanusModel", - "JanusVQVAE", - "JanusVisionModel" - ] - } - }, - "info.moe.jetmoe": { - "*": { - "repo": "jetmoe/jetmoe-8b", - "pkg": { - "0": { - "transformers": "JetMoeModel" - } - }, - "tasks": [ - "JetMoeForCausalLM", - "JetMoeModel", - "JetMoePreTrainedModel", - "JetMoeForSequenceClassification" - ] - } - }, - "info.vit.kosmos-2-patch14-224": { - "*": { - "repo": "microsoft/kosmos-2-patch14-224", - "pkg": { - "0": { - "transformers": "Kosmos2Model" - } - }, - "tasks": [ - "Kosmos2ForConditionalGeneration", - "Kosmos2Model", - "Kosmos2PreTrainedModel" - ] - } - }, - "info.vit.kosmos-2": { - "*": { - "repo": "microsoft/kosmos-2.5", - "pkg": { - "0": { - "transformers": "Kosmos2_5Model" - } - }, - "tasks": [ - "Kosmos2_5ForConditionalGeneration", - "Kosmos2_5Model", - "Kosmos2_5PreTrainedModel" - ] - } - }, - "info.stst.stt-en-trfs": { - "*": { - "repo": "kyutai/stt-2.6b-en-trfs", - "pkg": { - "0": { - "transformers": "KyutaiSpeechToTextModel" - } - }, - "tasks": [ - "KyutaiSpeechToTextPreTrainedModel", - "KyutaiSpeechToTextModel", - "KyutaiSpeechToTextForConditionalGeneration" - ] - } - }, - "info.aet.todo": { - "*": { - "repo": "TODO/TODO", - "pkg": { - "0": { - "transformers": "LasrForCTC" - } - }, - "tasks": [ - "LasrForCTC", - "LasrEncoder", - "LasrPreTrainedModel" - ] - } - }, - "info.stst.todo": { - "*": { - "repo": "TODO/TODO", - "pkg": { - "0": { - "transformers": "LasrEncoder" - } - }, - "tasks": [ - "LasrForCTC", - "LasrEncoder", - "LasrPreTrainedModel" - ] - } - }, - "info.art.layoutlm-uncased": { - "*": { - "repo": "microsoft/layoutlm-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMModel" - } - }, - "tasks": [ - "LayoutLMForMaskedLM", - "LayoutLMForSequenceClassification", - "LayoutLMForTokenClassification", - "LayoutLMForQuestionAnswering", - "LayoutLMModel", - "LayoutLMPreTrainedModel" - ] - } - }, - "info.art.layoutlmv2-uncased": { - "*": { - "repo": "microsoft/layoutlmv2-base-uncased", - "pkg": { - "0": { - "transformers": "LayoutLMv2Model" - } - }, - "tasks": [ - "LayoutLMv2ForQuestionAnswering", - "LayoutLMv2ForSequenceClassification", - "LayoutLMv2ForTokenClassification", - "LayoutLMv2Layer", - "LayoutLMv2Model", - "LayoutLMv2PreTrainedModel" - ] - } - }, - "info.vit.layoutlmv3": { - "*": { - "repo": "microsoft/layoutlmv3-base", - "pkg": { - "0": { - "transformers": "LayoutLMv3Model" - } - }, - "tasks": [ - "LayoutLMv3ForQuestionAnswering", - "LayoutLMv3ForSequenceClassification", - "LayoutLMv3ForTokenClassification", - "LayoutLMv3Model", - "LayoutLMv3PreTrainedModel" - ] - } - }, - "info.stst.led-16384": { - "*": { - "repo": "allenai/led-base-16384", - "pkg": { - "0": { - "transformers": "LEDModel" - } - }, - "tasks": [ - "LEDForConditionalGeneration", - "LEDForQuestionAnswering", - "LEDForSequenceClassification", - "LEDModel", - "LEDPreTrainedModel" - ] - } - }, - "info.gan.levit-128s": { - "*": { - "repo": "facebook/levit-128S", - "pkg": { - "0": { - "transformers": "LevitModel" - } - }, - "tasks": [ - "LevitForImageClassification", - "LevitForImageClassificationWithTeacher", - "LevitModel", - "LevitPreTrainedModel" - ] - } - }, - "info.stst.lfm": { - "*": { - "repo": "LiquidAI/LFM2-1.2B", - "pkg": { - "0": { - "transformers": "Lfm2Model" - } - }, - "tasks": [ - "Lfm2ForCausalLM", - "Lfm2Model", - "Lfm2PreTrainedModel" - ] - } - }, - "info.moe.lfm2-a": { - "*": { - "repo": "LiquidAI/LFM2-8B-A1B", - "pkg": { - "0": { - "transformers": "Lfm2MoeModel" - } - }, - "tasks": [ - "Lfm2MoeForCausalLM", - "Lfm2MoeModel", - "Lfm2MoePreTrainedModel" - ] - } - }, - "info.vit.lfm2-vl": { - "*": { - "repo": "LiquidAI/LFM2-VL-1.6B", - "pkg": { - "0": { - "transformers": "Lfm2VlModel" - } - }, - "tasks": [ - "Lfm2VlForConditionalGeneration", - "Lfm2VlPreTrainedModel", - "Lfm2VlModel" - ] - } - }, - "info.aet.lightglue-superpoint": { - "*": { - "repo": "ETH-CVG/lightglue_superpoint", - "pkg": { - "0": { - "transformers": "LightGlueForKeypointMatching" - } - }, - "tasks": [ - "LightGluePreTrainedModel", - "LightGlueForKeypointMatching" - ] - } - }, - "info.art.lilt-roberta-en": { - "*": { - "repo": "SCUT-DLVCLab/lilt-roberta-en-base", - "pkg": { - "0": { - "transformers": "LiltModel" - } - }, - "tasks": [ - "LiltForQuestionAnswering", - "LiltForSequenceClassification", - "LiltForTokenClassification", - "LiltModel", - "LiltPreTrainedModel" - ] - } - }, - "info.vit.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4ForConditionalGeneration" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.moe.llama-4-scout-16e": { - "*": { - "repo": "meta-llama/Llama-4-Scout-17B-16E", - "pkg": { - "0": { - "transformers": "Llama4TextModel" - } - }, - "tasks": [ - "Llama4PreTrainedModel", - "Llama4TextModel", - "Llama4VisionModel", - "Llama4ForCausalLM", - "Llama4ForConditionalGeneration" - ] - } - }, - "info.vit.llava": { - "*": { - "repo": "llava-hf/llava-9b", - "pkg": { - "0": { - "transformers": "LlavaModel" - } - }, - "file_256": [ - "f5ad57d3eda300a3195bc9c0bb36ab76ebe88831f128e9851e63440aff4a6741" - ], - "layer_b3": [ - "d7d6ccb9dbba90b64e4cd259b6309e56708b3f4fbd6e9f85e9f0410e549133ef" - ], - "layer_256": [ - "9969c41152aba689413b7f63888ecdc0c0badad2c2960e689ebc4c0e4a696c73" - ], - "tasks": [ - "LlavaForConditionalGeneration", - "LlavaPreTrainedModel", - "LlavaModel" - ] - } - }, - "info.vit.llava-next-video-hf": { - "*": { - "repo": "llava-hf/LLaVA-NeXT-Video-7B-hf", - "pkg": { - "0": { - "transformers": "LlavaNextVideoModel" - } - }, - "tasks": [ - "LlavaNextVideoForConditionalGeneration", - "LlavaNextVideoModel", - "LlavaNextVideoPreTrainedModel" - ] - } - }, - "info.vit.llava-onevision-qwen2-ov-hf": { - "*": { - "repo": "llava-hf/llava-onevision-qwen2-7b-ov-hf", - "pkg": { - "0": { - "transformers": "LlavaOnevisionModel" - } - }, - "tasks": [ - "LlavaOnevisionModel", - "LlavaOnevisionForConditionalGeneration", - "LlavaOnevisionPreTrainedModel" - ] - } - }, - "info.stst.longcat-flash-chat": { - "*": { - "repo": "meituan-longcat/LongCat-Flash-Chat", - "pkg": { - "0": { - "transformers": "LongcatFlashModel" - } - }, - "tasks": [ - "LongcatFlashPreTrainedModel", - "LongcatFlashModel", - "LongcatFlashForCausalLM" - ] - } - }, - "info.art.longformer-4096": { - "*": { - "repo": "allenai/longformer-base-4096", - "pkg": { - "0": { - "transformers": "LongformerModel" - } - }, - "tasks": [ - "LongformerForMaskedLM", - "LongformerForMultipleChoice", - "LongformerForQuestionAnswering", - "LongformerForSequenceClassification", - "LongformerForTokenClassification", - "LongformerModel", - "LongformerPreTrainedModel", - "LongformerSelfAttention" - ] - } - }, - "info.stst.long-t5-local": { - "*": { - "repo": "google/long-t5-local-base", - "pkg": { - "0": { - "transformers": "LongT5Model" - } - }, - "tasks": [ - "LongT5EncoderModel", - "LongT5ForConditionalGeneration", - "LongT5Model", - "LongT5PreTrainedModel" - ] - } - }, - "info.art.luke": { - "*": { - "repo": "studio-ousia/luke-base", - "pkg": { - "0": { - "transformers": "LukeModel" - } - }, - "tasks": [ - "LukeForEntityClassification", - "LukeForEntityPairClassification", - "LukeForEntitySpanClassification", - "LukeForMultipleChoice", - "LukeForQuestionAnswering", - "LukeForSequenceClassification", - "LukeForTokenClassification", - "LukeForMaskedLM", - "LukeModel", - "LukePreTrainedModel" - ] - } - }, - "info.art.lxmert-uncased": { - "*": { - "repo": "unc-nlp/lxmert-base-uncased", - "pkg": { - "0": { - "transformers": "LxmertModel" - } - }, - "tasks": [ - "LxmertEncoder", - "LxmertForPreTraining", - "LxmertForQuestionAnswering", - "LxmertModel", - "LxmertPreTrainedModel", - "LxmertVisualFeatureEncoder", - "LxmertXLayer" - ] - } - }, - "info.stst.m": { - "*": { - "repo": "facebook/m2m100_418M", - "pkg": { - "0": { - "transformers": "M2M100Model" - } - }, - "tasks": [ - "M2M100ForConditionalGeneration", - "M2M100Model", - "M2M100PreTrainedModel" - ] - } - }, - "info.ssm.mamba": { - "*": { - "repo": "state-spaces/mamba-2.8b", - "pkg": { - "0": { - "transformers": "MambaModel" - } - }, - "tasks": [ - "MambaForCausalLM", - "MambaModel", - "MambaPreTrainedModel", - "MambaCache" - ] - } - }, - "info.ssm.mamba2": { - "*": { - "repo": "AntonV/mamba2-2.7b-hf", - "pkg": { - "0": { - "transformers": "Mamba2Model" - } - }, - "tasks": [ - "Mamba2ForCausalLM", - "Mamba2Model", - "Mamba2PreTrainedModel" - ] - } - }, - "info.stst.opus-mt-en-de": { - "*": { - "repo": "Helsinki-NLP/opus-mt-en-de", - "pkg": { - "0": { - "transformers": "MarianModel" - } - }, - "tasks": [ - "MarianForCausalLM", - "MarianModel", - "MarianMTModel", - "MarianPreTrainedModel" - ] - } - }, - "info.art.markuplm": { - "*": { - "repo": "microsoft/markuplm-base", - "pkg": { - "0": { - "transformers": "MarkupLMModel" - } - }, - "tasks": [ - "MarkupLMForQuestionAnswering", - "MarkupLMForSequenceClassification", - "MarkupLMForTokenClassification", - "MarkupLMModel", - "MarkupLMPreTrainedModel" - ] - } - }, - "info.detr.mask2former-swin-coco-instance": { - "*": { - "repo": "facebook/mask2former-swin-small-coco-instance", - "pkg": { - "0": { - "transformers": "Mask2FormerModel" - } - }, - "tasks": [ - "Mask2FormerForUniversalSegmentation", - "Mask2FormerModel", - "Mask2FormerPreTrainedModel" - ] - } - }, - "info.detr.maskformer-swin-ade": { - "*": { - "repo": "facebook/maskformer-swin-base-ade", - "pkg": { - "0": { - "transformers": "MaskFormerModel" - } - }, - "tasks": [ - "MaskFormerForInstanceSegmentation", - "MaskFormerModel", - "MaskFormerPreTrainedModel" - ] - } - }, - "info.vit.swin-patch4-window7-224": { - "*": { - "repo": "microsoft/swin-tiny-patch4-window7-224", - "pkg": { - "0": { - "transformers": "MaskFormerSwinModel" - } - }, - "tasks": [ - "MaskFormerSwinBackbone", - "MaskFormerSwinModel", - "MaskFormerSwinPreTrainedModel" - ] - } - }, - "info.stst.mbart-cc25": { - "*": { - "repo": "facebook/mbart-large-cc25", - "pkg": { - "0": { - "transformers": "MBartModel" - } - }, - "tasks": [ - "MBartForCausalLM", - "MBartForConditionalGeneration", - "MBartForQuestionAnswering", - "MBartForSequenceClassification", - "MBartModel", - "MBartPreTrainedModel" - ] - } - }, - "info.art.megatron-bert-uncased": { - "*": { - "repo": "nvidia/megatron-bert-uncased-345m", - "pkg": { - "0": { - "transformers": "MegatronBertModel" - } - }, - "tasks": [ - "MegatronBertForCausalLM", - "MegatronBertForMaskedLM", - "MegatronBertForMultipleChoice", - "MegatronBertForNextSentencePrediction", - "MegatronBertForPreTraining", - "MegatronBertForQuestionAnswering", - "MegatronBertForSequenceClassification", - "MegatronBertForTokenClassification", - "MegatronBertModel", - "MegatronBertPreTrainedModel" - ] - } - }, - "info.vit.metaclip-2-worldwide-huge-quickgelu": { - "*": { - "repo": "facebook/metaclip-2-worldwide-huge-quickgelu", - "pkg": { - "0": { - "transformers": "MetaClip2Model" - } - }, - "tasks": [ - "MetaClip2Model", - "MetaClip2PreTrainedModel", - "MetaClip2TextModel", - "MetaClip2TextModelWithProjection", - "MetaClip2VisionModel", - "MetaClip2VisionModelWithProjection", - "MetaClip2ForImageClassification" - ] - } - }, - "info.vit.mgp-str": { - "*": { - "repo": "alibaba-damo/mgp-str-base", - "pkg": { - "0": { - "transformers": "MgpstrForSceneTextRecognition" - } - }, - "tasks": [ - "MgpstrModel", - "MgpstrPreTrainedModel", - "MgpstrForSceneTextRecognition" - ] - } - }, - "info.gan.mimi": { - "*": { - "repo": "kyutai/mimi", - "pkg": { - "0": { - "transformers": "MimiModel" - } - }, - "tasks": [ - "MimiModel", - "MimiPreTrainedModel" - ] - } - }, - "info.moe.max-text-01-hf": { - "*": { - "repo": "MiniMaxAI/MiniMax-Text-01-hf", - "pkg": { - "0": { - "transformers": "MiniMaxModel" - } - }, - "tasks": [ - "MiniMaxPreTrainedModel", - "MiniMaxModel", - "MiniMaxForCausalLM", - "MiniMaxForSequenceClassification", - "MiniMaxForTokenClassification", - "MiniMaxForQuestionAnswering" - ] - } - }, - "info.stst.stral-2410": { - "*": { - "repo": "mistralai/Ministral-8B-Instruct-2410", - "pkg": { - "0": { - "transformers": "MinistralModel" - } - }, - "tasks": [ - "MinistralPreTrainedModel", - "MinistralModel", - "MinistralForCausalLM", - "MinistralForSequenceClassification", - "MinistralForTokenClassification", - "MinistralForQuestionAnswering" - ] - } - }, - "info.stst.stral-3-2512": { - "*": { - "repo": "mistralai/Ministral-3-8B-Base-2512", - "pkg": { - "0": { - "transformers": "Ministral3Model" - } - }, - "tasks": [ - "Ministral3ForCausalLM", - "Ministral3ForQuestionAnswering", - "Ministral3Model", - "Ministral3PreTrainedModel", - "Ministral3ForSequenceClassification", - "Ministral3ForTokenClassification" - ] - } - }, - "info.stst.mistral-v0": { - "*": { - "repo": "mistralai/Mistral-7B-v0.1", - "pkg": { - "0": { - "transformers": "MistralModel" - } - }, - "tasks": [ - "MistralForCausalLM", - "MistralForQuestionAnswering", - "MistralModel", - "MistralPreTrainedModel", - "MistralForSequenceClassification", - "MistralForTokenClassification" - ] - } - }, - "info.vit.mistral-3-2503": { - "*": { - "repo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", - "pkg": { - "0": { - "transformers": "Mistral3Model" - } - }, - "tasks": [ - "Mistral3Model", - "Mistral3PreTrainedModel", - "Mistral3ForConditionalGeneration" - ] - } - }, - "info.moe.mixtral-8x": { - "*": { - "repo": "mistralai/Mixtral-8x7B-v0.1", - "pkg": { - "0": { - "transformers": "MixtralModel" - } - }, - "tasks": [ - "MixtralForCausalLM", - "MixtralForQuestionAnswering", - "MixtralModel", - "MixtralPreTrainedModel", - "MixtralForSequenceClassification", - "MixtralForTokenClassification" - ] - } - }, - "info.vit.mlcd-vit-bigg-patch14-336": { - "*": { - "repo": "DeepGlint-AI/mlcd-vit-bigG-patch14-336", - "pkg": { - "0": { - "transformers": "MLCDVisionModel" - } - }, - "tasks": [ - "MLCDPreTrainedModel", - "MLCDVisionModel" - ] - } - }, - "info.vit.llama-3-vision": { - "*": { - "repo": "meta-llama/Llama-3.2-11B-Vision", - "pkg": { - "0": { - "transformers": "MllamaModel" - } - }, - "tasks": [ - "MllamaForConditionalGeneration", - "MllamaForCausalLM", - "MllamaTextModel", - "MllamaVisionModel", - "MllamaPreTrainedModel", - "MllamaModel" - ] - } - }, - "info.detr.mm-grounding-dino-o365v1-goldg-v3det": { - "*": { - "repo": "openmmlab-community/mm_grounding_dino_tiny_o365v1_goldg_v3det", - "pkg": { - "0": { - "transformers": "MMGroundingDinoModel" - } - }, - "tasks": [ - "MMGroundingDinoForObjectDetection", - "MMGroundingDinoModel", - "MMGroundingDinoPreTrainedModel" - ] - } - }, - "info.art.mobilebert-uncased": { - "*": { - "repo": "google/mobilebert-uncased", - "pkg": { - "0": { - "transformers": "MobileBertModel" - } - }, - "tasks": [ - "MobileBertForMaskedLM", - "MobileBertForMultipleChoice", - "MobileBertForNextSentencePrediction", - "MobileBertForPreTraining", - "MobileBertForQuestionAnswering", - "MobileBertForSequenceClassification", - "MobileBertForTokenClassification", - "MobileBertLayer", - "MobileBertModel", - "MobileBertPreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v1-1--224": { - "*": { - "repo": "google/mobilenet_v1_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV1Model" - } - }, - "tasks": [ - "MobileNetV1ForImageClassification", - "MobileNetV1Model", - "MobileNetV1PreTrainedModel" - ] - } - }, - "info.vit.mobilenet-v2-1--224": { - "*": { - "repo": "google/mobilenet_v2_1.0_224", - "pkg": { - "0": { - "transformers": "MobileNetV2Model" - } - }, - "tasks": [ - "MobileNetV2ForImageClassification", - "MobileNetV2ForSemanticSegmentation", - "MobileNetV2Model", - "MobileNetV2PreTrainedModel" - ] - } - }, - "info.vit.mobilevit": { - "*": { - "repo": "apple/mobilevit-small", - "pkg": { - "0": { - "transformers": "MobileViTModel" - } - }, - "tasks": [ - "MobileViTForImageClassification", - "MobileViTForSemanticSegmentation", - "MobileViTModel", - "MobileViTPreTrainedModel" - ] - } - }, - "info.vit.mobilevitv2-1": { - "*": { - "repo": "apple/mobilevitv2-1.0-imagenet1k-256", - "pkg": { - "0": { - "transformers": "MobileViTV2Model" - } - }, - "tasks": [ - "MobileViTV2ForImageClassification", - "MobileViTV2ForSemanticSegmentation", - "MobileViTV2Model", - "MobileViTV2PreTrainedModel" - ] - } - }, - "info.aet.modernbert": { - "*": { - "repo": "answerdotai/ModernBERT-base", - "pkg": { - "0": { - "transformers": "ModernBertModel" - } - }, - "tasks": [ - "ModernBertModel", - "ModernBertPreTrainedModel", - "ModernBertForMaskedLM", - "ModernBertForSequenceClassification", - "ModernBertForTokenClassification", - "ModernBertForQuestionAnswering", - "ModernBertForMultipleChoice" - ] - } - }, - "info.aet.test-dec": { - "*": { - "repo": "blab-jhu/test-32m-dec", - "pkg": { - "0": { - "transformers": "ModernBertDecoderModel" - } - }, - "tasks": [ - "ModernBertDecoderModel", - "ModernBertDecoderPreTrainedModel", - "ModernBertDecoderForCausalLM", - "ModernBertDecoderForSequenceClassification" - ] - } - }, - "info.stst.moonshine": { - "*": { - "repo": "UsefulSensors/moonshine-tiny", - "pkg": { - "0": { - "transformers": "MoonshineModel" - } - }, - "tasks": [ - "MoonshineModel", - "MoonshinePreTrainedModel", - "MoonshineForConditionalGeneration" - ] - } - }, - "info.stst.hf-moshiko": { - "*": { - "repo": "kmhf/hf-moshiko", - "pkg": { - "0": { - "transformers": "MoshiModel" - } - }, - "tasks": [ - "MoshiForCausalLM", - "MoshiForConditionalGeneration", - "MoshiModel", - "MoshiPreTrainedModel" - ] - } - }, - "info.art.mpnet": { - "*": { - "repo": "microsoft/mpnet-base", - "pkg": { - "0": { - "transformers": "MPNetModel" - } - }, - "tasks": [ - "MPNetForMaskedLM", - "MPNetForMultipleChoice", - "MPNetForQuestionAnswering", - "MPNetForSequenceClassification", - "MPNetForTokenClassification", - "MPNetLayer", - "MPNetModel", - "MPNetPreTrainedModel" - ] - } - }, - "info.art.mpt": { - "*": { - "repo": "mosaicml/mpt-7b", - "pkg": { - "0": { - "transformers": "MptModel" - } - }, - "tasks": [ - "MptForCausalLM", - "MptModel", - "MptPreTrainedModel", - "MptForSequenceClassification", - "MptForTokenClassification", - "MptForQuestionAnswering" - ] - } - }, - "info.art.mra-512-4": { - "*": { - "repo": "uw-madison/mra-base-512-4", - "pkg": { - "0": { - "transformers": "MraModel" - } - }, - "tasks": [ - "MraForMaskedLM", - "MraForMultipleChoice", - "MraForQuestionAnswering", - "MraForSequenceClassification", - "MraForTokenClassification", - "MraLayer", - "MraModel", - "MraPreTrainedModel" - ] - } - }, - "info.stst.mt5": { - "*": { - "repo": "google/mt5-small", - "pkg": { - "0": { - "transformers": "MT5Model" - } - }, - "identifiers": [ - [ - 250112, - 2048 - ], - "text_encoders.mt5xl.transformer.shared.weight" - ], - "file_256": [ - "0524484ec81425ba9deef6fac1393a78ba9b1c9bfed704a4be5f9c7255975cc1", - "32f70f1d187e131a5fc3e4f0edc97ce89360d8e2f1d90177a443a05296097acc" - ], - "layer_b3": [ - "a1d616c37711ec7b9073d04734af2f5fd02f9035a322eb46efeace922e104c51" - ], - "layer_256": [ - "bd337daf0c1aa36896013109b406a0580aa3bb8ab9291d89df3015d737358e95", - "2e40c48c96fc7df636aad96d3e78ed0ba9f68c3059e21b7fcf917f284c569a61" - ], - "tasks": [ - "MT5EncoderModel", - "MT5ForConditionalGeneration", - "MT5ForQuestionAnswering", - "MT5ForSequenceClassification", - "MT5ForTokenClassification", - "MT5Model", - "MT5PreTrainedModel" - ] - } - }, - "info.art.musicgen": { - "*": { - "repo": "facebook/musicgen-small", - "pkg": { - "0": { - "transformers": "MusicgenModel" - } - }, - "tasks": [ - "MusicgenForConditionalGeneration", - "MusicgenForCausalLM", - "MusicgenModel", - "MusicgenPreTrainedModel" - ] - } - }, - "info.art.musicgen-melody": { - "*": { - "repo": "facebook/musicgen-melody", - "pkg": { - "0": { - "transformers": "MusicgenMelodyModel" - } - }, - "tasks": [ - "MusicgenMelodyForConditionalGeneration", - "MusicgenMelodyForCausalLM", - "MusicgenMelodyModel", - "MusicgenMelodyPreTrainedModel" - ] - } - }, - "info.stst.mvp": { - "*": { - "repo": "RUCAIBox/mvp", - "pkg": { - "0": { - "transformers": "MvpModel" - } - }, - "tasks": [ - "MvpForCausalLM", - "MvpForConditionalGeneration", - "MvpForQuestionAnswering", - "MvpForSequenceClassification", - "MvpModel", - "MvpPreTrainedModel" - ] - } - }, - "info.stst.nanochat-d32": { - "*": { - "repo": "karpathy/nanochat-d32", - "pkg": { - "0": { - "transformers": "NanoChatModel" - } - }, - "tasks": [ - "NanoChatPreTrainedModel", - "NanoChatModel", - "NanoChatForCausalLM" - ] - } - }, - "info.stst.nemotron-3-hf": { - "*": { - "repo": "mgoin/nemotron-3-8b-chat-4k-sft-hf", - "pkg": { - "0": { - "transformers": "NemotronModel" - } - }, - "tasks": [ - "NemotronForQuestionAnswering", - "NemotronForCausalLM", - "NemotronModel", - "NemotronPreTrainedModel", - "NemotronForSequenceClassification", - "NemotronForTokenClassification" - ] - } - }, - "info.moe.nllb-moe": { - "*": { - "repo": "facebook/nllb-moe-54b", - "pkg": { - "0": { - "transformers": "NllbMoeModel" - } - }, - "tasks": [ - "NllbMoeForConditionalGeneration", - "NllbMoeModel", - "NllbMoePreTrainedModel", - "NllbMoeTop2Router", - "NllbMoeSparseMLP" - ] - } - }, - "info.art.nystromformer-512": { - "*": { - "repo": "uw-madison/nystromformer-512", - "pkg": { - "0": { - "transformers": "NystromformerModel" - } - }, - "tasks": [ - "NystromformerForMaskedLM", - "NystromformerForMultipleChoice", - "NystromformerForQuestionAnswering", - "NystromformerForSequenceClassification", - "NystromformerForTokenClassification", - "NystromformerLayer", - "NystromformerModel", - "NystromformerPreTrainedModel" - ] - } - }, - "info.stst.olmo-hf": { - "*": { - "repo": "allenai/OLMo-7B-hf", - "pkg": { - "0": { - "transformers": "OlmoModel" - } - }, - "tasks": [ - "OlmoForCausalLM", - "OlmoModel", - "OlmoPreTrainedModel" - ] - } - }, - "info.stst.olmo2-1124-hf": { - "*": { - "repo": "allenai/Olmo-2-1124-7B", - "pkg": { - "0": { - "transformers": "Olmo2Model" - } - }, - "tasks": [ - "Olmo2ForCausalLM", - "Olmo2Model", - "Olmo2PreTrainedModel" - ] - } - }, - "info.stst.olmo-3-0725": { - "*": { - "repo": "allenai/OLMo-3-0725-1B", - "pkg": { - "0": { - "transformers": "Olmo3Model" - } - }, - "tasks": [ - "Olmo3ForCausalLM", - "Olmo3Model", - "Olmo3PreTrainedModel" - ] - } - }, - "info.moe.olmoe-0924": { - "*": { - "repo": "allenai/OLMoE-1B-7B-0924", - "pkg": { - "0": { - "transformers": "OlmoeModel" - } - }, - "tasks": [ - "OlmoeForCausalLM", - "OlmoeModel", - "OlmoePreTrainedModel" - ] - } - }, - "info.detr.omdet-turbo-swin-hf": { - "*": { - "repo": "omlab/omdet-turbo-swin-tiny-hf", - "pkg": { - "0": { - "transformers": "OmDetTurboForObjectDetection" - } - }, - "tasks": [ - "OmDetTurboForObjectDetection", - "OmDetTurboPreTrainedModel" - ] - } - }, - "info.detr.oneformer-ade-swin": { - "*": { - "repo": "shi-labs/oneformer_ade20k_swin_tiny", - "pkg": { - "0": { - "transformers": "OneFormerModel" - } - }, - "tasks": [ - "OneFormerForUniversalSegmentation", - "OneFormerModel", - "OneFormerPreTrainedModel" - ] - } - }, - "info.art.openai-gpt": { - "*": { - "repo": "openai-community/openai-gpt", - "pkg": { - "0": { - "transformers": "OpenAIGPTModel" - } - }, - "tasks": [ - "OpenAIGPTDoubleHeadsModel", - "OpenAIGPTForSequenceClassification", - "OpenAIGPTLMHeadModel", - "OpenAIGPTModel", - "OpenAIGPTPreTrainedModel" - ] - } - }, - "info.art.opt": { - "*": { - "repo": "facebook/opt-350m", - "pkg": { - "0": { - "transformers": "OPTModel" - } - }, - "tasks": [ - "OPTForCausalLM", - "OPTModel", - "OPTPreTrainedModel", - "OPTForSequenceClassification", - "OPTForQuestionAnswering" - ] - } - }, - "info.vit.ovis2-hf": { - "*": { - "repo": "thisisiron/Ovis2-1B-hf", - "pkg": { - "0": { - "transformers": "Ovis2Model" - } - }, - "tasks": [ - "Ovis2PreTrainedModel", - "Ovis2Model", - "Ovis2ForConditionalGeneration" - ] - } - }, - "info.vit.owlv2-patch16": { - "*": { - "repo": "google/owlv2-base-patch16", - "pkg": { - "0": { - "transformers": "Owlv2Model" - } - }, - "tasks": [ - "Owlv2Model", - "Owlv2PreTrainedModel", - "Owlv2TextModel", - "Owlv2VisionModel", - "Owlv2ForObjectDetection" - ] - } - }, - "info.vit.owlvit-patch32": { - "*": { - "repo": "google/owlvit-base-patch32", - "pkg": { - "0": { - "transformers": "OwlViTModel" - } - }, - "tasks": [ - "OwlViTModel", - "OwlViTPreTrainedModel", - "OwlViTTextModel", - "OwlViTVisionModel", - "OwlViTForObjectDetection" - ] - } - }, - "info.vit.paligemma": { - "*": { - "repo": "google/paligemma2-3b-mix-224", - "pkg": { - "0": { - "transformers": "PaliGemmaModel" - } - }, - "tasks": [ - "PaliGemmaForConditionalGeneration", - "PaliGemmaPreTrainedModel", - "PaliGemmaModel" - ] - } - }, - "info.aet.parakeet-ctc-b": { - "*": { - "repo": "nvidia/parakeet-ctc-1.1b", - "pkg": { - "0": { - "transformers": "ParakeetForCTC" - } - }, - "tasks": [ - "ParakeetForCTC", - "ParakeetEncoder", - "ParakeetPreTrainedModel" - ] - } - }, - "info.stst.parakeet-ctc-b": { - "*": { - "repo": "nvidia/parakeet-ctc-1.1b", - "pkg": { - "0": { - "transformers": "ParakeetEncoder" - } - }, - "tasks": [ - "ParakeetForCTC", - "ParakeetEncoder", - "ParakeetPreTrainedModel" - ] - } - }, - "info.mlp.patchtsmixer-etth1-pretrain": { - "*": { - "repo": "ibm/patchtsmixer-etth1-pretrain", - "pkg": { - "0": { - "transformers": "PatchTSMixerModel" - } - }, - "tasks": [ - "PatchTSMixerPreTrainedModel", - "PatchTSMixerModel", - "PatchTSMixerForPretraining", - "PatchTSMixerForPrediction", - "PatchTSMixerForTimeSeriesClassification", - "PatchTSMixerForRegression" - ] - } - }, - "info.art.patchtst": { - "*": { - "repo": "ibm/patchtst", - "pkg": { - "0": { - "transformers": "PatchTSTModel" - } - }, - "tasks": [ - "PatchTSTModel", - "PatchTSTPreTrainedModel", - "PatchTSTForPrediction", - "PatchTSTForPretraining", - "PatchTSTForRegression", - "PatchTSTForClassification" - ] - } - }, - "info.stst.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeAudioModel" - } - }, - "tasks": [ - "PeAudioFrameLevelModel", - "PeAudioModel", - "PeAudioEncoder" - ] - } - }, - "info.aet.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeAudioVideoModel" - } - }, - "tasks": [ - "PeAudioVideoModel", - "PeAudioVideoEncoder" - ] - } - }, - "info.vit.pe-av": { - "*": { - "repo": "facebook/pe-av-large", - "pkg": { - "0": { - "transformers": "PeVideoEncoder" - } - }, - "tasks": [ - "PeVideoEncoder", - "PeVideoModel" - ] - } - }, - "info.stst.pegasus": { - "*": { - "repo": "google/pegasus-large", - "pkg": { - "0": { - "transformers": "PegasusModel" - } - }, - "tasks": [ - "PegasusForCausalLM", - "PegasusForConditionalGeneration", - "PegasusModel", - "PegasusPreTrainedModel" - ] - } - }, - "info.stst.pegasus-x": { - "*": { - "repo": "google/pegasus-x-large", - "pkg": { - "0": { - "transformers": "PegasusXModel" - } - }, - "tasks": [ - "PegasusXForConditionalGeneration", - "PegasusXModel", - "PegasusXPreTrainedModel" - ] - } - }, - "info.vit.language-perceiver": { - "*": { - "repo": "deepmind/language-perceiver", - "pkg": { - "0": { - "transformers": "PerceiverModel" - } - }, - "tasks": [ - "PerceiverForImageClassificationConvProcessing", - "PerceiverForImageClassificationFourier", - "PerceiverForImageClassificationLearned", - "PerceiverForMaskedLM", - "PerceiverForMultimodalAutoencoding", - "PerceiverForOpticalFlow", - "PerceiverForSequenceClassification", - "PerceiverLayer", - "PerceiverModel", - "PerceiverPreTrainedModel" - ] - } - }, - "info.vit.perception-lm": { - "*": { - "repo": "facebook/Perception-LM-1B", - "pkg": { - "0": { - "transformers": "PerceptionLMModel" - } - }, - "tasks": [ - "PerceptionLMForConditionalGeneration", - "PerceptionLMPreTrainedModel", - "PerceptionLMModel" - ] - } - }, - "info.stst.persimmon": { - "*": { - "repo": "adept/persimmon-8b-base", - "pkg": { - "0": { - "transformers": "PersimmonModel" - } - }, - "tasks": [ - "PersimmonForCausalLM", - "PersimmonModel", - "PersimmonPreTrainedModel", - "PersimmonForSequenceClassification", - "PersimmonForTokenClassification" - ] - } - }, - "info.stst.phi-1": { - "*": { - "repo": "microsoft/phi-1", - "pkg": { - "0": { - "transformers": "PhiModel" - } - }, - "tasks": [ - "PhiPreTrainedModel", - "PhiModel", - "PhiForCausalLM", - "PhiForSequenceClassification", - "PhiForTokenClassification" - ] - } - }, - "info.stst.phi-3": { - "*": { - "repo": "microsoft/Phi-3-mini-4k-instruct", - "pkg": { - "0": { - "transformers": "Phi3Model" - } - }, - "tasks": [ - "Phi3PreTrainedModel", - "Phi3Model", - "Phi3ForCausalLM", - "Phi3ForSequenceClassification", - "Phi3ForTokenClassification" - ] - } - }, - "info.vit.phi-4": { - "*": { - "repo": "microsoft/Phi-4-multimodal-instruct", - "pkg": { - "0": { - "transformers": "Phi4MultimodalModel" - } - }, - "file_256": [ - "bc703090b63eda16f639fa4de7ac54635c23105ab1da2f6ec4d3403151d38ee6" - ], - "layer_b3": [ - "cf4add4ada6082f448788eaf2937f645b5212db88e06ee81475b8be0e99063dc" - ], - "layer_256": [ - "7ff992b780b2f8993dd6bb9612207943638b2a42badc976ce80893bc205e801b" - ], - "tasks": [ - "Phi4MultimodalAudioPreTrainedModel", - "Phi4MultimodalAudioModel", - "Phi4MultimodalVisionPreTrainedModel", - "Phi4MultimodalVisionModel", - "Phi4MultimodalPreTrainedModel", - "Phi4MultimodalModel", - "Phi4MultimodalForCausalLM" - ] - } - }, - "info.moe.phi-3-moe": { - "*": { - "repo": "microsoft/Phi-3.5-MoE-instruct", - "pkg": { - "0": { - "transformers": "PhimoeModel" - } - }, - "tasks": [ - "PhimoePreTrainedModel", - "PhimoeModel", - "PhimoeForCausalLM", - "PhimoeForSequenceClassification" - ] - } - }, - "info.vit.pixio-huge": { - "*": { - "repo": "facebook/pixio-huge", - "pkg": { - "0": { - "transformers": "PixioModel" - } - }, - "tasks": [ - "PixioModel", - "PixioPreTrainedModel", - "PixioBackbone" - ] - } - }, - "info.vit.pixtral": { - "*": { - "repo": "mistralai/Pixtral-12B-Base-2409", - "pkg": { - "0": { - "transformers": "PixtralVisionModel" - } - }, - "tasks": [ - "PixtralVisionModel", - "PixtralPreTrainedModel" - ] - } - }, - "info.stst.plbart": { - "*": { - "repo": "uclanlp/plbart-base", - "pkg": { - "0": { - "transformers": "PLBartModel" - } - }, - "tasks": [ - "PLBartForCausalLM", - "PLBartForConditionalGeneration", - "PLBartForSequenceClassification", - "PLBartModel", - "PLBartPreTrainedModel" - ] - } - }, - "info.vit.poolformer-s12": { - "*": { - "repo": "sail/poolformer_s12", - "pkg": { - "0": { - "transformers": "PoolFormerModel" - } - }, - "tasks": [ - "PoolFormerForImageClassification", - "PoolFormerModel", - "PoolFormerPreTrainedModel" - ] - } - }, - "info.stst.phetnet-uncased": { - "*": { - "repo": "microsoft/prophetnet-large-uncased", - "pkg": { - "0": { - "transformers": "ProphetNetModel" - } - }, - "tasks": [ - "ProphetNetDecoder", - "ProphetNetEncoder", - "ProphetNetForCausalLM", - "ProphetNetForConditionalGeneration", - "ProphetNetModel", - "ProphetNetPreTrainedModel" - ] - } - }, - "info.vit.pvt-224": { - "*": { - "repo": "Xrenya/pvt-tiny-224", - "pkg": { - "0": { - "transformers": "PvtModel" - } - }, - "tasks": [ - "PvtForImageClassification", - "PvtModel", - "PvtPreTrainedModel" - ] - } - }, - "info.vit.pvt-v2-b0": { - "*": { - "repo": "OpenGVLab/pvt_v2_b0", - "pkg": { - "0": { - "transformers": "PvtV2Model" - } - }, - "tasks": [ - "PvtV2ForImageClassification", - "PvtV2Model", - "PvtV2PreTrainedModel", - "PvtV2Backbone" - ] - } - }, - "info.stst.qwen2": { - "*": { - "repo": "Qwen/Qwen2-7B", - "pkg": { - "0": { - "transformers": "Qwen2Model" - } - }, - "tasks": [ - "Qwen2PreTrainedModel", - "Qwen2Model", - "Qwen2ForCausalLM", - "Qwen2RMSNorm", - "Qwen2ForSequenceClassification", - "Qwen2ForTokenClassification", - "Qwen2ForQuestionAnswering" - ] - } - }, - "info.vit.qwen2-vl": { - "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen2_5_VLModel" - } - }, - "tasks": [ - "Qwen2_5_VLForConditionalGeneration", - "Qwen2_5_VLModel", - "Qwen2_5_VLPreTrainedModel", - "Qwen2_5_VLTextModel" - ] - } - }, - "info.stst.qwen2-vl": { - "*": { - "repo": "Qwen/Qwen2-VL-7B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen2_5_VLTextModel" - } - }, - "file_256": [ - "1f48ac458d6fbd0aec53a116065a7ee3f1d34bddde544e25c16a05c9d5392b78", - "0e85c7111ce849293e97aa09ce1172352ecece023a3ecea7ac8311e326b47f3a", - "d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4", - "e10bd9583a77250376d9134cd6b46799029dfa3b4d7989c1050b3ec149cc7cf5" - ], - "layer_b3": [ - "e4f681bde70a753f30f83495a2aa340d251bf3d818eb5a1cbe58f85fd6ea0d40", - "47b062ce8ddb14845fb1a71d2fd88fd52a82e26561ba3eb05be057915a867775", - "b6386f70b528ffa9e09fdd8db8a7b91a7c462ed97b06963576c6139e25fdcf31", - "4cd449df9f9004a7e53005583a7e4cfa6de42912f03647d2ea799d489e9c1406" - ], - "layer_256": [ - "ed36a4a11c4ebebb10d1e010cb93e2e43fcaf975cd42bb6c9958537593d0d44d", - "f7f6f64e7b6d7826400a2fc0eef942a47c47bd5914e051ad0c8cd9ff5ff7982b", - "f341ed0f792cf0570ceb21d3b64ed14bf9875e9fcb90116851364eeed683a6ca", - "ba031d0da78afe24ae63558ad29b8028244a7bd4750a5615dab9079fe32a5fd7" - ], - "tasks": [ - "Qwen2_5_VLForConditionalGeneration", - "Qwen2_5_VLModel", - "Qwen2_5_VLPreTrainedModel", - "Qwen2_5_VLTextModel" - ] - } - }, - "info.aet.qwen2-audio": { - "*": { - "repo": "Qwen/Qwen2-Audio-7B", - "pkg": { - "0": { - "transformers": "Qwen2AudioEncoder" - } - }, - "tasks": [ - "Qwen2AudioForConditionalGeneration", - "Qwen2AudioPreTrainedModel", - "Qwen2AudioEncoder" - ] - } - }, - "info.moe.qwen15-moe-a": { - "*": { - "repo": "Qwen/Qwen1.5-MoE-A2.7B", - "pkg": { - "0": { - "transformers": "Qwen2MoeModel" - } - }, - "tasks": [ - "Qwen2MoeForCausalLM", - "Qwen2MoeForQuestionAnswering", - "Qwen2MoeModel", - "Qwen2MoePreTrainedModel", - "Qwen2MoeForSequenceClassification", - "Qwen2MoeForTokenClassification" - ] - } - }, - "info.stst.qwen3": { - "*": { - "repo": "Qwen/Qwen3-8B", - "pkg": { - "0": { - "transformers": "Qwen3Model" - } - }, - "tasks": [ - "Qwen3ForCausalLM", - "Qwen3ForQuestionAnswering", - "Qwen3PreTrainedModel", - "Qwen3Model", - "Qwen3ForSequenceClassification", - "Qwen3ForTokenClassification" - ] - } - }, - "info.moe.qwen3-a": { - "*": { - "repo": "Qwen/Qwen3-30B-A3B", - "pkg": { - "0": { - "transformers": "Qwen3MoeModel" - } - }, - "file_256": [ - "c56947057481fb5e7cdf766e442da81717b34addc88bbe8f3728fd25bd03cbae" - ], - "layer_b3": [ - "d2d1e0875202f5c9c84c781a2105620250733bd01832f67b2c17bc981d1eb508" - ], - "layer_256": [ - "408c01da57c4968b7b0e36d98a74e321153e7aeb058fea63ffd140e323526476" - ], - "tasks": [ - "Qwen3MoeForCausalLM", - "Qwen3MoeForQuestionAnswering", - "Qwen3MoeModel", - "Qwen3MoePreTrainedModel", - "Qwen3MoeForSequenceClassification", - "Qwen3MoeForTokenClassification" - ] - } - }, - "info.moe.qwen3-next-a": { - "*": { - "repo": "Qwen/Qwen3-Next-80B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3NextModel" - } - }, - "tasks": [ - "Qwen3NextForCausalLM", - "Qwen3NextForQuestionAnswering", - "Qwen3NextModel", - "Qwen3NextPreTrainedModel", - "Qwen3NextForSequenceClassification", - "Qwen3NextForTokenClassification" - ] - } - }, - "info.vit.qwen3-vl": { - "*": { - "repo": "Qwen/Qwen3-VL-4B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLModel" - } - }, - "tasks": [ - "Qwen3VLVisionModel", - "Qwen3VLForConditionalGeneration", - "Qwen3VLModel", - "Qwen3VLPreTrainedModel", - "Qwen3VLTextModel" - ] - } - }, - "info.vit.qwen3-vl-a": { - "*": { - "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLMoeModel" - } - }, - "tasks": [ - "Qwen3VLMoeVisionModel", - "Qwen3VLMoeForConditionalGeneration", - "Qwen3VLMoeModel", - "Qwen3VLMoePreTrainedModel", - "Qwen3VLMoeTextModel" - ] - } - }, - "info.moe.qwen3-vl-a": { - "*": { - "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLMoeTextModel" - } - }, - "tasks": [ - "Qwen3VLMoeVisionModel", - "Qwen3VLMoeForConditionalGeneration", - "Qwen3VLMoeModel", - "Qwen3VLMoePreTrainedModel", - "Qwen3VLMoeTextModel" - ] - } - }, - "info.stst.qwen3-vl": { - "*": { - "repo": "Qwen/Qwen3-VL-4B-Instruct", - "pkg": { - "0": { - "transformers": "Qwen3VLTextModel" - } - }, - "tasks": [ - "Qwen3VLVisionModel", - "Qwen3VLForConditionalGeneration", - "Qwen3VLModel", - "Qwen3VLPreTrainedModel", - "Qwen3VLTextModel" - ] - } - }, - "info.rnn.recurrentgemma": { - "*": { - "repo": "google/recurrentgemma-2b", - "pkg": { - "0": { - "transformers": "RecurrentGemmaModel" - } - }, - "tasks": [ - "RecurrentGemmaForCausalLM", - "RecurrentGemmaModel", - "RecurrentGemmaPreTrainedModel" - ] - } - }, - "info.art.reformer-crime-and-punishment": { - "*": { - "repo": "google/reformer-crime-and-punishment", - "pkg": { - "0": { - "transformers": "ReformerModel" - } - }, - "tasks": [ - "ReformerAttention", - "ReformerForMaskedLM", - "ReformerForQuestionAnswering", - "ReformerForSequenceClassification", - "ReformerLayer", - "ReformerModel", - "ReformerModelWithLMHead", - "ReformerPreTrainedModel" - ] - } - }, - "info.vit.regnet-y-040": { - "*": { - "repo": "facebook/regnet-y-040", - "pkg": { - "0": { - "transformers": "RegNetModel" - } - }, - "tasks": [ - "RegNetForImageClassification", - "RegNetModel", - "RegNetPreTrainedModel" - ] - } - }, - "info.art.rembert": { - "*": { - "repo": "google/rembert", - "pkg": { - "0": { - "transformers": "RemBertModel" - } - }, - "tasks": [ - "RemBertForCausalLM", - "RemBertForMaskedLM", - "RemBertForMultipleChoice", - "RemBertForQuestionAnswering", - "RemBertForSequenceClassification", - "RemBertForTokenClassification", - "RemBertLayer", - "RemBertModel", - "RemBertPreTrainedModel" - ] - } - }, - "info.vit.resnet-50": { - "*": { - "repo": "microsoft/resnet-50", - "pkg": { - "0": { - "transformers": "ResNetModel" - } - }, - "tasks": [ - "ResNetForImageClassification", - "ResNetModel", - "ResNetPreTrainedModel", - "ResNetBackbone" - ] - } - }, - "info.art.roberta": { - "*": { - "repo": "FacebookAI/roberta-base", - "pkg": { - "0": { - "transformers": "RobertaModel" - } - }, - "tasks": [ - "RobertaForCausalLM", - "RobertaForMaskedLM", - "RobertaForMultipleChoice", - "RobertaForQuestionAnswering", - "RobertaForSequenceClassification", - "RobertaForTokenClassification", - "RobertaModel", - "RobertaPreTrainedModel" - ] - } - }, - "info.art.efficient-mlm-m0-0": { - "*": { - "repo": "andreasmadsen/efficient_mlm_m0.40", - "pkg": { - "0": { - "transformers": "RobertaPreLayerNormModel" - } - }, - "tasks": [ - "RobertaPreLayerNormForCausalLM", - "RobertaPreLayerNormForMaskedLM", - "RobertaPreLayerNormForMultipleChoice", - "RobertaPreLayerNormForQuestionAnswering", - "RobertaPreLayerNormForSequenceClassification", - "RobertaPreLayerNormForTokenClassification", - "RobertaPreLayerNormModel", - "RobertaPreLayerNormPreTrainedModel" - ] - } - }, - "info.art.roc-bert-zh": { - "*": { - "repo": "weiweishi/roc-bert-base-zh", - "pkg": { - "0": { - "transformers": "RoCBertModel" - } - }, - "tasks": [ - "RoCBertForCausalLM", - "RoCBertForMaskedLM", - "RoCBertForMultipleChoice", - "RoCBertForPreTraining", - "RoCBertForQuestionAnswering", - "RoCBertForSequenceClassification", - "RoCBertForTokenClassification", - "RoCBertLayer", - "RoCBertModel", - "RoCBertPreTrainedModel" - ] - } - }, - "info.art.roformer-chinese": { - "*": { - "repo": "junnyu/roformer_chinese_base", - "pkg": { - "0": { - "transformers": "RoFormerModel" - } - }, - "tasks": [ - "RoFormerForCausalLM", - "RoFormerForMaskedLM", - "RoFormerForMultipleChoice", - "RoFormerForQuestionAnswering", - "RoFormerForSequenceClassification", - "RoFormerForTokenClassification", - "RoFormerLayer", - "RoFormerModel", - "RoFormerPreTrainedModel" - ] - } - }, - "info.detr.rtdetr-r50vd": { - "*": { - "repo": "PekingU/rtdetr_r50vd", - "pkg": { - "0": { - "transformers": "RTDetrModel" - } - }, - "tasks": [ - "RTDetrForObjectDetection", - "RTDetrModel", - "RTDetrPreTrainedModel" - ] - } - }, - "info.detr.rtdetr-r18vd": { - "*": { - "repo": "PekingU/rtdetr_r18vd", - "pkg": { - "0": { - "transformers": "RTDetrV2Model" - } - }, - "tasks": [ - "RTDetrV2Model", - "RTDetrV2PreTrainedModel", - "RTDetrV2ForObjectDetection" - ] - } - }, - "info.rnn.rwkv-4-pile": { - "*": { - "repo": "RWKV/rwkv-4-169m-pile", - "pkg": { - "0": { - "transformers": "RwkvModel" - } - }, - "tasks": [ - "RwkvForCausalLM", - "RwkvModel", - "RwkvPreTrainedModel" - ] - } - }, - "info.vit.sam-vit-huge": { - "*": { - "repo": "facebook/sam-vit-huge", - "pkg": { - "0": { - "transformers": "SamModel" - } - }, - "tasks": [ - "SamVisionModel", - "SamModel", - "SamPreTrainedModel" - ] - } - }, - "info.vit.sam2-hiera": { - "*": { - "repo": "facebook/sam2.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "Sam2Model" - } - }, - "tasks": [ - "Sam2Model", - "Sam2VisionModel", - "Sam2PreTrainedModel", - "Sam2HieraDetModel" - ] - } - }, - "info.vit.sam3": { - "*": { - "repo": "facebook/sam3", - "pkg": { - "0": { - "transformers": "Sam3Model" - } - }, - "tasks": [ - "Sam3Model", - "Sam3VisionModel", - "Sam3ViTModel", - "Sam3PreTrainedModel" - ] - } - }, - "info.vit.sam3-tracker1-hiera": { - "*": { - "repo": "facebook/sam3_tracker.1-hiera-tiny", - "pkg": { - "0": { - "transformers": "Sam3TrackerModel" - } - }, - "tasks": [ - "Sam3TrackerModel", - "Sam3TrackerPreTrainedModel" - ] - } - }, - "info.stst.sam3": { - "*": { - "repo": "facebook/sam3", - "pkg": { - "0": { - "transformers": "Sam3VideoModel" - } - }, - "tasks": [ - "Sam3VideoModel", - "Sam3VideoPreTrainedModel", - "Sam3VideoInferenceSession", - "Sam3VideoSegmentationOutput" - ] - } - }, - "info.vit.sam-hq-vit-h": { - "*": { - "repo": "sushmanth/sam_hq_vit_h", - "pkg": { - "0": { - "transformers": "SamHQModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.vit.sam-hq-vit-huge": { - "*": { - "repo": "syscv-community/sam-hq-vit-huge", - "pkg": { - "0": { - "transformers": "SamHQVisionModel" - } - }, - "tasks": [ - "SamHQModel", - "SamHQPreTrainedModel", - "SamHQVisionModel" - ] - } - }, - "info.aet.hf-seamless-m4t": { - "*": { - "repo": "facebook/hf-seamless-m4t-medium", - "pkg": { - "0": { - "transformers": "SeamlessM4TModel" - } - }, - "tasks": [ - "SeamlessM4TForTextToSpeech", - "SeamlessM4TForSpeechToSpeech", - "SeamlessM4TForTextToText", - "SeamlessM4TForSpeechToText", - "SeamlessM4TModel", - "SeamlessM4TPreTrainedModel", - "SeamlessM4TCodeHifiGan", - "SeamlessM4THifiGan", - "SeamlessM4TTextToUnitForConditionalGeneration", - "SeamlessM4TTextToUnitModel" - ] - } - }, - "info.stst.seamless-m4t-v2": { - "*": { - "repo": "facebook/seamless-m4t-v2-large", - "pkg": { - "0": { - "transformers": "SeamlessM4Tv2Model" - } - }, - "tasks": [ - "SeamlessM4Tv2ForTextToSpeech", - "SeamlessM4Tv2ForSpeechToSpeech", - "SeamlessM4Tv2ForTextToText", - "SeamlessM4Tv2ForSpeechToText", - "SeamlessM4Tv2Model", - "SeamlessM4Tv2PreTrainedModel" - ] - } - }, - "info.stst.seedoss": { - "*": { - "repo": "ByteDance-Seed/SeedOss-36B", - "pkg": { - "0": { - "transformers": "SeedOssModel" - } - }, - "tasks": [ - "SeedOssForCausalLM", - "SeedOssForQuestionAnswering", - "SeedOssPreTrainedModel", - "SeedOssModel", - "SeedOssForSequenceClassification", - "SeedOssForTokenClassification" - ] - } - }, - "info.vit.segformer-b0-finetuned-ade-512-512": { - "*": { - "repo": "nvidia/segformer-b0-finetuned-ade-512-512", - "pkg": { - "0": { - "transformers": "SegformerModel" - } - }, - "tasks": [ - "SegformerDecodeHead", - "SegformerForImageClassification", - "SegformerForSemanticSegmentation", - "SegformerLayer", - "SegformerModel", - "SegformerPreTrainedModel" - ] - } - }, - "info.vit.seggpt-vit": { - "*": { - "repo": "BAAI/seggpt-vit-large", - "pkg": { - "0": { - "transformers": "SegGptModel" - } - }, - "tasks": [ - "SegGptModel", - "SegGptPreTrainedModel", - "SegGptForImageSegmentation" - ] - } - }, - "info.aet.sew": { - "*": { - "repo": "asapp/sew-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWModel" - } - }, - "tasks": [ - "SEWForCTC", - "SEWForSequenceClassification", - "SEWModel", - "SEWPreTrainedModel" - ] - } - }, - "info.aet.sew-d": { - "*": { - "repo": "asapp/sew-d-tiny-100k", - "pkg": { - "0": { - "transformers": "SEWDModel" - } - }, - "tasks": [ - "SEWDForCTC", - "SEWDForSequenceClassification", - "SEWDModel", - "SEWDPreTrainedModel" - ] - } - }, - "info.vit.siglip2-patch16-224": { - "*": { - "repo": "google/siglip2-base-patch16-224", - "pkg": { - "0": { - "transformers": "Siglip2Model" - } - }, - "tasks": [ - "Siglip2Model", - "Siglip2PreTrainedModel", - "Siglip2TextModel", - "Siglip2VisionModel", - "Siglip2ForImageClassification" - ] - } - }, - "info.vit.siglip2-patch16-naflex": { - "*": { - "repo": "google/siglip2-base-patch16-naflex", - "pkg": { - "0": { - "transformers": "Siglip2VisionModel" - } - }, - "tasks": [ - "Siglip2Model", - "Siglip2PreTrainedModel", - "Siglip2TextModel", - "Siglip2VisionModel", - "Siglip2ForImageClassification" - ] - } - }, - "info.stst.smollm3": { - "*": { - "repo": "HuggingFaceTB/SmolLM3-3B", - "pkg": { - "0": { - "transformers": "SmolLM3Model" - } - }, - "tasks": [ - "SmolLM3PreTrainedModel", - "SmolLM3Model", - "SmolLM3ForCausalLM", - "SmolLM3ForSequenceClassification", - "SmolLM3ForTokenClassification", - "SmolLM3ForQuestionAnswering" - ] - } - }, - "info.vit.smolvlm": { - "*": { - "repo": "HuggingFaceTB/SmolVLM2-2.2B-Instruct", - "pkg": { - "0": { - "transformers": "SmolVLMModel" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.vit.siglip-so-patch14-384": { - "*": { - "repo": "google/siglip-so400m-patch14-384", - "pkg": { - "0": { - "transformers": "SmolVLMVisionTransformer" - } - }, - "tasks": [ - "SmolVLMForConditionalGeneration", - "SmolVLMPreTrainedModel", - "SmolVLMModel", - "SmolVLMVisionTransformer" - ] - } - }, - "info.aet.s2t-librispeech-asr": { - "*": { - "repo": "facebook/s2t-small-librispeech-asr", - "pkg": { - "0": { - "transformers": "Speech2TextModel" - } - }, - "tasks": [ - "Speech2TextForConditionalGeneration", - "Speech2TextModel", - "Speech2TextPreTrainedModel" - ] - } - }, - "info.stst.speecht5-asr": { - "*": { - "repo": "microsoft/speecht5_asr", - "pkg": { - "0": { - "transformers": "SpeechT5Model" - } - }, - "tasks": [ - "SpeechT5ForSpeechToText", - "SpeechT5ForSpeechToSpeech", - "SpeechT5ForTextToSpeech", - "SpeechT5Model", - "SpeechT5PreTrainedModel", - "SpeechT5HifiGan" - ] - } - }, - "info.art.splinter": { - "*": { - "repo": "tau/splinter-base", - "pkg": { - "0": { - "transformers": "SplinterModel" - } - }, - "tasks": [ - "SplinterForQuestionAnswering", - "SplinterForPreTraining", - "SplinterLayer", - "SplinterModel", - "SplinterPreTrainedModel" - ] - } - }, - "info.art.squeezebert-uncased": { - "*": { - "repo": "squeezebert/squeezebert-uncased", - "pkg": { - "0": { - "transformers": "SqueezeBertModel" - } - }, - "tasks": [ - "SqueezeBertForMaskedLM", - "SqueezeBertForMultipleChoice", - "SqueezeBertForQuestionAnswering", - "SqueezeBertForSequenceClassification", - "SqueezeBertForTokenClassification", - "SqueezeBertModel", - "SqueezeBertModule", - "SqueezeBertPreTrainedModel" - ] - } - }, - "info.stst.stablelm-4e1t": { - "*": { - "repo": "stabilityai/stablelm-3b-4e1t", - "pkg": { - "0": { - "transformers": "StableLmModel" - } - }, - "tasks": [ - "StableLmForCausalLM", - "StableLmModel", - "StableLmPreTrainedModel", - "StableLmForSequenceClassification", - "StableLmForTokenClassification" - ] - } - }, - "info.stst.starcoder2": { - "*": { - "repo": "bigcode/starcoder2-7b", - "pkg": { - "0": { - "transformers": "Starcoder2Model" - } - }, - "tasks": [ - "Starcoder2ForCausalLM", - "Starcoder2Model", - "Starcoder2PreTrainedModel", - "Starcoder2ForSequenceClassification", - "Starcoder2ForTokenClassification" - ] - } - }, - "info.vit.swiftformer-xs": { - "*": { - "repo": "MBZUAI/swiftformer-xs", - "pkg": { - "0": { - "transformers": "SwiftFormerModel" - } - }, - "tasks": [ - "SwiftFormerForImageClassification", - "SwiftFormerModel", - "SwiftFormerPreTrainedModel" - ] - } - }, - "info.vit.swin2sr-classicalsr-x2-64": { - "*": { - "repo": "caidas/swin2sr-classicalsr-x2-64", - "pkg": { - "0": { - "transformers": "Swin2SRModel" - } - }, - "tasks": [ - "Swin2SRForImageSuperResolution", - "Swin2SRModel", - "Swin2SRPreTrainedModel" - ] - } - }, - "info.vit.swinv2-patch4-window8-256": { - "*": { - "repo": "microsoft/swinv2-tiny-patch4-window8-256", - "pkg": { - "0": { - "transformers": "Swinv2Model" - } - }, - "tasks": [ - "Swinv2ForImageClassification", - "Swinv2ForMaskedImageModeling", - "Swinv2Model", - "Swinv2PreTrainedModel", - "Swinv2Backbone" - ] - } - }, - "info.moe.switch-8": { - "*": { - "repo": "google/switch-base-8", - "pkg": { - "0": { - "transformers": "SwitchTransformersModel" - } - }, - "tasks": [ - "SwitchTransformersEncoderModel", - "SwitchTransformersForConditionalGeneration", - "SwitchTransformersModel", - "SwitchTransformersPreTrainedModel", - "SwitchTransformersTop1Router", - "SwitchTransformersSparseMLP" - ] - } - }, - "info.stst.t5": { - "*": { - "repo": "google-t5/t5-small", - "pkg": { - "0": { - "transformers": "T5Model" - } - }, - "identifiers": [ - [ - 4096 - ], - "encoder.embed_tokens.weight", - "text_encoders.t5xxl.transformer.shared.weight", - "t5xxl", - "encoder.block.0.layer.1.DenseReluDense.wi.weight" - ], - "file_256": [ - "ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e", - "565cb2487351282e8e4dbeb88e63f4ad28217ce0439f5a8e6525a924807d2d9b", - "6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635", - "4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d", - "83690f3cc37cecb5e907f41ab0f7abb0855ef24a0a8aab9259f2888ce85a34e2", - "7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09", - "8490f7a22615c20651a63dbe7b4241929826a4de20292dc8e63bfc3c61e3654f", - "d8720addef2596fef86b1b22e4b62875c9118779ba8723759a75dfcbc649ffd5", - "7d0eac95abe8daae454bcd3d166b8bfc6a35fe68278f97479d62dbb6850f38c0", - "ceabd6f71c7112cfaa4dfca8711dda97b79fb9b25983f1c95532de226045f1f8", - "49e139f50824fef40908ef4307c851e7adaa8b91bed44054c4829600dbedfdda", - "211ade1d474f5dc83190aec8be5c4baf52643777790d64de0cbd84f63613e5e9", - "7894547154ba3fd6e364e66e2951ee82b4c3fc1ae0f95df6a4f9d1c5a4e98f17", - "eb529f693f4b17773a24e787fcba29486d5e1700dadcc20bb91e4c8b00212d08", - "d80116f6fc39801e4eef425a584e7a7a41cbe5119797bef2dad67299909fe2ae", - "31ebe18e901bfb6e5709a20ec1c95fce29bce2b9545073231e0f909a53239f5c", - "6be2b0b7e2de7cf2919340c88cb802a103a997ce46c53131cec91958c1db1af4", - "b51cbb10b1a7aac6dd1c3b62f0ed908bfd06e0b42d2f3577d43e061361f51dae", - "9ec60f6028534b7fe5af439fcb535d75a68592a9ca3fcdeb175ef89e3ee99825", - "8f5ab879234384235d56732f0cda07bf8801f30a49645248c5bfdeeb1665f64b", - "86427a1f4dba48940e45bf78d6db5bf0d48fce8b4656f5aba27955f06af9628e", - "88b696cfae098f03bb078cc5944ef03aec1e91ec020a6b016b723a0f0532558c", - "1dc600961d3c5ed081f6700485cdc7ed9cfb4631f2dc385b7ac6bd3c80846d0d", - "f28631189911f8d7931e8fe642a4cb2a3c51f50da7cabbfa06b89bafc19c00d0", - "de9dfdd19d7ba6859993cadec5100665dc7a4fb71e1c6c8970959cbdaf4366e3", - "7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686", - "2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94" - ], - "layer_b3": [ - "ca94e03b7b1fdcb0d6ff5205eac56f145d2dff8a9c489faf80935bfec8387f18", - "c0e2b054bedd782909191b05748a88c28d1538fa91789fec63f036ba01dcc001", - "672de9b79d14001de7d1109ffc52e4d0cccc3bfee6f45648fa347703b58e2b99", - "abdb187a996c51cb0469630c124b14eeb0bb8f5f635aca6c71dea264f8bd61ae", - "8926f862b7763fd9688af317eba7809aa71a478484be0c738c269de368ace4a7", - "e616b754cf55e55b3f9f17ab7e1fff95f0607c81782822fc1223ae22fb1e9f36", - "b79e5f1878a62cd726bb4f9fc1415cacb071d278440e9026290c7b36cb41e1d4", - "77619d5278d9f547ddac17d4d99df56cb6a3a9e660ae31b2f896a4297907e62e", - "c87c9d3cc7becc46ee34821299cf8551a6df5541582a45469a031bccdc4bd340", - "7e6c32c01c89fc5d1610c410135aa9708e77a7444510e5e479fa677ff2b53643", - "a49c2bc301733967ddff113790e301773dc5dd71368b657af4141458de593ced", - "c2ea94030ea362e03d73d448fa5353ace0a449dc38c51a4a49fb148444ebb8ef", - "4a90463350f08ef41479da1d561ab41b8f8b792f1603a092226a838156aebfb0", - "f86cd0324eebbffb81b15ad47dc8b63fedfa51dc222e44e1a958a7becce2bcb0", - "48c54c61c5f14e42761c6177539b2da3a22222516dab053952ca8d8e92f93d65", - "311332d9738773669128814d944b1e860a8e3176b37abf43370bc06b43b454d0", - "3f4e51dec6d542759cdea49b3bec14c090a4908f953fa3e182e2ea43b5b05402", - "beb25461e168359108add77263ea5cc121b7584cc4aa304ffc4e134783bb1d88", - "43313f90a359c8c1c787a7a833b1ab9f7a38204ba36d0ba587c658d0d9bf0852", - "fa9e97cdad26f55fedab83a3f114e0338c9cca3ea2bf8f1b168a6dfc5919bf8e", - "93108d67f8829a7e1e8f3773e9ce53c67f365889c2acfd69816ac80fd43f8e08", - "fc65a6cc55e89394d7bc0fa4ee952d63ce3bdc143b84b5aa4bb3edf7722a6b83", - "8163bc781a7e013dfeb806bbb828a36913cf119363ea5fcd9071d87a0c227cda", - "ad2ba63e1134bad1b15ee339313bc130708b2995e8b4b76fb44d727f28c26ad9", - "4a844772638ffed2f61d45eaac984094b92540fa1391a4098608fc73a6cd4fd8", - "76c31e1fd35da7de7cee97c1e7c5ccde640e6fac3e17a62e115ecf484c7196c3", - "a4d672e22b5bdd8f8b0885cec4a173d0466bb1dcbfbf8400cedcc41c2494f16c", - "d1860c3f01dc9f260d98b50d3d2bbc8dc2d3eefaa93778a8de9d7adfb897fc6e", - "b8719092fc58487406211f52dc55bf40b573ccfd29933a989c33a36b694f6f0a", - "795e272409bc4fa55f402485acf86b607256f91aa965295c5bb771c61f8e9e74" - ], - "layer_256": [ - "bb20f7805209379aea4d6548f17e551cf27d0f8426ca169e4df8234f718ed5ef", - "431580c2d86f9a9ed3500f776a4c997223e5644aed211f965354869ccfa4d76e", - "2ccd548c4ffe34168c60779ebd497b9b410981a2fda813c8723a24a805c94ea0", - "a608fc4e1cc9762e46187a1ce66e98e8ba4bc3a604cbfd96174bd876baea0fa1", - "dc9e74cdf535e0b7a17e1335d0d8b38a00f94facf0cb01363baee09945a25278", - "f07409710a69b2247aa4723a9b40d2225d5e5bfba7b60c51f0ea901fc2ef5ad9", - "ed28f8b6cc472f352fc840b5a9f841ff17d76ae6918f0676464dca20529aa92b", - "97c1a08f87c59b4c55ad4672841977cfce43ca7730bcd11d8c178a9330de1855", - "968972839b859a9c4457f190fad2e17e8585ce27d9ef318df4f5b4e902143944", - "4dbdeadc957c898c327197a3d8770188535672e9208beb29bbf48dfdf51c8955", - "669172c2b5e8b97774d9dd0227ede40c4d25cae3adae97d9f281d03531e7e137", - "39fff130b9ee240102c28a78ee1c4a643e9f800b734ff133f3ab2ad1357bd2f6", - "6e047ed8cb7007034ff15840dd53c92096f0e7ed5befa07808de8afa35d35874", - "adbd0baa059074501b7686db2b0c01715f3a317275c2657c5dfbfd6ee92389b7", - "eb63790fb32b5660de34fa42c2e608df58f7aa3680b4984f0ee9008fe613729c", - "f125c20a33b0ff2dbd4e8ad9acebc34383cb2ef98668169ef79a8c06655ced35", - "e64e0ac83a785ef584a0e86b347fae8f9e2bd84324a49396ca8a9fe7532a947b", - "70001b3ac1b66522142bb86e4c3e87e20c2bbd07276c763878e0838ef6184aad", - "f46fd1e2b5fef3b9f7ae80d183cc77f7be181117a72a0bb933bdef0bc6cd679e", - "83676d73726d101325a47c7f8a60cedf10bab99ea79a6bedad7761220cb4a625", - "a621a907586e5e270e7c7873b167364d8a935ff347d8240fa9bab319678da690", - "f0af1a089f40d8611db5c59469314f1547e2df23c6eff24860359b37ea9bd966", - "72478320b8dbfd9aeaea010dcf0896e3116fa5ab940f3b472882d9f9d2d7333f", - "9c1a88e36334a48d8482fec54b14ea1d5fd31f0dbb65d13cc616e63dc7c42be5", - "d0689f727e8ac4fef3ec4b1f29e8a3bd12e1116559eeefb2a1a457cd4e676d1e", - "fea158a4afcfaa6e95e04799bae0287de0c4fcb188f3b41768a46ce48c71c9df", - "2e5bc4e73312b5aec4c1a55631cb4ed69cf34ccaa6d1f28f7045f137a579b439", - "015fdecbc3b5369dbcb2302e4b79985437ac4496d1b9ad63316423a222fb0803" - ], - "tasks": [ - "T5EncoderModel", - "T5ForConditionalGeneration", - "T5Model", - "T5PreTrainedModel", - "T5ForQuestionAnswering", - "T5ForSequenceClassification", - "T5ForTokenClassification" - ] - } - }, - "info.stst.t5gemma-prefixlm": { - "*": { - "repo": "google/t5gemma-2b-2b-prefixlm-it", - "pkg": { - "0": { - "transformers": "T5GemmaModel" - } - }, - "tasks": [ - "T5GemmaForConditionalGeneration", - "T5GemmaModel", - "T5GemmaEncoderModel", - "T5GemmaPreTrainedModel", - "T5GemmaForSequenceClassification", - "T5GemmaForTokenClassification" - ] - } - }, - "info.stst.t5gemma-2": { - "*": { - "repo": "google/t5gemma-2-270m-270m", - "pkg": { - "0": { - "transformers": "T5Gemma2Model" - } - }, - "tasks": [ - "T5Gemma2ForConditionalGeneration", - "T5Gemma2Model", - "T5Gemma2PreTrainedModel", - "T5Gemma2ForSequenceClassification", - "T5Gemma2ForTokenClassification" - ] - } - }, - "info.detr.table-transformer-detection": { - "*": { - "repo": "microsoft/table-transformer-detection", - "pkg": { - "0": { - "transformers": "TableTransformerModel" - } - }, - "tasks": [ - "TableTransformerForObjectDetection", - "TableTransformerModel", - "TableTransformerPreTrainedModel" - ] - } - }, - "info.art.tapas-finetuned-sqa": { - "*": { - "repo": "google/tapas-base-finetuned-sqa", - "pkg": { - "0": { - "transformers": "TapasModel" - } - }, - "tasks": [ - "TapasForMaskedLM", - "TapasForQuestionAnswering", - "TapasForSequenceClassification", - "TapasModel", - "TapasPreTrainedModel" - ] - } - }, - "info.vit.textnet": { - "*": { - "repo": "czczup/textnet-base", - "pkg": { - "0": { - "transformers": "TextNetModel" - } - }, - "tasks": [ - "TextNetBackbone", - "TextNetModel", - "TextNetPreTrainedModel", - "TextNetForImageClassification" - ] - } - }, - "info.stst.time-series-transformer-tourism-monthly": { - "*": { - "repo": "huggingface/time-series-transformer-tourism-monthly", - "pkg": { - "0": { - "transformers": "TimeSeriesTransformerModel" - } - }, - "tasks": [ - "TimeSeriesTransformerForPrediction", - "TimeSeriesTransformerModel", - "TimeSeriesTransformerPreTrainedModel" - ] - } - }, - "info.art.timesfm-2-pytorch": { - "*": { - "repo": "google/timesfm-2.0-500m-pytorch", - "pkg": { - "0": { - "transformers": "TimesFmModel" - } - }, - "tasks": [ - "TimesFmModelForPrediction", - "TimesFmPreTrainedModel", - "TimesFmModel" - ] - } - }, - "info.vit.timesformer-finetuned-k600": { - "*": { - "repo": "facebook/timesformer-base-finetuned-k600", - "pkg": { - "0": { - "transformers": "TimesformerModel" - } - }, - "tasks": [ - "TimesformerModel", - "TimesformerForVideoClassification", - "TimesformerPreTrainedModel" - ] - } - }, - "info.detr.resnet18-a1-in": { - "*": { - "repo": "timm/resnet18.a1_in1k", - "pkg": { - "0": { - "transformers": "TimmWrapperModel" - } - }, - "tasks": [ - "TimmWrapperPreTrainedModel", - "TimmWrapperModel", - "TimmWrapperForImageClassification" - ] - } - }, - "info.detr.tvp": { - "*": { - "repo": "Intel/tvp-base", - "pkg": { - "0": { - "transformers": "TvpModel" - } - }, - "tasks": [ - "TvpModel", - "TvpPreTrainedModel", - "TvpForVideoGrounding" - ] - } - }, - "info.vit.udop": { - "*": { - "repo": "microsoft/udop-large", - "pkg": { - "0": { - "transformers": "UdopModel" - } - }, - "tasks": [ - "UdopForConditionalGeneration", - "UdopPreTrainedModel", - "UdopModel", - "UdopEncoderModel" - ] - } - }, - "info.stst.umt5": { - "*": { - "repo": "google/umt5-small", - "pkg": { - "0": { - "transformers": "UMT5Model" - } - }, - "identifiers": [ - "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight" - ], - "file_256": [ - "a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58", - "decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72", - "0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6", - "c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99", - "7b8850f1961e1cf8a77cca4c964a358d303f490833c6c087d0cff4b2f99db2af", - "c3355d30191f1f066b26d93fba017ae9809dce6c627dda5f6a66eaa651204f68", - "fa1d36fd54f171ae60fea915c23bd77986b330bbed9729f0d2f8ecbe9168bc48", - "4a3176f32fd70c0a335b4419fcbf8c86cc875e23498c0fc06f5b4aa0930889e0", - "adbc782b9145a27e15d63dfa25057efca0ac75e2db7d372c901ddaa130ca2def", - "b7e2ca4c493c9d51fa951005e8ceba2f4b6b6877cfb4c36a8955c6cd68a1dba7", - "2521d4de0bf9e1cc6549866463ceae85e4ec3239bc6063f7488810be39033bbc", - "9209b4c77b34ad8cf3f06b04c6eaa27e7beeebb348a31f85e3b38a1d719b09ed", - "8bc12d80bc0413573fa58a93626117440b4528f640dd9cb310732e05fa9e6c3e", - "f64f8d6dc4d8a24276df69d0ccea789aae686f7417950a41e6568c30cb478a5c", - "17cf97a5bbbc60a646d6105b832b6f657ce904a8a1ad970e4b59df0c67584a40", - "eaea358bb438c5d211721a4feecc162000e3636e9cb96f51e216f1f44ebd12ce" - ], - "layer_b3": [ - "cd92b29c9099a640e3f5d4a76e64b3467f87f6c056119e0defdff94d311ad6de", - "1c943dbcb8b328a7c6c852921ddaefbd84c9df8c83bc51fe303c1f06cb734102", - "1639a6467af0db1e15828d33b878e568cba1335947eeadd481170bcdc9ba8e33", - "72a0329740dee29a2c099eec3c320b3945590a74293356014c30249fe69652e5", - "0374cba03c607ffe8ab8f04994d82f82e80901dc7578f1a9a6cb2637608be5d5", - "d75a407f873e1cfa1a0a36214b53b14bfebe9253ea263465151c07f0d57f3f29", - "621153502b985c143d304318c91dc3d10296d24268c81e3538fc336fdc84c915", - "43bb052945d38a68bec27c3d26162e88e306e6074d027d3b4b2b8ae2b1851691", - "98f50ea5d55e61c1478df47e567e48bdd036d240b9129e64d53a826406900adc", - "9400313b8eae31699473daa5f840d25a4ef660f68de9a7894f1a28f214f23384", - "9f13826b8e4ddde24d80de6a947a7868e26cea25dda52790ee6ed695ff72b9bb", - "475773ab108a537ff904b84e7f3a80129ba4983deb7170b6b52c922ece6069ce", - "5ef27b3c1eddb08cfe41b452cf9529d86dff811645d40c165bae324486d19e96", - "e170559d8551cfe651344594e54c0a9a90c0068b00f3866f6e9a3737e20925cb", - "e8dc7442a20bcdc7b6e5dd0265939d88896eab5ddd33ee16f1f09537e65914b8", - "4d3d5049857d01741780daf01e96617092973305637b435f4895499a26bbaede", - "7a2adadc2372feda23b2169337276adda6d1fdef82ba69f0d3321c4c6ba8c604", - "0a7c61a85bb3f51f75924de48ef3f5e87cbf8901f600cbfcae97f5e2919c4148" - ], - "layer_256": [ - "467916d35f3053dce1d40d998fcaf6aa03feda75aa578d964dd61461e23641a3", - "58deeef888d4ded4ffababfbf8da27227a4a6ff8adfa42016e12c0180f713816", - "178ebd3fa3418d33a2e45a80d8b9d3662ff4a8e75f3de3f0332f82c505d8152a", - "8700dcb651465fe6c925b7ad6068b58b32951832fff0ed19819510f8d0713ee5", - "954f2129ba166e746c71433f717b572d8869ec14b32b7f214d1701d3b1120047", - "32f5fc1daea014b6488b96c2a1330e0aad87e074844fa3e2e3f20b9e58440395", - "9245abaf6df8a4b5fcc828ecbcd7b21a1b19bf5f3c4388fb5c8eabc140276dce", - "172d0fbbd379ae014a7008e148813818494e9e645db802fd000d443369df9d17", - "2fa68a26b0386aaf9123d2b4067dafc8631ee724602197dd353f3ea5a61dac8a", - "16f0054014e6d07b86b0526d5bcfed7d2aa3aebe3e44e6758933d90cbd3da46e", - "fd62047f5d27ff43210c117dc0f253c101e694a5331d6b684688606c92c65ccf", - "ddc4f38db9f132fb1b736c1d693b5c039a2d6fe83bdf4f1c1e7a2745b5d79124", - "9e9ab11b3ea059b84ae2bcc5be76ab3f730a486d92a16f1fd2a959bdc2ede08f", - "bfb178b1ce27f00e122d2328c662fdef6cc239c07efc749aa61ae2d395441b02", - "50addf6a911b90194a75b0212429d1af55eb2f9d24715479b9ccc4a40adc299b", - "2e46e9f1b714d72160d3b3b775a845b3049a01396fab935f1278d9e8de2ef0c6", - "db8d2b49d9042e39d6531b33ec3bebb9cdf42b9e6ad56163f08da2a7da2a53cd", - "2d81d19ad5440422b85e0b17c71914269f6c25c9b1fa321c0dd6119ddb41d62d" - ], - "tasks": [ - "UMT5EncoderModel", - "UMT5ForConditionalGeneration", - "UMT5ForQuestionAnswering", - "UMT5ForSequenceClassification", - "UMT5ForTokenClassification", - "UMT5Model", - "UMT5PreTrainedModel" - ] - } - }, - "info.aet.unispeech-1500h-cv": { - "*": { - "repo": "microsoft/unispeech-large-1500h-cv", - "pkg": { - "0": { - "transformers": "UniSpeechModel" - } - }, - "tasks": [ - "UniSpeechForCTC", - "UniSpeechForPreTraining", - "UniSpeechForSequenceClassification", - "UniSpeechModel", - "UniSpeechPreTrainedModel" - ] - } - }, - "info.aet.unispeech-sat-100h-libri-ft": { - "*": { - "repo": "microsoft/unispeech-sat-base-100h-libri-ft", - "pkg": { - "0": { - "transformers": "UniSpeechSatModel" - } - }, - "tasks": [ - "UniSpeechSatForAudioFrameClassification", - "UniSpeechSatForCTC", - "UniSpeechSatForPreTraining", - "UniSpeechSatForSequenceClassification", - "UniSpeechSatForXVector", - "UniSpeechSatModel", - "UniSpeechSatPreTrainedModel" - ] - } - }, - "info.gan.univnet-dev": { - "*": { - "repo": "dg845/univnet-dev", - "pkg": { - "0": { - "transformers": "UnivNetModel" - } - }, - "tasks": [ - "UnivNetModel" - ] - } - }, - "info.stst.vaultgemma": { - "*": { - "repo": "google/vaultgemma-7b", - "pkg": { - "0": { - "transformers": "VaultGemmaModel" - } - }, - "tasks": [ - "VaultGemmaForCausalLM", - "VaultGemmaModel", - "VaultGemmaPreTrainedModel" - ] - } - }, - "info.vit.videollama3-image-hf": { - "*": { - "repo": "lkhl/VideoLLaMA3-2B-Image-HF", - "pkg": { - "0": { - "transformers": "VideoLlama3Model" - } - }, - "tasks": [ - "VideoLlama3VisionModel", - "VideoLlama3PreTrainedModel", - "VideoLlama3Model", - "VideoLlama3ForConditionalGeneration" - ] - } - }, - "info.vit.video-llava-hf": { - "*": { - "repo": "LanguageBind/Video-LLaVA-7B-hf", - "pkg": { - "0": { - "transformers": "VideoLlavaModel" - } - }, - "tasks": [ - "VideoLlavaPreTrainedModel", - "VideoLlavaModel", - "VideoLlavaForConditionalGeneration" - ] - } - }, - "info.vit.videomae": { - "*": { - "repo": "MCG-NJU/videomae-base", - "pkg": { - "0": { - "transformers": "VideoMAEModel" - } - }, - "tasks": [ - "VideoMAEForPreTraining", - "VideoMAEModel", - "VideoMAEPreTrainedModel", - "VideoMAEForVideoClassification" - ] - } - }, - "info.vit.vilt-b32-mlm": { - "*": { - "repo": "dandelin/vilt-b32-mlm", - "pkg": { - "0": { - "transformers": "ViltModel" - } - }, - "tasks": [ - "ViltForImageAndTextRetrieval", - "ViltForImagesAndTextClassification", - "ViltForTokenClassification", - "ViltForMaskedLM", - "ViltForQuestionAnswering", - "ViltLayer", - "ViltModel", - "ViltPreTrainedModel" - ] - } - }, - "info.vit.vip-llava-hf": { - "*": { - "repo": "ybelkada/vip-llava-7b-hf", - "pkg": { - "0": { - "transformers": "VipLlavaModel" - } - }, - "tasks": [ - "VipLlavaModel", - "VipLlavaForConditionalGeneration", - "VipLlavaPreTrainedModel" - ] - } - }, - "info.vit.japanese-clip-vit-h-14-bert-wider": { - "*": { - "repo": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", - "pkg": { - "0": { - "transformers": "VisionTextDualEncoderModel" - } - }, - "tasks": [ - "VisionTextDualEncoderModel" - ] - } - }, - "info.art.visualbert-vqa-coco-pre": { - "*": { - "repo": "uclanlp/visualbert-vqa-coco-pre", - "pkg": { - "0": { - "transformers": "VisualBertModel" - } - }, - "tasks": [ - "VisualBertForMultipleChoice", - "VisualBertForPreTraining", - "VisualBertForQuestionAnswering", - "VisualBertForRegionToPhraseAlignment", - "VisualBertForVisualReasoning", - "VisualBertLayer", - "VisualBertModel", - "VisualBertPreTrainedModel" - ] - } - }, - "info.vit.vit-patch16-224": { - "*": { - "repo": "google/vit-base-patch16-224", - "pkg": { - "0": { - "transformers": "ViTModel" - } - }, - "tasks": [ - "ViTForImageClassification", - "ViTForMaskedImageModeling", - "ViTModel", - "ViTPreTrainedModel" - ] - } - }, - "info.vit.vit-mae": { - "*": { - "repo": "facebook/vit-mae-base", - "pkg": { - "0": { - "transformers": "ViTMAEModel" - } - }, - "tasks": [ - "ViTMAEForPreTraining", - "ViTMAELayer", - "ViTMAEModel", - "ViTMAEPreTrainedModel" - ] - } - }, - "info.vit.vit-msn": { - "*": { - "repo": "facebook/vit-msn-base", - "pkg": { - "0": { - "transformers": "ViTMSNModel" - } - }, - "tasks": [ - "ViTMSNModel", - "ViTMSNForImageClassification", - "ViTMSNPreTrainedModel" - ] - } - }, - "info.vit.vitdet-patch16-224": { - "*": { - "repo": "google/vitdet-base-patch16-224", - "pkg": { - "0": { - "transformers": "VitDetModel" - } - }, - "tasks": [ - "VitDetModel", - "VitDetPreTrainedModel", - "VitDetBackbone" - ] - } - }, - "info.art.mms-tts-eng": { - "*": { - "repo": "facebook/mms-tts-eng", - "pkg": { - "0": { - "transformers": "VitsModel" - } - }, - "tasks": [ - "VitsModel", - "VitsPreTrainedModel" - ] - } - }, - "info.vit.vivit16x2-kinetics400": { - "*": { - "repo": "google/vivit-b-16x2-kinetics400", - "pkg": { - "0": { - "transformers": "VivitModel" - } - }, - "tasks": [ - "VivitModel", - "VivitPreTrainedModel", - "VivitForVideoClassification" - ] - } - }, - "info.vit.vjepa2-vitl-fpc64-256": { - "*": { - "repo": "facebook/vjepa2-vitl-fpc64-256", - "pkg": { - "0": { - "transformers": "VJEPA2Model" - } - }, - "tasks": [ - "VJEPA2Model", - "VJEPA2PreTrainedModel", - "VJEPA2ForVideoClassification" - ] - } - }, - "info.stst.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralForConditionalGeneration" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.aet.voxtral-2507": { - "*": { - "repo": "mistralai/Voxtral-Mini-3B-2507", - "pkg": { - "0": { - "transformers": "VoxtralEncoder" - } - }, - "tasks": [ - "VoxtralPreTrainedModel", - "VoxtralEncoder", - "VoxtralForConditionalGeneration" - ] - } - }, - "info.aet.wav2vec2-960h": { - "*": { - "repo": "facebook/wav2vec2-base-960h", - "pkg": { - "0": { - "transformers": "Wav2Vec2Model" - } - }, - "tasks": [ - "Wav2Vec2ForAudioFrameClassification", - "Wav2Vec2ForCTC", - "Wav2Vec2ForMaskedLM", - "Wav2Vec2ForPreTraining", - "Wav2Vec2ForSequenceClassification", - "Wav2Vec2ForXVector", - "Wav2Vec2Model", - "Wav2Vec2PreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-bert-rel-pos": { - "*": { - "repo": "facebook/w2v-bert-2.0", - "pkg": { - "0": { - "transformers": "Wav2Vec2BertModel" - } - }, - "tasks": [ - "Wav2Vec2BertForAudioFrameClassification", - "Wav2Vec2BertForCTC", - "Wav2Vec2BertForSequenceClassification", - "Wav2Vec2BertForXVector", - "Wav2Vec2BertModel", - "Wav2Vec2BertPreTrainedModel" - ] - } - }, - "info.aet.wav2vec2-conformer-rel-pos": { - "*": { - "repo": "facebook/wav2vec2-conformer-rel-pos-large", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerModel" - } - }, - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.aet.wavlm": { - "*": { - "repo": "microsoft/wavlm-base", - "pkg": { - "0": { - "transformers": "WavLMModel" - } - }, - "tasks": [ - "WavLMForAudioFrameClassification", - "WavLMForCTC", - "WavLMForSequenceClassification", - "WavLMForXVector", - "WavLMModel", - "WavLMPreTrainedModel" - ] - } - }, - "info.aet.whisper": { - "*": { - "repo": "openai/whisper-tiny", - "pkg": { - "0": { - "transformers": "WhisperModel" - } - }, - "tasks": [ - "WhisperForCausalLM", - "WhisperForConditionalGeneration", - "WhisperModel", - "WhisperPreTrainedModel", - "WhisperForAudioClassification" - ] - } - }, - "info.vit.xclip-patch32": { - "*": { - "repo": "microsoft/xclip-base-patch32", - "pkg": { - "0": { - "transformers": "XCLIPModel" - } - }, - "tasks": [ - "XCLIPModel", - "XCLIPPreTrainedModel", - "XCLIPTextModel", - "XCLIPVisionModel" - ] - } - }, - "info.gan.x-codec": { - "*": { - "repo": "Manel/X-Codec", - "pkg": { - "0": { - "transformers": "XcodecModel" - } - }, - "tasks": [ - "XcodecModel", - "XcodecPreTrainedModel" - ] - } - }, - "info.art.xglm": { - "*": { - "repo": "facebook/xglm-564M", - "pkg": { - "0": { - "transformers": "XGLMModel" - } - }, - "tasks": [ - "XGLMForCausalLM", - "XGLMModel", - "XGLMPreTrainedModel" - ] - } - }, - "info.art.xlm-mlm-en-2048": { - "*": { - "repo": "FacebookAI/xlm-mlm-en-2048", - "pkg": { - "0": { - "transformers": "XLMModel" - } - }, - "tasks": [ - "XLMForMultipleChoice", - "XLMForQuestionAnswering", - "XLMForQuestionAnsweringSimple", - "XLMForSequenceClassification", - "XLMForTokenClassification", - "XLMModel", - "XLMPreTrainedModel", - "XLMWithLMHeadModel" - ] - } - }, - "info.art.xlm-roberta": { - "*": { - "repo": "FacebookAI/xlm-roberta-base", - "pkg": { - "0": { - "transformers": "XLMRobertaModel" - } - }, - "tasks": [ - "XLMRobertaForCausalLM", - "XLMRobertaForMaskedLM", - "XLMRobertaForMultipleChoice", - "XLMRobertaForQuestionAnswering", - "XLMRobertaForSequenceClassification", - "XLMRobertaForTokenClassification", - "XLMRobertaModel", - "XLMRobertaPreTrainedModel" - ] - } - }, - "info.art.xlm-roberta-xl": { - "*": { - "repo": "facebook/xlm-roberta-xl", - "pkg": { - "0": { - "transformers": "XLMRobertaXLModel" - } - }, - "tasks": [ - "XLMRobertaXLForCausalLM", - "XLMRobertaXLForMaskedLM", - "XLMRobertaXLForMultipleChoice", - "XLMRobertaXLForQuestionAnswering", - "XLMRobertaXLForSequenceClassification", - "XLMRobertaXLForTokenClassification", - "XLMRobertaXLModel", - "XLMRobertaXLPreTrainedModel" - ] - } - }, - "info.art.xlnet-cased": { - "*": { - "repo": "xlnet/xlnet-large-cased", - "pkg": { - "0": { - "transformers": "XLNetModel" - } - }, - "tasks": [ - "XLNetForMultipleChoice", - "XLNetForQuestionAnswering", - "XLNetForQuestionAnsweringSimple", - "XLNetForSequenceClassification", - "XLNetForTokenClassification", - "XLNetLMHeadModel", - "XLNetModel", - "XLNetPreTrainedModel" - ] - } - }, - "info.lstm.xlstm": { - "*": { - "repo": "NX-AI/xLSTM-7b", - "pkg": { - "0": { - "transformers": "xLSTMModel" - } - }, - "tasks": [ - "xLSTMForCausalLM", - "xLSTMModel", - "xLSTMPreTrainedModel" - ] - } - }, - "info.art.xmod": { - "*": { - "repo": "facebook/xmod-base", - "pkg": { - "0": { - "transformers": "XmodModel" - } - }, - "tasks": [ - "XmodForCausalLM", - "XmodForMaskedLM", - "XmodForMultipleChoice", - "XmodForQuestionAnswering", - "XmodForSequenceClassification", - "XmodForTokenClassification", - "XmodModel", - "XmodPreTrainedModel" - ] - } - }, - "info.cnn.yolos": { - "*": { - "repo": "hustvl/yolos-base", - "pkg": { - "0": { - "transformers": "YolosModel" - } - }, - "tasks": [ - "YolosForObjectDetection", - "YolosModel", - "YolosPreTrainedModel" - ] - } - }, - "info.art.yoso-4096": { - "*": { - "repo": "uw-madison/yoso-4096", - "pkg": { - "0": { - "transformers": "YosoModel" - } - }, - "tasks": [ - "YosoForMaskedLM", - "YosoForMultipleChoice", - "YosoForQuestionAnswering", - "YosoForSequenceClassification", - "YosoForTokenClassification", - "YosoLayer", - "YosoModel", - "YosoPreTrainedModel" - ] - } - }, - "info.ssm.zamba-v1": { - "*": { - "repo": "Zyphra/Zamba-7B-v1", - "pkg": { - "0": { - "transformers": "ZambaModel" - } - }, - "tasks": [ - "ZambaForCausalLM", - "ZambaForSequenceClassification", - "ZambaModel", - "ZambaPreTrainedModel" - ] - } - }, - "info.ssm.zamba2": { - "*": { - "repo": "Zyphra/Zamba2-2.7B", - "pkg": { - "0": { - "transformers": "Zamba2Model" - } - }, - "tasks": [ - "Zamba2ForCausalLM", - "Zamba2ForSequenceClassification", - "Zamba2Model", - "Zamba2PreTrainedModel" - ] - } - }, - "ops.precision.uint": { - "U8": { - "pkg": { - "0": { - "torch": { - "uint8": { - "variant": "uint8" - } - } - } - } - }, - "U16": { - "pkg": { - "0": { - "torch": { - "uint16": { - "variant": "uint16" - } - } - } - } - }, - "U32": { - "pkg": { - "0": { - "torch": { - "uint32": { - "variant": "uint32" - } - } - } - } - }, - "U64": { - "pkg": { - "0": { - "torch": { - "uint64": { - "variant": "uint64" - } - } - } - } - }, - "U1": { - "pkg": { - "0": { - "torch": { - "uint1": { - "variant": "uint1" - } - } - } - } - }, - "U2": { - "pkg": { - "0": { - "torch": { - "uint2": { - "variant": "uint2" - } - } - } - } - }, - "U3": { - "pkg": { - "0": { - "torch": { - "uint3": { - "variant": "uint3" - } - } - } - } - }, - "U4": { - "pkg": { - "0": { - "torch": { - "uint4": { - "variant": "uint4" - } - } - } - } - }, - "U5": { - "pkg": { - "0": { - "torch": { - "uint5": { - "variant": "uint5" - } - } - } - } - }, - "U6": { - "pkg": { - "0": { - "torch": { - "uint6": { - "variant": "uint6" - } - } - } - } - }, - "U7": { - "pkg": { - "0": { - "torch": { - "uint7": { - "variant": "uint7" - } - } - } - } - } - }, - "ops.precision.int": { - "I8": { - "pkg": { - "0": { - "torch": { - "int8": { - "variant": "int8" - } - } - } - } - }, - "I16": { - "pkg": { - "0": { - "torch": { - "int16": { - "variant": "int16" - } - } - } - } - }, - "I32": { - "pkg": { - "0": { - "torch": { - "int32": { - "variant": "int32" - } - } - } - } - }, - "I64": { - "pkg": { - "0": { - "torch": { - "int64": { - "variant": "int64" - } - } - } - } - }, - "Q8": { - "pkg": { - "0": { - "torch": { - "qint8": { - "variant": "qint8" - } - } - } - } - }, - "Q32": { - "pkg": { - "0": { - "torch": { - "qint32": { - "variant": "qint32" - } - } - } - } - }, - "I1": { - "pkg": { - "0": { - "torch": { - "int1": { - "variant": "int1" - } - } - } - } - }, - "I2": { - "pkg": { - "0": { - "torch": { - "int2": { - "variant": "int2" - } - } - } - } - }, - "I3": { - "pkg": { - "0": { - "torch": { - "int3": { - "variant": "int3" - } - } - } - } - }, - "I4": { - "pkg": { - "0": { - "torch": { - "int4": { - "variant": "int4" - } - } - } - } - }, - "I5": { - "pkg": { - "0": { - "torch": { - "int5": { - "variant": "int5" - } - } - } - } - }, - "I6": { - "pkg": { - "0": { - "torch": { - "int6": { - "variant": "int6" - } - } - } - } - }, - "I7": { - "pkg": { - "0": { - "torch": { - "int7": { - "variant": "int7" - } - } - } - } - } - }, - "ops.precision.float": { - "F16": { - "pkg": { - "0": { - "torch": { - "float16": { - "variant": "fp16" - } - } - } - } - }, - "F32": { - "pkg": { - "0": { - "torch": { - "float32": { - "variant": "fp32" - } - } - } - } - }, - "F64": { - "pkg": { - "0": { - "torch": { - "float64": { - "variant": "fp64" - } - } - } - } - }, - "F8_E5M2": { - "pkg": { - "0": { - "torch": { - "float8_e5m2": { - "variant": "fp8_e5m2" - } - } - } - } - }, - "F8_E4M3": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fn": { - "variant": "fp8_e4m3fn" - } - } - } - } - }, - "F8_E5M2FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e5m2fnuz": { - "variant": "fp8_e5m2fnuz" - } - } - } - } - }, - "F8_E4M3FNUZ": { - "pkg": { - "0": { - "torch": { - "float8_e4m3fnuz": { - "variant": "fp8_e4m3fnuz" - } - } - } - } - }, - "F8_E8M0FNU": { - "pkg": { - "0": { - "torch": { - "float8_e8m0fnu": { - "variant": "fp8_e8m0fnu" - } - } - } - } - }, - "F8_E2M1": { - "pkg": { - "0": { - "torch": { - "float4_e2m1fn_x2": { - "variant": "fp4_e2m1fn_x2" - } - } - } - } - } - }, - "ops.precision.complex": { - "C32": { - "pkg": { - "0": { - "torch": { - "complex32": { - "variant": "complex32" - } - } - } - } - }, - "C64": { - "pkg": { - "0": { - "torch": { - "complex64": { - "variant": "complex64" - } - } - } - } - }, - "C128": { - "pkg": { - "0": { - "torch": { - "complex128": { - "variant": "complex128" - } - } - } - } - } - }, - "ops.precision.bool": { - "Bbool": { - "pkg": { - "0": { - "torch": { - "bool": { - "variant": "bool" - } - } - } - } - } - }, - "ops.precision.quint": { - "Q8": { - "pkg": { - "0": { - "torch": { - "quint8": { - "variant": "quint8" - } - } - } - } - }, - "Q4x2": { - "pkg": { - "0": { - "torch": { - "quint4x2": { - "variant": "quint4x2" - } - } - } - } - }, - "Q2x4": { - "pkg": { - "0": { - "torch": { - "quint2x4": { - "variant": "quint2x4" - } - } - } - } - } - }, - "ops.precision.bfloat": { - "B16": { - "pkg": { - "0": { - "torch": { - "bfloat16": { - "variant": "bf16" - } - } - } - } - } - }, - "ops.precision.bits": { - "B1x8": { - "pkg": { - "0": { - "torch": { - "bits1x8": { - "variant": "bits1x8" - } - } - } - } - }, - "B2x4": { - "pkg": { - "0": { - "torch": { - "bits2x4": { - "variant": "bits2x4" - } - } - } - } - }, - "B4x2": { - "pkg": { - "0": { - "torch": { - "bits4x2": { - "variant": "bits4x2" - } - } - } - } - }, - "B8": { - "pkg": { - "0": { - "torch": { - "bits8": { - "variant": "bits8" - } - } - } - } - }, - "B16": { - "pkg": { - "0": { - "torch": { - "bits16": { - "variant": "bits16" - } - } - } - } - } - }, - "ops.scheduler.amused": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "AmusedScheduler", - "module_path": "diffusers.schedulers.scheduling_amused" - } - } - } - }, - "ops.scheduler.cmstochasticiterative": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CMStochasticIterativeScheduler", - "module_path": "diffusers.schedulers.scheduling_consistency_models" - } - } - } - }, - "ops.scheduler.cogvideoxddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_cogvideox" - } - } - } - }, - "ops.scheduler.cogvideoxdpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "CogVideoXDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_dpm_cogvideox" - } - } - } - }, - "ops.scheduler.ddiminverse": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_inverse" - } - } - } - }, - "ops.scheduler.ddimparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim_parallel" - } - } - } - }, - "ops.scheduler.ddim": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDIMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddim" - } - } - } - }, - "ops.scheduler.ddpmparallel": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMParallelScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_parallel" - } - } - } - }, - "ops.scheduler.ddpm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm" - } - } - } - }, - "ops.scheduler.ddpmwuerstchen": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "DDPMWuerstchenScheduler", - "module_path": "diffusers.schedulers.scheduling_ddpm_wuerstchen" - } - } - } - }, - "ops.scheduler.deis": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DEISMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_deis_multistep" - } - } - } - }, - "ops.scheduler.dpminverse": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepInverseScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep_inverse" - } - } - } - }, - "ops.scheduler.dpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "DPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.dpmsinglestep": { - "solver": { - "pkg": { - "0": { - "diffusers": "DPMSolverSinglestepScheduler", - "module_path": "diffusers.schedulers.scheduling_dpmsolver_singlestep" - } - } - } - }, - "ops.scheduler.edmdpm": { - "multistep": { - "pkg": { - "0": { - "diffusers": "EDMDPMSolverMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_dpmsolver_multistep" - } - } - } - }, - "ops.scheduler.edmeuler": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "EDMEulerScheduler", - "module_path": "diffusers.schedulers.scheduling_edm_euler" - } - } - } - }, - "ops.scheduler.eulerancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerAncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_ancestral_discrete" - } - } - } - }, - "ops.scheduler.euler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "EulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatcheuler": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchEulerDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_euler_discrete" - } - } - } - }, - "ops.scheduler.flowmatchheun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "FlowMatchHeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_heun_discrete" - } - } - } - }, - "ops.scheduler.flowmatchlcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "FlowMatchLCMScheduler", - "module_path": "diffusers.schedulers.scheduling_flow_match_lcm" - } - } - } - }, - "ops.scheduler.heun": { - "discrete": { - "pkg": { - "0": { - "diffusers": "HeunDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_heun_discrete" - } - } - } - }, - "ops.scheduler.ipndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "IPNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_ipndm" - } - } - } - }, - "ops.scheduler.karrasve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "KarrasVeScheduler", - "module_path": "diffusers.schedulers.deprecated.scheduling_karras_ve" - } - } - } - }, - "ops.scheduler.kdpm2ancestral": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2AncestralDiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete" - } - } - } - }, - "ops.scheduler.kdpm2": { - "discrete": { - "pkg": { - "0": { - "diffusers": "KDPM2DiscreteScheduler", - "module_path": "diffusers.schedulers.scheduling_k_dpm_2_discrete" - } - } - } - }, - "ops.scheduler.lcm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "LCMScheduler", - "module_path": "diffusers.schedulers.scheduling_lcm" - } - } - } - }, - "ops.scheduler.pndm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "PNDMScheduler", - "module_path": "diffusers.schedulers.scheduling_pndm" - } - } - } - }, - "ops.scheduler.repaint": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "RePaintScheduler", - "module_path": "diffusers.schedulers.scheduling_repaint" - } - } - } - }, - "ops.scheduler.sa": { - "solver": { - "pkg": { - "0": { - "diffusers": "SASolverScheduler", - "module_path": "diffusers.schedulers.scheduling_sasolver" - } - } - } - }, - "ops.scheduler.scm": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "SCMScheduler", - "module_path": "diffusers.schedulers.scheduling_scm" - } - } - } - }, - "ops.scheduler.scoresdeve": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "ScoreSdeVeScheduler", - "module_path": "diffusers.schedulers.scheduling_sde_ve" - } - } - } - }, - "ops.scheduler.tcd": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "TCDScheduler", - "module_path": "diffusers.schedulers.scheduling_tcd" - } - } - } - }, - "ops.scheduler.unclip": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "UnCLIPScheduler", - "module_path": "diffusers.schedulers.scheduling_unclip" - } - } - } - }, - "ops.scheduler.unipc": { - "multistep": { - "pkg": { - "0": { - "diffusers": "UniPCMultistepScheduler", - "module_path": "diffusers.schedulers.scheduling_unipc_multistep" - } - } - } - }, - "ops.scheduler.vqdiffusion": { - "scheduler": { - "pkg": { - "0": { - "diffusers": "VQDiffusionScheduler", - "module_path": "diffusers.schedulers.scheduling_vq_diffusion" - } - } - } - }, - "ops.scheduler.karrasdiffusion": { - "schedulers": { - "pkg": { - "0": { - "diffusers": "KarrasDiffusionSchedulers", - "module_path": "diffusers.schedulers.scheduling_utils" - } - } - } - }, - "info.lora.dmd": { - "stable-diffusion-xl-1": { - "repo": "tianweiy/DMD2", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "timesteps": [ - 999, - 749, - 499, - 249 - ] - }, - "scheduler": { - "ops.scheduler.lcm": "" - } - } - }, - "file_256": [ - "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", - "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb" - ] - } - }, - "info.lora.dpo": { - "stable-diffusion-xl-1": { - "repo": "radames/sdxl-DPO-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5, - "num_inference_steps": 4 - }, - "scheduler": { - "ops.scheduler.dpm": { - "algorithm_type": "sde-dpmsolver++", - "use_karras_sigmas": true, - "order": 2 - } - } - } - }, - "file_256": [ - "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", - "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad" - ] - } - }, - "info.lora.flash": { - "stable-diffusion-xl-1": { - "repo": "jasperai/flash-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": "ops.scheduler.lcm" - } - }, - "file_256": [ - "afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7" - ] - }, - "pixart-alpha": { - "repo": "jasperai/flash-pixart", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b" - ] - }, - "stable-diffusion-3": { - "repo": "jasperai/flash-sd3", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15" - ] - }, - "stable-diffusion-v1-5": { - "repo": "jasperai/flash-sd", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - }, - "file_256": [ - "99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f" - ] - } - }, - "info.lora.hyper": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - } - } - }, - "file_256": { - "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": { - "num_inference_steps": 12 - }, - "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": { - "num_inference_steps": 8 - }, - "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "flux1-dev": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - } - } - }, - "file_256": { - "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": { - "num_inference_steps": 16 - }, - "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": { - "num_inference_steps": 4 - }, - "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": { - "num_inference_steps": 8 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "ByteDance/Hyper-SD", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": { - "num_inference_steps": 12 - }, - "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": { - "num_inference_steps": 8 - }, - "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": { - "num_inference_steps": 1, - "guidance_scale": 0.0 - }, - "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - } - }, - "info.lora.lcm": { - "stable-diffusion-xl-1": { - "repo": "latent-consistency/lcm-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141" - ] - }, - "ssd": { - "repo": "latent-consistency/lcm-lora-ssd-1b", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b" - ] - }, - "segmind-vega": { - "repo": "segmind/Segmind-VegaRT", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "gen_kwargs": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb" - ] - }, - "stable-diffusion-v1-5": { - "repo": "latent-consistency/lcm-lora-sdv1-5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 8 - } - } - }, - "file_256": [ - "8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4" - ] - } - }, - "info.lora.lightning": { - "stable-diffusion-xl-1": { - "repo": "ByteDance/SDXL-Lightning", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0 - } - } - } - } - }, - "info.lora.pcm": { - "stable-diffusion-xl-1": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": { - "num_inference_steps": 16 - }, - "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": { - "num_inference_steps": 16 - }, - "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": { - "num_inference_steps": 4 - }, - "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": { - "num_inference_steps": 4 - }, - "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": { - "num_inference_steps": 8 - }, - "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": { - "num_inference_steps": 8 - }, - "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - }, - "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-v1-5": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": { - "num_inference_steps": 16 - }, - "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": { - "num_inference_steps": 4 - }, - "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": { - "num_inference_steps": 8 - }, - "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": { - "num_inference_steps": 16, - "guidance_scale": 0.0 - }, - "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": { - "num_inference_steps": 2, - "guidance_scale": 0.0 - }, - "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": { - "num_inference_steps": 4, - "guidance_scale": 0.0 - }, - "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": { - "num_inference_steps": 8, - "guidance_scale": 0.0 - } - } - }, - "stable-diffusion-3": { - "repo": "wangfuyun/PCM_Weights", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": { - "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": { - "num_inference_steps": 2, - "guidance_scale": 1.2 - }, - "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - }, - "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": { - "num_inference_steps": 4, - "guidance_scale": 1.2 - } - } - } - }, - "info.lora.slam": { - "stable-diffusion-xl-1": { - "repo": "alimama-creative/slam-lora-sdxl", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "scheduler": { - "ops.scheduler.lcm": { - "timestep_spacing": "trailing" - } - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 1 - } - } - }, - "file_256": [ - "22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91" - ] - }, - "stable-diffusion-v1-5": { - "repo": "alimama-creative/slam-sd1.5", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - } - } - }, - "info.lora.spo": { - "stable-diffusion-xl-1": { - "repo": "SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 5.0 - } - } - }, - "file_256": [ - "0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df" - ] - }, - "stable-diffusion-v1-5": { - "repo": "SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "guidance_scale": 7.5 - } - } - }, - "file_256": [ - "1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4" - ] - } - }, - "info.lora.tcd": { - "stable-diffusion-xl-1": { - "repo": "h1t/TCD-SDXL-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - }, - "generation": { - "num_inference_steps": 4, - "guidance_scale": 0, - "eta": 0.3 - }, - "scheduler": { - "ops.scheduler.tcd": {} - } - } - }, - "file_256": [ - "2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba" - ] - }, - "stable-diffusion-v1-5": { - "repo": "h1t/TCD-SD15-LoRA", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": {} - } - } - }, - "file_256": [ - "eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232" - ], - "layer_256": [ - "e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75" - ], - "layer_b3": [ - "90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b" - ] - } - }, - "info.lora.turbo": { - "stable-diffusion-xl-1": { - "file_256": [ - "a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69" - ] - }, - "flux1-dev": { - "repo": "alimama-creative/FLUX.1-Turbo-Alpha", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 0.125 - } - }, - "generation": { - "guidance_scale": 3.5, - "num_inference_steps": 8, - "max_sequence_length": 512 - } - } - }, - "file_256": [ - "77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff" - ] - }, - "stable-diffusion-3": { - "repo": "tensorart/stable-diffusion-3.5-large-TurboX", - "pkg": { - "0": { - "diffusers": { - "load_lora_weights": { - "fuse": 1.0 - } - }, - "scheduler": { - "ops.scheduler.flow-match": { - "shift": 5 - } - } - } - }, - "file_256": { - "fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": { - "num_inference_steps": "8" - } - } - } - }, - "info.art.audiogen": { - "*": { - "repo": "facebook/audiogen-medium", - "pkg": { - "0": { - "audiocraft": "models.AudioGen", - "generation": { - "duration": 5 - }, - "stage_2": { - "audiocraft": ".data.audioaudio_write", - "generation": { - "strategy": "loudness", - "loudness_compressor": true - } - } - } - } - } - }, - "info.art.parler-tts-v1": { - "*": { - "repo": "parler-tts/parler-tts-large-v1", - "pkg": { - "0": { - "parler_tts": "ParlerTTSForConditionalGeneration", - "generation": { - "return_tensors": "pt" - } - } - } - } - }, - "info.gan.snac-st": { - "*": { - "repo": "Zuellni/snac-24khz-ST", - "pkg": { - "0": { - "snac": "SNAC" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio" - } - }, - "file_256": [ - "e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", - "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d" - ], - "layer_256": [ - "35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", - "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841" - ], - "layer_b3": [ - "18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", - "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119" - ] - } - }, - "info.gan.kokoro": { - "*": { - "repo": "hexgrad/Kokoro-82M", - "pkg": { - "0": { - "kokoro": "KPipeline" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", - "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4" - ], - "layer_256": [ - "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", - "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b" - ], - "layer_b3": [ - "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", - "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", - "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e932dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92" - ] - } - }, - "info.stst.silero-vad": { - "*": { - "repo": "freddyaboulton/silero-vad", - "pkg": { - "0": { - "onnx": "onnx" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - }, - "file_256": [ - "591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9" - ], - "layer_256": [ - "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd" - ], - "layer_b3": [ - "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", - "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", - "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", - "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e" - ] - } - }, - "info.stst.wav2vec2-conformer-rope-960h-ft": { - "*": { - "repo": "facebook/wav2vec2-conformer-rope-large-960h-ft", - "pkg": { - "0": { - "transformers": "Wav2Vec2ConformerForCTC" - } - }, - "file_256": [ - "97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d" - ], - "layer_256": [ - "1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d" - ], - "layer_b3": [ - "6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb" - ], - "tasks": [ - "Wav2Vec2ConformerForAudioFrameClassification", - "Wav2Vec2ConformerForCTC", - "Wav2Vec2ConformerForPreTraining", - "Wav2Vec2ConformerForSequenceClassification", - "Wav2Vec2ConformerForXVector", - "Wav2Vec2ConformerModel", - "Wav2Vec2ConformerPreTrainedModel" - ] - } - }, - "info.art.orpheus-0-ft": { - "*": { - "repo": "canopylabs/orpheus-3b-0.1-ft", - "pkg": { - "0": { - "orpheus_tts": "OrpheusModel", - "generation": { - "max_model_len": 2048 - } - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.art.outetts-0": { - "*": { - "repo": "OuteAI/OuteTTS-0.3-1B", - "pkg": { - "0": { - "outetts": "InterfaceHF" - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - "generation": { - "audio_format": "wav", - "join_audio": true, - "verbose": false - } - } - } - } - }, - "info.gan.speecht5-hifigan": { - "*": { - "file_256": [ - "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c" - ], - "layer_256": [ - "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770" - ], - "layer_b3": [ - "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956" - ] - } - }, - "info.dit.flux1-dev": { - "mystic": { - "repo": "enhanceaiteam/Mystic", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 16, - "guidance_scale": 7.5, - "width": 768, - "height": 1024 - } - } - }, - "file_256": [ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac" - ], - "layer_256": [ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e" - ], - "layer_b3": [ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68" - ] - }, - "flux1-lite": { - "repo": "freepik/flux.1-lite-8b", - "pkg": { - "0": { - "generation": { - "num_inference_steps": 28 - } - } - }, - "file_256": [ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747" - ], - "layer_256": [ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee" - ], - "layer_b3": [ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf" - ] - }, - "f-lite": { - "repo": "freepik/f-lite", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "f-lite-texture": { - "repo": "freepik/f-lite-texture", - "pkg": { - "0": { - "f_lite": "FLitePipeline", - "generation": { - "num_inference_steps": 28 - } - } - } - }, - "flux": { - "repo": "TencentARC/flux-mini", - "file_256": [ - "4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee" - ], - "layer_256": [ - "e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0" - ], - "layer_b3": [ - "c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3" - ] - }, - "flex2": { - "repo": "ostris/Flex.2-preview", - "file_256": [ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02" - ], - "layer_256": [ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" - ], - "layer_b3": [ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076" - ] - }, - "flex1-alpha": { - "repo": "ostris/Flex.1-alpha", - "file_256": [ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee" - ], - "layer_256": [ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" - ], - "layer_b3": [ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6" - ] - }, - "*": { - "pkg": { - "0": { - "precision": "ops.precision.bfloat.B16", - "generation": { - "height": 1024, - "width": 1024, - "guidance_scale": 3.5, - "num_inference_steps": 50, - "max_sequence_length": 512 - } - }, - "1": { - "mflux": "flux.flux.Flux1", - "generation": { - "height": 1024, - "width": 1024, - "gudance": 3.5, - "num_inference_steps": 25 - } - } - }, - "file_256": [ - "f6315581b7cddd450b9aba72b4e9ccf8b6580dc1a6b9538aff43ee26a1a3b6c2", - "1b2170ac37156d4cf91909eb6834bb8adac84bc1fce8098a29cfb03738df84ad", - "4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7", - "d86a3038eacaa720682cb9b1da3c49fecf8a3ded605af4def6061eaa18903eb8", - "b7d840eef01c27dfd72ae9143c261355a51bab3b2662263a6cb0059d55347c3d" - ], - "layer_b3": [ - "261559c8eaccae558f72621804a9ee188d338e45e2c622a58db709ac190198ba", - "87f5d565c66e40eb02eb96498243ad81afcbf86192db99a4fc8fff215470320e", - "e61d10a394902dadca9367467b2245070f651f4553ec4a96192fbba64e820acb" - ], - "layer_256": [ - "3db58cf834d2f81abb1e035131956da4c90451074c681d0db10810e55e60c2c4", - "ddf1a34a06b355ce2bcd0f9beb0713450d9bcdc61a03a6bc37716361735e96f1", - "ad8763121f98e28bc4a3d5a8b494c1e8f385f14abe92fc0ca5e4ab3191f3a881" - ], - "identifiers": [ - "double_blocks.12.txt_mod.lin.weight", - "add_q_proj.weight", - "single_transformer_blocks.9.norm.linear.weight" - ], - "tasks": [ - "Image", - "Redux", - "Kontext", - "Depth", - "Fill", - "ConceptAttention", - "ControlNet", - "CavTon", - "IC-Edit" - ] - } - }, - "info.dit.wan2-flf2v-720p": { - "diffusers": { - "repo": "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers", - "file_256": [ - "", - "" - ], - "layer_256": [ - "" - ], - "layer_b3": [ - "" - ] - } - }, - "ops.patch.hidiffusion": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "hidiffusion": { - "apply_hidiffusion": { - "timesteps": "StableDiffusionXLTimesteps" - } - }, - "generation": { - "height": 2048, - "width": 2048, - "eta": 1.0, - "guidance_scale": 7.5, - "num_inference_steps": 10 - } - } - } - } - }, - "ops.scheduler.align-your-steps": { - "stable-diffusion-xl-1": { - "pkg": { - "0": { - "diffusers": "schedulers.scheduling_utils.AysSchedules", - "generation": { - "timesteps": "StableDiffusionXLTimesteps", - "num_inference_steps": 10 - } - } - } - } - }, - "info.art.chameleon": { - "lumina-mgpt-1024": { - "repo": "Alpha-VLLM/Lumina-mGPT-7B-1024", - "pkg": { - "0": { - "inference_solver": { - "FlexARInferenceSolver": { - "precision": "bf16", - "target_size": 768 - } - }, - "generation": { - "images": [], - "qas": [ - [ - "q1", - null - ] - ], - "max_gen_len": 8192, - "temperature": 1.0 - } - }, - "1": { - "inference_solver": "ChameleonXLLMXForConditionalGeneration" - } - }, - "file_256": [ - "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", - "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", - "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", - "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b" - ], - "layer_256": [ - "eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25" - ], - "layer_b3": [ - "6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656" - ] - } - }, - "info.vit.clip-vit-patch14": { - "*": { - "repo": "openai/clip-vit-large-patch14", - "pkg": { - "0": { - "transformers": "CLIPTextModel" - } - }, - "file_256": [ - "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", - "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", - "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", - "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", - "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", - "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", - "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", - "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", - "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", - "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", - "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", - "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", - "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", - "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", - "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", - "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", - "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1" - ], - "layer_256": [ - "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", - "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", - "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", - "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", - "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", - "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", - "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", - "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", - "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", - "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", - "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", - "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", - "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3" - ], - "layer_b3": [ - "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", - "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", - "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", - "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", - "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", - "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", - "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", - "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", - "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", - "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", - "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", - "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", - "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", - "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", - "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", - "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-g-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-g-14-laion2B-s12B-b42K", - "pkg": { - "0": { - "transformers": "CLIPTextModelWithProjection" - } - }, - "file_256": [ - "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", - "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", - "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", - "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", - "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", - "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", - "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", - "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", - "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", - "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b" - ], - "layer_256": [ - "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", - "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", - "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", - "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", - "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", - "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", - "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46" - ], - "layer_b3": [ - "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", - "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", - "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", - "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", - "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", - "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", - "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.vit.clip-vit-h-14-laion-s-b": { - "*": { - "repo": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K", - "pkg": { - "0": { - "transformers": "CLIPModel" - } - }, - "file_256": [ - "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", - "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", - "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161" - ], - "layer_256": [ - "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", - "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", - "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c" - ], - "layer_b3": [ - "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", - "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", - "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4" - ], - "tasks": [ - "CLIPModel", - "CLIPPreTrainedModel", - "CLIPTextModel", - "CLIPTextModelWithProjection", - "CLIPVisionModel", - "CLIPVisionModelWithProjection", - "CLIPForImageClassification" - ] - } - }, - "info.aet.chatglm3": { - "*": { - "repo": "zai-org/chatglm3-6b", - "pkg": { - "0": { - "transformers": "AutoModel" - } - }, - "file_256": [ - "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", - "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d" - ], - "layer_256": [ - "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44" - ], - "layer_b3": [ - "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481" - ] - } - }, - "info.art.qwen2": { - "bagel-mot": { - "repo": "ByteDance-Seed/BAGEL-7B-MoT", - "pkg": { - "0": { - "Bagel": "app" - } - } - } - }, - "info.vae.tae": { - "stable-diffusion-3": { - "repo": "madebyollin/taesd3", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399" - ] - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/taesdxl", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f" - ] - }, - "stable-diffusion-v1-5": { - "repo": "madebyollin/taesd", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549" - ] - }, - "flux1-dev": { - "repo": "madebyollin/taef1", - "pkg": { - "0": { - "diffusers": "AutoencoderTiny" - } - }, - "file_256": [ - "927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449" - ] - } - }, - "info.vae.kl": { - "qwen-image": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLQwenImage" - } - }, - "file_256": [ - "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344" - ], - "layer_256": [ - "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc" - ], - "layer_b3": [ - "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b" - ] - }, - "ltx-video": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLLTXVideo" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "allegro": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLAllegro" - } - }, - "file_256": [ - "47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a" - ], - "layer_256": [ - "bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f" - ], - "layer_b3": [ - "93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0" - ] - }, - "cosmos-1-diffusion-video2world": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCosmos" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "easyanimatev5-zh": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMagvit" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "hunyuanvideo-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLHunyuanVideo" - } - }, - "file_256": [ - "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", - "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", - "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", - "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0" - ] - }, - "mochi-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLMochi" - } - }, - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "audioldm-s-v2": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5" - ], - "layer_256": [ - "54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6" - ], - "layer_b3": [ - "00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de" - ] - }, - "stable-video-diffusion-img2vid-xt": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLTemporalDecoder" - } - } - }, - "stable-diffusion-xl-1": { - "repo": "madebyollin/sdxl-vae-fp16-fix", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", - "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", - "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", - "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", - "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", - "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", - "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", - "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0" - ] - }, - "stable-diffusion-xl-1*": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", - "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", - "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", - "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff" - ], - "layer_256": [ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0" - ], - "layer_b3": [ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74" - ] - }, - "shuttle-jaguar": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904" - ], - "layer_256": [ - "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b" - ], - "layer_b3": [ - "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", - "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0" - ] - }, - "flux1-dev": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", - "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", - "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", - "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc" - ], - "layer_256": [ - "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", - "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", - "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", - "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80" - ], - "layer_b3": [ - "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", - "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903" - ] - }, - "musicldm": { - "file_256": [ - "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4" - ], - "layer_256": [ - "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f" - ], - "layer_b3": [ - "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0" - ] - }, - "stable-diffusion-v1-5": { - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - }, - "file_256": [ - "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", - "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", - "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", - "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", - "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", - "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", - "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", - "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c" - ], - "layer_256": [ - "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", - "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3" - ], - "layer_b3": [ - "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", - "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833" - ] - } - }, - "info.vae.wan": { - "wan2-i2v-480p": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLWan", - "precision": "ops.precision.float.F32" - } - }, - "file_256": [ - "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", - "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b" - ], - "layer_256": [ - "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", - "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e" - ], - "layer_b3": [ - "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", - "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433" - ] - }, - "skyreels-v2-t2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "skyreels-v2-i2v-720p": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.cogvideox": { - "cogvideox-i2v": { - "pkg": { - "0": { - "diffusers": "AutoencoderKLCogVideoX" - } - }, - "file_256": [ - "a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e" - ], - "layer_256": [ - "43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e" - ], - "layer_b3": [ - "246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb" - ] - }, - "cogvideox-fun-v-pose": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - }, - "consisid": { - "file_256": [], - "layer_256": [], - "layer_b3": [] - } - }, - "info.vae.dc": { - "sana-1024px-bf16": { - "pkg": { - "0": { - "diffusers": "AutoencoderDC" - } - }, - "file_256": [ - "15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f" - ], - "layer_256": [ - "abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde" - ], - "layer_b3": [ - "cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0" - ] - } - }, - "info.vae.oobleck": { - "stable-audio-open-1": { - "pkg": { - "0": { - "diffusers": "AutoencoderOobleck" - } - } - } - }, - "info.vae.eq": { - "stable-diffusion-xl-1": { - "repo": "KBlueLeaf/EQ-SDXL-VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - }, - "info.vae.ms-lc-eq": { - "stable-diffusion-xl-1": { - "repo": "Anzhc/MS-LC-EQ-D-VR_VAE", - "pkg": { - "0": { - "diffusers": "AutoencoderKL" - } - } - } - } -} \ No newline at end of file diff --git a/mir/__init__.py b/mir/__init__.py index c2ad045..1922713 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -10,6 +10,7 @@ ROOT_PATH = os.path.dirname(__file__) MIR_PATH_NAMED = os.path.join(ROOT_PATH, "mir.json") + BREAKING = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["breaking"] SEARCH = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["search"] PARAMETERS = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["parameters"] diff --git a/data/__init__.py b/mir/data/__init__.py similarity index 90% rename from data/__init__.py rename to mir/data/__init__.py index c766341..a8f596e 100644 --- a/data/__init__.py +++ b/mir/data/__init__.py @@ -14,6 +14,6 @@ MIGRATIONS = read_json_file(os.path.join(ROOT_PATH, "data", "migrations.json")) NN_FILTER = read_json_file(os.path.join(ROOT_PATH, "data", "nn_filter.json")) PARAMETERS = read_json_file(os.path.join(ROOT_PATH, "data", "parameters.json")) -PREFIXES = read_json_file(os.path.join(ROOT_PATH, "data", "prefixes.json")) +PIPE_MARKERS = read_json_file(os.path.join(ROOT_PATH, "data", "pipe_markers.json")) TAG_SCRAPE = read_json_file(os.path.join(ROOT_PATH, "data", "tag_scrape.json")) TRANSFORMERS_ADDS = read_json_file(os.path.join(ROOT_PATH, "data", "transformers_adds.json")) diff --git a/data/diffusers_adds.json b/mir/data/diffusers_adds.json similarity index 99% rename from data/diffusers_adds.json rename to mir/data/diffusers_adds.json index 6f39afd..1de001e 100644 --- a/data/diffusers_adds.json +++ b/mir/data/diffusers_adds.json @@ -361,7 +361,7 @@ "generation": { "height": 1024, "width": 1024, - "gudance": 3.5, + "guidance": 3.5, "num_inference_steps": 25 } } diff --git a/data/exclusions.json b/mir/data/exclusions.json similarity index 100% rename from data/exclusions.json rename to mir/data/exclusions.json diff --git a/data/migrations.json b/mir/data/migrations.json similarity index 68% rename from data/migrations.json rename to mir/data/migrations.json index 8f696e7..5bc9929 100644 --- a/data/migrations.json +++ b/mir/data/migrations.json @@ -28,23 +28,23 @@ "THUDM/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", "zai-org/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air" }, - "model": { - "bark": "suno/bark", - "aria_text": "rhymes-ai/Aria-Chat", - "cwm": "facebook/cwm", - "decision_transformer": "edbeeching/decision-transformer-gym-hopper-medium", - "distilbert": "distilbert-base-uncased", - "gpt_bigcode": "bigcode/gpt_bigcode-santacoder", - "granite": "ibm-granite/granite-3.3-2b-base", - "granitemoe": "ibm-research/PowerMoE-3b", - "granitemoehybrid": "ibm-granite/granite-4.0-h-small", - "musicgen": "facebook/musicgen-small", - "seamless_m4t_v2": "facebook/seamless-m4t-v2-large", - "timm_backbone": "microsoft/resnet-50", - "gpt_oss": "openai/gpt-oss-120b", - "bert": "google-bert/bert-base-uncased", - "timm_wrapper": "timm/resnet18.a1_in1k", - "vision-text-dual-encoder": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" + "config": { + "BarkConfig": "suno/bark", + "AriaTextConfig": "rhymes-ai/Aria-Chat", + "CwmConfig": "facebook/cwm", + "DecisionTransformerConfig": "edbeeching/decision-transformer-gym-hopper-medium", + "DistilBertConfig": "distilbert-base-uncased", + "GPTBigCodeConfig": "bigcode/gpt_bigcode-santacoder", + "GraniteConfig": "ibm-granite/granite-3.3-2b-base", + "GraniteMoeConfig": "ibm-research/PowerMoE-3b", + "GraniteMoeHybridConfig": "ibm-granite/granite-4.0-h-small", + "MusicgenConfig": "facebook/musicgen-small", + "SeamlessM4Tv2Config": "facebook/seamless-m4t-v2-large", + "TimmBackboneConfig": "microsoft/resnet-50", + "GptOssConfig": "openai/gpt-oss-120b", + "BertConfig": "google-bert/bert-base-uncased", + "TimmWrapperConfig": "timm/resnet18.a1_in1k", + "VisionTextDualEncoderConfig": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" }, "module": { "blip_diffusion": "blip_diffusion", diff --git a/data/nn_filter.json b/mir/data/nn_filter.json similarity index 100% rename from data/nn_filter.json rename to mir/data/nn_filter.json diff --git a/data/parameters.json b/mir/data/parameters.json similarity index 74% rename from data/parameters.json rename to mir/data/parameters.json index 5a3f650..18e927c 100644 --- a/data/parameters.json +++ b/mir/data/parameters.json @@ -1,10 +1,10 @@ { - "bark": { + "BarkConfig": { "n_head": [ "" ] }, - "aria_text": { + "AriaTextConfig": { "vision_config": [ "" ], @@ -12,17 +12,17 @@ "" ] }, - "cwm": { + "CwmConfig": { "n_head": [ "" ] }, - "bert": { + "BertConfig": { "act_dropout": [ "" ] }, - "timm_wrapper": { + "TimmWrapperConfig": { "_resnet_": [ "" ] diff --git a/data/prefixes.json b/mir/data/pipe_markers.json similarity index 100% rename from data/prefixes.json rename to mir/data/pipe_markers.json diff --git a/data/tag_scrape.json b/mir/data/tag_scrape.json similarity index 100% rename from data/tag_scrape.json rename to mir/data/tag_scrape.json diff --git a/data/transformers_adds.json b/mir/data/transformers_adds.json similarity index 100% rename from data/transformers_adds.json rename to mir/data/transformers_adds.json diff --git a/mir/generate/.notes.txt b/mir/generate/.notes.txt deleted file mode 100644 index e133139..0000000 --- a/mir/generate/.notes.txt +++ /dev/null @@ -1,66 +0,0 @@ -# type: ignore -# ruff: noqa - -tag_model_from_repo - -mir_tag_from_config -import_submodules - - -constants -tag_scheduler -read_json_file -mir_prefix_from_forward_pass - -Set Data Format -Find classes -get_repo_from_class_map -check repo/model migration - -transformers_index - classmapentry - + find_transformers_classes - +check_migrations - get_repo_from_class_map - mir_tag_from_config - check_migrations - import_submodules tokenizers - - -diffusers_index - docstringentry - find_diffusers_classes - check_migrations - retrieve_diffusers_docstrings - import_submodules module for model class - import_submodules model class - extract_init_parameters - create_pipe_entry - extract_init_parameters - mir_prefix_from_forward_pass - tag_model_from_repo - check_migrations - -add_mir_dtype - + tag_dtype - MIRDatabase - -add_mir_schedulers - tag_scheduler - - -task_analysis - import_submodules - mapped_cls - import_submodules - tag_scheduler - resolve_code_names - - -# def create_model_tag(model_header,metadata_dict): -# parse_file = parse_model_header(model_header) -# reconstructed_file_path = os.path.join(disk_path,each_file) -# attribute_dict = metadata_dict | {"disk_path": reconstructed_file_path} -# file_metadata = parse_file | attribute_dict -# index_tag = create_model_tag(file_metadata) -# \ No newline at end of file diff --git a/mir/generate/__main__.py b/mir/generate/__main__.py index 8a1e85b..2255ae6 100644 --- a/mir/generate/__main__.py +++ b/mir/generate/__main__.py @@ -274,3 +274,121 @@ def pipe(mir_db: MIRDatabase = None): if __name__ == "__main__": pipe() + + +def main(mir_db: Callable | None = None, remake: bool = True) -> None: + """Build the database""" + from sys import modules as sys_modules + + if __name__ != "__main__" and "pytest" not in sys_modules: # + import argparse + + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", + usage="mir-maid", + epilog="""Does NOT include results of `mir-task` and `mir-pipe`. These commands should be run separately. Output: + 2025-08-03 14:22:47 INFO ('Wrote 0 lines to MIR database file.',) + 2025-08-03 14:22:47 INFO ('Wrote #### lines to MIR database file.',)""", + ) + parser.add_argument( + "-r", + "--remake_off", + action="store_true", + default=False, + help="Prevent erasing and remaking the MIR database file (default: False, always start from a completely empty MIR file)", + ) + + args = parser.parse_args() + remake = not args.remake_off + + from mir.automata import ( + add_mir_audio, + add_mir_diffusion, + add_mir_dtype, + add_mir_llm, + add_mir_lora, + add_mir_schedulers, + add_mir_vae, + hf_pkg_to_mir, + mir_update, + ) + from mir.config.json_io import write_json_file + + if remake: + os.remove(MIR_PATH_NAMED) + folder_path_named = os.path.dirname(MIR_PATH_NAMED) + mode = "x" + else: + mode = "w" + write_json_file(folder_path_named, file_name="mir.json", data={"expected": "data"}, mode=mode) + mir_db = MIRDatabase() + mir_db.database.pop("expected", {}) + hf_pkg_to_mir(mir_db) + add_mir_dtype(mir_db) + add_mir_schedulers(mir_db) + add_mir_lora(mir_db) + add_mir_audio(mir_db) + add_mir_diffusion(mir_db) + add_mir_llm(mir_db) + add_mir_vae(mir_db) + mir_db.write_to_disk() + mir_db = MIRDatabase() + mir_db = MIRDatabase() + mir_update(mir_db) + mir_db.write_to_disk() + + +if __name__ == "__main__": + remake: bool = True + tasks = True + pipes = True + + from sys import modules as sys_modules + + if "pytest" not in sys_modules: # + import argparse + + parser = argparse.ArgumentParser( + formatter_class=argparse.RawTextHelpFormatter, + description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", + usage="python -m nnll.mir.maid", + epilog="""Includes `mir-task` and `mir-pipe` by default. Output: + 2025-08-15 19:41:18 INFO ('Wrote 0 lines to MIR database file.',) + 2025-08-15 19:38:48 INFO ('Wrote ### lines to MIR database file.',) + INFO ('Wrote ### lines to MIR database file.',) + INFO ('Wrote ### lines to MIR database file.',)""", + ) + parser.add_argument( + "-r", + "--remake_off", + action="store_true", + default=False, + help="Don't erase and remake the MIR database (default: False)", + ) + parser.add_argument( + "-t", + "--tasks_off", + action="store_true", + default=False, + help="Don't append task information to the MIR database (default: False)", + ) + parser.add_argument( + "-p", + "--pipes_off", + action="store_true", + default=False, + help="Don't append pipeline information to the MIR database (default: False)", + ) + + args = parser.parse_args() + remake = not args.remake_off + tasks = not args.tasks_off + pipes = not args.pipes_off + + main(remake=remake) + update_mir() + from mir.inspect.tasks import pipe, run_task + + mir_db = run_task() + pipe(mir_db) diff --git a/mir/generate/diffusers/doc_parse.py b/mir/generate/diffusers/doc_parse.py index 67c3103..18e091b 100644 --- a/mir/generate/diffusers/doc_parse.py +++ b/mir/generate/diffusers/doc_parse.py @@ -6,7 +6,7 @@ from pydantic import BaseModel, field_validator from mir import NFO from mir.generate.diffusers import DocParseData -from mir.data import PREFIXES +from mir.data import PIPE_MARKERS class DocStringValidator: @@ -58,34 +58,35 @@ def normalize_doc(cls, docs: str) -> str: def doc_match(self, prefix_set: List[str] | None = None): if prefix_set is None: - prefix_set = PREFIXES["pipe_prefixes"] + prefix_set = PIPE_MARKERS["pipe_variables"] candidate = None staged = None + prior_candidate = "" for prefix in prefix_set: candidate = self.doc_string.partition(prefix)[2] prior_candidate = self.doc_string.partition(prefix)[0] if candidate: - staged = candidate if any(call_type in candidate for call_type in PREFIXES["staged_call_types"]) else None + staged = candidate if any(call_method in candidate for call_method in PIPE_MARKERS["staged_call_methods"]) else None break return candidate, prior_candidate, staged def parse(self) -> DocParseData | None: - candidate, prior_candidate, staged = self.doc_match(PREFIXES["pipe_prefixes"]) + candidate, prior_candidate, staged = self.doc_match(PIPE_MARKERS["pipe_prefixes"]) if candidate: pipe_class, pipe_repo = self._extract_class_and_repo( segment=candidate, - call_types=PREFIXES["call_types"], + call_methods=PIPE_MARKERS["call_types"], prior_text=prior_candidate, ) motion_adapter = "motion_adapter" in candidate or "adapter" in candidate if motion_adapter and pipe_repo: - staged, prior_candidate, _ = self.doc_match(PREFIXES["pipe_prefixes"][2:]) # skip the adapter statements + staged, prior_candidate, _ = self.doc_match(PIPE_MARKERS["pipe_prefixes"][2:]) # skip the adapter statements staged_class, staged_repo = ( self._extract_class_and_repo( segment=staged, - call_types=PREFIXES["staged_call_types"] if not motion_adapter else PREFIXES["call_types"], + call_methods=PIPE_MARKERS["staged_call_types"] if not motion_adapter else PIPE_MARKERS["call_types"], prior_text=prior_candidate, prior_class=pipe_class, ) @@ -104,23 +105,23 @@ def parse(self) -> DocParseData | None: def _extract_class_and_repo( self, segment: str, - call_types: List[str], + call_methods: List[str], prior_text: str, prior_class: Optional[str] = None, ) -> Tuple[Optional[str], Optional[str]]: pipe_class = None pipe_repo = None - for call_type in call_types: - if call_type in segment: - pipe_class = segment.partition(call_type)[0].strip().split("= ")[-1].split(".")[-1] - if prior_class == pipe_class and prior_text.split(call_type)[-1].strip().replace(")", ""): - pipe_class = prior_text.partition(call_type)[0].strip().split("= ")[-1] - repo_segment = segment.partition(call_type)[2].partition(")")[0] + for method_name in call_methods: + if method_name in segment: + pipe_class = segment.partition(method_name)[0].strip().split("= ")[-1].split(".")[-1] + if prior_class == pipe_class and prior_text.split(method_name)[-1].strip().replace(")", ""): + pipe_class = prior_text.partition(method_name)[0].strip().split("= ")[-1] + repo_segment = segment.partition(method_name)[2].partition(")")[0] else: - repo_segment = segment.partition(call_type)[2].partition(")")[0] + repo_segment = segment.partition(method_name)[2].partition(")")[0] pipe_repo = repo_segment.replace("...", "").partition('",')[0].strip('" ') if not DocStringValidator.is_valid_repo_path(pipe_repo): - for reference in PREFIXES["repo_variables"]: + for reference in PIPE_MARKERS["repo_variables"]: if reference in segment: pipe_repo = self._resolve_variable(reference, prior_text) break # Not empty!! 确保解析的路径不是空的！！ diff --git a/mir/generate/from_module.py b/mir/generate/from_module.py index c85ec70..bbc6288 100644 --- a/mir/generate/from_module.py +++ b/mir/generate/from_module.py @@ -8,11 +8,6 @@ from importlib import import_module from typing import Callable, Type -from mir import NFO -from mir.generate import REGEX -from mir.generate.diffusers import IMPORT_STRUCTURE -from mir.generate.transformers import MODEL_MAPPING_NAMES - def import_object_named(module: str, pkg_name_or_abs_path: str) -> Callable | None: """Convert two strings into a callable function or property\n @@ -20,6 +15,7 @@ def import_object_named(module: str, pkg_name_or_abs_path: str) -> Callable | No :param library_path: Base package for the module :return: The callable attribute or property """ + from mir import NFO module_normalized: str = module.strip() library = pkg_name_or_abs_path.strip() @@ -89,22 +85,24 @@ def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: return import_path -def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: - """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n - :param class_name: To return only one class, defaults to None - :param pkg_name: optional field for library, defaults to "transformers" - :param path_format: Retrieve just the code name, or the full module path and code name within the package - :return: A list of all code names, or the one corresponding to the provided class""" +# def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: +# """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n +# :param class_name: To return only one class, defaults to None +# :param pkg_name: optional field for library, defaults to "transformers" +# :param path_format: Retrieve just the code name, or the full module path and code name within the package +# :return: A list of all code names, or the one corresponding to the provided class""" +# from mir.generate.diffusers import IMPORT_STRUCTURE +# from mir.generate.transformers import MODEL_MAPPING_NAMES - package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES - pkg_name = pkg_name.lower() - MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) - if module_name: - if isinstance(module_name, Type): - module_name = module_name.__name__ - code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") - return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") - return list(MAPPING_NAMES) +# package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES +# pkg_name = pkg_name.lower() +# MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) +# if module_name: +# if isinstance(module_name, Type): +# module_name = module_name.__name__ +# code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") +# return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") +# return list(MAPPING_NAMES) def to_domain_tag(transformers: bool = False, **kwargs): @@ -112,8 +110,9 @@ def to_domain_tag(transformers: bool = False, **kwargs): :param transformers: Use transformers data instead of diffusers data, defaults to False :raises ValueError: Model type not detected :return: MIR prefix based on model configuration""" + from mir.data import NN_FILTER - data = REGEX + data = NN_FILTER if transformers: flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object diff --git a/mir/generate/indexers.py b/mir/generate/indexers.py index 8ef00f3..51f755a 100644 --- a/mir/generate/indexers.py +++ b/mir/generate/indexers.py @@ -4,7 +4,34 @@ """類發現和拆卸""" # pylint:disable=no-name-in-module -from mir.generate import MIGRATIONS +from mir import NFO +from mir.data import MIGRATIONS +from mir.maid import MIRDatabase +from mir.spec import mir_entry + + +def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: + """Generate MIR HF Hub model database + :param new_data: Data for the MIR database + :param mir_database: MIRDatabase instance + """ + for series, comp_name in new_data.items(): + id_segment = series.split(".") + for compatibility in comp_name: + # dbug(id_segment) + try: + mir_db.add( + mir_entry( + domain=id_segment[0], + arch=id_segment[1], + series=id_segment[2], + comp=compatibility, + **new_data[series][compatibility], + ), + ) + except IndexError: # as error_log: + NFO(f"Failed to create series: {series} compatibility: {comp_name} ") + # dbug(error_log) def migrations(repo_path: str): diff --git a/mir/generate/transformers/__init__.py b/mir/generate/transformers/__init__.py index cbdf6f8..e3f09b3 100644 --- a/mir/generate/transformers/__init__.py +++ b/mir/generate/transformers/__init__.py @@ -2,32 +2,15 @@ # -from dataclasses import dataclass, field -from typing import Callable - from transformers.models.auto.configuration_auto import CONFIG_MAPPING from transformers.models.auto.modeling_auto import ( MODEL_MAPPING, # config: model map MODEL_MAPPING_NAMES, + AutoModel, ) -from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING_NAMES +from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING from mir.generate.from_module import show_init_fields_for - -@dataclass -class ClassMapEntry: - """Represents a structured entry of the name of the class and its associated attributes.""" - - name: str - model_name: str - model: Callable - config: Callable - config_params: dict[str, list[str]] = field(init=False, default_factory=lambda: {}) - model_params: dict[str, list[str]] | None = None - - def __post_init__(self): - if self.model: - self.model_params = show_init_fields_for(self.model) - if self.config: - self.config_params = show_init_fields_for(self.config) +AUTO_MAP = AutoModel._model_mapping +REVERSE_MAP = AUTO_MAP._reverse_config_mapping diff --git a/mir/generate/transformers/index.py b/mir/generate/transformers/index.py index adc8c65..8c53762 100644 --- a/mir/generate/transformers/index.py +++ b/mir/generate/transformers/index.py @@ -1,216 +1,126 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # - -from typing import Callable - -from mir import NFO, DBUQ -from mir.data import PARAMETERS -from mir.generate.from_module import import_object_named, to_domain_tag -from mir.generate.indexers import migrations -from mir.tag import tag_model_from_repo -from mir.generate.transformers import CONFIG_MAPPING, MODEL_MAPPING, TOKENIZER_MAPPING_NAMES, ClassMapEntry - - -def mapped_cls(model_identifier: str): - """Get model class from identifier without calling huggingface_hub.\n - :param model_identifier: Model identifier like "bert-base-uncased" or "gpt2" - :return: Model class (e.g., BertModel, GPT2Model) - """ - import transformers - from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES - from transformers.models.auto.modeling_auto import MODEL_MAPPING, MODEL_MAPPING_NAMES - - code_name = model_identifier.split("/")[-1].split("-")[0].lower() - - model_class_name = MODEL_MAPPING_NAMES.get(code_name, None) - - config_class_name = CONFIG_MAPPING_NAMES.get(code_name) - if config_class_name: - config_class = getattr(transformers, config_class_name, None) - if config_class: - model_class = MODEL_MAPPING.get(config_class, None) - if model_class: - if isinstance(model_class, tuple): - model_class = model_class[0] - return model_class - - normalized = code_name.replace("_", "-") - if normalized != code_name: - if model_class_name := MODEL_MAPPING_NAMES.get(normalized, None): - if isinstance(model_class_name, tuple): - model_class_name = model_class_name[0] - return getattr(transformers, model_class_name, None) - - return None - - -def get_repo_from_class_map(class_map: ClassMapEntry) -> str | None: - """The name of the repository that is associated with a transformers configuration class\n - :param class_map: Transformers class information extracted from dependency - :returns: A string matching the repo path for the class""" - - import re - - doc_attempt = [] - if hasattr(class_map.config, "forward"): - doc_attempt = [getattr(class_map.config, "forward")] - doc_attempt.append(class_map.config) - for pattern in doc_attempt: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) - if matches: - try: - repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - NFO(f"ERROR >>{matches} : LOG >> {error_log}") - continue - return repo_path - return None - - -def find_transformers_classes() -> list[ClassMapEntry]: - """Eat the 🤗Transformers classes as a treat, leaving any tasty subclass class morsels neatly arranged as a dictionary.\n - Nom.\n - :return: Tasty mapping of subclasses to their class references""" - - model_data = [] - for config_name, config_obj in CONFIG_MAPPING.items(): - model_params = None - if model_obj := MODEL_MAPPING.get(config_obj, None): - if isinstance(model_obj, Callable): - model_obj = (model_obj,) - assert isinstance(model_obj, tuple), f"Expected model class object, got {model_obj} type {type(model_obj)}" - for model_class in model_obj: - if model_params and ("inspect" not in model_params["config"]) and ("deprecated" not in list(model_params["config"])): - pass - else: - model_params = None - model_name = model_class.__name__ - model_data.append( - ClassMapEntry( - name=config_name, - model_name=model_name.split(".")[-1], - model=model_class, # type: ignore - config=config_obj, - ), - ) - return model_data - - -def mir_tag_from_config(class_map: ClassMapEntry, repo_path: str) -> tuple[str, str, str]: - """Change a transformers config class into a MIR series and comp\n - :param class_map: Transformers class information extracted from dependency - :param repo_path: The - """ - - mir_prefix = to_domain_tag(transformers=True, **class_map.config_params) - if not mir_prefix: - if class_map.model_params: - if mir_prefix := to_domain_tag(transformers=True, **class_map.model_params): - pass - else: - raise ValueError(f"Unable to determine MIR prefix from {class_map, repo_path}") - else: - raise ValueError(f"Unrecognized model type, no tag matched {class_map.name} with {class_map.config_params} or {class_map.model_params}") - mir_prefix = "info." + mir_prefix - if class_map.name != "funnel": - mir_suffix, mir_comp = tag_model_from_repo(repo_path) - else: - mir_suffix, mir_comp = ["funnel", "*"] - mir_series = mir_prefix + "." + mir_suffix - return mir_series, mir_comp, mir_suffix - - -def show_transformers_tasks(class_name: str | None = None, code_name: str | None = None) -> list[str]: - """Retrieves a list of task classes associated with a specified transformer class.\n - :param class_name: The name of the transformer class to inspect. - :param pkg_type: The dependency for the module - :param alt_method: Use an alternate method to return the classes - :return: A list of task classes associated with the specified transformer.""" - - task_classes = None - - if not code_name: - class_obj: Callable = import_object_named(class_name, "transformers") - class_module: Callable = import_object_named(*class_obj.__module__.split(".", 1)[-1:], class_obj.__module__.split(".", 1)[0]) - if class_module and class_module.__name__ != "DummyPipe": - task_classes = getattr(class_module, "__all__") - else: +from typing import Any, Callable + +from chanfig import NestedDict + +from mir.generate.transformers.raw_data import PrepareData + + +class HarvestClasses: + def __init__(self) -> None: + """Initializes the HarvestClasses instance with an empty list to store raw class data.""" + self.raw_data = [] + from mir.maid import MIRDatabase + + self.mir_db = MIRDatabase() + self.find_transformers_classes() + self.info = NestedDict({}) + + def find_transformers_classes(self) -> None: + """Finds and collects PrepareData entries for all transformer classes defined in AUTO_MAP.\n + :return: List of PrepareData entries representing the transformer classes.""" + + from mir.generate.transformers import AUTO_MAP + + model_data = [] + for pair_map in AUTO_MAP.items(): + config_class, model_class = pair_map # type:ignore + if isinstance(model_class, tuple): + model_class: Callable = model_class[0] + print(model_class) + if config_data := self.extract_config_class_data(config_class): + if model_data := self.extract_model_class_data(model_class): + if prepared_data := PrepareData(**config_data, **model_data): # type:ignore + self.add_to_database(prepared_data) + + def extract_config_class_data(self, config_class: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: + """Extracts information from config classes.\n + :param config_class: Model class or callable returning model classes. + :return: dictionary of discovered elements""" + from mir.data import MIGRATIONS, PARAMETERS + from mir.generate.from_module import show_init_fields_for + + config_name = config_class.__name__ + config_params = PARAMETERS.get(config_name, {}) + repo_path = MIGRATIONS["config"].get(config_name, {}) + if not config_params: + config_params = show_init_fields_for(config_class) + if not repo_path: + repo_path = self.config_to_repo(config_class) + if not repo_path or not config_params or "inspect" in config_params or "deprecated" in config_params: return None - elif code_name: - from httpx import HTTPStatusError - - from mir.generate.transformers.index import mapped_cls - - try: - model_class = mapped_cls(code_name) - if model_class is not None: - # Convert class type to list containing the class name string - task_classes = [model_class.__name__] - else: - return None - except (OSError, HTTPStatusError) as e: - DBUQ(f"Error mapping class {code_name}: {e}") + return { + "name": config_name, + "config": config_class, + "config_params": config_params, + "repo_path": repo_path, + } + + def extract_model_class_data(self, model_class: Callable) -> dict[str, str | Any] | None: + """Extracts information from model classes.\n + :param model_class: Model class or callable returning model classes. + :return: dictionary of discovered elements""" + from mir.generate.from_module import show_init_fields_for # Ensure it's a tuple for consistency. + + model_data: dict[str, str | Any] = {"model": model_class} + model_params = show_init_fields_for(model_class) + if "inspect" in model_params or "deprecated" in model_params: return None - - return task_classes - - -def transformers_index(): - """Generate LLM model data for MIR index\n - :return: Dictionary ready to be applied to MIR data fields""" - - missing_config_params = PARAMETERS - - mir_data = {} - transformers_data: list[ClassMapEntry] = find_transformers_classes() - for entry in transformers_data: - repo_path = get_repo_from_class_map(entry) - if entry.name == "bert": - print(entry) - if config := missing_config_params.get(entry.name, {}): - entry.config_params = config.get("params", entry.config_params) - repo_path = config.get("repo_path", repo_path) - if entry.name == "bert": - print(entry) - if not repo_path: - raise ValueError(f"Unable to determine repo from {entry}") - if entry.config_params: - mir_series, mir_comp, mir_suffix = mir_tag_from_config(entry, repo_path) - # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) - - repo_path = migrations(repo_path) - tk_pkg = {} - tokenizer_classes = TOKENIZER_MAPPING_NAMES.get(entry.name) - if isinstance(tokenizer_classes, str): - tokenizer_classes = [tokenizer_classes] - # mode = modalities.get("mode") - if tokenizer_classes: - index = 0 - for tokenizer in tokenizer_classes: - if tokenizer: - tokenizer_class = import_object_named(tokenizer, "transformers") - tk_pkg.setdefault(index, {"transformers": f"{tokenizer_class.__module__}.{tokenizer_class.__name__}"}) - index += 1 - if tk_pkg: - mir_data.get("info.encoder.tokenizer", mir_data.setdefault("info.encoder.tokenizer", {})).update( - { - mir_suffix: { - "pkg": tk_pkg, - } - }, - ) - mir_data.setdefault( - mir_series, + else: + return model_data | { + "model_params": model_params, + } + + def config_to_repo(self, config_class: Callable) -> str | None: + """Extracts the repository path from the configuration class documentation.\n + :param config_class: Configuration class to extract repository path from. + :return: Repository path as a string if found, otherwise None.""" + import re + + from mir import NFO + + doc_check = [config_class] + if hasattr(config_class, "forward"): + doc_check.append(config_class.forward) # type: ignore + for pattern in doc_check: + doc_string = pattern.__doc__ + repo_brackets = r"\[([^\]]+)\]" + matches = re.findall(repo_brackets, doc_string) # type: ignore + if matches: + try: + self.repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + NFO(f"ERROR >>{matches} : LOG >> {error_log}") + continue + + def add_to_database(self, prepared_data: PrepareData) -> None: + if hasattr(prepared_data, "tokenizer"): + token_info = NestedDict( { - mir_comp: { - "repo": repo_path, - "pkg": { - 0: {"transformers": entry.model_name}, + "encoder": { + "tokenizer": { + prepared_data.mir_comp: { + "pkg": {f"{prepared_data.tokenizer.__module__}.{prepared_data.tokenizer.__name__}"}, + }, }, - # "mode": mode, }, - }, + } ) - return mir_data + + info = NestedDict( + { + prepared_data.mir_arch: { + prepared_data.mir_series: { + prepared_data.mir_comp: { + "repo": prepared_data.repo_path, + "pkg": {"transformers": prepared_data.model_name}, + "tokenizer": {f"info.encoder.tokenizer.{prepared_data.mir_comp}"}, + } + } + } + } + ) + self.info = token_info | info + print(f"added {prepared_data}") diff --git a/mir/generate/transformers/raw_data.py b/mir/generate/transformers/raw_data.py new file mode 100644 index 0000000..39cce6d --- /dev/null +++ b/mir/generate/transformers/raw_data.py @@ -0,0 +1,66 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from dataclasses import dataclass, field +from typing import Callable + + +@dataclass +class PrepareData: + """Represents a structured entry of the name of the class and its associated attributes.""" + + name: str + model: Callable + config: Callable + repo_path: str + config_params: dict[str, list[str]] + model_params: dict[str, list[str]] | None = None + mir_arch: str = field(init=False) + mir_series: str = field(init=False) + mir_comp: str = field(init=False) + + def __post_init__(self) -> None: + """Initializes the PrepareData instance by setting derived attributes.""" + from mir.generate.transformers import REVERSE_MAP, TOKENIZER_MAPPING + + self.model_name: str = self.model.__name__.split(".")[-1] + if tokenizer := TOKENIZER_MAPPING.get(self.config, None): + self.tokenizer = tokenizer + self.tokenizer_pkg: dict[str, str] | None = {"transformers": f"{self.tokenizer.__module__}.{self.tokenizer.__name__}"} + if internal_name := REVERSE_MAP.get(self.config): + self.internal_name = internal_name + self.model_to_tasks() + self.mir_tag_from_config() + + def model_to_tasks(self) -> None: + """Transform a single model class into derivative classes for specific tasks.\n + :return: A list of task classes associated with the model.""" + from pathlib import Path + from importlib import import_module + + import_path = Path(self.model.__module__).stem + parent_module = import_module(import_path) + + if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": + self.task_classes = parent_module.__all__ + else: + self.task_classes = [self.model.__name__] + + def mir_tag_from_config(self) -> None: + """Generates MIR series and component tags based on the configuration class.\n + :return: Tuple containing MIR series, component, and suffix tags.""" + + from mir.generate.from_module import to_domain_tag + from mir.tag import tag_model_from_repo + + mir_prefix = to_domain_tag(transformers=True, **self.config_params) + if not mir_prefix: + if self.model_params: + if mir_prefix := to_domain_tag(transformers=True, **self.model_params): + pass + raise ValueError(f"Unable to determine MIR prefix from {self}") + else: + raise ValueError(f"Unrecognized model type, no tag matched {self.name} with {self.config_params} or {self.model_params}") + self.mir_arch = mir_prefix + self.mir_series, self.mir_comp = tag_model_from_repo(self.repo_path) diff --git a/mir/generate/transformers/tokenizers.py b/mir/generate/transformers/tokenizers.py new file mode 100644 index 0000000..a395d0e --- /dev/null +++ b/mir/generate/transformers/tokenizers.py @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +import re +from importlib import import_module + +from mir.generate.transformers import TOKENIZER_MAPPING +from mir.maid import MIRDatabase +from mir.spec import mir_entry + + +def tag_tokenizers(config_class: Callable): + tokenizer_class = TOKENIZER_MAPPING[config_class] # type: ignore + if tokenizer_class: + { "pkg":{"transformers": f"{tokenizer_class.__module__}.{tokenizer_class.__name__}"}) + if tk_pkg: + mir_data.get("info.encoder.tokenizer", mir_data.setdefault("info.encoder.tokenizer", {})).update( + { + mir_suffix: { + "pkg": tk_pkg, + } + }, + ) + return tokenizer_class diff --git a/mir/generate/write_to_mir.py b/mir/generate/write_to_mir.py deleted file mode 100644 index 4976502..0000000 --- a/mir/generate/write_to_mir.py +++ /dev/null @@ -1,31 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from mir.spec import mir_entry -from mir import NFO -from mir.maid import MIRDatabase - - -def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: - """Generate MIR HF Hub model database - :param new_data: Data for the MIR database - :param mir_database: MIRDatabase instance - """ - for series, comp_name in new_data.items(): - id_segment = series.split(".") - for compatibility in comp_name: - # dbug(id_segment) - try: - mir_db.add( - mir_entry( - domain=id_segment[0], - arch=id_segment[1], - series=id_segment[2], - comp=compatibility, - **new_data[series][compatibility], - ), - ) - except IndexError: # as error_log: - NFO(f"Failed to create series: {series} compatibility: {comp_name} ") - # dbug(error_log) diff --git a/mir/maid.py b/mir/maid.py index a25a3eb..acdf86c 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -5,24 +5,26 @@ # pylint: disable=possibly-used-before-assignment, line-too-long import os -from typing import Any, Callable, List, Optional +from typing import Any, List, Optional -from mir.config.constants import MIR_PATH_NAMED -from mir.config.json_io import read_json_file, write_json_file -from mir.config.console import dbuq +from mir import MIR_PATH_NAMED +from mir.json_io import read_json_file, write_json_file class MIRDatabase: - """Machine Intelligence Resource Database""" + """Machine Intelligence Resource Database Object + Database search and read/write operations""" def __init__(self, database: dict | None = None) -> None: from json.decoder import JSONDecodeError + from mir import DBUQ if not database: + self.database = {"expected": "data"} try: - self.database: dict[str, Any] = read_json_file(MIR_PATH_NAMED) + self.read_from_disk() except JSONDecodeError as error_log: - dbuq(error_log) + DBUQ(error_log) self.database = {} def add(self, resource: dict[str, Any]) -> None: @@ -39,12 +41,10 @@ def add(self, resource: dict[str, Any]) -> None: def write_to_disk(self, data: Optional[dict] = None) -> None: # pylint:disable=unused-argument """Save data to JSON file\n""" - from mir.config.console import nfo + from mir import NFO if not os.path.exists(MIR_PATH_NAMED): mode = "x" - if not self.database: - self.database = {"expected": "data"} else: mode = "w" # except (FileNotFoundError, OSError) as error_log: @@ -52,7 +52,7 @@ def write_to_disk(self, data: Optional[dict] = None) -> None: # pylint:disable= write_json_file(os.path.dirname(MIR_PATH_NAMED), file_name="mir.json", data=self.database, mode=mode) written_data = self.read_from_disk() - nfo(f"Wrote {len(written_data)} lines to MIR database file.") + NFO(f"Wrote {len(written_data)} lines to MIR database file.") self.database = written_data def read_from_disk(self, data: Optional[dict] = None) -> dict[str, Any]: @@ -60,7 +60,8 @@ def read_from_disk(self, data: Optional[dict] = None) -> dict[str, Any]: :param data: mir decorator auto-populated, defaults to None :return: dict of MIR data""" if not os.path.exists(MIR_PATH_NAMED): - return {} + self.write_to_disk({}) + return self.database else: self.database = read_json_file(MIR_PATH_NAMED) return self.database @@ -75,7 +76,7 @@ def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibilit :return: A list of likely options and their MIR paths""" import re - from mir.config.constants import SEARCH_SUFFIX + from mir import SEARCH results = [] if isinstance(maybe_match, str): @@ -86,8 +87,8 @@ def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibilit else: maybe_match = list(maybe_match.keys()) for option in maybe_match: - option_lower = re.sub(SEARCH_SUFFIX, "", option.lower()) - target = re.sub(SEARCH_SUFFIX, "", target.lower()) + option_lower = re.sub(SEARCH, "", option.lower()) + target = re.sub(SEARCH, "", target.lower()) if option_lower: if option_lower: if option_lower in target: @@ -146,7 +147,7 @@ def find_tag(self, field: str, target: str, sub_field: Optional[str] = None, dom :raises KeyError: Target string not found """ import re - from mir.config.console import nfo + from mir import NFO parameters = r"-gguf|-exl2|-exl3|-onnx|-awq|-mlx|-ov" # target = target.lower().strip("-") @@ -168,123 +169,5 @@ def find_tag(self, field: str, target: str, sub_field: Optional[str] = None, dom if best_match := self.grade_maybes(self.matches, target): return best_match else: - nfo(f"Query '{target}' not found when {len(self.database)}'{field}' options searched\n") + NFO(f"Query '{target}' not found when {len(self.database)}'{field}' options searched\n") return None - - -def main(mir_db: Callable | None = None, remake: bool = True) -> None: - """Build the database""" - from sys import modules as sys_modules - - if __name__ != "__main__" and "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="mir-maid", - epilog="""Does NOT include results of `mir-task` and `mir-pipe`. These commands should be run separately. Output: - 2025-08-03 14:22:47 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-03 14:22:47 INFO ('Wrote #### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Prevent erasing and remaking the MIR database file (default: False, always start from a completely empty MIR file)", - ) - - args = parser.parse_args() - remake = not args.remake_off - - from mir.automata import ( - add_mir_audio, - add_mir_diffusion, - add_mir_dtype, - add_mir_llm, - add_mir_lora, - add_mir_schedulers, - add_mir_vae, - hf_pkg_to_mir, - mir_update, - ) - from mir.config.json_io import write_json_file - - if remake: - os.remove(MIR_PATH_NAMED) - folder_path_named = os.path.dirname(MIR_PATH_NAMED) - mode = "x" - else: - mode = "w" - write_json_file(folder_path_named, file_name="mir.json", data={"expected": "data"}, mode=mode) - mir_db = MIRDatabase() - mir_db.database.pop("expected", {}) - hf_pkg_to_mir(mir_db) - add_mir_dtype(mir_db) - add_mir_schedulers(mir_db) - add_mir_lora(mir_db) - add_mir_audio(mir_db) - add_mir_diffusion(mir_db) - add_mir_llm(mir_db) - add_mir_vae(mir_db) - mir_db.write_to_disk() - mir_db = MIRDatabase() - mir_db = MIRDatabase() - mir_update(mir_db) - mir_db.write_to_disk() - - -if __name__ == "__main__": - remake: bool = True - tasks = True - pipes = True - - from sys import modules as sys_modules - - if "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="python -m nnll.mir.maid", - epilog="""Includes `mir-task` and `mir-pipe` by default. Output: - 2025-08-15 19:41:18 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-15 19:38:48 INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Don't erase and remake the MIR database (default: False)", - ) - parser.add_argument( - "-t", - "--tasks_off", - action="store_true", - default=False, - help="Don't append task information to the MIR database (default: False)", - ) - parser.add_argument( - "-p", - "--pipes_off", - action="store_true", - default=False, - help="Don't append pipeline information to the MIR database (default: False)", - ) - - args = parser.parse_args() - remake = not args.remake_off - tasks = not args.tasks_off - pipes = not args.pipes_off - - main(remake=remake) - update_mir() - from mir.inspect.tasks import pipe, run_task - - mir_db = run_task() - pipe(mir_db) diff --git a/data/mir.json b/mir/mir.json similarity index 100% rename from data/mir.json rename to mir/mir.json diff --git a/mir/spec/docstring_patterns.json b/mir/spec/docstring_patterns.json deleted file mode 100644 index 691ab3c..0000000 --- a/mir/spec/docstring_patterns.json +++ /dev/null @@ -1,41 +0,0 @@ -{ - "uncommon_naming": { - "blip_diffusion": "blip_diffusion", - "cogvideo": "cogvideox", - "cogview3": "cogview3plus", - "deepfloyd_if": "if", - "cosmos": "cosmos2_text2image", - "visualcloze": "visualcloze_generation", - "marigold": "marigold_depth" - }, - "exclusion_list": [ - "auto_pipeline", - "consistency_models", - "pipeline_utils", - "deprecated", - "ddim", - "ddpm", - "deprecated", - "autopipeline", - "dance_diffusion", - "diffusionpipeline", - "dit", - "latent_consistency_models", - "latent_diffusion", - "ledits_pp", - "pag", - "paint_by_example", - "semantic_stable_diffusion", - "stable_diffusion_attend_and_excite", - "stable_diffusion_diffedit", - "stable_diffusion_k_diffusion", - "stable_diffusion_panorama", - "stable_diffusion_safe", - "stable_diffusion_sag", - "t2i_adapter", - "text_to_video_synthesis", - "unclip", - "unidiffuser", - "controlnet_hunyuandit" - ] -} \ No newline at end of file diff --git a/mir/spec/missing_params.json b/mir/spec/missing_params.json deleted file mode 100644 index c3aebdc..0000000 --- a/mir/spec/missing_params.json +++ /dev/null @@ -1,73 +0,0 @@ -{ - "bark": { - "repo_path": "suno/bark", - "params": { - "n_head": [ - "" - ] - } - }, - "aria_text": { - "repo_path": "rhymes-ai/Aria-Chat", - "params": { - "vision_config": [ - "" - ], - "text_config": [ - "" - ] - } - }, - "cwm": { - "repo_path": "facebook/cwm", - "params": { - "n_head": [ - "" - ] - } - }, - "decision_transformer": { - "repo_path": "edbeeching/decision-transformer-gym-hopper-medium" - }, - "distilbert": { - "repo_path": "distilbert-base-uncased" - }, - "gpt_bigcode": { - "repo_path": "bigcode/gpt_bigcode-santacoder" - }, - "granite": { - "repo_path": "ibm-granite/granite-3.3-2b-base" - }, - "granitemoe": { - "repo_path": "ibm-research/PowerMoE-3b" - }, - "granitemoehybrid": { - "repo_path": "ibm-granite/granite-4.0-h-small" - }, - "musicgen": { - "repo_path": "facebook/musicgen-small" - }, - "seamless_m4t_v2": { - "repo_path": "facebook/seamless-m4t-v2-large" - }, - "timm_backbone": { - "repo_path": "microsoft/resnet-50" - }, - "gpt_oss": { - "repo_path": "openai/gpt-oss-120b" - }, - "bert": { - "repo_path": "google-bert/bert-base-uncased" - }, - "timm_wrapper": { - "repo_path": "timm/resnet18.a1_in1k", - "params": { - "_resnet_": [ - "" - ] - } - }, - "vision-text-dual-encoder": { - "repo_path": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" - } -} \ No newline at end of file diff --git a/mir/spec/repo_migrations.json b/mir/spec/repo_migrations.json deleted file mode 100644 index 799f906..0000000 --- a/mir/spec/repo_migrations.json +++ /dev/null @@ -1,29 +0,0 @@ -{ - "/helium-2b": "/helium-1-2b", - "allenai/Olmo2-7B-1124-hf": "allenai/Olmo-2-1124-7B", - "apple/mobilevitv2-1.0": "apple/mobilevitv2-1.0-imagenet1k-256", - "caidas/swin2SR-classical-sr-x2-64": "caidas/swin2SR-classical-sr-x2-64", - "facebook/hiera-base-224": "facebook/hiera-base-224-hf", - "facebook/sam_hq-vit-huge": "syscv-community/sam-hq-vit-huge", - "facebook/vit_msn_base": "facebook/vit-msn-base", - "facebook/wav2vec2-bert-rel-pos-large": "facebook/w2v-bert-2.0", - "google/gemma-3-4b": "google/gemma-3-4b-it", - "google/gemma2-7b": "google/gemma-2-9b", - "google/gemma3_text-7b": "google/gemma-3-12b-it", - "IDEA-Research/dab_detr-base": "IDEA-Research/dab-detr-resnet-50", - "LGAI-EXAONE/EXAONE-4.0-Instruct": "LGAI-EXAONE/EXAONE-4.0-32B", - "meta/chameleon-7b'": "facebook/chameleon-7b", - "mixtralai/Mixtral-8x7B": "mistralai/Mixtral-8x7B-v0.1", - "paligemma-hf/paligemma-2b": "google/paligemma2-3b-mix-224", - "pixtral-hf/pixtral-9b": "mistralai/Pixtral-12B-Base-2409", - "Qwen/Qwen2-7B-beta": "Qwen/Qwen2-7B", - "Qwen/Qwen3-15B-A2B": "Qwen/Qwen3-30B-A3B", - "s-JoL/Open-Llama-V1": "openlm-research/open_llama_3b", - "Salesforce/instruct-blip-flan-t5": "Salesforce/instructblip-flan-t5-xl", - "state-spaces/mamba2-2.8b": "AntonV/mamba2-2.7b-hf", - "ibm-fms/FalconH1-9.8b-2.2T-hf": "tiiuae/Falcon-H1-34B-Instruct", - "nvidia/nemotron-3-8b-base-4k-hf": "mgoin/nemotron-3-8b-chat-4k-sft-hf", - "THUDM/": "zai-org/", - "THUDM/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air", - "zai-org/GLM-4-100B-A10B": "zai-org/GLM-4.5-Air" -} \ No newline at end of file diff --git a/mir/tag.py b/mir/tag.py index 6cb4d16..38b8929 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -2,17 +2,15 @@ # from typing import Any -from mir import PARAMETERS, BREAKING, SEARCH -def tag_model_from_repo(repo_title: str, decoder=False, data: dict | None = None) -> tuple[str, Any]: +def tag_model_from_repo(repo_title: str, decoder=False) -> tuple[str, Any]: """Create a mir label from a repo path\n :param mir_prefix: Known period-separated prefix and model type :param repo_path: Typical remote source repo path, A URL without domain :return: The assembled mir tag with compatibility pre-separated""" import re - - # print(repo_title) + from mir import PARAMETERS, BREAKING root = "decoder" if decoder else "*" repo_title = repo_title.split(":latest")[0] diff --git a/pyproject.toml b/pyproject.toml index 4c33193..7d95cc5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -24,6 +24,7 @@ classifiers = [ "Topic :: Scientific/Engineering :: Artificial Intelligence", ] dependencies = [ + "chanfig>=0.0.114", "diffusers>=0.35.2", "ftfy>=6.3.1", "huggingface-hub[hf-xet]>=1.1.7", diff --git a/uv.lock b/uv.lock index c945785..3616533 100644 --- a/uv.lock +++ b/uv.lock @@ -37,6 +37,20 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/e6/ad/3cc14f097111b4de0040c83a525973216457bbeeb63739ef1ed275c1c021/certifi-2026.1.4-py3-none-any.whl", hash = "sha256:9943707519e4add1115f44c2bc244f782c0249876bf51b6599fee1ffbedd685c", size = 152900, upload-time = "2026-01-04T02:42:40.15Z" }, ] +[[package]] +name = "chanfig" +version = "0.0.114" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "lazy-imports" }, + { name = "pyyaml" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/5e/54/f34f58b4b883eb22594246f0da686f3f71d88c2614eee7d4551345411641/chanfig-0.0.114.tar.gz", hash = "sha256:50de7928d29e048042c1c62affbc3d8e3fd31b91ae4e1670bf10478a718ba9c0", size = 6416742, upload-time = "2025-12-16T08:38:16.136Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/cd/ee/5e806a325abbfce8633828c396bd274ebdd0a1cfd4b43ad20671da69e0ee/chanfig-0.0.114-py3-none-any.whl", hash = "sha256:7b2332f0c89000e732e34569d0c6b98fb9ac3a3969ba54c8f95e3a9e074acc45", size = 59250, upload-time = "2025-12-16T08:38:14.048Z" }, +] + [[package]] name = "charset-normalizer" version = "3.4.4" @@ -311,6 +325,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67", size = 134899, upload-time = "2025-03-05T20:05:00.369Z" }, ] +[[package]] +name = "lazy-imports" +version = "1.2.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/25/67/04432aae0c1e2729bff14e1841f4a3fb63a9e354318e66622251487760c3/lazy_imports-1.2.0.tar.gz", hash = "sha256:3c546b3c1e7c4bf62a07f897f6179d9feda6118e71ef6ecc47a339cab3d2e2d9", size = 24470, upload-time = "2025-12-28T13:51:51.218Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/cd/62/60ed24fa8707f10c1c5aef94791252b820be3dd6bdfc6e2fcdb08bc8912f/lazy_imports-1.2.0-py3-none-any.whl", hash = "sha256:97134d6552e2ba16f1a278e316f05313ab73b360e848e40d593d08a5c2406fdf", size = 18681, upload-time = "2025-12-28T13:51:49.802Z" }, +] + [[package]] name = "markdown2" version = "2.5.4" @@ -399,6 +422,7 @@ name = "mir" version = "0.0.1" source = { editable = "." } dependencies = [ + { name = "chanfig" }, { name = "diffusers" }, { name = "ftfy" }, { name = "huggingface-hub", extra = ["hf-xet"] }, @@ -422,6 +446,7 @@ dev = [ [package.metadata] requires-dist = [ + { name = "chanfig", specifier = ">=0.0.114" }, { name = "diffusers", git = "https://github.com/huggingface/diffusers" }, { name = "ftfy", specifier = ">=6.3.1" }, { name = "huggingface-hub", extras = ["hf-xet"], specifier = ">=1.1.7" }, From 846037a94046b67ee8c3315ad952f7ab8e003328 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Wed, 14 Jan 2026 22:03:18 -0500 Subject: [PATCH 07/16] ~nice API --- mir/__init__.py | 12 +- mir/data/nn_filter.json | 4 +- mir/generate/automata.py | 54 ------- mir/generate/from_module.py | 9 +- mir/generate/tasks.py | 8 +- mir/generate/transformers/__init__.py | 2 +- .../transformers/{index.py => harvest.py} | 56 ++----- mir/generate/transformers/raw_data.py | 40 ++--- mir/generate/transformers/tokenizers.py | 24 --- mir/maid.py | 71 ++++++--- mir/tag.py | 143 +++++++++++++----- 11 files changed, 199 insertions(+), 224 deletions(-) rename mir/generate/transformers/{index.py => harvest.py} (69%) delete mode 100644 mir/generate/transformers/tokenizers.py diff --git a/mir/__init__.py b/mir/__init__.py index 1922713..c688644 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -1,9 +1,12 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # + import os +from importlib import import_module +from logging import DEBUG, INFO, Logger from mir.json_io import read_json_file -from logging import DEBUG, INFO, Logger +from mir.generate.transformers.harvest import HarvestClasses NFO = Logger(INFO).info DBUQ = Logger(DEBUG).debug @@ -17,3 +20,10 @@ SEMANTIC = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["semantic"] SUFFIX = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["suffix"] IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] + + +tag_name = lambda path: path.rsplit(".", 1) +mir_run = lambda parts: getattr(import_module(parts[0]), parts[1]) + + +Mir = HarvestClasses().db.db diff --git a/mir/data/nn_filter.json b/mir/data/nn_filter.json index 66e5fc3..4638ce1 100644 --- a/mir/data/nn_filter.json +++ b/mir/data/nn_filter.json @@ -17,7 +17,7 @@ "scheduler": "", "resnet": "" }, - "transformer": { + "transformers": { "mlp": [ "prediction_channel_indices" ], @@ -139,7 +139,7 @@ "tie_codebooks_embeddings" ] }, - "diffuser": { + "diffusers": { "lora": [ "motion_adapter" ], diff --git a/mir/generate/automata.py b/mir/generate/automata.py index da548b5..ad5b0c8 100644 --- a/mir/generate/automata.py +++ b/mir/generate/automata.py @@ -28,64 +28,10 @@ sd3_series, sd3_comp = tag_model_from_repo("stable-diffusion-3.5-medium") # -def assimilate(mir_db: MIRDatabase, data_tuple: List[Tuple[Dict[str, Any]]]) -> None: - """Merge new data into a pre-generated MIR database, updating while preserving existing data structures.\n - :param mir_db: The MIRDatabase instance - :param data_tuple: A list of tuples, each containing:\n - - arch (str): The architecture name - - series (str): The series name - - `new_data`: New data to be merged into the database. - :raises TypeError: If any field in `new_data` is not a dictionary. - """ - - def update_nested_dict(target, source): - for key, value in source.items(): - if isinstance(value, dict) and key in target: - if isinstance(target, dict): - update_nested_dict(target[key], value) - else: - if isinstance(source, dict): - # dbuq(target) - target.setdefault(key, value) - else: - target = {key: value} - - dbuq(f"{data_tuple}, {len(data_tuple)}") - for arch, series, new_data in data_tuple: - mir_data = mir_db.database[f"{arch}.{series}"] - for comp, field_data in new_data.items(): - if not isinstance(field_data, dict): - raise TypeError(f"{field_data} <-- Cannot combine with database: Not `dict()`") - - # dbuq(f"{arch}.{series} : {comp}") - update_nested_dict(mir_data.setdefault(comp, {}), field_data) - - if series == sdxl_series: - for field, field_data in field_data.items(): - if isinstance(field_data, dict): - for definition, sub_def_data in field_data.items(): - # dbug(definition) - if isinstance(sub_def_data, dict): - mir_data[comp][field].setdefault(definition, {}) - update_nested_dict(mir_data[comp][field][definition], sub_def_data) - - # def auto_gan etc etc # ai-forever/Real-ESRGAN -def mir_update(mir_db: MIRDatabase, task_list: list = None, pipe_list: list = None): - """Create mir unet info database""" - - additional_tags = [tag_pipe(*entry) for entry in diffusers_addons] - additional_tags.extend([tag_base_model(*entry) for entry in transformers_addons]) - - assimilate( - mir_db, # format - additional_tags, - ) - - def add_mir_diffusion(mir_db: MIRDatabase): """Create MIR entries missing from the database""" diff --git a/mir/generate/from_module.py b/mir/generate/from_module.py index bbc6288..a39778f 100644 --- a/mir/generate/from_module.py +++ b/mir/generate/from_module.py @@ -105,19 +105,14 @@ def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: # return list(MAPPING_NAMES) -def to_domain_tag(transformers: bool = False, **kwargs): +def to_domain_tag(library: str, **kwargs): """Set type of MIR prefix depending on model type\n :param transformers: Use transformers data instead of diffusers data, defaults to False :raises ValueError: Model type not detected :return: MIR prefix based on model configuration""" from mir.data import NN_FILTER - data = NN_FILTER - - if transformers: - flags = data["arch"]["transformer"] # pylint:disable=unsubscriptable-object - else: - flags = data["arch"]["diffuser"] # pylint:disable=unsubscriptable-object + flags = NN_FILTER["arch"][library] # pylint:disable=unsubscriptable-object for mir_prefix, key_match in flags.items(): if any(kwargs.get(param, None) for param in key_match): return mir_prefix diff --git a/mir/generate/tasks.py b/mir/generate/tasks.py index 1e28e2e..5da5834 100644 --- a/mir/generate/tasks.py +++ b/mir/generate/tasks.py @@ -39,7 +39,7 @@ async def detect_tasks(self, mir_db: MIRDatabase, field_name: str = "pkg") -> di :rtype: dict""" data_tuple = [] - for series, compatibility_data in mir_db.database.items(): + for series, compatibility_data in mir_db.db.items(): if ( series.startswith("info.") # formatting comment and not any(tag for tag in self.skip_series if series.startswith(tag)) @@ -68,7 +68,7 @@ async def detect_pipes(self, mir_db: MIRDatabase, field_name: str = "pkg") -> di :rtype: dict""" data_tuple = [] - for series, compatibility_data in mir_db.database.items(): + for series, compatibility_data in mir_db.db.items(): if ( series.startswith("info.") # formatting comment and not any(series.startswith(tag) for tag in self.skip_series) @@ -133,14 +133,14 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir sub_field = pipe_class.__module__.split(".")[0] scheduler_series, scheduler_comp = tag_scheduler(class_name) mir_tag = [f"ops.scheduler.{scheduler_series}", scheduler_comp] - if not mir_db.database.get(mir_tag[0], {}).get(mir_tag[1]): + if not mir_db.db.get(mir_tag[0], {}).get(mir_tag[1]): mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="ops.scheduler") DBUQ(f"scheduler {mir_tag} {class_name} {sub_field} ") elif pipe_role == "vae": sub_field = pipe_class.__module__.split(".")[0] mir_comp = series.rsplit(".", 1)[-1] DBUQ(mir_comp) - mir_tag = [mir_id for mir_id, comp_data in mir_db.database.items() if "info.vae" in mir_id and next(iter(comp_data)) == mir_comp] + mir_tag = [mir_id for mir_id, comp_data in mir_db.db.items() if "info.vae" in mir_id and next(iter(comp_data)) == mir_comp] if mir_tag: mir_tag.append(mir_comp) # keep mir tag as single list elif class_name != "AutoencoderKL": diff --git a/mir/generate/transformers/__init__.py b/mir/generate/transformers/__init__.py index e3f09b3..9eaedd4 100644 --- a/mir/generate/transformers/__init__.py +++ b/mir/generate/transformers/__init__.py @@ -10,7 +10,7 @@ ) from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING -from mir.generate.from_module import show_init_fields_for +from mir.generate.transformers.harvest import HarvestClasses AUTO_MAP = AutoModel._model_mapping REVERSE_MAP = AUTO_MAP._reverse_config_mapping diff --git a/mir/generate/transformers/index.py b/mir/generate/transformers/harvest.py similarity index 69% rename from mir/generate/transformers/index.py rename to mir/generate/transformers/harvest.py index 8c53762..c36cd92 100644 --- a/mir/generate/transformers/index.py +++ b/mir/generate/transformers/harvest.py @@ -3,25 +3,22 @@ from typing import Any, Callable -from chanfig import NestedDict - from mir.generate.transformers.raw_data import PrepareData +from mir.tag import MIRTag class HarvestClasses: def __init__(self) -> None: """Initializes the HarvestClasses instance with an empty list to store raw class data.""" - self.raw_data = [] from mir.maid import MIRDatabase - self.mir_db = MIRDatabase() + self.db = MIRDatabase() + self.raw_data = [] self.find_transformers_classes() - self.info = NestedDict({}) def find_transformers_classes(self) -> None: """Finds and collects PrepareData entries for all transformer classes defined in AUTO_MAP.\n :return: List of PrepareData entries representing the transformer classes.""" - from mir.generate.transformers import AUTO_MAP model_data = [] @@ -29,11 +26,11 @@ def find_transformers_classes(self) -> None: config_class, model_class = pair_map # type:ignore if isinstance(model_class, tuple): model_class: Callable = model_class[0] - print(model_class) if config_data := self.extract_config_class_data(config_class): if model_data := self.extract_model_class_data(model_class): if prepared_data := PrepareData(**config_data, **model_data): # type:ignore - self.add_to_database(prepared_data) + mir_tag = MIRTag("info", prepared_data) + self.db.add_tag(mir_tag) def extract_config_class_data(self, config_class: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: """Extracts information from config classes.\n @@ -44,12 +41,14 @@ def extract_config_class_data(self, config_class: Callable) -> dict[str, str | C config_name = config_class.__name__ config_params = PARAMETERS.get(config_name, {}) - repo_path = MIGRATIONS["config"].get(config_name, {}) if not config_params: config_params = show_init_fields_for(config_class) + repo_path = MIGRATIONS["config"].get(config_name, {}) if not repo_path: repo_path = self.config_to_repo(config_class) - if not repo_path or not config_params or "inspect" in config_params or "deprecated" in config_params: + if not repo_path or not config_params: + return None + elif "inspect" in config_params or "deprecated" in config_params: return None return { "name": config_name, @@ -86,41 +85,14 @@ def config_to_repo(self, config_class: Callable) -> str | None: doc_check.append(config_class.forward) # type: ignore for pattern in doc_check: doc_string = pattern.__doc__ - repo_brackets = r"\[([^\]]+)\]" - matches = re.findall(repo_brackets, doc_string) # type: ignore + matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore if matches: try: - self.repo_path = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) except StopIteration as error_log: NFO(f"ERROR >>{matches} : LOG >> {error_log}") continue - def add_to_database(self, prepared_data: PrepareData) -> None: - if hasattr(prepared_data, "tokenizer"): - token_info = NestedDict( - { - "encoder": { - "tokenizer": { - prepared_data.mir_comp: { - "pkg": {f"{prepared_data.tokenizer.__module__}.{prepared_data.tokenizer.__name__}"}, - }, - }, - }, - } - ) - - info = NestedDict( - { - prepared_data.mir_arch: { - prepared_data.mir_series: { - prepared_data.mir_comp: { - "repo": prepared_data.repo_path, - "pkg": {"transformers": prepared_data.model_name}, - "tokenizer": {f"info.encoder.tokenizer.{prepared_data.mir_comp}"}, - } - } - } - } - ) - self.info = token_info | info - print(f"added {prepared_data}") + +if __name__ == "__main__": + HarvestClasses() diff --git a/mir/generate/transformers/raw_data.py b/mir/generate/transformers/raw_data.py index 39cce6d..fdbe5dd 100644 --- a/mir/generate/transformers/raw_data.py +++ b/mir/generate/transformers/raw_data.py @@ -3,7 +3,7 @@ from dataclasses import dataclass, field -from typing import Callable +from typing import Callable, Any @dataclass @@ -12,13 +12,11 @@ class PrepareData: name: str model: Callable - config: Callable + config: type repo_path: str config_params: dict[str, list[str]] - model_params: dict[str, list[str]] | None = None - mir_arch: str = field(init=False) - mir_series: str = field(init=False) - mir_comp: str = field(init=False) + model_params: dict[str, list[str]] | None = field(init=True, default_factory=lambda: {"": [""]}) + tasks: list[str] = field(init=False, default_factory=lambda: [""]) def __post_init__(self) -> None: """Initializes the PrepareData instance by setting derived attributes.""" @@ -26,12 +24,10 @@ def __post_init__(self) -> None: self.model_name: str = self.model.__name__.split(".")[-1] if tokenizer := TOKENIZER_MAPPING.get(self.config, None): - self.tokenizer = tokenizer - self.tokenizer_pkg: dict[str, str] | None = {"transformers": f"{self.tokenizer.__module__}.{self.tokenizer.__name__}"} + self.tokenizer: tuple[type[Any] | None, type[Any] | None] = tokenizer if internal_name := REVERSE_MAP.get(self.config): self.internal_name = internal_name self.model_to_tasks() - self.mir_tag_from_config() def model_to_tasks(self) -> None: """Transform a single model class into derivative classes for specific tasks.\n @@ -41,26 +37,10 @@ def model_to_tasks(self) -> None: import_path = Path(self.model.__module__).stem parent_module = import_module(import_path) - + self.tasks = [] if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": - self.task_classes = parent_module.__all__ + for module in parent_module.__all__: + if (module.lower() != module) and (module != self.model_name) and (module != self.config.__name__): + self.tasks.append(module) else: - self.task_classes = [self.model.__name__] - - def mir_tag_from_config(self) -> None: - """Generates MIR series and component tags based on the configuration class.\n - :return: Tuple containing MIR series, component, and suffix tags.""" - - from mir.generate.from_module import to_domain_tag - from mir.tag import tag_model_from_repo - - mir_prefix = to_domain_tag(transformers=True, **self.config_params) - if not mir_prefix: - if self.model_params: - if mir_prefix := to_domain_tag(transformers=True, **self.model_params): - pass - raise ValueError(f"Unable to determine MIR prefix from {self}") - else: - raise ValueError(f"Unrecognized model type, no tag matched {self.name} with {self.config_params} or {self.model_params}") - self.mir_arch = mir_prefix - self.mir_series, self.mir_comp = tag_model_from_repo(self.repo_path) + self.tasks = [self.model.__name__] diff --git a/mir/generate/transformers/tokenizers.py b/mir/generate/transformers/tokenizers.py deleted file mode 100644 index a395d0e..0000000 --- a/mir/generate/transformers/tokenizers.py +++ /dev/null @@ -1,24 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import re -from importlib import import_module - -from mir.generate.transformers import TOKENIZER_MAPPING -from mir.maid import MIRDatabase -from mir.spec import mir_entry - - -def tag_tokenizers(config_class: Callable): - tokenizer_class = TOKENIZER_MAPPING[config_class] # type: ignore - if tokenizer_class: - { "pkg":{"transformers": f"{tokenizer_class.__module__}.{tokenizer_class.__name__}"}) - if tk_pkg: - mir_data.get("info.encoder.tokenizer", mir_data.setdefault("info.encoder.tokenizer", {})).update( - { - mir_suffix: { - "pkg": tk_pkg, - } - }, - ) - return tokenizer_class diff --git a/mir/maid.py b/mir/maid.py index acdf86c..ef7ba78 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -9,34 +9,67 @@ from mir import MIR_PATH_NAMED from mir.json_io import read_json_file, write_json_file +from mir.tag import MIRTag class MIRDatabase: """Machine Intelligence Resource Database Object Database search and read/write operations""" - def __init__(self, database: dict | None = None) -> None: + def __init__(self, db: dict | None = None) -> None: + from chanfig import NestedDict from json.decoder import JSONDecodeError from mir import DBUQ - if not database: - self.database = {"expected": "data"} + if not db: + self.db = NestedDict() try: self.read_from_disk() except JSONDecodeError as error_log: DBUQ(error_log) - self.database = {} + self.db = NestedDict() - def add(self, resource: dict[str, Any]) -> None: - """Merge pre-existing MIR entries, or add new ones - :param resource: Entry to apply + def add_tag(self, mir_tag: MIRTag): + """Add or update entry to MIR Database + :param prepared_data: An instance of PrepareData to convert into tags """ - parent_key = next(iter(resource)) - if self.database is not None: - if self.database.get(parent_key, 0): - self.database[parent_key] = self.database[parent_key] | resource[parent_key] + from chanfig import NestedDict + + library = mir_tag.pkg.split(".")[0] + pkg = {library: (mir_tag.pkg,)} + if hasattr(mir_tag.data, "tokenizer") and mir_tag.data.tokenizer: + info = NestedDict({f"info.encoder.tokenizer.{mir_tag.series}": {mir_tag.tokenizer_pkg}}) + self._update_data(self.db, info) + pkg = pkg | {"tokenizer": f"info.encoder.tokenizer.{mir_tag.series}"} + if hasattr(mir_tag, "comp"): + info = NestedDict({f"info.{mir_tag.arch}.{mir_tag.series}{mir_tag.comp}": pkg}) + else: + info = NestedDict({f"info.{mir_tag.arch}.{mir_tag.series}": pkg}) + self._update_data(self.db, info) + + self.db = NestedDict(self.db) + + def _update_data(self, target, source): + """Recursively merges `source` into `target` without overwriting nested dictionaries entirely.""" + + for key, value in source.items(): + if isinstance(value, dict) and key in target and isinstance(target[key], dict): + self._update_data(target[key], value) + else: + # Update only if key doesn't exist or value is not a dict to avoid overwriting + if key not in target or not isinstance(target[key], dict): + target.setdefault(key, value) + + # Handle cases where source might have non-dict values that should update target's non-dict values + for key in target: + if key not in source and isinstance(target[key], dict): + continue + elif key not in source and not isinstance(target[key], dict): + # If key exists in target but not in source and is not a dict, ensure it's preserved + pass else: - self.database[parent_key] = resource[parent_key] + # Additional logic if needed for specific conditions + pass def write_to_disk(self, data: Optional[dict] = None) -> None: # pylint:disable=unused-argument """Save data to JSON file\n""" @@ -50,10 +83,10 @@ def write_to_disk(self, data: Optional[dict] = None) -> None: # pylint:disable= # except (FileNotFoundError, OSError) as error_log: # nfo(f"MIR file not found before write, regenerating... {error_log}") - write_json_file(os.path.dirname(MIR_PATH_NAMED), file_name="mir.json", data=self.database, mode=mode) + write_json_file(os.path.dirname(MIR_PATH_NAMED), file_name="mir.json", data=self.db, mode=mode) written_data = self.read_from_disk() NFO(f"Wrote {len(written_data)} lines to MIR database file.") - self.database = written_data + self.db = written_data def read_from_disk(self, data: Optional[dict] = None) -> dict[str, Any]: """Populate mir database\n @@ -61,10 +94,10 @@ def read_from_disk(self, data: Optional[dict] = None) -> dict[str, Any]: :return: dict of MIR data""" if not os.path.exists(MIR_PATH_NAMED): self.write_to_disk({}) - return self.database + return self.db else: - self.database = read_json_file(MIR_PATH_NAMED) - return self.database + self.db = read_json_file(MIR_PATH_NAMED) + return self.db def _stage_maybes(self, maybe_match: str, target: str, series: str, compatibility: str) -> list[str | bool]: """Process a single value for matching against the target\n @@ -154,7 +187,7 @@ def find_tag(self, field: str, target: str, sub_field: Optional[str] = None, dom target = re.sub(parameters, "", target) self.matches = [] - for series, comp in self.database.items(): + for series, comp in self.db.items(): if (not domain) or series.startswith(domain): for compatibility, fields in comp.items(): if maybe_match := fields.get(field): @@ -169,5 +202,5 @@ def find_tag(self, field: str, target: str, sub_field: Optional[str] = None, dom if best_match := self.grade_maybes(self.matches, target): return best_match else: - NFO(f"Query '{target}' not found when {len(self.database)}'{field}' options searched\n") + NFO(f"Query '{target}' not found when {len(self.db)}'{field}' options searched\n") return None diff --git a/mir/tag.py b/mir/tag.py index 38b8929..495040e 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -1,43 +1,106 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import Any - - -def tag_model_from_repo(repo_title: str, decoder=False) -> tuple[str, Any]: - """Create a mir label from a repo path\n - :param mir_prefix: Known period-separated prefix and model type - :param repo_path: Typical remote source repo path, A URL without domain - :return: The assembled mir tag with compatibility pre-separated""" - import re - from mir import PARAMETERS, BREAKING - - root = "decoder" if decoder else "*" - repo_title = repo_title.split(":latest")[0] - repo_title = repo_title.split(":Q")[0] - repo_title = repo_title.split(r"/")[-1].lower() - pattern = r"^.*[v]?(\d{1}+\.\d).*" - match = re.findall(pattern, repo_title) - if match: - if next(iter(match)): - repo_title = repo_title.replace(next(iter(match))[-1], "") - parts = repo_title.replace(".", "").split("-") - if len(parts) == 1: - parts = repo_title.split("_") - subtraction_prefixes = r"\d.b-|\-rl|tiny|large|mlx|onnx|gguf|medium|base|multimodal|mini|instruct|full|:latest|preview|small|pro|beta|hybrid|plus|dpo|community" - - pattern_2 = re.compile(PARAMETERS) - clean_parts = [re.sub(pattern_2, "", segment.lower()) for segment in parts] - cleaned_string = "-".join([x for x in clean_parts if x]) - cleaned_string = re.sub(subtraction_prefixes, "", cleaned_string) - cleaned_string = re.sub("-it", "", cleaned_string.replace("-bit", "")).replace("--", "-") - cleaned_string = cleaned_string.replace("-b-", "") - # print(cleaned_string) - suffix_match = re.findall(BREAKING, cleaned_string) # Check for breaking suffixes first - if suffix_match: - suffix = next(iter(suffix for suffix in suffix_match[0] if suffix)) - cleaned_string = re.sub(suffix.lower(), "-", cleaned_string).rstrip("-,") - else: - suffix = root - cleaned_string = re.sub(r"[._]+", "-", cleaned_string.lower()).strip("-_") - return (cleaned_string, suffix) +from dataclasses import dataclass, field +from typing import Callable + +from mir.generate.transformers.raw_data import PrepareData + + +@dataclass +class MIRTag: + """Represents a MIR tag associated with a specific domain and model data.\n + + Attributes:\n + domain: The domain of the MIR tag. + prepared_data: Object containing prepared model data. + arch: The architecture component of the MIR tag (generated). + series: The series component of the MIR tag (generated). + pkg Package information associated with the MIR tag (generated). + tokenizer_pkg Dependency package information associated with the MIR tag (generated). + """ + + domain: str + data: PrepareData + arch: str = field(init=False) + series: str = field(init=False) + pkg: str = field(default_factory=str) + tokenizer_pkg: str = field(default_factory=str) + + def __post_init__(self) -> None: + """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" + from mir.maid import MIRDatabase + + self.mir_db = MIRDatabase() + self.pkg = self.generate_pkg(pkg=self.data.model) + if hasattr(self.data, "tokenizer") and self.data.tokenizer: + self.tokenizer_pkg = self.generate_pkg(pkg=self.data.tokenizer) # type:ignore + self.generate_arch() + self.generate_series_and_comp(repo_title=self.data.repo_path) + + def generate_pkg(self, pkg: Callable) -> str: + """Generates package information for the MIR tag based on class. + :param pkg: A class object (model, tokenizer, etc) to build a tag from""" + + return f"{pkg.__module__}.{pkg.__name__}" + + def generate_arch(self) -> None: + """Generates the architecture part of the MIR tag based on prepared data.\n + :raises ValueError: If no suitable tag can be determined.""" + from mir.generate.from_module import to_domain_tag + + library = self.pkg.split(".")[0] + arch = to_domain_tag(library, **self.data.config_params) + if not arch: + if self.data.model_params: + if arch := to_domain_tag(library, **self.data.model_params): + pass + raise ValueError(f"Unable to determine MIR prefix from {self}") + else: + raise ValueError( + f"Unrecognized model type, \ + no tag matched {self.data.name} \ + with {self.data.config_params} or {self.data.model_params}", + ) + self.arch = arch + + def generate_series_and_comp(self, repo_title: str, decoder=False) -> None: + """Generates the MIR tag components from a repository title.\n + :param repo_title: The title of the repository from which to derive the MIR tag. + :param decoder: Boolean flag indicating if the model is a decoder. + :return: A tuple containing the cleaned tag string and suffix.""" + + import re + + from mir import BREAKING, PARAMETERS + + root = "decoder" if decoder else "*" + repo_title = repo_title.split(":latest")[0] + repo_title = repo_title.split(":Q")[0] + repo_title = repo_title.split(r"/")[-1].lower() + pattern = r"^.*[v]?(\d{1}+\.\d).*" + match = re.findall(pattern, repo_title) + if match: + if next(iter(match)): + repo_title = repo_title.replace(next(iter(match))[-1], "") + parts = repo_title.replace(".", "").split("-") + if len(parts) == 1: + parts = repo_title.split("_") + subtraction_prefixes = r"\d.b-|\-rl|tiny|large|mlx|onnx|gguf|medium|base|multimodal|mini|instruct|full|:latest|preview|small|pro|beta|hybrid|plus|dpo|community" + + pattern_2 = re.compile(PARAMETERS) + clean_parts = [re.sub(pattern_2, "", segment.lower()) for segment in parts] + cleaned_string = "-".join([x for x in clean_parts if x]) + cleaned_string = re.sub(subtraction_prefixes, "", cleaned_string) + cleaned_string = re.sub("-it", "", cleaned_string.replace("-bit", "")).replace("--", "-") + cleaned_string = cleaned_string.replace("-b-", "") + suffix_match = re.findall(BREAKING, cleaned_string) # Check for breaking suffixes first + if suffix_match: + suffix = next(iter(suffix for suffix in suffix_match[0] if suffix)) + cleaned_string = re.sub(suffix.lower(), "-", cleaned_string).rstrip("-,") + else: + suffix = root + cleaned_string = re.sub(r"[.-]+", "_", cleaned_string.lower()).strip("-_") + self.series = cleaned_string + if suffix != "*": + self.comp = suffix From 7f7bb0b3f67e77629c91a8497be00c77df28f5ff Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sat, 17 Jan 2026 15:46:35 -0500 Subject: [PATCH 08/16] ~transformers complete --- mir/__init__.py | 4 +- mir/framework.py | 114 ++++++++++++++++++ mir/generate/transformers/harvest.py | 14 ++- mir/maid.py | 47 ++------ mir/package.py | 0 mir/tag.py | 36 ++---- tests/{ => old}/test_class_parent.py | 0 tests/{ => old}/test_deconstructors_root.py | 0 tests/{ => old}/test_doc_parser.py | 0 tests/{ => old}/test_find_docstring_run.py | 0 .../test_gather_diffusers_metadata.py | 0 tests/{ => old}/test_json_io.py | 0 tests/{ => old}/test_mir_db_create_restore.py | 0 tests/{ => old}/test_mir_merge.py | 0 tests/{ => old}/test_mir_search.py | 0 tests/{ => old}/test_mir_tagging.py | 0 tests/{ => old}/test_regex_constants.py | 0 tests/{ => old}/test_resolve_code_names.py | 0 tests/{ => old}/test_seek_class.py | 0 tests/{ => old}/test_task.py | 0 tests/{ => old}/test_taskanalyzer.py | 0 tests/test_mir_generate.py | 21 ++++ 22 files changed, 170 insertions(+), 66 deletions(-) create mode 100644 mir/framework.py create mode 100644 mir/package.py rename tests/{ => old}/test_class_parent.py (100%) rename tests/{ => old}/test_deconstructors_root.py (100%) rename tests/{ => old}/test_doc_parser.py (100%) rename tests/{ => old}/test_find_docstring_run.py (100%) rename tests/{ => old}/test_gather_diffusers_metadata.py (100%) rename tests/{ => old}/test_json_io.py (100%) rename tests/{ => old}/test_mir_db_create_restore.py (100%) rename tests/{ => old}/test_mir_merge.py (100%) rename tests/{ => old}/test_mir_search.py (100%) rename tests/{ => old}/test_mir_tagging.py (100%) rename tests/{ => old}/test_regex_constants.py (100%) rename tests/{ => old}/test_resolve_code_names.py (100%) rename tests/{ => old}/test_seek_class.py (100%) rename tests/{ => old}/test_task.py (100%) rename tests/{ => old}/test_taskanalyzer.py (100%) create mode 100644 tests/test_mir_generate.py diff --git a/mir/__init__.py b/mir/__init__.py index c688644..4e83592 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -22,8 +22,8 @@ IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] -tag_name = lambda path: path.rsplit(".", 1) -mir_run = lambda parts: getattr(import_module(parts[0]), parts[1]) +tag = lambda path: path.rsplit(".", 1) +run = lambda parts: getattr(import_module(parts[0]), parts[1]) Mir = HarvestClasses().db.db diff --git a/mir/framework.py b/mir/framework.py new file mode 100644 index 0000000..077f7ca --- /dev/null +++ b/mir/framework.py @@ -0,0 +1,114 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Any, Callable +from dataclasses import dataclass, field +from mir.generate.transformers.raw_data import PrepareData +from mir.tag import MIRTag + + +@dataclass +class MIRPackage: + data: Callable | str | dict[str, str] + library: str = field(init=False, default_factory=str) + package: dict[str, dict[str, str]] = field(init=False, default_factory=dict[str, dict[str, str]]) + framework: dict[str, dict[str, str]] = field(init=False, default_factory=dict[str, dict[str, str]]) + + def __init__(self): + pass + + def __call__(self, data: Callable | str | dict[str, str]): + self.data = data + if isinstance(self.data, Callable): + self.generate_package() + + def generate_package(self) -> None: + """Generates package information for the MIR tag based on class. + :param pkg: A class object (model, tokenizer, etc) to build a tag from""" + self.domain = "ops" + module_path = self.data.__module__ + self.library = module_path.split(".")[0] + self.package: dict[str, dict[str, str]] = {self.library: {"model": f"{module_path}.{self.data.__name__}"}} + + def add_framework(self, framework_data) -> None: + self.domain = "info" + self.framework = {self.library: framework_data} + + +class MIRNesting: + """Build tag components from the extracted data\n + :param mir_tag: An instance of MIR tag with the necessary information + :param name: Identification string to store data underneath + :param mir_package: Instance of MIRPackage to store inside the nested dict + :param prepared_data: Instance of PrepareData to attribute the final information + :returns: The final, assembled MIR tag""" + + loops: list[str] + framework_data: dict[str, str | dict[str, Any]] = {} + repo: str | None = field(default_factory=str | None) + framework: dict[str, str] = field(init=False) + tokenizer: str | None = field(default_factory=str) + + def __init__(self, mir_tag: MIRTag) -> None: + self.mir_tag = mir_tag + self.loops = [] + self.framework_data = {} + + def __call__(self, mir_package: MIRPackage, prepared_data: PrepareData | None = None): + if hasattr(mir_package, "library"): + self.library = mir_package.library + if prepared_data: + self.framework_data.setdefault("repo", prepared_data.repo_path) + if hasattr(mir_package, "tokenizer"): + name = "tokenizer" + self.package = mir_package.package + self.nest_data( + name=name, + domain=mir_package.domain, + arch="encoder", + series="tokenizer", + comp=self.mir_tag.series, + ) + self.framework_data.setdefault("tokenizer", f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}") + else: + data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + self.framework_data.setdefault("model", data + comp) + else: + self.framework_data.setdefault("model", data) + + if hasattr(mir_package, "framework"): + name = "framework" + self.package = mir_package.framework + else: + name = "model" + self.package = mir_package.package + if hasattr(prepared_data, "tasks") and prepared_data.tasks: + self.package[mir_package.library].setdefault("tasks", prepared_data.tasks) + self.nest_data( + name=name, + domain=mir_package.domain, + arch=self.mir_tag.arch, + series=self.mir_tag.series, + comp=comp, + ) + self.loops.append(name) + + def nest_data(self, name: str, domain: str, arch: str, series: str, comp: str | None = None) -> None: + from chanfig import NestedDict + + if comp: + nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) + nest[domain][arch][series] = self.package + else: + nest = NestedDict({f"{domain}.{arch}": {series: ""}}) + nest[domain][arch][series] = self.package + setattr(self, name, nest) + + +# data[domain][arch][series] = pkg_data +# if tag_data.comp: +# data[tag_datadomain][arch][series][comp_tag] = pkg_data +# self.generate_pkg("pkg", self.raw_data.model) +# self.generate_pkg("tokenizer_pkg", self.raw_data.tokenizer) +# framework: dict[str,FrameworkBundle] diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index c36cd92..0e07255 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -3,6 +3,7 @@ from typing import Any, Callable +from mir.framework import MIRNesting, MIRPackage from mir.generate.transformers.raw_data import PrepareData from mir.tag import MIRTag @@ -29,8 +30,17 @@ def find_transformers_classes(self) -> None: if config_data := self.extract_config_class_data(config_class): if model_data := self.extract_model_class_data(model_class): if prepared_data := PrepareData(**config_data, **model_data): # type:ignore - mir_tag = MIRTag("info", prepared_data) - self.db.add_tag(mir_tag) + mir_tag = MIRTag(prepared_data) + mir_package = MIRPackage() + mir_nest = MIRNesting(mir_tag) + mir_package(data=prepared_data.model) + mir_nest(mir_package, prepared_data) + if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: + mir_package(data=prepared_data.tokenizer) + mir_nest(mir_package) + mir_package.add_framework(mir_nest.framework_data) + mir_nest(mir_package) + self.db.add_data(mir_nest, *mir_nest.loops) def extract_config_class_data(self, config_class: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: """Extracts information from config classes.\n diff --git a/mir/maid.py b/mir/maid.py index ef7ba78..5f0111d 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -8,13 +8,14 @@ from typing import Any, List, Optional from mir import MIR_PATH_NAMED +from mir.framework import MIRNesting from mir.json_io import read_json_file, write_json_file from mir.tag import MIRTag class MIRDatabase: - """Machine Intelligence Resource Database Object - Database search and read/write operations""" + """Machine Intelligence Resource database object\n + Database query and read/write operations""" def __init__(self, db: dict | None = None) -> None: from chanfig import NestedDict @@ -29,48 +30,24 @@ def __init__(self, db: dict | None = None) -> None: DBUQ(error_log) self.db = NestedDict() - def add_tag(self, mir_tag: MIRTag): - """Add or update entry to MIR Database - :param prepared_data: An instance of PrepareData to convert into tags - """ + def add_data(self, mir_nest: MIRNesting, *args) -> None: + """Add entry to MIR Database\n + :param mir_tag: An instance of MIRTag to be added to the database""" from chanfig import NestedDict - library = mir_tag.pkg.split(".")[0] - pkg = {library: (mir_tag.pkg,)} - if hasattr(mir_tag.data, "tokenizer") and mir_tag.data.tokenizer: - info = NestedDict({f"info.encoder.tokenizer.{mir_tag.series}": {mir_tag.tokenizer_pkg}}) - self._update_data(self.db, info) - pkg = pkg | {"tokenizer": f"info.encoder.tokenizer.{mir_tag.series}"} - if hasattr(mir_tag, "comp"): - info = NestedDict({f"info.{mir_tag.arch}.{mir_tag.series}{mir_tag.comp}": pkg}) - else: - info = NestedDict({f"info.{mir_tag.arch}.{mir_tag.series}": pkg}) - self._update_data(self.db, info) - + for nested_tag in args: + self._include_data(self.db, getattr(mir_nest, nested_tag)) self.db = NestedDict(self.db) - def _update_data(self, target, source): - """Recursively merges `source` into `target` without overwriting nested dictionaries entirely.""" - + def _include_data(self, target: dict[str, Any], source: dict[str, Any]): + """Recursively merges `source` into `target` without overwriting nested dictionaries or their entries.""" for key, value in source.items(): - if isinstance(value, dict) and key in target and isinstance(target[key], dict): - self._update_data(target[key], value) + if isinstance(value, dict) and key in target and isinstance(target[key], dict): # 递归 recurse + self._include_data(target[key], value) else: - # Update only if key doesn't exist or value is not a dict to avoid overwriting if key not in target or not isinstance(target[key], dict): target.setdefault(key, value) - # Handle cases where source might have non-dict values that should update target's non-dict values - for key in target: - if key not in source and isinstance(target[key], dict): - continue - elif key not in source and not isinstance(target[key], dict): - # If key exists in target but not in source and is not a dict, ensure it's preserved - pass - else: - # Additional logic if needed for specific conditions - pass - def write_to_disk(self, data: Optional[dict] = None) -> None: # pylint:disable=unused-argument """Save data to JSON file\n""" diff --git a/mir/package.py b/mir/package.py new file mode 100644 index 0000000..e69de29 diff --git a/mir/tag.py b/mir/tag.py index 495040e..c31266f 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -2,7 +2,6 @@ # from dataclasses import dataclass, field -from typing import Callable from mir.generate.transformers.raw_data import PrepareData @@ -12,55 +11,38 @@ class MIRTag: """Represents a MIR tag associated with a specific domain and model data.\n Attributes:\n - domain: The domain of the MIR tag. prepared_data: Object containing prepared model data. arch: The architecture component of the MIR tag (generated). series: The series component of the MIR tag (generated). - pkg Package information associated with the MIR tag (generated). - tokenizer_pkg Dependency package information associated with the MIR tag (generated). + comp The compatibility component of the MIR tag (generated, optional). """ - domain: str - data: PrepareData + raw_data: PrepareData arch: str = field(init=False) series: str = field(init=False) - pkg: str = field(default_factory=str) - tokenizer_pkg: str = field(default_factory=str) def __post_init__(self) -> None: """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" - from mir.maid import MIRDatabase - - self.mir_db = MIRDatabase() - self.pkg = self.generate_pkg(pkg=self.data.model) - if hasattr(self.data, "tokenizer") and self.data.tokenizer: - self.tokenizer_pkg = self.generate_pkg(pkg=self.data.tokenizer) # type:ignore self.generate_arch() - self.generate_series_and_comp(repo_title=self.data.repo_path) - - def generate_pkg(self, pkg: Callable) -> str: - """Generates package information for the MIR tag based on class. - :param pkg: A class object (model, tokenizer, etc) to build a tag from""" - - return f"{pkg.__module__}.{pkg.__name__}" + self.generate_series_and_comp(repo_title=self.raw_data.repo_path) def generate_arch(self) -> None: """Generates the architecture part of the MIR tag based on prepared data.\n :raises ValueError: If no suitable tag can be determined.""" from mir.generate.from_module import to_domain_tag - library = self.pkg.split(".")[0] - arch = to_domain_tag(library, **self.data.config_params) + library = self.raw_data.model.__module__.split(".")[0] + arch = to_domain_tag(library, **self.raw_data.config_params) if not arch: - if self.data.model_params: - if arch := to_domain_tag(library, **self.data.model_params): + if self.raw_data.model_params: + if arch := to_domain_tag(library, **self.raw_data.model_params): pass raise ValueError(f"Unable to determine MIR prefix from {self}") else: raise ValueError( f"Unrecognized model type, \ - no tag matched {self.data.name} \ - with {self.data.config_params} or {self.data.model_params}", + no tag matched {self.raw_data.name} \ + with {self.raw_data.config_params} or {self.raw_data.model_params}", ) self.arch = arch diff --git a/tests/test_class_parent.py b/tests/old/test_class_parent.py similarity index 100% rename from tests/test_class_parent.py rename to tests/old/test_class_parent.py diff --git a/tests/test_deconstructors_root.py b/tests/old/test_deconstructors_root.py similarity index 100% rename from tests/test_deconstructors_root.py rename to tests/old/test_deconstructors_root.py diff --git a/tests/test_doc_parser.py b/tests/old/test_doc_parser.py similarity index 100% rename from tests/test_doc_parser.py rename to tests/old/test_doc_parser.py diff --git a/tests/test_find_docstring_run.py b/tests/old/test_find_docstring_run.py similarity index 100% rename from tests/test_find_docstring_run.py rename to tests/old/test_find_docstring_run.py diff --git a/tests/test_gather_diffusers_metadata.py b/tests/old/test_gather_diffusers_metadata.py similarity index 100% rename from tests/test_gather_diffusers_metadata.py rename to tests/old/test_gather_diffusers_metadata.py diff --git a/tests/test_json_io.py b/tests/old/test_json_io.py similarity index 100% rename from tests/test_json_io.py rename to tests/old/test_json_io.py diff --git a/tests/test_mir_db_create_restore.py b/tests/old/test_mir_db_create_restore.py similarity index 100% rename from tests/test_mir_db_create_restore.py rename to tests/old/test_mir_db_create_restore.py diff --git a/tests/test_mir_merge.py b/tests/old/test_mir_merge.py similarity index 100% rename from tests/test_mir_merge.py rename to tests/old/test_mir_merge.py diff --git a/tests/test_mir_search.py b/tests/old/test_mir_search.py similarity index 100% rename from tests/test_mir_search.py rename to tests/old/test_mir_search.py diff --git a/tests/test_mir_tagging.py b/tests/old/test_mir_tagging.py similarity index 100% rename from tests/test_mir_tagging.py rename to tests/old/test_mir_tagging.py diff --git a/tests/test_regex_constants.py b/tests/old/test_regex_constants.py similarity index 100% rename from tests/test_regex_constants.py rename to tests/old/test_regex_constants.py diff --git a/tests/test_resolve_code_names.py b/tests/old/test_resolve_code_names.py similarity index 100% rename from tests/test_resolve_code_names.py rename to tests/old/test_resolve_code_names.py diff --git a/tests/test_seek_class.py b/tests/old/test_seek_class.py similarity index 100% rename from tests/test_seek_class.py rename to tests/old/test_seek_class.py diff --git a/tests/test_task.py b/tests/old/test_task.py similarity index 100% rename from tests/test_task.py rename to tests/old/test_task.py diff --git a/tests/test_taskanalyzer.py b/tests/old/test_taskanalyzer.py similarity index 100% rename from tests/test_taskanalyzer.py rename to tests/old/test_taskanalyzer.py diff --git a/tests/test_mir_generate.py b/tests/test_mir_generate.py new file mode 100644 index 0000000..8ceacd0 --- /dev/null +++ b/tests/test_mir_generate.py @@ -0,0 +1,21 @@ +def test_info_key_exists_and_library_is_not_nested(): + from mir import Mir + + print(Mir.info.cnn.yolos) + result = Mir.info.cnn.yolos["transformers"] # should not throw + assert result == "ops.cnn.yolos" + + +def test_ops_key_exists_and_library_is_not_tested(): + from mir import Mir + + print(Mir.ops.cnn.yolos) + result = Mir.ops.cnn.yolos["transformers"] # should not throw + assert result["model"] == "transformers.models.yolos.modeling_yolos.YolosModel" + expected_tasks = [ + "YolosPreTrainedModel", + "YolosForObjectDetection", + "YolosImageProcessorFast", + "YolosImageProcessor", + ] + assert all(task in result["tasks"] for task in expected_tasks) From 474426bc892ccf71c06dfb793a9fd755b63cc3ca Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sat, 17 Jan 2026 17:59:21 -0500 Subject: [PATCH 09/16] ~patched_tokenizers --- mir/__init__.py | 4 - mir/__main__.py | 21 ++++ mir/framework.py | 133 +++++++++++++------------- mir/generate/transformers/harvest.py | 9 +- mir/generate/transformers/raw_data.py | 1 + tests/test_mir_generate.py | 9 +- 6 files changed, 103 insertions(+), 74 deletions(-) create mode 100644 mir/__main__.py diff --git a/mir/__init__.py b/mir/__init__.py index 4e83592..ba063fb 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -22,8 +22,4 @@ IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] -tag = lambda path: path.rsplit(".", 1) -run = lambda parts: getattr(import_module(parts[0]), parts[1]) - - Mir = HarvestClasses().db.db diff --git a/mir/__main__.py b/mir/__main__.py new file mode 100644 index 0000000..4e892d4 --- /dev/null +++ b/mir/__main__.py @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Callable +from importlib import import_module + +tag = lambda path: path.rsplit(".", 1) # noqa +run = lambda parts: getattr(import_module(parts[0]), parts[1]) + + +def get_attribute_chain(root_object: Callable, attribute_path: str): + """Retrieve a nested attribute from *root_object* using a dot‑separated string.\n + :param root_object : The object from which the attribute chain will be resolved. + :param attribute_path : Dot‑separated attribute names, e.g. ``"ops.cnn.yolos"``. + :returns: The final attribute value reached by following the chain. + :raises: AttributeError If any part of the chain does not exist on the current object.""" + + current = root_object + for part in attribute_path.split("."): + current = getattr(current, part) + return current diff --git a/mir/framework.py b/mir/framework.py index 077f7ca..aa0a440 100644 --- a/mir/framework.py +++ b/mir/framework.py @@ -10,36 +10,29 @@ @dataclass class MIRPackage: data: Callable | str | dict[str, str] - library: str = field(init=False, default_factory=str) - package: dict[str, dict[str, str]] = field(init=False, default_factory=dict[str, dict[str, str]]) - framework: dict[str, dict[str, str]] = field(init=False, default_factory=dict[str, dict[str, str]]) + package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - def __init__(self): - pass - - def __call__(self, data: Callable | str | dict[str, str]): + def __init__(self, data: Callable | str | dict[str, str]): + self.package = {} self.data = data - if isinstance(self.data, Callable): + if not isinstance(self.data, dict): self.generate_package() def generate_package(self) -> None: """Generates package information for the MIR tag based on class. :param pkg: A class object (model, tokenizer, etc) to build a tag from""" self.domain = "ops" - module_path = self.data.__module__ - self.library = module_path.split(".")[0] - self.package: dict[str, dict[str, str]] = {self.library: {"model": f"{module_path}.{self.data.__name__}"}} + model = f"{self.data.__module__}.{self.data.__name__}" + self.package: dict[str, str] = {"model": model} def add_framework(self, framework_data) -> None: self.domain = "info" - self.framework = {self.library: framework_data} + self.package = framework_data class MIRNesting: """Build tag components from the extracted data\n :param mir_tag: An instance of MIR tag with the necessary information - :param name: Identification string to store data underneath - :param mir_package: Instance of MIRPackage to store inside the nested dict :param prepared_data: Instance of PrepareData to attribute the final information :returns: The final, assembled MIR tag""" @@ -49,66 +42,78 @@ class MIRNesting: framework: dict[str, str] = field(init=False) tokenizer: str | None = field(default_factory=str) - def __init__(self, mir_tag: MIRTag) -> None: + def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData) -> None: + """\nInitialize the framework with MIR tag and prepared data.\n + :param mir_tag : The MIR tag instance. + :param prepared_data : The prepared data for processing.""" self.mir_tag = mir_tag + + self.prepared_data = prepared_data self.loops = [] self.framework_data = {} - def __call__(self, mir_package: MIRPackage, prepared_data: PrepareData | None = None): - if hasattr(mir_package, "library"): - self.library = mir_package.library - if prepared_data: - self.framework_data.setdefault("repo", prepared_data.repo_path) - if hasattr(mir_package, "tokenizer"): - name = "tokenizer" - self.package = mir_package.package - self.nest_data( - name=name, - domain=mir_package.domain, - arch="encoder", - series="tokenizer", - comp=self.mir_tag.series, - ) - self.framework_data.setdefault("tokenizer", f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}") - else: - data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + def __call__(self, mir_package: MIRPackage) -> None: + """Dispatches a MIRPackage to the appropriate handler based on its domain. + :param mir_package: An instance of MIRPackage with the requisite data to tag""" + + if (mir_package.domain == "ops" and + hasattr(self.prepared_data, "tokenizer") and + self.prepared_data.tokenizer and self.loops== ['model']): + self._process("tokenizer", mir_package) + elif mir_package.domain == "ops": + self._process("model", mir_package) + elif mir_package.domain == "info": + self._process("framework", mir_package) + + def _process(self, name: str, mir_package: MIRPackage) -> None: + """Common routine for handling a package: store tag data, nest the package, + and record the name of the newly-created attribute.\n + :param name: Identification string to store data underneath + :param mir_package: An instance of MIRPackage with the requisite data""" + + is_framework = name == "framework" + is_model = name == "model" + + + if is_framework: + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + tag_data += comp + self.framework_data.setdefault("repo", self.prepared_data.repo_path) + elif is_model: + package_data = {self.prepared_data.library: mir_package.package} + if hasattr(self.prepared_data, "tasks") and self.prepared_data.tasks: + package_data[self.prepared_data.library].setdefault("tasks", self.prepared_data.tasks) + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" if comp := getattr(self.mir_tag, "comp", None): - self.framework_data.setdefault("model", data + comp) - else: - self.framework_data.setdefault("model", data) - - if hasattr(mir_package, "framework"): - name = "framework" - self.package = mir_package.framework - else: - name = "model" - self.package = mir_package.package - if hasattr(prepared_data, "tasks") and prepared_data.tasks: - self.package[mir_package.library].setdefault("tasks", prepared_data.tasks) - self.nest_data( - name=name, - domain=mir_package.domain, - arch=self.mir_tag.arch, - series=self.mir_tag.series, - comp=comp, - ) + tag_data += comp + self.framework_data.setdefault(name, tag_data) + else: # tokenizer case + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}" + self.framework_data.setdefault(name, tag_data) + + self.nest_data(name=name, tag_data=tag_data, package_data=package_data) self.loops.append(name) - def nest_data(self, name: str, domain: str, arch: str, series: str, comp: str | None = None) -> None: + def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: + """Nest data into a hierarchical attribute structure.\n + :param name: Attribute name to store the nested data + :param tag_data: Dotted path string for nesting + :param package_data: Data to be stored in the nested structure""" + from chanfig import NestedDict - if comp: + tag_parts = tuple(x for x in tag_data.split(".")) + + if len(tag_parts) ==4: + domain, arch, series, comp = tag_parts nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) - nest[domain][arch][series] = self.package + nest[domain][arch][series][comp] = package_data else: + domain, arch, series = tag_parts nest = NestedDict({f"{domain}.{arch}": {series: ""}}) - nest[domain][arch][series] = self.package - setattr(self, name, nest) - + nest[domain][arch][series] = package_data -# data[domain][arch][series] = pkg_data -# if tag_data.comp: -# data[tag_datadomain][arch][series][comp_tag] = pkg_data -# self.generate_pkg("pkg", self.raw_data.model) -# self.generate_pkg("tokenizer_pkg", self.raw_data.tokenizer) -# framework: dict[str,FrameworkBundle] + setattr(self, name, nest) diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index 0e07255..235bf76 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -31,12 +31,11 @@ def find_transformers_classes(self) -> None: if model_data := self.extract_model_class_data(model_class): if prepared_data := PrepareData(**config_data, **model_data): # type:ignore mir_tag = MIRTag(prepared_data) - mir_package = MIRPackage() - mir_nest = MIRNesting(mir_tag) - mir_package(data=prepared_data.model) - mir_nest(mir_package, prepared_data) + mir_nest = MIRNesting(mir_tag, prepared_data) + mir_package = MIRPackage(data=prepared_data.model) + mir_nest(mir_package) if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: - mir_package(data=prepared_data.tokenizer) + mir_package = MIRPackage(data=prepared_data.tokenizer) mir_nest(mir_package) mir_package.add_framework(mir_nest.framework_data) mir_nest(mir_package) diff --git a/mir/generate/transformers/raw_data.py b/mir/generate/transformers/raw_data.py index fdbe5dd..0664c45 100644 --- a/mir/generate/transformers/raw_data.py +++ b/mir/generate/transformers/raw_data.py @@ -27,6 +27,7 @@ def __post_init__(self) -> None: self.tokenizer: tuple[type[Any] | None, type[Any] | None] = tokenizer if internal_name := REVERSE_MAP.get(self.config): self.internal_name = internal_name + self.library = self.model.__module__.split(".")[0] self.model_to_tasks() def model_to_tasks(self) -> None: diff --git a/tests/test_mir_generate.py b/tests/test_mir_generate.py index 8ceacd0..211790d 100644 --- a/tests/test_mir_generate.py +++ b/tests/test_mir_generate.py @@ -3,7 +3,7 @@ def test_info_key_exists_and_library_is_not_nested(): print(Mir.info.cnn.yolos) result = Mir.info.cnn.yolos["transformers"] # should not throw - assert result == "ops.cnn.yolos" + assert result == {"repo": "hustvl/yolos-base", "model": "ops.cnn.yolos"} def test_ops_key_exists_and_library_is_not_tested(): @@ -19,3 +19,10 @@ def test_ops_key_exists_and_library_is_not_tested(): "YolosImageProcessor", ] assert all(task in result["tasks"] for task in expected_tasks) + + +def test_ops_tokenizer_created(): + from mir import Mir + + result = Mir.ops.encoder.tokenizer.zamba2['transformers'] + assert result == {"model": "transformers.models.llama.tokenization_llama.LlamaTokenizer"} From bdf37ec419dfd034a854e6e928b0888d01b63bc5 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sat, 17 Jan 2026 18:07:21 -0500 Subject: [PATCH 10/16] ~more elegant solution --- mir/framework.py | 2 ++ mir/generate/transformers/harvest.py | 37 +++++++++++++++------------- 2 files changed, 22 insertions(+), 17 deletions(-) diff --git a/mir/framework.py b/mir/framework.py index aa0a440..d6e402b 100644 --- a/mir/framework.py +++ b/mir/framework.py @@ -17,6 +17,8 @@ def __init__(self, data: Callable | str | dict[str, str]): self.data = data if not isinstance(self.data, dict): self.generate_package() + else: + self.add_framework(self.data) def generate_package(self) -> None: """Generates package information for the MIR tag based on class. diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index 235bf76..d1fb779 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -22,24 +22,27 @@ def find_transformers_classes(self) -> None: :return: List of PrepareData entries representing the transformer classes.""" from mir.generate.transformers import AUTO_MAP - model_data = [] - for pair_map in AUTO_MAP.items(): - config_class, model_class = pair_map # type:ignore + for config_class, model_class in AUTO_MAP.items(): if isinstance(model_class, tuple): - model_class: Callable = model_class[0] - if config_data := self.extract_config_class_data(config_class): - if model_data := self.extract_model_class_data(model_class): - if prepared_data := PrepareData(**config_data, **model_data): # type:ignore - mir_tag = MIRTag(prepared_data) - mir_nest = MIRNesting(mir_tag, prepared_data) - mir_package = MIRPackage(data=prepared_data.model) - mir_nest(mir_package) - if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: - mir_package = MIRPackage(data=prepared_data.tokenizer) - mir_nest(mir_package) - mir_package.add_framework(mir_nest.framework_data) - mir_nest(mir_package) - self.db.add_data(mir_nest, *mir_nest.loops) + model_class = model_class[0] + if not (config_data := self.extract_config_class_data(config_class)): + continue + if not (model_data := self.extract_model_class_data(model_class)): + continue + if not (prepared_data := PrepareData(**config_data, **model_data)): # type:ignore + continue + + mir_tag = MIRTag(prepared_data) + mir_nest = MIRNesting(mir_tag, prepared_data) + packages = [MIRPackage(data=prepared_data.model)] + if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: + packages.append(MIRPackage(data=prepared_data.tokenizer)) + packages.append(MIRPackage(data=mir_nest.framework_data)) + for pkg in packages: + mir_nest(pkg) + + + self.db.add_data(mir_nest, *mir_nest.loops) def extract_config_class_data(self, config_class: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: """Extracts information from config classes.\n From 714f59d0cf872fe3c75c8167fbbcbf259de2ddcb Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sat, 17 Jan 2026 23:18:43 -0500 Subject: [PATCH 11/16] ~noodle --- mir/data/exclusions.json | 3 +- mir/data/migrations.json | 12 ++-- mir/framework.py | 12 ++-- mir/generate/diffusers/__init__.py | 26 +------ mir/generate/diffusers/doc_parse.py | 92 +++++++++--------------- mir/generate/diffusers/harvest.py | 103 ++++++++++++++++++++++++++ mir/generate/diffusers/index.py | 27 ++----- mir/generate/diffusers/raw_data.py | 59 +++++++++++++++ mir/generate/tasks.py | 104 ++++----------------------- mir/generate/transformers/harvest.py | 8 +-- mir/tag.py | 61 ++++++++++++---- tests/subclasses_test.py | 0 12 files changed, 279 insertions(+), 228 deletions(-) create mode 100644 mir/generate/diffusers/harvest.py create mode 100644 mir/generate/diffusers/raw_data.py create mode 100644 tests/subclasses_test.py diff --git a/mir/data/exclusions.json b/mir/data/exclusions.json index e386bb2..e35cfed 100644 --- a/mir/data/exclusions.json +++ b/mir/data/exclusions.json @@ -27,6 +27,7 @@ "text_to_video_synthesis", "unclip", "unidiffuser", - "controlnet_hunyuandit" + "controlnet_hunyuandit", + "pipeline_stable_diffusion_xl_inpaint" ] } \ No newline at end of file diff --git a/mir/data/migrations.json b/mir/data/migrations.json index 5bc9929..755664f 100644 --- a/mir/data/migrations.json +++ b/mir/data/migrations.json @@ -46,13 +46,9 @@ "TimmWrapperConfig": "timm/resnet18.a1_in1k", "VisionTextDualEncoderConfig": "hakuhodo-tech/japanese-clip-vit-h-14-bert-wider" }, - "module": { - "blip_diffusion": "blip_diffusion", - "cogvideo": "cogvideox", - "cogview3": "cogview3plus", - "deepfloyd_if": "if", - "cosmos": "cosmos2_text2image", - "visualcloze": "visualcloze_generation", - "marigold": "marigold_depth" + "migrated_pipes": { + "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", + "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", + "ChromaPipeline": "lodestones/Chroma" } } \ No newline at end of file diff --git a/mir/framework.py b/mir/framework.py index d6e402b..fd5d2d4 100644 --- a/mir/framework.py +++ b/mir/framework.py @@ -3,6 +3,7 @@ from typing import Any, Callable from dataclasses import dataclass, field +from mir.generate.diffusers.raw_data import DPrepareData from mir.generate.transformers.raw_data import PrepareData from mir.tag import MIRTag @@ -12,7 +13,7 @@ class MIRPackage: data: Callable | str | dict[str, str] package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - def __init__(self, data: Callable | str | dict[str, str]): + def __init__(self, data: Callable | str | dict[str, str] | dict[str, Any]): self.package = {} self.data = data if not isinstance(self.data, dict): @@ -44,7 +45,7 @@ class MIRNesting: framework: dict[str, str] = field(init=False) tokenizer: str | None = field(default_factory=str) - def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData) -> None: + def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData | DPrepareData) -> None: """\nInitialize the framework with MIR tag and prepared data.\n :param mir_tag : The MIR tag instance. :param prepared_data : The prepared data for processing.""" @@ -58,9 +59,7 @@ def __call__(self, mir_package: MIRPackage) -> None: """Dispatches a MIRPackage to the appropriate handler based on its domain. :param mir_package: An instance of MIRPackage with the requisite data to tag""" - if (mir_package.domain == "ops" and - hasattr(self.prepared_data, "tokenizer") and - self.prepared_data.tokenizer and self.loops== ['model']): + if mir_package.domain == "ops" and hasattr(self.prepared_data, "tokenizer") and self.prepared_data.tokenizer and self.loops == ["model"]: # type: ignore self._process("tokenizer", mir_package) elif mir_package.domain == "ops": self._process("model", mir_package) @@ -76,7 +75,6 @@ def _process(self, name: str, mir_package: MIRPackage) -> None: is_framework = name == "framework" is_model = name == "model" - if is_framework: package_data = {self.prepared_data.library: mir_package.package} tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" @@ -109,7 +107,7 @@ def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: tag_parts = tuple(x for x in tag_data.split(".")) - if len(tag_parts) ==4: + if len(tag_parts) == 4: domain, arch, series, comp = tag_parts nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) nest[domain][arch][series][comp] = package_data diff --git a/mir/generate/diffusers/__init__.py b/mir/generate/diffusers/__init__.py index 2f50daa..c19bcec 100644 --- a/mir/generate/diffusers/__init__.py +++ b/mir/generate/diffusers/__init__.py @@ -1,31 +1,7 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # - -from dataclasses import dataclass from typing import Callable +from dataclasses import dataclass, field from diffusers.pipelines import _import_structure as IMPORT_STRUCTURE from diffusers.pipelines.auto_pipeline import SUPPORTED_TASKS_MAPPINGS, _get_task_class as GET_TASK_CLASS - - -@dataclass -class DocStringEntry: - """Represents a structured entry of package name, file name, and docstring.""" - - package_name: str - doc_string: str - file_name: str - pipe_module: Callable - - -class DocParseData: - pipe_class: str - pipe_repo: str - staged_class: str | None = None - staged_repo: str | None = None - - def __init__(self, pipe_class: str, pipe_repo: str, staged_class: str | None = None, staged_repo: str | None = None): - self.pipe_class = pipe_class - self.pipe_repo = pipe_repo - self.staged_class = staged_class - self.staged_repo = staged_repo diff --git a/mir/generate/diffusers/doc_parse.py b/mir/generate/diffusers/doc_parse.py index 18e091b..0e70ba3 100644 --- a/mir/generate/diffusers/doc_parse.py +++ b/mir/generate/diffusers/doc_parse.py @@ -1,11 +1,9 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import List, Optional, Tuple - +from typing import List, Optional, Callable from pydantic import BaseModel, field_validator from mir import NFO -from mir.generate.diffusers import DocParseData from mir.data import PIPE_MARKERS @@ -40,84 +38,69 @@ def validate_repo_path(repo_path: Optional[str], segment: str) -> Optional[str]: return None return repo_path - @staticmethod - def validate_pipe_class(pipe_class: Optional[str]) -> bool: - """Validate that a pipe class name is present.\n - :param pipe_class: Pipe class name to validate - :returns: True if class name is valid, False otherwise - """ - return pipe_class is not None and pipe_class.strip() != "" - class DocStringParser(BaseModel): doc_string: str + model: Callable @field_validator("doc_string") def normalize_doc(cls, docs: str) -> str: return DocStringValidator.normalize_doc_string(docs) - def doc_match(self, prefix_set: List[str] | None = None): - if prefix_set is None: - prefix_set = PIPE_MARKERS["pipe_variables"] - candidate = None - staged = None - prior_candidate = "" - for prefix in prefix_set: - candidate = self.doc_string.partition(prefix)[2] - prior_candidate = self.doc_string.partition(prefix)[0] - if candidate: - staged = candidate if any(call_method in candidate for call_method in PIPE_MARKERS["staged_call_methods"]) else None - break - - return candidate, prior_candidate, staged + def __init__(self, doc_string, model) -> None: + self.doc_string = doc_string + self.model = model - def parse(self) -> DocParseData | None: - candidate, prior_candidate, staged = self.doc_match(PIPE_MARKERS["pipe_prefixes"]) + def __post_init__(self) -> dict[str, str] | None: + candidate, prior_candidate, staged = self.doc_match(PIPE_MARKERS["pipe_variables"]) if candidate: - pipe_class, pipe_repo = self._extract_class_and_repo( + pipe_repo = self._extract_class_and_repo( segment=candidate, - call_methods=PIPE_MARKERS["call_types"], + call_methods=PIPE_MARKERS["call_methods"], prior_text=prior_candidate, ) motion_adapter = "motion_adapter" in candidate or "adapter" in candidate if motion_adapter and pipe_repo: - staged, prior_candidate, _ = self.doc_match(PIPE_MARKERS["pipe_prefixes"][2:]) # skip the adapter statements + staged, prior_candidate, _ = self.doc_match(PIPE_MARKERS["pipe_variables"][2:]) # skip the adapter statements - staged_class, staged_repo = ( + staged_repo = ( self._extract_class_and_repo( segment=staged, - call_methods=PIPE_MARKERS["staged_call_types"] if not motion_adapter else PIPE_MARKERS["call_types"], + call_methods=PIPE_MARKERS["staged_call_methods"] if not motion_adapter else PIPE_MARKERS["call_methods"], prior_text=prior_candidate, - prior_class=pipe_class, ) if staged - else (None, None) + else None ) - if motion_adapter and pipe_class and staged_class is not None: - pipe_class = staged_class - staged_repo = None - staged_class = None - if DocStringValidator.validate_pipe_class(pipe_class): - # dbuq(f"class :{pipe_class}, repo : {pipe_repo}, staged_class: {staged_class}, staged_repo:{staged_repo} \n") - return DocParseData(pipe_class=pipe_class, pipe_repo=pipe_repo, staged_class=staged_class, staged_repo=staged_repo) + self.pipe_repo = pipe_repo + self.staged_repo = staged_repo + + def doc_match(self, prefix_set: List[str] | None = None): + if prefix_set is None: + prefix_set = PIPE_MARKERS["pipe_variables"] + candidate = None + staged = None + prior_candidate = "" + for prefix in prefix_set: + candidate = self.doc_string.partition(prefix)[2] + prior_candidate = self.doc_string.partition(prefix)[0] + if candidate: + staged = candidate if any(call_method in candidate for call_method in PIPE_MARKERS["staged_call_methods"]) else None + break + + return candidate, prior_candidate, staged def _extract_class_and_repo( self, segment: str, call_methods: List[str], prior_text: str, - prior_class: Optional[str] = None, - ) -> Tuple[Optional[str], Optional[str]]: - pipe_class = None + ) -> str | None: pipe_repo = None for method_name in call_methods: if method_name in segment: - pipe_class = segment.partition(method_name)[0].strip().split("= ")[-1].split(".")[-1] - if prior_class == pipe_class and prior_text.split(method_name)[-1].strip().replace(")", ""): - pipe_class = prior_text.partition(method_name)[0].strip().split("= ")[-1] - repo_segment = segment.partition(method_name)[2].partition(")")[0] - else: + if not (repo_segment := segment.partition(method_name)[2].partition(")")[0]): repo_segment = segment.partition(method_name)[2].partition(")")[0] pipe_repo = repo_segment.replace("...", "").partition('",')[0].strip('" ') if not DocStringValidator.is_valid_repo_path(pipe_repo): @@ -126,11 +109,11 @@ def _extract_class_and_repo( pipe_repo = self._resolve_variable(reference, prior_text) break # Not empty!! 确保解析的路径不是空的！！ pipe_repo = DocStringValidator.validate_repo_path(pipe_repo, segment) - return pipe_class, pipe_repo + return pipe_repo - return pipe_class, pipe_repo + return pipe_repo - def _resolve_variable(self, reference: str, prior_text: str) -> Optional[str]: + def _resolve_variable(self, reference: str, prior_text: str) -> str | None: """Try to find the variable from other lines / 尝试从其他行中找到它（例如，多行定义）""" var_name = reference search = f"{var_name} =" @@ -156,8 +139,3 @@ def _resolve_variable(self, reference: str, prior_text: str) -> Optional[str]: NFO(f"Warning: {search} not found in docstring.") return None - - -def parse_docs(doc_string: str) -> DocParseData | None: - parser = DocStringParser(doc_string=doc_string) - return parser.parse() diff --git a/mir/generate/diffusers/harvest.py b/mir/generate/diffusers/harvest.py new file mode 100644 index 0000000..6ed0d9b --- /dev/null +++ b/mir/generate/diffusers/harvest.py @@ -0,0 +1,103 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from importlib import import_module +from pkgutil import walk_packages +from inspect import getmro + +from mir.framework import MIRNesting +from mir.generate.diffusers.raw_data import DPrepareData +from mir.tag import MIRTag + + +class HarvestClasses: + def __init__(self) -> None: + self.parsed_docs = [] + pass + + def find_diffusers_docstrings(self) -> None: + """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n + :return: Docstrings for common diffusers models""" + + self.extract_model_data() + + def extract_model_data(self): + from mir.generate.diffusers import EXCLUSIONS + from mir.generate.tasks import TaskAnalyzer + + subclasses = self.subclasses_of("diffusers", "DiffusionPipeline") + for path, class_obj in subclasses.items(): + if path.rsplit(".", 1)[-1] in EXCLUSIONS["exclusion_list"].get("model_path", "."): + continue + base_path = path.rsplit(".", 1)[0] + model_path = import_module(base_path) + if doc_string := getattr(model_path, "EXAMPLE_DOC_STRING", None): + prepared_data = DPrepareData(doc_string=doc_string, model=class_obj, model_path=base_path) + mir_tag = MIRTag(prepared_data) + task_analysis = TaskAnalyzer() + mir_nest = MIRNesting(mir_tag, prepared_data) + + def subclasses_of(self, package_name: str, base_class_name: str): + """ + Return a dict mapping `.` → class object + for every class in `package_name` that subclasses a class named + `base_class_name`. + + The implementation is intentionally defensive: it avoids + triggering `__getattr__` on lazy‑loaded submodules that might + raise a `RuntimeError`. Instead of `inspect.getmembers`, it + iterates over the module's `__dict__` which contains only + attributes that have already been imported. + """ + + results = {} + root_pkg = import_module(package_name) + for finder, mod_name, is_pkg in walk_packages(root_pkg.__path__, root_pkg.__name__ + "."): + try: + module = import_module(mod_name) + except (ImportError, ModuleNotFoundError, RuntimeError): + continue + + # Iterate over all *already* imported members in the module + for name, obj in module.__dict__.items(): + if not isinstance(obj, type): + continue + # Ensure the class is defined in this module, not imported + if obj.__module__ != mod_name: + continue + try: + bases = getmro(obj)[1:] # skip the class itself + except ValueError: + continue + for base in bases: + if base.__name__ == base_class_name: + fqcn = f"{mod_name}.{name}" + results[fqcn] = obj + break + + return results + + # def extract_model_data(self,pipe_name, file_name: str) -> dict | None: + # migrated_pipes = MIGRATIONS["migrated_pipes"] + # pkg_path = f"diffusers.pipelines.{pipe_name}.{file_name}" + # pipe_file: Callable = import_object_named(file_name, pkg_path) or import_module(pkg_path) + # if pipe_file and (doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None)): #where pipe class and repo are + # docstrings= DocStringEntry(package_name=pipe_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) + # DocStringParser(doc_string=docstrings.doc_string) + # self.parsed_docs.pipe_repo = migrated_pipes.get(self.parsed_docs.pipe_class, self.parsed_docs.pipe_repo) + # model = import_object_named(parsed_data.pipe_class, docstrings.pipe_module.__name__) + # model_data = show_init_fields_for(model,"diffusers") + # return {"model_params": model_data} + + +# for pipe_name in IMPORT_STRUCTURE.keys(): +# if pipe_name not in exclusion_list and (import_name := getattr(diffusers_pipelines, str(pipe_name))): +# file_specific = uncommon_naming.get(pipe_name, pipe_name) +# file_names:list[str] = [getattr(import_name, "_import_structure", {})] or [f"pipeline_{file_specific}"] +# for file_name in file_names: +# if not file_name in exclusion_list or not (model_data := self.extract_model_data(pipe_name, file_name)): +# continue +# if not (prepared_data := PrepareData( **model_data)): +# continue +# else: +# continue diff --git a/mir/generate/diffusers/index.py b/mir/generate/diffusers/index.py index 06628e8..852fc24 100644 --- a/mir/generate/diffusers/index.py +++ b/mir/generate/diffusers/index.py @@ -7,11 +7,9 @@ from mir import DBUQ, NFO from mir.data import EXCLUSIONS -from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS, DocParseData, DocStringEntry -from mir.generate.diffusers.doc_parse import parse_docs +from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS from mir.generate.from_module import import_object_named, show_init_fields_for, to_domain_tag from mir.generate.indexers import migrations -from mir.tag import tag_model_from_repo def retrieve_diffusers_docstrings( @@ -128,25 +126,6 @@ def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: continue -def show_diffusers_tasks(code_name: str, class_name: str | None = None) -> list[str]: - """Return Diffusers task pipes based on package-specific query\n - :param class_name: To find task pipes from a Diffusers class pipe, defaults to None - :param code_name: To find task pipes from a Transformers class pipe, defaults to None - :return: A list of alternate class pipelines derived from the specified class""" - - alt_tasks = set() - for task_map in SUPPORTED_TASKS_MAPPINGS: - task_class = GET_TASK_CLASS(task_map, class_name, False) - if task_class: - alt_tasks.add(task_class.__name__) - DBUQ(task_class) - for model_code, pipe_class_obj in task_map.items(): - if code_name in model_code: - alt_tasks.add(pipe_class_obj.__name__) - - return list(alt_tasks) - - def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: """Generate diffusion model data for MIR index\n :return: Dictionary ready to be applied to MIR data fields @@ -160,7 +139,9 @@ def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt "ChromaPipeline": "lodestones/Chroma", } - + for class_name, swap_repo in special_classes.items(): + if parsed_data.pipe_class == class_name: + parsed_data.pipe_repo = swap_repo extracted_docstrings = find_diffusers_docstrings() model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] pipe_data = {} # pipeline_stable_diffusion_xl_inpaint diff --git a/mir/generate/diffusers/raw_data.py b/mir/generate/diffusers/raw_data.py new file mode 100644 index 0000000..3e37836 --- /dev/null +++ b/mir/generate/diffusers/raw_data.py @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from dataclasses import dataclass, field +from typing import Callable, get_type_hints + + +@dataclass +class DPrepareData: + name: str + doc_string: str + model: Callable + model_path: str + repo_path: str = field(init=False, default_factory=str) + model_name: str = field(init=False, default_factory=str) + staged_repo: str | None = field(init=False, default_factory=str | None) + tasks: list[str] = field(init=False, default_factory=lambda: [""]) + + def __init__(self, **kwargs) -> None: + for key, value in kwargs.items(): + setattr(self, key, value) + + def __post_init__(self) -> None: + from mir.data import MIGRATIONS + from mir.generate.diffusers.doc_parse import DocStringParser + from mir.generate.from_module import show_init_fields_for + + self.model_name = self.model.__name__ + self.library = self.model.__module__.split(".", 1)[0] + self.model_params = show_init_fields_for(self.model, "diffusers") + self.type_params = get_type_hints(self.model.__init__) + doc_parser = DocStringParser(self.doc_string, self.model) + if repo_path := MIGRATIONS["migrated_pipes"].get(self.model.__name__, False): + self.repo_path = repo_path + else: + if repo_path := doc_parser.pipe_repo: + self.repo_path = repo_path + if staged_repo := doc_parser.staged_repo: + self.staged_repo = staged_repo + + def show_diffusers_tasks(self) -> list[str]: + """Return Diffusers task pipes based on package-specific query\n + :param class_name: To find task pipes from a Diffusers class pipe, defaults to None + :param code_name: To find task pipes from a Transformers class pipe, defaults to None + :return: A list of alternate class pipelines derived from the specified class""" + from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS + + alt_tasks = set() + internal_name = self.model_path.rsplit(".", 2)[-2] + for task_map in SUPPORTED_TASKS_MAPPINGS: + task_class = GET_TASK_CLASS(task_map, self.model, False) + if task_class: + alt_tasks.add(task_class.__name__) + for model_code, pipe_class_obj in task_map.items(): + if internal_name in model_code: + alt_tasks.add(pipe_class_obj.__name__) + + return list(alt_tasks) diff --git a/mir/generate/tasks.py b/mir/generate/tasks.py index 5da5834..b037bdf 100644 --- a/mir/generate/tasks.py +++ b/mir/generate/tasks.py @@ -3,12 +3,11 @@ from typing import Any, Callable, List, get_type_hints -from mir.generate.from_module import get_internal_name_for, import_object_named -from mir.generate.transformers.index import show_transformers_tasks from mir.maid import MIRDatabase from mir.generate.diffusers.index import show_diffusers_tasks from mir.generate.diffusers.schedulers import tag_scheduler from mir import DBUQ +from mir.tag import MIRTag flatten_map: List[Any] = lambda nested, unpack: [element for iterative in getattr(nested, unpack)() for element in iterative] flatten_map.__annotations__ = {"nested": List[str], "unpack": str} @@ -29,36 +28,7 @@ def __init__(self) -> None: self.skip_types = ["int", "bool", "float", "Optional", "NoneType", "List", "UNet2DConditionModel"] self.mflux_tasks = ["Image", "Redux", "Kontext", "Depth", "Fill", "ConceptAttention", "ControlNet", "CavTon", "IC-Edit"] - async def detect_tasks(self, mir_db: MIRDatabase, field_name: str = "pkg") -> dict: - """Detects and traces tasks MIR data\n - :param mir_db:: An instance of MIRDatabase containing the database of information. - :type mir_db: MIRDatabase - :param field_name: The name of the field in compatibility data to process for task detection, defaults to "pkg". - :type field_name: str, optional - :return: A dictionary mapping series names to their respective compatibility and traced tasks. - :rtype: dict""" - - data_tuple = [] - for series, compatibility_data in mir_db.db.items(): - if ( - series.startswith("info.") # formatting comment - and not any(tag for tag in self.skip_series if series.startswith(tag)) - and not any(tag for tag in self.skip_classes if tag in series) - ): - for compatibility, field_data in compatibility_data.items(): - if field_data and field_data.get(field_name, {}).get("0"): - tasks_for_class = {"tasks": []} - for _, pkg_tree in field_data[field_name].items(): - detected_tasks = await self.trace_tasks(pkg_tree=pkg_tree) - if detected_tasks: - for task in detected_tasks: - if task not in tasks_for_class["tasks"]: - tasks_for_class["tasks"].append(task) - data_tuple.append((*series.rsplit(".", 1), {compatibility: tasks_for_class})) - - return data_tuple - - async def detect_pipes(self, mir_db: MIRDatabase, field_name: str = "pkg") -> dict: + async def detect_pipes(self, mir_tag: MIRTag, model: Callable, type_params: dict) -> dict: """Detects and traces Pipes MIR data\n :param mir_db:: An instance of MIRDatabase containing the database of information. :type mir_db: MIRDatabase @@ -68,29 +38,18 @@ async def detect_pipes(self, mir_db: MIRDatabase, field_name: str = "pkg") -> di :rtype: dict""" data_tuple = [] - for series, compatibility_data in mir_db.db.items(): - if ( - series.startswith("info.") # formatting comment - and not any(series.startswith(tag) for tag in self.skip_series) - and not any(tag for tag in self.skip_classes if tag in series) - ): - for compatibility, field_data in compatibility_data.items(): - if field_data and field_data.get(field_name, {}).get("0"): - for _, pkg_tree in field_data[field_name].items(): - if pkg_tree and next(iter(pkg_tree)) == "diffusers": - module_name = pkg_tree[next(iter(pkg_tree))] - DBUQ(f"{module_name} pipe originator") - class_obj = import_object_named(module_name, "diffusers") - pipe_args = get_type_hints(class_obj.__init__) - detected_pipe = await self.hyperlink_to_mir(pipe_args, series, mir_db) - data_tuple.append((*series.rsplit(".", 1), {compatibility: detected_pipe})) + tasks = show_diffusers_tasks(code_name= class_name=model.__name__) + detected_pipe = await self.hyperlink_to_mir(type_params, mir_tag.series) + if hasattr(mir_tag, "comp") and mir_tag.comp: + data_tuple.append((*mir_tag.series, {mir_tag.comp: detected_pipe})) + else: + data_tuple.append(({mir_tag.series: detected_pipe})) return data_tuple - async def hyperlink_to_mir(self, pipe_args: dict, series: str, mir_db: MIRDatabase): + async def hyperlink_to_mir(self, pipe_args: dict, series: str): """Maps pipeline components to MIR tags/IDs based on class names and roles.\n :param pipe_args: Dictionary of pipeline roles to their corresponding classes - :param mir_db: MIRDatabase instance for querying tags/IDs :return: Dictionary mapping pipeline roles to associated MIR tags/IDs""" mir_tag: None | list[str] = None @@ -108,23 +67,22 @@ async def hyperlink_to_mir(self, pipe_args: dict, series: str, mir_db: MIRDataba mir_tag = None class_name = union_class.__name__ if not any(segment for segment in self.skip_types if class_name == segment): - mir_tag, class_name = await self.tag_class(pipe_class=union_class, pipe_role=pipe_role, series=series, mir_db=mir_db) + mir_tag, class_name = await self.tag_class(pipe_class=union_class, pipe_role=pipe_role, series=series) # mir_tag = mir_db.find_tag(field="tasks", target=class_name) # dbuq(f"{mir_tag} {class_name}") detected_links["pipe_names"][pipe_role].append(mir_tag if mir_tag else class_name) else: - mir_tag, class_name = await self.tag_class(pipe_class=pipe_class, pipe_role=pipe_role, series=series, mir_db=mir_db) + mir_tag, class_name = await self.tag_class(pipe_class=pipe_class, pipe_role=pipe_role, series=series) detected_links["pipe_names"][pipe_role] = mir_tag if mir_tag else [class_name] mir_tag = None class_name = None return detected_links - async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir_db: MIRDatabase) -> tuple[str | None]: + async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str) -> tuple[str | None]: """Maps a class to MIR tags/IDs based on its name and role.\n :param pipe_class: Class to be mapped :param pipe_role: Role of the class in the pipeline :param series: Series identifier for the component - :param mir_db: MIRDatabase instance for querying tags/IDs :return: Tuple containing MIR tag and class name""" mir_tag = None @@ -133,47 +91,11 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str, mir sub_field = pipe_class.__module__.split(".")[0] scheduler_series, scheduler_comp = tag_scheduler(class_name) mir_tag = [f"ops.scheduler.{scheduler_series}", scheduler_comp] - if not mir_db.db.get(mir_tag[0], {}).get(mir_tag[1]): - mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="ops.scheduler") DBUQ(f"scheduler {mir_tag} {class_name} {sub_field} ") elif pipe_role == "vae": sub_field = pipe_class.__module__.split(".")[0] mir_comp = series.rsplit(".", 1)[-1] DBUQ(mir_comp) - mir_tag = [mir_id for mir_id, comp_data in mir_db.db.items() if "info.vae" in mir_id and next(iter(comp_data)) == mir_comp] - if mir_tag: - mir_tag.append(mir_comp) # keep mir tag as single list - elif class_name != "AutoencoderKL": - DBUQ(pipe_class) - mir_tag = mir_db.find_tag(field="pkg", target=class_name, sub_field=sub_field, domain="info.vae") - DBUQ(f"vae {mir_tag} {class_name} {sub_field} ") - else: - mir_tag = mir_db.find_tag(field="tasks", target=class_name) + mir_tag = "info.vae" return mir_tag, class_name - async def trace_tasks(self, pkg_tree: dict[str, str | int | list[str | int]]) -> List[str]: - """Trace tasks for a given MIR entry.\n - :param entry: The object containing the model information. - :return: A sorted list of tasks applicable to the model.""" - - preformatted_task_data = None - filtered_tasks = None - snip_words: set[str] = {"load_tf_weights_in"} - package_name = next(iter(pkg_tree)) - DBUQ(pkg_tree) - class_name = pkg_tree[package_name] - DBUQ(f"{package_name}, {class_name}") - if class_name not in self.skip_auto: - if isinstance(class_name, dict): - class_name = next(iter(list(class_name))) - if package_name == "transformers": - preformatted_task_data = show_transformers_tasks(class_name=class_name) - elif package_name == "diffusers": - code_name = get_internal_name_for(class_name, package_name) - preformatted_task_data = show_diffusers_tasks(code_name=code_name, class_name=class_name) - preformatted_task_data.sort() - elif package_name == "mflux": - preformatted_task_data = self.mflux_tasks - if preformatted_task_data: - filtered_tasks = [task for task in preformatted_task_data for snip in snip_words if snip not in task] - return filtered_tasks # package_name, class_name diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index d1fb779..7c33dc5 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -22,21 +22,21 @@ def find_transformers_classes(self) -> None: :return: List of PrepareData entries representing the transformer classes.""" from mir.generate.transformers import AUTO_MAP - for config_class, model_class in AUTO_MAP.items(): + for config_class, model_class in AUTO_MAP.items(): #type: ignore if isinstance(model_class, tuple): - model_class = model_class[0] + model_class: Callable = model_class[0] if not (config_data := self.extract_config_class_data(config_class)): continue if not (model_data := self.extract_model_class_data(model_class)): continue - if not (prepared_data := PrepareData(**config_data, **model_data)): # type:ignore + if not (prepared_data := PrepareData(**config_data, **model_data)): # type:ignore , _Lazyautomapping tuple continue mir_tag = MIRTag(prepared_data) mir_nest = MIRNesting(mir_tag, prepared_data) packages = [MIRPackage(data=prepared_data.model)] if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: - packages.append(MIRPackage(data=prepared_data.tokenizer)) + packages.append(MIRPackage(data=prepared_data.tokenizer)) #type: ignore , _Lazyautomapping tuple packages.append(MIRPackage(data=mir_nest.framework_data)) for pkg in packages: mir_nest(pkg) diff --git a/mir/tag.py b/mir/tag.py index c31266f..3df4200 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -4,6 +4,7 @@ from dataclasses import dataclass, field from mir.generate.transformers.raw_data import PrepareData +from mir.generate.diffusers.raw_data import DPrepareData @dataclass @@ -17,14 +18,15 @@ class MIRTag: comp The compatibility component of the MIR tag (generated, optional). """ - raw_data: PrepareData + raw_data: PrepareData | DPrepareData arch: str = field(init=False) series: str = field(init=False) + decoder: bool = False def __post_init__(self) -> None: """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" self.generate_arch() - self.generate_series_and_comp(repo_title=self.raw_data.repo_path) + self.generate_series_and_comp(repo_path=self.raw_data.repo_path) def generate_arch(self) -> None: """Generates the architecture part of the MIR tag based on prepared data.\n @@ -32,7 +34,11 @@ def generate_arch(self) -> None: from mir.generate.from_module import to_domain_tag library = self.raw_data.model.__module__.split(".")[0] - arch = to_domain_tag(library, **self.raw_data.config_params) + if hasattr(self.raw_data, "config_params"): + arch = to_domain_tag(library, **self.raw_data.config_params) # type: ignore + else: + arch = None + self.decoder = "decoder" in [self.raw_data.model_params] if not arch: if self.raw_data.model_params: if arch := to_domain_tag(library, **self.raw_data.model_params): @@ -42,11 +48,11 @@ def generate_arch(self) -> None: raise ValueError( f"Unrecognized model type, \ no tag matched {self.raw_data.name} \ - with {self.raw_data.config_params} or {self.raw_data.model_params}", + with {self.raw_data}", ) self.arch = arch - def generate_series_and_comp(self, repo_title: str, decoder=False) -> None: + def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: """Generates the MIR tag components from a repository title.\n :param repo_title: The title of the repository from which to derive the MIR tag. :param decoder: Boolean flag indicating if the model is a decoder. @@ -57,17 +63,17 @@ def generate_series_and_comp(self, repo_title: str, decoder=False) -> None: from mir import BREAKING, PARAMETERS root = "decoder" if decoder else "*" - repo_title = repo_title.split(":latest")[0] - repo_title = repo_title.split(":Q")[0] - repo_title = repo_title.split(r"/")[-1].lower() + repo_path = repo_path.split(":latest")[0] + repo_path = repo_path.split(":Q")[0] + repo_path = repo_path.split(r"/")[-1].lower() pattern = r"^.*[v]?(\d{1}+\.\d).*" - match = re.findall(pattern, repo_title) + match = re.findall(pattern, repo_path) if match: if next(iter(match)): - repo_title = repo_title.replace(next(iter(match))[-1], "") - parts = repo_title.replace(".", "").split("-") + repo_path = repo_path.replace(next(iter(match))[-1], "") + parts = repo_path.replace(".", "").split("-") if len(parts) == 1: - parts = repo_title.split("_") + parts = repo_path.split("_") subtraction_prefixes = r"\d.b-|\-rl|tiny|large|mlx|onnx|gguf|medium|base|multimodal|mini|instruct|full|:latest|preview|small|pro|beta|hybrid|plus|dpo|community" pattern_2 = re.compile(PARAMETERS) @@ -86,3 +92,34 @@ def generate_series_and_comp(self, repo_title: str, decoder=False) -> None: self.series = cleaned_string if suffix != "*": self.comp = suffix + + # def generate_pipe_tag(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: + # """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n + # :param repo_path (str): Repository path. + # :param model_class_obj (str): The model class function + # :raises TypeError: If 'repo_path' or 'class_name' are not set. + # :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. + # """ + # import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name + + # if hasattr(diffusers, class_name): + # model_class_obj = getattr(diffusers, class_name) + # sub_segments = show_init_fields_for(model_class_obj, "diffusers") + + # else: + # mir_prefix = to_domain_tag(**sub_segments) + # if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: + # NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") + # else: + # mir_prefix = "info." + mir_prefix + + # mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) + # mir_series = mir_prefix + "." + mir_series + # repo_path = migrations(repo_path) + # # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) + # prefixed_data = { + # "repo": repo_path, + # "pkg": {0: {"diffusers": class_name}}, + # # "mode": modalities.get("mode"), + # } + # return mir_series, {mir_comp: prefixed_data} diff --git a/tests/subclasses_test.py b/tests/subclasses_test.py new file mode 100644 index 0000000..e69de29 From a49a4054725f2abf4e58a53480560bfd8c62a687 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Sun, 18 Jan 2026 21:35:43 -0500 Subject: [PATCH 12/16] ~put together diffusers initial parts --- MIR.egg-info/SOURCES.txt | 41 +-- mir/__init__.py | 4 +- .../automata.py => _deprecated/_automata.py} | 0 mir/{generate => _deprecated}/_extras.py | 93 ++++-- .../guiders.py => _deprecated/_guiders.py} | 27 ++ mir/_deprecated/_index.py | 270 ++++++++++++++++++ .../_schedulers.py} | 0 mir/data/__init__.py | 1 + mir/data/component_names.json | 20 ++ mir/data/nn_filter.json | 15 +- mir/framework.py | 119 -------- mir/generate/{tasks.py => _tasks.py} | 27 +- mir/generate/diffusers/attention.py | 26 -- mir/generate/diffusers/doc_parse.py | 10 +- mir/generate/diffusers/harvest.py | 110 +++---- mir/generate/diffusers/index.py | 214 -------------- mir/generate/diffusers/raw_data.py | 34 ++- mir/generate/from_module.py | 77 +---- mir/generate/indexers.py | 46 --- mir/generate/mlx/{index.py => harvest.py} | 0 mir/generate/transformers/__init__.py | 2 - mir/generate/transformers/harvest.py | 16 +- mir/maid.py | 3 +- mir/package.py | 109 +++++++ mir/tag.py | 105 ++++--- pyproject.toml | 5 + tests/test_mir_generate_diffusers.py | 6 + ...e.py => test_mir_generate_transformers.py} | 14 +- 28 files changed, 742 insertions(+), 652 deletions(-) rename mir/{generate/automata.py => _deprecated/_automata.py} (100%) rename mir/{generate => _deprecated}/_extras.py (65%) rename mir/{generate/diffusers/guiders.py => _deprecated/_guiders.py} (68%) create mode 100644 mir/_deprecated/_index.py rename mir/{generate/diffusers/schedulers.py => _deprecated/_schedulers.py} (100%) create mode 100644 mir/data/component_names.json delete mode 100644 mir/framework.py rename mir/generate/{tasks.py => _tasks.py} (86%) delete mode 100644 mir/generate/diffusers/attention.py delete mode 100644 mir/generate/diffusers/index.py delete mode 100644 mir/generate/indexers.py rename mir/generate/mlx/{index.py => harvest.py} (100%) create mode 100644 tests/test_mir_generate_diffusers.py rename tests/{test_mir_generate.py => test_mir_generate_transformers.py} (69%) diff --git a/MIR.egg-info/SOURCES.txt b/MIR.egg-info/SOURCES.txt index e7d1cc2..0867f5a 100644 --- a/MIR.egg-info/SOURCES.txt +++ b/MIR.egg-info/SOURCES.txt @@ -13,9 +13,12 @@ MIR.egg-info/entry_points.txt MIR.egg-info/requires.txt MIR.egg-info/top_level.txt mir/__init__.py +mir/__main__.py +mir/framework.py mir/json_io.py mir/maid.py mir/mir.json +mir/package.py mir/tag.py mir/data/__init__.py mir/data/diffusers_adds.json @@ -37,30 +40,34 @@ mir/generate/diffusers/__init__.py mir/generate/diffusers/attention.py mir/generate/diffusers/doc_parse.py mir/generate/diffusers/guiders.py +mir/generate/diffusers/harvest.py mir/generate/diffusers/index.py +mir/generate/diffusers/raw_data.py mir/generate/diffusers/schedulers.py mir/generate/mlx/__init__.py mir/generate/mlx/index.py mir/generate/torch/__init__.py mir/generate/torch/dtypes.py mir/generate/transformers/__init__.py -mir/generate/transformers/index.py +mir/generate/transformers/harvest.py mir/generate/transformers/raw_data.py -mir/generate/transformers/tokenizers.py mir/spec/__init__.py mir/spec/regex.json -tests/test_class_parent.py -tests/test_deconstructors_root.py -tests/test_doc_parser.py -tests/test_find_docstring_run.py -tests/test_gather_diffusers_metadata.py -tests/test_json_io.py -tests/test_mir_db_create_restore.py -tests/test_mir_merge.py -tests/test_mir_search.py -tests/test_mir_tagging.py -tests/test_regex_constants.py -tests/test_resolve_code_names.py -tests/test_seek_class.py -tests/test_task.py -tests/test_taskanalyzer.py \ No newline at end of file +tests/subclasses_test.py +tests/test_mir_generate_diffusers.py +tests/test_mir_generate_transformers.py +tests/old/test_class_parent.py +tests/old/test_deconstructors_root.py +tests/old/test_doc_parser.py +tests/old/test_find_docstring_run.py +tests/old/test_gather_diffusers_metadata.py +tests/old/test_json_io.py +tests/old/test_mir_db_create_restore.py +tests/old/test_mir_merge.py +tests/old/test_mir_search.py +tests/old/test_mir_tagging.py +tests/old/test_regex_constants.py +tests/old/test_resolve_code_names.py +tests/old/test_seek_class.py +tests/old/test_task.py +tests/old/test_taskanalyzer.py \ No newline at end of file diff --git a/mir/__init__.py b/mir/__init__.py index ba063fb..3405a0f 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -6,7 +6,6 @@ from logging import DEBUG, INFO, Logger from mir.json_io import read_json_file -from mir.generate.transformers.harvest import HarvestClasses NFO = Logger(INFO).info DBUQ = Logger(DEBUG).debug @@ -21,5 +20,8 @@ SUFFIX = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["suffix"] IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] +# from mir.generate.transformers.harvest import HarvestClasses +# Mir = HarvestClasses().db.db +from mir.generate.diffusers.harvest import HarvestClasses Mir = HarvestClasses().db.db diff --git a/mir/generate/automata.py b/mir/_deprecated/_automata.py similarity index 100% rename from mir/generate/automata.py rename to mir/_deprecated/_automata.py diff --git a/mir/generate/_extras.py b/mir/_deprecated/_extras.py similarity index 65% rename from mir/generate/_extras.py rename to mir/_deprecated/_extras.py index c1b0366..39af779 100644 --- a/mir/generate/_extras.py +++ b/mir/_deprecated/_extras.py @@ -36,27 +36,6 @@ def _class_parent(code_name: str, pkg_name: str) -> Optional[List[str]]: return import_path -def _extract_inherited_classes(model_class: Union[Callable, str], pkg_name: Optional[str] = None) -> Optional[Dict[str, List[str]]]: - """Strips tags from module's base classes and extracts inherited class members.\n - If `module` is a string, it requires the `library` argument to convert it into a callable.\n - :param module: A module or string representing a module. - :param library: Library name required if `module` is a string. Defaults to None. - :returns: Mapping indices to class path segments, or None if invalid input.""" - - if isinstance(model_class, str): - if not pkg_name: - NFO("Provide a library type argument to process strings") - return None - model_class = import_object_named(model_class, pkg_name) - signature = model_class.__bases__ - class_names = [] - for index, class_annotation in enumerate(signature): - tag_stripped = str(class_annotation)[8:-2] - module_segments = tag_stripped.split(".") - class_names.append(module_segments) - return class_names - - def _trace_classes(pipe_class: str, pkg_name: str) -> Dict[str, List[str]]: """Retrieve all compatible pipe forms\n NOTE: Mainly for Diffusers @@ -189,3 +168,75 @@ def tag_transformers_model(repo_path: str, class_name: str, addendum: dict | Non else: mir_prefix = f"info.{mir_prefix}" return mir_prefix, base_series, {base_comp: addendum} + + +# def extract_model_data(self,pipe_name, file_name: str) -> dict | None: +# migrated_pipes = MIGRATIONS["migrated_pipes"] +# pkg_path = f"diffusers.pipelines.{pipe_name}.{file_name}" +# pipe_file: Callable = import_object_named(file_name, pkg_path) or import_module(pkg_path) +# if pipe_file and (doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None)): #where pipe class and repo are +# docstrings= DocStringEntry(package_name=pipe_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) +# DocStringParser(doc_string=docstrings.doc_string) +# self.parsed_docs.pipe_repo = migrated_pipes.get(self.parsed_docs.pipe_class, self.parsed_docs.pipe_repo) +# model = import_object_named(parsed_data.pipe_class, docstrings.pipe_module.__name__) +# model_data = show_init_fields_for(model,"diffusers") +# return {"model_params": model_data} + + +# for pipe_name in IMPORT_STRUCTURE.keys(): +# if pipe_name not in exclusion_list and (import_name := getattr(diffusers_pipelines, str(pipe_name))): +# file_specific = uncommon_naming.get(pipe_name, pipe_name) +# file_names:list[str] = [getattr(import_name, "_import_structure", {})] or [f"pipeline_{file_specific}"] +# for file_name in file_names: +# if not file_name in exclusion_list or not (model_data := self.extract_model_data(pipe_name, file_name)): +# continue +# if not (prepared_data := PrepareData( **model_data)): +# continue +# else: +# continue + + +# def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: +# """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n +# ### NOTE: in most cases `__module__` makes this redundant +# :param code_name: The internal name for the model in the third-party API. +# :param pkg_name: The API Package +# :return: A list corresponding to the path of the model, or None if not found +# :raises KeyError: for invalid pkg_name +# """ + +# pkg_paths = { +# "diffusers": "pipelines", +# "transformers": "models", +# } +# folder_name = code_name.replace("-", "_") +# pkg_name = pkg_name.lower() +# folder_path = pkg_paths[pkg_name] +# package_obj = import_module(pkg_name) +# folder_path_named = [folder_path, folder_name] +# pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) +# # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) +# if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: +# import_path = [pkg_name] +# import_path.extend(folder_path_named) +# return import_path + + +# def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: +# """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n +# :param class_name: To return only one class, defaults to None +# :param pkg_name: optional field for library, defaults to "transformers" +# :param path_format: Retrieve just the code name, or the full module path and code name within the package +# :return: A list of all code names, or the one corresponding to the provided class""" +# from mir.generate.diffusers import IMPORT_STRUCTURE +# from mir.generate.transformers import MODEL_MAPPING_NAMES + +# package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES +# pkg_name = pkg_name.lower() +# MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) +# if module_name: +# if isinstance(module_name, Type): +# module_name = module_name.__name__ +# code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") +# return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") +# return list(MAPPING_NAMES) diff --git a/mir/generate/diffusers/guiders.py b/mir/_deprecated/_guiders.py similarity index 68% rename from mir/generate/diffusers/guiders.py rename to mir/_deprecated/_guiders.py index 39789af..b791829 100644 --- a/mir/generate/diffusers/guiders.py +++ b/mir/_deprecated/_guiders.py @@ -59,3 +59,30 @@ # }, # ), + +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +# def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet +# from diffusers.models.attention_processor import AttentionProcessor + +# mir_data +# for series, comp_name in mir_data.items(): +# id_segment = series.split(".") +# for compatibility in comp_name: +# dbug(id_segment) +# try: +# mir_db.add( +# mir_entry( +# domain=id_segment[0], +# arch=id_segment[1], +# series=id_segment[2], +# comp=compatibility, +# **mir_data[series][compatibility], +# ), +# ) +# except IndexError as error_log: +# nfo(f"Failed to create series: {series} compatibility: {comp_name} ") +# dbug(error_log) + diff --git a/mir/_deprecated/_index.py b/mir/_deprecated/_index.py new file mode 100644 index 0000000..813bcdd --- /dev/null +++ b/mir/_deprecated/_index.py @@ -0,0 +1,270 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +# import os +# from importlib import import_module +# from typing import Any, Generator + +# from mir import DBUQ, NFO +# from mir.data import EXCLUSIONS +# from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS +# from mir.generate.from_module import import_object_named, show_init_fields_for, to_domain_tag +# from mir.generate.indexers import migrations + + +# def retrieve_diffusers_docstrings( +# package_name: str, +# file_names: list[str], +# ) -> Generator[DocStringEntry]: +# """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n +# :param pkg_name: Package under ``diffusers.pipelines``.\n +# :param file_names: A list of related file names.\n +# :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n +# :return: DocString Entry class.\n +# """ + +# module_location: str | None = import_module("diffusers.pipelines").__file__ +# module_path = os.path.dirname(module_location) + +# for file_name in file_names: +# assert isinstance(file_name, str), f"Expected path to be string, got {file_name} type {type(file_name)}" +# if file_name == "pipeline_stable_diffusion_xl_inpaint": +# continue + +# pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" +# DBUQ(pkg_path) + +# if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): +# pipe_file = import_object_named(file_name, pkg_path) or import_module(pkg_path) or NFO(f"Failed to import {pkg_path}") +# if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): +# yield DocStringEntry(package_name=package_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) +# else: +# NFO(f"Doc string attribute missing for {package_name}/{file_name}") +# else: +# NFO(f"Path not found for {package_name}/{file_name}") + +# return + + +# def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: +# """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n +# :param repo_path (str): Repository path. +# :param model_class_obj (str): The model class function +# :raises TypeError: If 'repo_path' or 'class_name' are not set. +# :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. +# """ +# import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name + +# control_net = ["Control", "Controlnet"] # +# mir_prefix = "info" +# if hasattr(diffusers, class_name): +# model_class_obj = getattr(diffusers, class_name) +# sub_segments = show_init_fields_for(model_class_obj, "diffusers") +# decoder = "decoder" in sub_segments +# if repo_path in ["kandinsky-community/kandinsky-3"]: +# mir_prefix = "info.unet" +# if repo_path in ["openai/shap-e"]: +# mir_prefix = "info.unet" +# class_name = "ShapEPipeline" +# elif class_name == "MotionAdapter": +# mir_prefix = "info.lora" +# elif class_name == "WanPipeline": +# mir_prefix = "info.dit" +# elif class_name == "CogVideoXVideoToVideoPipeline": +# class_name = "CogVideoXPipeline" +# elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): +# mir_prefix = "info.controlnet" +# else: +# mir_prefix = to_domain_tag(**sub_segments) +# if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: +# NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") +# else: +# mir_prefix = "info." + mir_prefix +# if class_name == "StableDiffusion3InpaintPipeline" or repo_path in ["stabilityai/stable-diffusion-3-medium-diffusers"]: +# class_name = "StableDiffusion3Pipeline" +# repo_path = "stabilityai/stable-diffusion-3.5-medium" +# if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: +# class_name = "HunyuanVideoPipeline" +# mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) +# mir_series = mir_prefix + "." + mir_series +# repo_path = migrations(repo_path) +# # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) +# prefixed_data = { +# "repo": repo_path, +# "pkg": {0: {"diffusers": class_name}}, +# # "mode": modalities.get("mode"), +# } +# return mir_series, {mir_comp: prefixed_data} + + +# def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: +# """Convert model repo pipes to MIR tags, classifying by feature\n +# :param name: Repo path +# :param class_name: The HF Diffusers class for the model +# :return: A segmented MIR tag useful for appending index entries""" +# mir_series, mir_data = create_pipe_entry(repo_path=repo_path, class_name=class_name) +# mir_prefix, mir_series = mir_series.rsplit(".", 1) +# mir_comp = list(mir_data)[0] +# return mir_prefix, mir_series, {mir_comp: addendum} + + +# def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: +# """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n +# :return: Docstrings for common diffusers models""" +# import diffusers.pipelines as diffusers_pipelines + +# docstring_patterns = EXCLUSIONS +# exclusion_list = docstring_patterns["exclusion_list"] +# uncommon_naming = docstring_patterns["uncommon_naming"] +# for pipe_name in IMPORT_STRUCTURE.keys(): +# if pipe_name not in exclusion_list: +# file_specific = uncommon_naming.get(pipe_name, pipe_name) +# if import_name := getattr(diffusers_pipelines, str(pipe_name)): +# file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] +# yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) +# else: +# continue + + +# def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: +# """Generate diffusion model data for MIR index\n +# :return: Dictionary ready to be applied to MIR data fields +# """ +# special_repos = { +# "black-forest-labs/FLUX.1-schnell": "black-forest-labs/FLUX.1-dev", +# # "stabilityai/stable-diffusion-3-medium-diffusers": "stabilityai/stable-diffusion-3.5-medium", +# } +# special_classes = { +# # "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", # NOT sd3 +# "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt +# "ChromaPipeline": "lodestones/Chroma", +# } +# for class_name, swap_repo in special_classes.items(): +# if parsed_data.pipe_class == class_name: +# parsed_data.pipe_repo = swap_repo +# extracted_docstrings = find_diffusers_docstrings() +# model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] +# pipe_data = {} # pipeline_stable_diffusion_xl_inpaint + +# for extracted in model_info: +# parsed_data: DocParseData = parse_docs(extracted.doc_string) +# if parsed_data is None: +# print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") +# continue +# for class_name, swap_repo in special_classes.items(): +# if parsed_data.pipe_class == class_name: +# parsed_data.pipe_repo = swap_repo +# break +# model_class_obj = import_object_named(parsed_data.pipe_class, extracted.pipe_module.__name__) +# if not model_class_obj: +# continue +# try: +# series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) +# except TypeError: +# pass # Attempt 1 +# if pipe_data.get(series): +# if "img2img" in parsed_data.pipe_class.lower(): +# continue +# pipe_data.setdefault(series, {}).update(comp_data) +# special_conditions = special_repos | special_classes +# if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): +# test = special_conditions.get(parsed_data.pipe_repo) +# if test: +# staged_repo = test +# parsed_data.staged_class = parsed_data.pipe_class +# try: +# series, comp_data = create_pipe_entry( +# staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, +# parsed_data.staged_class # +# if parsed_data.staged_class +# else parsed_data.pipe_class, +# ) +# except TypeError as error_log: +# NFO(series, comp_data) +# NFO(error_log) +# continue # Attempt 2, +# pipe_data.setdefault(series, {}).update(comp_data) +# return dict(pipe_data) + + +# def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: +# from nnll.download.hub_cache import download_hub_file + +# model_file = download_hub_file( +# repo_id=f"{repo_id}/tree/main/{arch}", +# source="huggingface", +# file_name="diffusion_pytorch_model.safetensors.index.json", +# local_dir=".tmp", +# ) + + +# @MODE_DATA.decorator +# def add_mode_types(mir_tag: list[str], data: dict | None = None) -> dict[str, list[str] | str]: +# """_summary_\n +# :param mir_tag: _description_ +# :param data: _description_, defaults to None +# :return: _description_""" +# fused_tag = ".".join(mir_tag) + +# mir_details = { +# "mode": data.get(fused_tag, {}).get("pipeline_tag"), +# "pkg_type": data.get(fused_tag, {}).get("library_type"), +# "tags": data.get(fused_tag, {}).get("tags"), +# } +# return mir_details + + +# def generate_pipe_tag(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: +# """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n +# :param repo_path (str): Repository path. +# :param model_class_obj (str): The model class function +# :raises TypeError: If 'repo_path' or 'class_name' are not set. +# :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. +# """ +# import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name + +# if hasattr(diffusers, class_name): +# model_class_obj = getattr(diffusers, class_name) +# sub_segments = show_init_fields_for(model_class_obj, "diffusers") + +# else: +# mir_prefix = to_domain_tag(**sub_segments) +# if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: +# NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") +# else: +# mir_prefix = "info." + mir_prefix + +# mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) +# mir_series = mir_prefix + "." + mir_series +# repo_path = migrations(repo_path) +# # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) +# prefixed_data = { +# "repo": repo_path, +# "pkg": {0: {"diffusers": class_name}}, +# # "mode": modalities.get("mode"), +# } +# return mir_series, {mir_comp: prefixed_data} + + +# def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: +# """Generate MIR HF Hub model database +# :param new_data: Data for the MIR database +# :param mir_database: MIRDatabase instance +# """ +# for series, comp_name in new_data.items(): +# id_segment = series.split(".") +# for compatibility in comp_name: +# # dbug(id_segment) +# try: +# mir_db.add( +# mir_entry( +# domain=id_segment[0], +# arch=id_segment[1], +# series=id_segment[2], +# comp=compatibility, +# **new_data[series][compatibility], +# ), +# ) +# except IndexError: # as error_log: +# NFO(f"Failed to create series: {series} compatibility: {comp_name} ") +# # dbug(error_log) diff --git a/mir/generate/diffusers/schedulers.py b/mir/_deprecated/_schedulers.py similarity index 100% rename from mir/generate/diffusers/schedulers.py rename to mir/_deprecated/_schedulers.py diff --git a/mir/data/__init__.py b/mir/data/__init__.py index a8f596e..2e0dc48 100644 --- a/mir/data/__init__.py +++ b/mir/data/__init__.py @@ -17,3 +17,4 @@ PIPE_MARKERS = read_json_file(os.path.join(ROOT_PATH, "data", "pipe_markers.json")) TAG_SCRAPE = read_json_file(os.path.join(ROOT_PATH, "data", "tag_scrape.json")) TRANSFORMERS_ADDS = read_json_file(os.path.join(ROOT_PATH, "data", "transformers_adds.json")) +COMPONENT_NAMES = read_json_file(os.path.join(ROOT_PATH, "data", "component_names.json")) diff --git a/mir/data/component_names.json b/mir/data/component_names.json new file mode 100644 index 0000000..b371ec3 --- /dev/null +++ b/mir/data/component_names.json @@ -0,0 +1,20 @@ +{ + "components": [ + "scheduler", + "vae", + "unet", + "transformer", + "transformer_2", + "transformer_3", + "text_model", + "text_model_2", + "text_model_3", + "text_model_4", + "tokenizer", + "tokenizer_1", + "tokenizer_2", + "tokenizer_3", + "tokenizer_4", + "feature_extractor" + ] +} \ No newline at end of file diff --git a/mir/data/nn_filter.json b/mir/data/nn_filter.json index 4638ce1..25399b5 100644 --- a/mir/data/nn_filter.json +++ b/mir/data/nn_filter.json @@ -140,19 +140,30 @@ ] }, "diffusers": { + "vae": [ + "autoencoder", + "autoencoders" + ], + "scheduler": [ + "scheduler", + "schedulers" + ], "lora": [ "motion_adapter" ], "controlnet": [ - "controlnet" + "controlnet", + "controlnets" ], "unet": [ "unet", + "unets", "prior", "decoder" ], "dit": [ - "transformer" + "transformer", + "transformers" ] } } diff --git a/mir/framework.py b/mir/framework.py deleted file mode 100644 index fd5d2d4..0000000 --- a/mir/framework.py +++ /dev/null @@ -1,119 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Any, Callable -from dataclasses import dataclass, field -from mir.generate.diffusers.raw_data import DPrepareData -from mir.generate.transformers.raw_data import PrepareData -from mir.tag import MIRTag - - -@dataclass -class MIRPackage: - data: Callable | str | dict[str, str] - package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - - def __init__(self, data: Callable | str | dict[str, str] | dict[str, Any]): - self.package = {} - self.data = data - if not isinstance(self.data, dict): - self.generate_package() - else: - self.add_framework(self.data) - - def generate_package(self) -> None: - """Generates package information for the MIR tag based on class. - :param pkg: A class object (model, tokenizer, etc) to build a tag from""" - self.domain = "ops" - model = f"{self.data.__module__}.{self.data.__name__}" - self.package: dict[str, str] = {"model": model} - - def add_framework(self, framework_data) -> None: - self.domain = "info" - self.package = framework_data - - -class MIRNesting: - """Build tag components from the extracted data\n - :param mir_tag: An instance of MIR tag with the necessary information - :param prepared_data: Instance of PrepareData to attribute the final information - :returns: The final, assembled MIR tag""" - - loops: list[str] - framework_data: dict[str, str | dict[str, Any]] = {} - repo: str | None = field(default_factory=str | None) - framework: dict[str, str] = field(init=False) - tokenizer: str | None = field(default_factory=str) - - def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData | DPrepareData) -> None: - """\nInitialize the framework with MIR tag and prepared data.\n - :param mir_tag : The MIR tag instance. - :param prepared_data : The prepared data for processing.""" - self.mir_tag = mir_tag - - self.prepared_data = prepared_data - self.loops = [] - self.framework_data = {} - - def __call__(self, mir_package: MIRPackage) -> None: - """Dispatches a MIRPackage to the appropriate handler based on its domain. - :param mir_package: An instance of MIRPackage with the requisite data to tag""" - - if mir_package.domain == "ops" and hasattr(self.prepared_data, "tokenizer") and self.prepared_data.tokenizer and self.loops == ["model"]: # type: ignore - self._process("tokenizer", mir_package) - elif mir_package.domain == "ops": - self._process("model", mir_package) - elif mir_package.domain == "info": - self._process("framework", mir_package) - - def _process(self, name: str, mir_package: MIRPackage) -> None: - """Common routine for handling a package: store tag data, nest the package, - and record the name of the newly-created attribute.\n - :param name: Identification string to store data underneath - :param mir_package: An instance of MIRPackage with the requisite data""" - - is_framework = name == "framework" - is_model = name == "model" - - if is_framework: - package_data = {self.prepared_data.library: mir_package.package} - tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" - if comp := getattr(self.mir_tag, "comp", None): - tag_data += comp - self.framework_data.setdefault("repo", self.prepared_data.repo_path) - elif is_model: - package_data = {self.prepared_data.library: mir_package.package} - if hasattr(self.prepared_data, "tasks") and self.prepared_data.tasks: - package_data[self.prepared_data.library].setdefault("tasks", self.prepared_data.tasks) - tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" - if comp := getattr(self.mir_tag, "comp", None): - tag_data += comp - self.framework_data.setdefault(name, tag_data) - else: # tokenizer case - package_data = {self.prepared_data.library: mir_package.package} - tag_data = f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}" - self.framework_data.setdefault(name, tag_data) - - self.nest_data(name=name, tag_data=tag_data, package_data=package_data) - self.loops.append(name) - - def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: - """Nest data into a hierarchical attribute structure.\n - :param name: Attribute name to store the nested data - :param tag_data: Dotted path string for nesting - :param package_data: Data to be stored in the nested structure""" - - from chanfig import NestedDict - - tag_parts = tuple(x for x in tag_data.split(".")) - - if len(tag_parts) == 4: - domain, arch, series, comp = tag_parts - nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) - nest[domain][arch][series][comp] = package_data - else: - domain, arch, series = tag_parts - nest = NestedDict({f"{domain}.{arch}": {series: ""}}) - nest[domain][arch][series] = package_data - - setattr(self, name, nest) diff --git a/mir/generate/tasks.py b/mir/generate/_tasks.py similarity index 86% rename from mir/generate/tasks.py rename to mir/generate/_tasks.py index b037bdf..5c746ef 100644 --- a/mir/generate/tasks.py +++ b/mir/generate/_tasks.py @@ -2,9 +2,8 @@ # -from typing import Any, Callable, List, get_type_hints -from mir.maid import MIRDatabase -from mir.generate.diffusers.index import show_diffusers_tasks +from typing import Any, Callable, List +from mir.generate.diffusers.raw_data import DPrepareData from mir.generate.diffusers.schedulers import tag_scheduler from mir import DBUQ from mir.tag import MIRTag @@ -14,7 +13,13 @@ class TaskAnalyzer: - def __init__(self) -> None: + prepared_data: DPrepareData + mir_tag: MIRTag + tasks: dict[str, str] | None = None + + def __init__(self, prepared_data: DPrepareData, mir_tag: MIRTag) -> None: + self.prepared_data = prepared_data + self.mir_tag = mir_tag self.skip_series = [ "info.lora", "info.vae", @@ -28,7 +33,7 @@ def __init__(self) -> None: self.skip_types = ["int", "bool", "float", "Optional", "NoneType", "List", "UNet2DConditionModel"] self.mflux_tasks = ["Image", "Redux", "Kontext", "Depth", "Fill", "ConceptAttention", "ControlNet", "CavTon", "IC-Edit"] - async def detect_pipes(self, mir_tag: MIRTag, model: Callable, type_params: dict) -> dict: + async def __post_init__(self) -> None: """Detects and traces Pipes MIR data\n :param mir_db:: An instance of MIRDatabase containing the database of information. :type mir_db: MIRDatabase @@ -38,14 +43,13 @@ async def detect_pipes(self, mir_tag: MIRTag, model: Callable, type_params: dict :rtype: dict""" data_tuple = [] - tasks = show_diffusers_tasks(code_name= class_name=model.__name__) - detected_pipe = await self.hyperlink_to_mir(type_params, mir_tag.series) - if hasattr(mir_tag, "comp") and mir_tag.comp: - data_tuple.append((*mir_tag.series, {mir_tag.comp: detected_pipe})) + detected_pipe = await self.hyperlink_to_mir(self.prepared_data.model_params, self.mir_tag.series) + if hasattr(self.mir_tag, "comp") and self.mir_tag.comp: + self.tasks(*self.mir_tag.series, {self.mir_tag.comp: detected_pipe}) else: - data_tuple.append(({mir_tag.series: detected_pipe})) + self.tasks({self.mir_tag.series: self.prepared_data.model_path}) - return data_tuple + self.tasks = data_tuple async def hyperlink_to_mir(self, pipe_args: dict, series: str): """Maps pipeline components to MIR tags/IDs based on class names and roles.\n @@ -98,4 +102,3 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str) -> DBUQ(mir_comp) mir_tag = "info.vae" return mir_tag, class_name - diff --git a/mir/generate/diffusers/attention.py b/mir/generate/diffusers/attention.py deleted file mode 100644 index 00df941..0000000 --- a/mir/generate/diffusers/attention.py +++ /dev/null @@ -1,26 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -# def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet -# from diffusers.models.attention_processor import AttentionProcessor - -# mir_data -# for series, comp_name in mir_data.items(): -# id_segment = series.split(".") -# for compatibility in comp_name: -# dbug(id_segment) -# try: -# mir_db.add( -# mir_entry( -# domain=id_segment[0], -# arch=id_segment[1], -# series=id_segment[2], -# comp=compatibility, -# **mir_data[series][compatibility], -# ), -# ) -# except IndexError as error_log: -# nfo(f"Failed to create series: {series} compatibility: {comp_name} ") -# dbug(error_log) - diff --git a/mir/generate/diffusers/doc_parse.py b/mir/generate/diffusers/doc_parse.py index 0e70ba3..2d7aa7b 100644 --- a/mir/generate/diffusers/doc_parse.py +++ b/mir/generate/diffusers/doc_parse.py @@ -42,16 +42,15 @@ def validate_repo_path(repo_path: Optional[str], segment: str) -> Optional[str]: class DocStringParser(BaseModel): doc_string: str model: Callable + model_path: str + pipe_repo: str | None = None + staged_repo: str | None = None @field_validator("doc_string") def normalize_doc(cls, docs: str) -> str: return DocStringValidator.normalize_doc_string(docs) - def __init__(self, doc_string, model) -> None: - self.doc_string = doc_string - self.model = model - - def __post_init__(self) -> dict[str, str] | None: + def parse(self) -> dict[str, str] | None: candidate, prior_candidate, staged = self.doc_match(PIPE_MARKERS["pipe_variables"]) if candidate: pipe_repo = self._extract_class_and_repo( @@ -79,6 +78,7 @@ def __post_init__(self) -> dict[str, str] | None: def doc_match(self, prefix_set: List[str] | None = None): if prefix_set is None: prefix_set = PIPE_MARKERS["pipe_variables"] + assert prefix_set is not None candidate = None staged = None prior_candidate = "" diff --git a/mir/generate/diffusers/harvest.py b/mir/generate/diffusers/harvest.py index 6ed0d9b..db40d91 100644 --- a/mir/generate/diffusers/harvest.py +++ b/mir/generate/diffusers/harvest.py @@ -2,42 +2,82 @@ # from importlib import import_module -from pkgutil import walk_packages from inspect import getmro +from typing import Any, Callable, get_type_hints -from mir.framework import MIRNesting from mir.generate.diffusers.raw_data import DPrepareData +from mir.package import MIRNesting, MIRPackage from mir.tag import MIRTag class HarvestClasses: def __init__(self) -> None: - self.parsed_docs = [] - pass + """Initializes the HarvestClasses instance with an empty list to store raw class data.""" + from mir.maid import MIRDatabase + + self.db = MIRDatabase() + self.raw_data = [] + self.find_diffusers_docstrings() def find_diffusers_docstrings(self) -> None: """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n :return: Docstrings for common diffusers models""" - self.extract_model_data() - - def extract_model_data(self): - from mir.generate.diffusers import EXCLUSIONS - from mir.generate.tasks import TaskAnalyzer + # from mir.generate.tasks import TaskAnalyzer - subclasses = self.subclasses_of("diffusers", "DiffusionPipeline") - for path, class_obj in subclasses.items(): - if path.rsplit(".", 1)[-1] in EXCLUSIONS["exclusion_list"].get("model_path", "."): + subclasses = self.extract_subclass_data("diffusers", "DiffusionPipeline") + for module_path, model in subclasses.items(): + if not (base_data := self.extract_base_data(module_path)): + continue + if not (model_data := self.extract_model_class_data(model)): continue - base_path = path.rsplit(".", 1)[0] - model_path = import_module(base_path) - if doc_string := getattr(model_path, "EXAMPLE_DOC_STRING", None): - prepared_data = DPrepareData(doc_string=doc_string, model=class_obj, model_path=base_path) - mir_tag = MIRTag(prepared_data) - task_analysis = TaskAnalyzer() - mir_nest = MIRNesting(mir_tag, prepared_data) - - def subclasses_of(self, package_name: str, base_class_name: str): + if not (prepared_data := DPrepareData(**base_data, **model_data)): + continue + mir_tag = MIRTag(prepared_data) + # task_analysis = TaskAnalyzer(prepared_data=prepared_data, mir_tag=mir_tag) + mir_nest = MIRNesting(mir_tag, prepared_data) + packages = {"model": MIRPackage(data=prepared_data.model)} + for component_name, component_model in prepared_data.model_params.items(): + if hasattr(prepared_data, component_name): + packages.setdefault(component_name, MIRPackage(data=component_model)) + packages.setdefault("framework", MIRPackage(data=mir_nest.framework_data)) + # print(packages) + mir_nest(packages) + + self.db.add_data(mir_nest, *mir_nest.loops) + + def extract_base_data(self, module_path: str) -> dict[str, str] | None: + from mir.data import EXCLUSIONS + + if module_path.rsplit(".", 1)[-1] in EXCLUSIONS["exclusion_list"]: + return None + base_path = module_path.rsplit(".", 1)[0] + model_path = import_module(base_path) + if doc_string := getattr(model_path, "EXAMPLE_DOC_STRING", None): + return { + "doc_string": doc_string, + "model_path": base_path, + } + return None + + def extract_model_class_data(self, model: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: + model_name: str = model.__name__ + library: str = model.__module__.split(".", 1)[0] + model_params: dict[str, Any] = get_type_hints(model.__init__) + for module in model_params.values(): + module_name = module.__module__ + library_path = f"{library}.models." + if library_path in module_name: + module_name = module_name.replace(library_path, "").split(".")[0] + return { + "model": model, + "model_name": model_name, + "model_params": model_params, + "library": library, + } + return None + + def extract_subclass_data(self, package_name: str, base_class_name: str): """ Return a dict mapping `.` → class object for every class in `package_name` that subclasses a class named @@ -49,6 +89,7 @@ def subclasses_of(self, package_name: str, base_class_name: str): iterates over the module's `__dict__` which contains only attributes that have already been imported. """ + from pkgutil import walk_packages results = {} root_pkg = import_module(package_name) @@ -58,11 +99,9 @@ def subclasses_of(self, package_name: str, base_class_name: str): except (ImportError, ModuleNotFoundError, RuntimeError): continue - # Iterate over all *already* imported members in the module for name, obj in module.__dict__.items(): if not isinstance(obj, type): continue - # Ensure the class is defined in this module, not imported if obj.__module__ != mod_name: continue try: @@ -76,28 +115,3 @@ def subclasses_of(self, package_name: str, base_class_name: str): break return results - - # def extract_model_data(self,pipe_name, file_name: str) -> dict | None: - # migrated_pipes = MIGRATIONS["migrated_pipes"] - # pkg_path = f"diffusers.pipelines.{pipe_name}.{file_name}" - # pipe_file: Callable = import_object_named(file_name, pkg_path) or import_module(pkg_path) - # if pipe_file and (doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None)): #where pipe class and repo are - # docstrings= DocStringEntry(package_name=pipe_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) - # DocStringParser(doc_string=docstrings.doc_string) - # self.parsed_docs.pipe_repo = migrated_pipes.get(self.parsed_docs.pipe_class, self.parsed_docs.pipe_repo) - # model = import_object_named(parsed_data.pipe_class, docstrings.pipe_module.__name__) - # model_data = show_init_fields_for(model,"diffusers") - # return {"model_params": model_data} - - -# for pipe_name in IMPORT_STRUCTURE.keys(): -# if pipe_name not in exclusion_list and (import_name := getattr(diffusers_pipelines, str(pipe_name))): -# file_specific = uncommon_naming.get(pipe_name, pipe_name) -# file_names:list[str] = [getattr(import_name, "_import_structure", {})] or [f"pipeline_{file_specific}"] -# for file_name in file_names: -# if not file_name in exclusion_list or not (model_data := self.extract_model_data(pipe_name, file_name)): -# continue -# if not (prepared_data := PrepareData( **model_data)): -# continue -# else: -# continue diff --git a/mir/generate/diffusers/index.py b/mir/generate/diffusers/index.py deleted file mode 100644 index 852fc24..0000000 --- a/mir/generate/diffusers/index.py +++ /dev/null @@ -1,214 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import os -from importlib import import_module -from typing import Any, Generator - -from mir import DBUQ, NFO -from mir.data import EXCLUSIONS -from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS -from mir.generate.from_module import import_object_named, show_init_fields_for, to_domain_tag -from mir.generate.indexers import migrations - - -def retrieve_diffusers_docstrings( - package_name: str, - file_names: list[str], -) -> Generator[DocStringEntry]: - """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n - :param pkg_name: Package under ``diffusers.pipelines``.\n - :param file_names: A list of related file names.\n - :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n - :return: DocString Entry class.\n - """ - - module_location: str | None = import_module("diffusers.pipelines").__file__ - module_path = os.path.dirname(module_location) - - for file_name in file_names: - assert isinstance(file_name, str), f"Expected path to be string, got {file_name} type {type(file_name)}" - if file_name == "pipeline_stable_diffusion_xl_inpaint": - continue - - pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" - DBUQ(pkg_path) - - if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): - pipe_file = import_object_named(file_name, pkg_path) or import_module(pkg_path) or NFO(f"Failed to import {pkg_path}") - if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): - yield DocStringEntry(package_name=package_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) - else: - NFO(f"Doc string attribute missing for {package_name}/{file_name}") - else: - NFO(f"Path not found for {package_name}/{file_name}") - - return - - -def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: - """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n - :param repo_path (str): Repository path. - :param model_class_obj (str): The model class function - :raises TypeError: If 'repo_path' or 'class_name' are not set. - :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. - """ - import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name - - control_net = ["Control", "Controlnet"] # - mir_prefix = "info" - if hasattr(diffusers, class_name): - model_class_obj = getattr(diffusers, class_name) - sub_segments = show_init_fields_for(model_class_obj, "diffusers") - decoder = "decoder" in sub_segments - if repo_path in ["kandinsky-community/kandinsky-3"]: - mir_prefix = "info.unet" - if repo_path in ["openai/shap-e"]: - mir_prefix = "info.unet" - class_name = "ShapEPipeline" - elif class_name == "MotionAdapter": - mir_prefix = "info.lora" - elif class_name == "WanPipeline": - mir_prefix = "info.dit" - elif class_name == "CogVideoXVideoToVideoPipeline": - class_name = "CogVideoXPipeline" - elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): - mir_prefix = "info.controlnet" - else: - mir_prefix = to_domain_tag(**sub_segments) - if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: - NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") - else: - mir_prefix = "info." + mir_prefix - if class_name == "StableDiffusion3InpaintPipeline" or repo_path in ["stabilityai/stable-diffusion-3-medium-diffusers"]: - class_name = "StableDiffusion3Pipeline" - repo_path = "stabilityai/stable-diffusion-3.5-medium" - if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: - class_name = "HunyuanVideoPipeline" - mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) - mir_series = mir_prefix + "." + mir_series - repo_path = migrations(repo_path) - # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) - prefixed_data = { - "repo": repo_path, - "pkg": {0: {"diffusers": class_name}}, - # "mode": modalities.get("mode"), - } - return mir_series, {mir_comp: prefixed_data} - - -def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: - """Convert model repo pipes to MIR tags, classifying by feature\n - :param name: Repo path - :param class_name: The HF Diffusers class for the model - :return: A segmented MIR tag useful for appending index entries""" - mir_series, mir_data = create_pipe_entry(repo_path=repo_path, class_name=class_name) - mir_prefix, mir_series = mir_series.rsplit(".", 1) - mir_comp = list(mir_data)[0] - return mir_prefix, mir_series, {mir_comp: addendum} - - -def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: - """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n - :return: Docstrings for common diffusers models""" - import diffusers.pipelines as diffusers_pipelines - - docstring_patterns = EXCLUSIONS - exclusion_list = docstring_patterns["exclusion_list"] - uncommon_naming = docstring_patterns["uncommon_naming"] - for pipe_name in IMPORT_STRUCTURE.keys(): - if pipe_name not in exclusion_list: - file_specific = uncommon_naming.get(pipe_name, pipe_name) - if import_name := getattr(diffusers_pipelines, str(pipe_name)): - file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] - yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) - else: - continue - - -def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: - """Generate diffusion model data for MIR index\n - :return: Dictionary ready to be applied to MIR data fields - """ - special_repos = { - "black-forest-labs/FLUX.1-schnell": "black-forest-labs/FLUX.1-dev", - # "stabilityai/stable-diffusion-3-medium-diffusers": "stabilityai/stable-diffusion-3.5-medium", - } - special_classes = { - # "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", # NOT sd3 - "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt - "ChromaPipeline": "lodestones/Chroma", - } - for class_name, swap_repo in special_classes.items(): - if parsed_data.pipe_class == class_name: - parsed_data.pipe_repo = swap_repo - extracted_docstrings = find_diffusers_docstrings() - model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] - pipe_data = {} # pipeline_stable_diffusion_xl_inpaint - - for extracted in model_info: - parsed_data: DocParseData = parse_docs(extracted.doc_string) - if parsed_data is None: - print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") - continue - for class_name, swap_repo in special_classes.items(): - if parsed_data.pipe_class == class_name: - parsed_data.pipe_repo = swap_repo - break - model_class_obj = import_object_named(parsed_data.pipe_class, extracted.pipe_module.__name__) - if not model_class_obj: - continue - try: - series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) - except TypeError: - pass # Attempt 1 - if pipe_data.get(series): - if "img2img" in parsed_data.pipe_class.lower(): - continue - pipe_data.setdefault(series, {}).update(comp_data) - special_conditions = special_repos | special_classes - if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): - test = special_conditions.get(parsed_data.pipe_repo) - if test: - staged_repo = test - parsed_data.staged_class = parsed_data.pipe_class - try: - series, comp_data = create_pipe_entry( - staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, - parsed_data.staged_class # - if parsed_data.staged_class - else parsed_data.pipe_class, - ) - except TypeError as error_log: - NFO(series, comp_data) - NFO(error_log) - continue # Attempt 2, - pipe_data.setdefault(series, {}).update(comp_data) - return dict(pipe_data) - - -# def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: -# from nnll.download.hub_cache import download_hub_file - -# model_file = download_hub_file( -# repo_id=f"{repo_id}/tree/main/{arch}", -# source="huggingface", -# file_name="diffusion_pytorch_model.safetensors.index.json", -# local_dir=".tmp", -# ) - - -# @MODE_DATA.decorator -# def add_mode_types(mir_tag: list[str], data: dict | None = None) -> dict[str, list[str] | str]: -# """_summary_\n -# :param mir_tag: _description_ -# :param data: _description_, defaults to None -# :return: _description_""" -# fused_tag = ".".join(mir_tag) - -# mir_details = { -# "mode": data.get(fused_tag, {}).get("pipeline_tag"), -# "pkg_type": data.get(fused_tag, {}).get("library_type"), -# "tags": data.get(fused_tag, {}).get("tags"), -# } -# return mir_details diff --git a/mir/generate/diffusers/raw_data.py b/mir/generate/diffusers/raw_data.py index 3e37836..e86dbfb 100644 --- a/mir/generate/diffusers/raw_data.py +++ b/mir/generate/diffusers/raw_data.py @@ -8,29 +8,23 @@ @dataclass class DPrepareData: - name: str doc_string: str model: Callable model_path: str + library: str + model_name: str + model_params: dict[str, list[str]] = field(init=True, default_factory=lambda: {"": [""]}) repo_path: str = field(init=False, default_factory=str) - model_name: str = field(init=False, default_factory=str) - staged_repo: str | None = field(init=False, default_factory=str | None) + staged_repo: str | None = field(init=False, default_factory=str) tasks: list[str] = field(init=False, default_factory=lambda: [""]) - - def __init__(self, **kwargs) -> None: - for key, value in kwargs.items(): - setattr(self, key, value) + name: str = field(init=False, default_factory=str) def __post_init__(self) -> None: from mir.data import MIGRATIONS from mir.generate.diffusers.doc_parse import DocStringParser - from mir.generate.from_module import show_init_fields_for - self.model_name = self.model.__name__ - self.library = self.model.__module__.split(".", 1)[0] - self.model_params = show_init_fields_for(self.model, "diffusers") - self.type_params = get_type_hints(self.model.__init__) - doc_parser = DocStringParser(self.doc_string, self.model) + doc_parser = DocStringParser(doc_string=self.doc_string, model=self.model, model_path=self.model_path) + doc_parser.parse() if repo_path := MIGRATIONS["migrated_pipes"].get(self.model.__name__, False): self.repo_path = repo_path else: @@ -38,22 +32,26 @@ def __post_init__(self) -> None: self.repo_path = repo_path if staged_repo := doc_parser.staged_repo: self.staged_repo = staged_repo + self.show_diffusers_tasks() + for name, model in self.model_params.items(): + setattr(self, name, model) + print(name, model) - def show_diffusers_tasks(self) -> list[str]: + def show_diffusers_tasks(self) -> None: """Return Diffusers task pipes based on package-specific query\n :param class_name: To find task pipes from a Diffusers class pipe, defaults to None :param code_name: To find task pipes from a Transformers class pipe, defaults to None :return: A list of alternate class pipelines derived from the specified class""" from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS - alt_tasks = set() - internal_name = self.model_path.rsplit(".", 2)[-2] + alt_tasks = set({}) + self.internal_name = self.model_path.rsplit(".", 2)[-1] for task_map in SUPPORTED_TASKS_MAPPINGS: task_class = GET_TASK_CLASS(task_map, self.model, False) if task_class: alt_tasks.add(task_class.__name__) for model_code, pipe_class_obj in task_map.items(): - if internal_name in model_code: + if self.internal_name in model_code: alt_tasks.add(pipe_class_obj.__name__) - return list(alt_tasks) + self.tasks = [x for x in alt_tasks] diff --git a/mir/generate/from_module.py b/mir/generate/from_module.py index a39778f..fffb820 100644 --- a/mir/generate/from_module.py +++ b/mir/generate/from_module.py @@ -4,9 +4,22 @@ # 模块发现和解构 import inspect -import os + from importlib import import_module -from typing import Callable, Type +from typing import Callable + + +def migrations(repo_path: str): + """Replaces old organization names in repository paths with new ones.\n + :param repo_path: Original repository path containing old organization names + :return: Updated repository path with new organization names""" + from mir.data import MIGRATIONS + + repo_migrations = MIGRATIONS + for old_name, new_name in repo_migrations.items(): + if old_name in repo_path: + repo_path = repo_path.replace(old_name, new_name) + return repo_path def import_object_named(module: str, pkg_name_or_abs_path: str) -> Callable | None: @@ -57,63 +70,3 @@ def show_init_fields_for(module: Callable | str, package_name: str | None = None class_names = dict(class_names) return class_names - - -def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n - ### NOTE: in most cases `__module__` makes this redundant - :param code_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - - pkg_paths = { - "diffusers": "pipelines", - "transformers": "models", - } - folder_name = code_name.replace("-", "_") - pkg_name = pkg_name.lower() - folder_path = pkg_paths[pkg_name] - package_obj = import_module(pkg_name) - folder_path_named = [folder_path, folder_name] - pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) - # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) - if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: - import_path = [pkg_name] - import_path.extend(folder_path_named) - return import_path - - -# def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: -# """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n -# :param class_name: To return only one class, defaults to None -# :param pkg_name: optional field for library, defaults to "transformers" -# :param path_format: Retrieve just the code name, or the full module path and code name within the package -# :return: A list of all code names, or the one corresponding to the provided class""" -# from mir.generate.diffusers import IMPORT_STRUCTURE -# from mir.generate.transformers import MODEL_MAPPING_NAMES - -# package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES -# pkg_name = pkg_name.lower() -# MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) -# if module_name: -# if isinstance(module_name, Type): -# module_name = module_name.__name__ -# code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") -# return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") -# return list(MAPPING_NAMES) - - -def to_domain_tag(library: str, **kwargs): - """Set type of MIR prefix depending on model type\n - :param transformers: Use transformers data instead of diffusers data, defaults to False - :raises ValueError: Model type not detected - :return: MIR prefix based on model configuration""" - from mir.data import NN_FILTER - - flags = NN_FILTER["arch"][library] # pylint:disable=unsubscriptable-object - for mir_prefix, key_match in flags.items(): - if any(kwargs.get(param, None) for param in key_match): - return mir_prefix - return None diff --git a/mir/generate/indexers.py b/mir/generate/indexers.py deleted file mode 100644 index 51f755a..0000000 --- a/mir/generate/indexers.py +++ /dev/null @@ -1,46 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -"""類發現和拆卸""" -# pylint:disable=no-name-in-module - -from mir import NFO -from mir.data import MIGRATIONS -from mir.maid import MIRDatabase -from mir.spec import mir_entry - - -def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: - """Generate MIR HF Hub model database - :param new_data: Data for the MIR database - :param mir_database: MIRDatabase instance - """ - for series, comp_name in new_data.items(): - id_segment = series.split(".") - for compatibility in comp_name: - # dbug(id_segment) - try: - mir_db.add( - mir_entry( - domain=id_segment[0], - arch=id_segment[1], - series=id_segment[2], - comp=compatibility, - **new_data[series][compatibility], - ), - ) - except IndexError: # as error_log: - NFO(f"Failed to create series: {series} compatibility: {comp_name} ") - # dbug(error_log) - - -def migrations(repo_path: str): - """Replaces old organization names in repository paths with new ones.\n - :param repo_path: Original repository path containing old organization names - :return: Updated repository path with new organization names""" - - repo_migrations = MIGRATIONS - for old_name, new_name in repo_migrations.items(): - if old_name in repo_path: - repo_path = repo_path.replace(old_name, new_name) - return repo_path diff --git a/mir/generate/mlx/index.py b/mir/generate/mlx/harvest.py similarity index 100% rename from mir/generate/mlx/index.py rename to mir/generate/mlx/harvest.py diff --git a/mir/generate/transformers/__init__.py b/mir/generate/transformers/__init__.py index 9eaedd4..7cd0886 100644 --- a/mir/generate/transformers/__init__.py +++ b/mir/generate/transformers/__init__.py @@ -10,7 +10,5 @@ ) from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING -from mir.generate.transformers.harvest import HarvestClasses - AUTO_MAP = AutoModel._model_mapping REVERSE_MAP = AUTO_MAP._reverse_config_mapping diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index 7c33dc5..90de8f6 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -3,7 +3,7 @@ from typing import Any, Callable -from mir.framework import MIRNesting, MIRPackage +from mir.package import MIRNesting, MIRPackage from mir.generate.transformers.raw_data import PrepareData from mir.tag import MIRTag @@ -14,7 +14,6 @@ def __init__(self) -> None: from mir.maid import MIRDatabase self.db = MIRDatabase() - self.raw_data = [] self.find_transformers_classes() def find_transformers_classes(self) -> None: @@ -22,7 +21,7 @@ def find_transformers_classes(self) -> None: :return: List of PrepareData entries representing the transformer classes.""" from mir.generate.transformers import AUTO_MAP - for config_class, model_class in AUTO_MAP.items(): #type: ignore + for config_class, model_class in AUTO_MAP.items(): # type: ignore if isinstance(model_class, tuple): model_class: Callable = model_class[0] if not (config_data := self.extract_config_class_data(config_class)): @@ -34,13 +33,12 @@ def find_transformers_classes(self) -> None: mir_tag = MIRTag(prepared_data) mir_nest = MIRNesting(mir_tag, prepared_data) - packages = [MIRPackage(data=prepared_data.model)] - if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: - packages.append(MIRPackage(data=prepared_data.tokenizer)) #type: ignore , _Lazyautomapping tuple - packages.append(MIRPackage(data=mir_nest.framework_data)) - for pkg in packages: - mir_nest(pkg) + packages = {"model": MIRPackage(data=prepared_data.model)} + if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: + packages.setdefault("tokenizer", MIRPackage(data=prepared_data.tokenizer)) # type: ignore , _Lazyautomapping tuple + packages.setdefault("framework", MIRPackage(data=mir_nest.framework_data)) + mir_nest(packages) self.db.add_data(mir_nest, *mir_nest.loops) diff --git a/mir/maid.py b/mir/maid.py index 5f0111d..14ef49f 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -8,9 +8,8 @@ from typing import Any, List, Optional from mir import MIR_PATH_NAMED -from mir.framework import MIRNesting +from mir.package import MIRNesting from mir.json_io import read_json_file, write_json_file -from mir.tag import MIRTag class MIRDatabase: diff --git a/mir/package.py b/mir/package.py index e69de29..97187e9 100644 --- a/mir/package.py +++ b/mir/package.py @@ -0,0 +1,109 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Any, Callable +from dataclasses import dataclass, field +from mir.generate.diffusers.raw_data import DPrepareData +from mir.generate.transformers.raw_data import PrepareData +from mir.tag import MIRTag + + +@dataclass +class MIRPackage: + data: Callable | str | dict[str, str] + package: dict[str, str] = field(init=False, default_factory=dict[str, str]) + + def __init__(self, data: Callable | str | dict[str, str] | dict[str, Any]): + self.package = {} + self.data = data + if not isinstance(self.data, dict): + self.generate_package() + else: + self.add_framework(self.data) + + def generate_package(self) -> None: + """Generates package information for the MIR tag based on class. + :param pkg: A class object (model, tokenizer, etc) to build a tag from""" + self.domain = "ops" + model = f"{self.data.__module__}.{self.data.__name__}" + self.package: dict[str, str] = {"model": model} + + def add_framework(self, framework_data) -> None: + self.domain = "info" + self.package = framework_data + + +class MIRNesting: + """Build tag components from the extracted data\n + :param mir_tag: An instance of MIR tag with the necessary information + :param prepared_data: Instance of PrepareData to attribute the final information + :returns: The final, assembled MIR tag""" + + loops: list[str] + framework_data: dict[str, str | dict[str, Any]] = {} + repo: str | None = field(default_factory=str | None) + framework: dict[str, str] = field(init=False) + tokenizer: str | None = field(default_factory=str) + + def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData | DPrepareData) -> None: + """\nInitialize the framework with MIR tag and prepared data.\n + :param mir_tag : The MIR tag instance. + :param prepared_data : The prepared data for processing.""" + self.mir_tag = mir_tag + + self.prepared_data = prepared_data + self.loops = [] + self.framework_data = {} + + def __call__(self, packages: dict[str, MIRPackage]) -> None: + """Common routine for handling a package: store tag data, nest the package, + and record the name of the newly-created attribute.\n + :param name: Identification string to store data underneath + :param mir_package: An instance of MIRPackage with the requisite data""" + + for name, mir_package in packages.items(): + is_framework = name == "framework" + is_model = name == "model" + + if is_framework: + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + tag_data += comp + self.framework_data.setdefault("repo", self.prepared_data.repo_path) + elif is_model: + package_data = {self.prepared_data.library: mir_package.package} + if hasattr(self.prepared_data, "tasks") and self.prepared_data.tasks: + package_data[self.prepared_data.library].setdefault("tasks", self.prepared_data.tasks) + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + tag_data += comp + self.framework_data.setdefault(name, tag_data) + elif is_tokenizer: # tokenizer case + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}" + self.framework_data.setdefault(name, tag_data) + + self.nest_data(name=name, tag_data=tag_data, package_data=package_data) + self.loops.append(name) + + def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: + """Nest data into a hierarchical attribute structure.\n + :param name: Attribute name to store the nested data + :param tag_data: Dotted path string for nesting + :param package_data: Data to be stored in the nested structure""" + + from chanfig import NestedDict + + tag_parts = tuple(x for x in tag_data.split(".")) + + if len(tag_parts) == 4: + domain, arch, series, comp = tag_parts + nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) + nest[domain][arch][series][comp] = package_data + else: + domain, arch, series = tag_parts + nest = NestedDict({f"{domain}.{arch}": {series: ""}}) + nest[domain][arch][series] = package_data + + setattr(self, name, nest) diff --git a/mir/tag.py b/mir/tag.py index 3df4200..82f7b8b 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -31,26 +31,19 @@ def __post_init__(self) -> None: def generate_arch(self) -> None: """Generates the architecture part of the MIR tag based on prepared data.\n :raises ValueError: If no suitable tag can be determined.""" - from mir.generate.from_module import to_domain_tag + arch = None library = self.raw_data.model.__module__.split(".")[0] if hasattr(self.raw_data, "config_params"): - arch = to_domain_tag(library, **self.raw_data.config_params) # type: ignore - else: + arch = self.tag_architecture(library, **self.raw_data.config_params) # type: ignore + elif hasattr(self.raw_data, "model_params"): arch = None self.decoder = "decoder" in [self.raw_data.model_params] + arch = self.tag_architecture(library, **self.raw_data.model_params) # type: ignore if not arch: - if self.raw_data.model_params: - if arch := to_domain_tag(library, **self.raw_data.model_params): - pass - raise ValueError(f"Unable to determine MIR prefix from {self}") - else: - raise ValueError( - f"Unrecognized model type, \ - no tag matched {self.raw_data.name} \ - with {self.raw_data}", - ) - self.arch = arch + print(f"Unrecognized model type, no tag matched {self.raw_data.name} with {self.raw_data.model_name}") + else: + self.arch = arch def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: """Generates the MIR tag components from a repository title.\n @@ -93,33 +86,57 @@ def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: if suffix != "*": self.comp = suffix - # def generate_pipe_tag(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: - # """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n - # :param repo_path (str): Repository path. - # :param model_class_obj (str): The model class function - # :raises TypeError: If 'repo_path' or 'class_name' are not set. - # :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. - # """ - # import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name - - # if hasattr(diffusers, class_name): - # model_class_obj = getattr(diffusers, class_name) - # sub_segments = show_init_fields_for(model_class_obj, "diffusers") - - # else: - # mir_prefix = to_domain_tag(**sub_segments) - # if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: - # NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") - # else: - # mir_prefix = "info." + mir_prefix - - # mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) - # mir_series = mir_prefix + "." + mir_series - # repo_path = migrations(repo_path) - # # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) - # prefixed_data = { - # "repo": repo_path, - # "pkg": {0: {"diffusers": class_name}}, - # # "mode": modalities.get("mode"), - # } - # return mir_series, {mir_comp: prefixed_data} + def tag_architecture(self, library: str, **kwargs) -> str | None: + """Set type of MIR prefix depending on model type\n + :param library: Library source of the original data + :raises ValueError: Model type not detected + :return: MIR prefix based on model configuration""" + from mir.data import NN_FILTER + + flags = NN_FILTER["arch"][library] # pylint:disable=unsubscriptable-object + if library == "diffusers": + for module_type, module_obj in kwargs.items(): + module_name = module_obj.__module__ + library_path = f"{library}.models." + if library_path in module_name: + module_name = module_name.replace(library_path, "").split(".")[0] + if mir_prefix := [match for match in flags if module_name in flags[match]]: + return mir_prefix[0] + for mir_prefix, key_match in flags.items(): + if any(kwargs.get(param, None) for param in key_match): + return mir_prefix + return None + + +def tag_scheduler(self, scheduler_name: str) -> tuple[str, str]: + """Create a mir label from a scheduler operation\n + :param class_name: Known period-separated prefix and model type + :return: The assembled mir tag with compatibility pre-separated""" + import re + + series_name = None + comp_name = None + patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] + for scheduler in patterns: + compiled = re.compile(scheduler) + match = re.search(compiled, scheduler_name) + if match: + comp_name = match.group() + comp_name = comp_name.lower() + break + for pattern in patterns: + series_name = re.sub(pattern, "", scheduler_name) + if not series_name: + series_name = scheduler_name + series_name.lower() + assert series_name is not None, "Expected series tag but got None" + assert comp_name is not None, "Expected compatibility tag but got None" + return series_name, comp_name + + +def tag_tokenizer(): + pass + + +def tag_tokenizer(): + pass diff --git a/pyproject.toml b/pyproject.toml index 7d95cc5..0b71665 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -70,3 +70,8 @@ dev = [ [tool.ruff.lint] ignore = ["E731"] + +[tool.pytest.ini_options] +filterwarnings = [ + "ignore::DeprecationWarning", +] \ No newline at end of file diff --git a/tests/test_mir_generate_diffusers.py b/tests/test_mir_generate_diffusers.py new file mode 100644 index 0000000..2db66d0 --- /dev/null +++ b/tests/test_mir_generate_diffusers.py @@ -0,0 +1,6 @@ +def test_info_key_exists_and_library_is_not_nested(): + from mir.generate.diffusers.harvest import HarvestClasses + + Mir = HarvestClasses().db.db + + # print(Mir) diff --git a/tests/test_mir_generate.py b/tests/test_mir_generate_transformers.py similarity index 69% rename from tests/test_mir_generate.py rename to tests/test_mir_generate_transformers.py index 211790d..2fd0a11 100644 --- a/tests/test_mir_generate.py +++ b/tests/test_mir_generate_transformers.py @@ -1,5 +1,7 @@ def test_info_key_exists_and_library_is_not_nested(): - from mir import Mir + from mir.generate.transformers.harvest import HarvestClasses + + Mir = HarvestClasses().db.db print(Mir.info.cnn.yolos) result = Mir.info.cnn.yolos["transformers"] # should not throw @@ -7,7 +9,9 @@ def test_info_key_exists_and_library_is_not_nested(): def test_ops_key_exists_and_library_is_not_tested(): - from mir import Mir + from mir.generate.transformers.harvest import HarvestClasses + + Mir = HarvestClasses().db.db print(Mir.ops.cnn.yolos) result = Mir.ops.cnn.yolos["transformers"] # should not throw @@ -22,7 +26,9 @@ def test_ops_key_exists_and_library_is_not_tested(): def test_ops_tokenizer_created(): - from mir import Mir + from mir.generate.transformers.harvest import HarvestClasses + + Mir = HarvestClasses().db.db - result = Mir.ops.encoder.tokenizer.zamba2['transformers'] + result = Mir.ops.encoder.tokenizer.zamba2["transformers"] assert result == {"model": "transformers.models.llama.tokenization_llama.LlamaTokenizer"} From c45dc1a6231bf41b89f46847575dac8760855b25 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Tue, 20 Jan 2026 18:59:07 -0500 Subject: [PATCH 13/16] ~stepping through progress --- mir/__init__.py | 4 +- mir/_deprecated/_automata.py | 1996 ------------------- mir/_deprecated/_extras.py | 242 --- mir/_deprecated/_guiders.py | 88 - mir/_deprecated/_index.py | 270 --- mir/_deprecated/_schedulers.py | 74 - mir/generate/_tasks.py | 2 +- mir/generate/diffusers/harvest.py | 94 +- mir/generate/diffusers/package.py | 69 + mir/generate/diffusers/raw_data.py | 55 +- mir/generate/diffusers/tasks.py | 34 + mir/generate/transformers/harvest.py | 118 +- mir/generate/transformers/package.py | 56 + mir/generate/transformers/raw_data.py | 41 +- mir/generate/transformers/tasks.py | 32 + mir/package.py | 28 +- mir/tag.py | 20 +- tests/old/test_class_parent.py | 35 - tests/old/test_deconstructors_root.py | 22 - tests/old/test_doc_parser.py | 143 -- tests/old/test_find_docstring_run.py | 5 - tests/old/test_gather_diffusers_metadata.py | 49 - tests/old/test_json_io.py | 42 - tests/old/test_mir_db_create_restore.py | 160 -- tests/old/test_mir_merge.py | 122 -- tests/old/test_mir_search.py | 98 - tests/old/test_mir_tagging.py | 44 - tests/old/test_regex_constants.py | 27 - tests/old/test_resolve_code_names.py | 44 - tests/old/test_seek_class.py | 18 - tests/old/test_task.py | 11 - tests/old/test_taskanalyzer.py | 320 --- tests/test_harvest_transformers.py | 6 + tests/test_inspect.py | 7 + tests/test_mir_generate_diffusers.py | 4 +- tests/test_mir_generate_transformers.py | 12 +- 36 files changed, 303 insertions(+), 4089 deletions(-) delete mode 100644 mir/_deprecated/_automata.py delete mode 100644 mir/_deprecated/_extras.py delete mode 100644 mir/_deprecated/_guiders.py delete mode 100644 mir/_deprecated/_index.py delete mode 100644 mir/_deprecated/_schedulers.py create mode 100644 mir/generate/diffusers/package.py create mode 100644 mir/generate/diffusers/tasks.py create mode 100644 mir/generate/transformers/package.py create mode 100644 mir/generate/transformers/tasks.py delete mode 100644 tests/old/test_class_parent.py delete mode 100644 tests/old/test_deconstructors_root.py delete mode 100644 tests/old/test_doc_parser.py delete mode 100644 tests/old/test_find_docstring_run.py delete mode 100644 tests/old/test_gather_diffusers_metadata.py delete mode 100644 tests/old/test_json_io.py delete mode 100644 tests/old/test_mir_db_create_restore.py delete mode 100644 tests/old/test_mir_merge.py delete mode 100644 tests/old/test_mir_search.py delete mode 100644 tests/old/test_mir_tagging.py delete mode 100644 tests/old/test_regex_constants.py delete mode 100644 tests/old/test_resolve_code_names.py delete mode 100644 tests/old/test_seek_class.py delete mode 100644 tests/old/test_task.py delete mode 100644 tests/old/test_taskanalyzer.py create mode 100644 tests/test_harvest_transformers.py create mode 100644 tests/test_inspect.py diff --git a/mir/__init__.py b/mir/__init__.py index 3405a0f..c43d89b 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -22,6 +22,6 @@ # from mir.generate.transformers.harvest import HarvestClasses # Mir = HarvestClasses().db.db -from mir.generate.diffusers.harvest import HarvestClasses +# from mir.generate.diffusers.harvest import HarvestClasses -Mir = HarvestClasses().db.db +# Mir = HarvestClasses().db.db diff --git a/mir/_deprecated/_automata.py b/mir/_deprecated/_automata.py deleted file mode 100644 index ad5b0c8..0000000 --- a/mir/_deprecated/_automata.py +++ /dev/null @@ -1,1996 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -"""自動化索引""" -# regex to remove \[[^\]]*\] -# (?m)^\s*"[^"]+"(?=\s*:) -# (?m)^\s*"[^"]+"\s?: -# modelspec sai https://github.com/Stability-AI/ModelSpec - -from importlib import import_module -import re -from typing import Dict, List, Tuple, Any - -import torch - -from mir.indexers import diffusers_index, transformers_index -from mir.maid import MIRDatabase -from mir.spec import mir_entry -from mir.tag import tag_model_from_repo, tag_scheduler, tag_base_model, tag_pipe - - -sd1_series, sd1_comp = tag_model_from_repo("stable-diffusion-v1-5/stable-diffusion-v1-5") -sdxl_series, sdxl_comp = tag_model_from_repo("stabilityai/stable-diffusion-xl-base-1.0") -dev_series, dev_comp = tag_model_from_repo("black-forest-labs/FLUX.1-dev") -schnell_series, schnell_comp = tag_model_from_repo("black-forest-labs/FLUX.1-schnell") -ssd_series, ssd_comp = tag_model_from_repo("segmind/SSD-1B") -vega_series, vega_comp = tag_model_from_repo("segmind/Segmind-Vega") -sd3_series, sd3_comp = tag_model_from_repo("stable-diffusion-3.5-medium") # - - -# def auto_gan etc etc -# ai-forever/Real-ESRGAN - - -def add_mir_diffusion(mir_db: MIRDatabase): - """Create MIR entries missing from the database""" - - repo = "microsoft/speecht5_hifigan" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="gan", - series=series, - comp=comp, - file_256=[ - "d9dc6513c30a5b86c2497712690c04fe74b4aa79fdab6d490b34fcb4e24c590c", - ], - layer_b3=[ - "85b5acdf29ad04c63f885383340d8e3445ae0055521f82cabb82bd09cfb9a956", - ], - layer_256=[ - "bd52b538e7ac05711be9321cfb7619d4056996ce32923c9c91ee02cf69154770", - ], - ) - ) - series, comp = tag_model_from_repo("lodestones/Chroma") - repo = "lodestones/Chroma1-HD" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - "0": { - # "diffusers": "ChromaPipeline", - "generation": { - "num_inference_steps": 40, - # "guidance_scale": 3.0, - # "num_images_per_prompt": 1, - }, - } - }, - file_256=[ - "d845553f11e6afe8139c41ca73678f9f03eab2e68d2e1c6f03ae19509a4d546", # sai - "1b2993a44e63b2250496f69edce643bac2fb79833cf92ba8dd95cbd764d970c7", # annealed sai - "2dd46f08516246df1f582047cc09268ce4f747357baff05b13148e71519029fc", # diffusers - ], - # layer_b3=[ - # "8da38c3719e77a38a20356c9f92f5ca0101c17406d7a9817323cf67b74088520", # diffusers - # ], - # layer_256=[ - # "267798815e0855c2253061c6a6ab70edf9590e8ea1ba9b4621eeb0f6615ee37b", - # ], - ) - ) - repo = "lodestones/Chroma1-Flash" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - "0": { - "diffusers": "ChromaPipeline", - "generation": { - "num_inference_steps": 8, - "guidance_scale": 1.0, - "num_images_per_prompt": 1, - }, - }, - }, - file_256=[ - "2c0c7d908d04418a48b453c293237a9826d54472cf0ba76e28697d1309d1021b", # sai - "c88f6794753ba23e8f6bf8c84cf220daa35a6aa16d54ea0c3e0136f52e5da7e1", # sai delta - "c759d67ca3ef50a9a1c242e3291c57f406646f226a95f43f66577996494986db", # diffusers - ], - # layer_b3= [""], - # "layer_256"= [""], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp="pony-diffusion", - file_256=["67ab2fd8ec439a89b3fedb15cc65f54336af163c7eb5e4f2acc98f090a29b0b3"], - layer_b3=["bf4c2154daa4ece7292277b210d081f98759e9ed4d5c889564632e3ccc4a1071"], - layer_256=["465425d4420dcf5aa4b4d5b456db11a1fcc7c8f61b2e4a87e2470297c98bb96e"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp="pony-diffusion-turbo", - file_256=[ - "7555ac941f3a767833830ba5cc9a4508a9777cbf97b487b6baf0400ab7000587", # turbomerge - "9322f9d91b28abf09e4137bc02ec806af23510221a164e71b81778e61cc3b4b2", # turbosimple - ], - layer_b3=[ - "1e8f23fcd4be0f00eb52368b91c709fffa8a3b8e21772b92b2e0671eed9117d0", - "5c8b3f34f9d0a58135cf72fbfe9b5d75b5545a10e3d726478543fa7cc510a8bc", - ], - layer_256=[ - "7edf51ef09b39c46937a4e4141707c040cd12af0d95299a4d3cd2b7d3fabe035", - "74e4dbc89d57d61ff7e8af8b0fddcf7466ba233d53ca4ffb7777138991bc3d52", - ], - ) - ) - repo = "cagliostrolab/animagine-xl-4.0" - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "8ece83aa1bed1fb39a2b81f1660f0ce6889218e493c1f2ed55e9f15f59a7e03f", # v4 - "6327eca98bfb6538dd7a4edce22484a1bbc57a8cff6b11d075d40da1afb847ac", # v4 opt - "1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766", # v3 - "e3c47aedb06418c6c331443cd89f2b3b3b34b7ed2102a3d4c4408a8d35aad6b0", # v3.1 - ], - layer_b3=[ - "268ffbb120670b9c4b25158bd474c787740884b7738b48203aa03c4c3f00028f", - "18fda1a55cad137d62c81d4328f5ece85d88b126261e06b9e14ab68055d5d484", - "bae9bc8a5c43145bcf92ee3391618d9eaddd689f626991bae202de9cf5f1e70e", - "d6bc5ccafa2b97c867b13a1e7a8c2c7ad9c4877055a66c71bb773557bc306447", - ], - layer_256=[ - "c21d1c38813e078817122e12866ab39f5aa7f56945dd4a8beee3cae1e0f139e7", - "b916c162c981155aaf74e93d5314038af6767bb5a129c51ee05a1fb6a206c6ac", - "ecc6bfc73824a2d7c3b0ca184854a235859f329c83768f017b07a19a535d17b4", - "97f6ca05de7fbdae7aacb2427a552f924492176c474a23dd252c192e1c0e9d65", - ], - ) - ) - repo = "OnomaAIResearch/Illustrious-XL-v2.0" - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "c2a1a3eaa13d4c107dc7e00c3fe830cab427aa026362740ea094745b3422a331", # v2 - "536863e9f0c13b0ce834e2f8a19ada425ee4f722c0ad3d0051ec7e6adaa8156c", # 1.1 - "3e15ba00387db678ab4a099f75771c4f5ac67fda9e7100a01d263eaf30145aa9", # 0.1 - "e3d12d0f76d61aa31d2668a2217e5b642592193f2946842c44d7056ea5469cce", # 0.1 guided - "735cf3fefcbdc4f7817f53247e38b836ffd27c7641af6d8daa21d245242cb4bd", # 1.0 - ], - layer_b3=[ - "93b061baf21d743d592327a61f027d099d8e18da9808a76c7704ad123eba4a29", - "dc05fed2acbc73cef4c377cfa2a681c5cf6d065b88d8bf70d371bbcce6a223a8", - "8eb1c30327e5b71b35b9a4513dc5f2cac9f244667393c0eedb10a26aa9991cd8", - "3dafbe31f6ebaffa3d054e1b37049e1147faa2474ceb6dab7bc3c4cded0c845e", - "892533778ee14454938f7b50830093f58e12f1e14560a148f71927e4ccff5f5c", - ], - layer_256=[ - "397791b3d77affb7bd35c5ded7377493c6bf456920a41388ba95bd0157109803", - "b23c02b8519c6777a1f271662f4251a59468c4b3e11184a2d722fa8929b4ea48", - "a373981494f5508c124a1960bdd096bbc96935fbb54b1218f563206d3892c176", - "b709df257c40d9d981f686f2880bbe64f43b78805b7213768d659a142a593efd", - "f1e6b4cab0fce608dca6fa851384e8728202449f16270fbd1f0c4c5ec4946c10", - ], - ) - ) - repo = "playgroundai/playground-v2.5-1024px-aesthetic" - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "11b6d7bce65674659cc6b7ea960658436edfd80e566cb240ebd4bfbc3e2076c8", # 2.5 diffusers - "bcaa7dd6780974f000b17b5a6c63e6f867a75c51ffa85c67d6b196882c69b992", # 2.5 aes sai fp16 - "956dca99114aaa5c3eb526381309d37ee96737e78ed64c8ae613409f47c3f65a", # 2.5 aes sai - "933778ce76c1fc0ca918b37e1488411b8a99bbd3279c12f527a3ac995a340864", # 2.5 fp16 diffusers - "5c7d38880d0940e6795158b7608ccef89217272b1f2a9331c5b0a2adffcd82c4", # v2 sai - "0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a", # v2 sai fp16 - ], - layer_b3=[ - "d55b22740da2d5b98020ad2390cdc0a7ee08cf9e0d98c11957f16cc20c49815b", # 2.5 diffusers - "7e9be9bd9a3aed1ad7207e2f77c98c24c3a75f6adcc9b53514033c6c3365d289", # 2.5 aes sai fp16 - "5c6dfcc8d01dfb64723f8f5785caa080e2987859c0a050470bfdbe5312be9efc", # 2.5 aes sai - "703f775c6e48ed5b0eba6e847414f047bcd4adc677dbc1bf221b3ef05b2ac471", # 2.5 diffusers fp16 - "72d4ebe4af61f8a7add8fe36b8acd16602894279fb5a744ad50b5b5bac7067b8", # v2 sai - "acb757b851db12cdf9d4365a45ee0d6e64afa77ac95583bb82711baf7c4125fd", # v2 sai fp16 - ], - layer_256=[ - "adb7be228d4ee6e583c3e5ae4ddb579fef64c3987617ce4d4aff3eb7f8d6a3f7", - "d4813e9f984aa76cb4ac9bf0972d55442923292d276e97e95cb2f49a57227843", # 2.5 aes sai fp16 - "fe2e9edf7e3923a80e64c2552139d8bae926cc3b028ca4773573a6ba60e67c20", - "bc7021473a04a6de3fe0d0fed600875d852ad1ad9d47c445278f66ce9e8ec7a0" # 2.5 fp16 diffusers - "fc94481f0c52b21c5ac1fdade8d9c5b210f7239253f86ef21e6198fe393ed60e", # v2 sai - "a6f31493ceeb51c88c5239188b9078dc64ba66d3fc5958ad48c119115b06120c", # v2 sai fp16 - ], - pkg={ - 0: { - "diffusers": "DiffusionPipeline", - "precision": "ops.precision.float.F16", - "generation": {"num_inference_steps": 50, "guidance_scale": 3}, - } - }, - identifiers=[ - "edm_mean", - [1, 4, 1, 1], - 2516, - ], - ) - ) - repo = "segmind/Segmind-Vega" - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "94762e983e5942056be73c5c1d4464b8ffa1ada500b4fef1267550e2447953ce", # modelspec sai - "1ab33e37fbb2566c55cd729e4ab79cc2f99cd9d0a578fabc7a2cf4ee47968be1", # diffusers - "8cfa375669b1222d6fecf470f41b2abb370c76a90ab9568964c4bb15b34ec8a2", # diffusers fp16 - ], - layer_b3=[ - "2f353c5e6ed0a2c05af00d014e18e65f69f1ce8c48f8eefbf8ad71b34f940fbf", - "cc34bd3135d7cafc3cb6e3f6e7cb6896c98277bad52877a952ddbd2ffe222e01", - "b90efdc848f5386d5250b6fb233ce380cf6cc299f497cfa1d2feaef22f87c9d1", - ], - layer_256=[ - "029b89ee311110c8f945dbdfc52c1d5daeb1e78c353c38aa3141ec68ce28e7cc", - "5cdb948e5f3873300679073391d48fc648171f02093d7737d078557ff75762bb", - "f73afbe43cc76571cb86ebcfced618668a2fb2252b0bc6ba88d6e942bae75741", - ], - ) - ) - repo = "segmind/SSD-1B" - - mir_db.add( - mir_entry( - domain="info", - arch="unet", - series=sdxl_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "7cb406ec0662e91570a79f3c4fb8f0ea5325bffe6af5d9382edae838698f72bd", # modelspec sai - "1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d", # a1111 aio - "0bf1ce6b065a6b969ab02dc8e8fa21eb20ee189b10935c49ce68c77a7e432c1c", - "02ed8ebd0ed55aec686fcf20946d7a1659a31f9f8d9c3798cd254ba6b67434ca", # diffusers - "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a", # diffusers fp16 - ], - layer_b3=[ - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", # modelspec sai - "1d6c0216da57fe98e7ad29e9653566725f5b2a87845fdbdcda257b3be817b5f4", # a1111 aio - "c074dc38e8ec836816b91cbcc2ca17f80d6106de8d196d416ef9a27c8837ee45", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6", - ], - layer_256=[ - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "b365a3631c6c74532f3a571c84c68e088be35496d35be1e932031713ddd2a2f4", - "52267d5d327a2ba92c7a14261a9d081df621b8366819b1bb3a47d130523a813c", - "89f86d9c846495870416b4945b6a46a517f28405e5bab666feb4057f012340be", - "535b47e9b70da6494878ca6d45af3f2e201b7f17748432911c12232e586855e6", - ], - ) - ) - repo = "shuttleai/shuttle-3.1-aesthetic" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=schnell_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - 2: { - "diffusers": "DiffusionPipeline", - "generation": {"guidance_scale": 3.5, "num_inference_steps": 4}, - } - }, - file_256=[ - "176871da1d5d2d511a52ae9b0dd70faa1f5d1b7734b7e33ed6b4bffa52050e0d", - "4b80d37681eaed07b7f5b3825a392da929d1620933ede7c2749ef3613cc53f42", - ], - layer_b3=[ - "ff422d1734abf33366e87bbf44267dc6096c5d499e695287c35558174877412e", - "5ad8034eac6b82d842311437101c52b5d35826ce34994940d9e667e702a0d45c", - ], - layer_256=[ - "e5d95de314cbfc49b79479118a1ac0b90fc95ccd6bb1a5c95803996d6cebf8fe", - "d299e8ea4a605917ab98a4a7330d4d398b4ae295efbf458eeeceb5ff1bd7959a", - ], - ) - ) - repo = "shuttleai/shuttle-3-diffusion" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=schnell_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - 2: { - "diffusers": "DiffusionPipeline", - "generation": {"guidance_scale": 3.5, "num_inference_steps": 4}, - } - }, - file_256=[ - "a5b04df4072698395387c21e8da0176d03f6557e0c38ff1dd3bf469ebab9d0fd", # fp8 - "a91b46de2055b3511ee87523b57862648856e8c00100161d5b520543a7302755", # norm - "23a77c86189d5934da48bf44bb871cf80ba99177ffd3fd5272cdecb208c8b8be", # mlx q8 - "d3782d5a8f6e82c6676e8e26d54020934ada589d2aceb17fc5ca604b1bd55da8", # mlx q4 - ], - layer_b3=[ - "4dd3174edf6b680ce9daf3de643e33ae2c4f09a4d5968da61ea48885f3a193c0", - "9fdf191b2c58b2a6e190396e12314530593dca4f2a2bee389ec5175da5e52af8", - "ad203ad6a00d8b1315337e34069e7c41016ea407469a536de8ad6807042017fd", - ], - layer_256=[ - "14d0e1b573023deb5a4feaddf85ebca10ab2abf3452c433e2e3ae93acb216443", - "7ce8d449b32a9c959431ade729b513ee7a6457f11e1c13e3ef04dd8db3494621", - "9c3395f67a3d844483b77f0ddd5e2ea64b61732fa9d9da19845bb8ae574c1f8c", - ], - ) - ) - repo = "enhanceaiteam/Mystic" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={0: {"generation": {"num_inference_steps": 16, "guidance_scale": 7.5, "width": 768, "height": 1024}}}, - file_256=[ - "179d4000e44295f6dfadc0e4ac210146454724d46371b82657200ff9fb5c68a9", # mlx 0 - "48ca85274e3b67f07f70dd84b67725e62395c2f7b188394342716f783ea4c6ac", # mlx q8 - ], - layer_b3=[ - "91074aaebe1b5f3b2e7755d3c092af7eb240e92a192360690f1033949d3c8a68", # mlx 0 - ], - layer_256=[ - "3942e6a52dbb0abaf63b031d9c4eda0df47576b51d4c81361978a3dc27b1309e", # mlx 0 - ], - ) - ) - repo = "shuttleai/shuttle-jaguar" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=schnell_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - 2: { - "diffusers": "DiffusionPipeline", - "generation": {"guidance_scale": 3.5, "num_inference_steps": 4}, - } - }, - file_256=[ - "dcbc4f2470b177eed12c7d7515c0e7342515a849ebd31a50c8d8d43913d7bd32", - "26a7aa64c0798a3549e1d767932da0a7fb82b49f8edcbdcde804a20d9ed1478f", # mlx q8 - ], - layer_b3=[ - "9906c29933d0c33a6ee8d9712f33fa8bd4b35b46a1c7b565ae48832b757dd980", - "89c453c4bf99220405687eed984dace4492bdae1b6fb08f3d9629145b1a11672", # mlx q8 - ], - sha_256=[ - "4eacf27e5659f5dc42f34c407cbe9e1e202290692df754eb68fe913f59fa2941", - ], - ) - ) - repo = "freepik/flux.1-lite-8b" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={0: {"generation": {"num_inference_steps": 28}}}, - file_256=[ - "09e970a7b8d1813ea7cacd48f9a944fd223882b137a8f4f3b61d864cdc20bbec", # mlx q8 - "de90e69945c2f4afcb9b6a057ce48190905c984370fce76b16ba3b97d46e2747", # mlx q4 - ], - layer_b3=[ - "9276fa4805efeb45c08cca32c5b51d490e57a2ce5c15ef476a8e468a509c5cdf", - ], - layer_256=[ - "e1afe2f9b1ca55b3c659293cf3237f6b5571f5c4e826bad025ff0f7b54dc34ee", - ], - ) - ) - repo = "freepik/f-lite-7b" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, - ) - ) - repo = "freepik/f-lite-texture" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, - ) - ) - repo = "freepik/f-lite" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={0: {"f_lite": "FLitePipeline", "generation": {"num_inference_steps": 28}}}, - ) - ) - repo = "TencentARC/flux-mini" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=["4236455adeaeb4ed444d63b253ec99805022d17e962ed7261ada9c72ce11cfee"], - layer_b3=["c1a6f83585398fe452d20596a79a522e2986f4c2c01a40e7bfd787af113735d3"], - layer_256=["e4a0d8cf2034da094518ab058da1d4aea14e00d132c6152a266ec196ffef02d0"], - ), - ) - repo = "ostris/Flex.2-preview" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "0407108e446a4f57efffc5e7518bc374876af970d3c6068dc4074de0d221c615", # modelspec sai - "df168ba94d5f96c478b24604a6beedff6189047152190509c73c162ea0d8ec02", # mlx - ], - layer_b3=[ - "7f85cdc186896da6965b57d5edb672f08663075d2b207f0e20e328c4034a8076", # mlx - ], - layer_256=[ - "5063de856be5365807d12b47ef6919b4ac611a72651739b2b4050e113bed7a83" # mlx, - ], - ), - ) - repo = "ostris/Flex.1-alpha" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=dev_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "5d6dce30a266ccbf530c3a3bf253cd5486720a8fb71cdeed556c28304201dc2f", # modelspec sai - "7acf8771b80a91eaa21566abe8c7d9d3ba33d8688e6e98446827749aee7ca1ee", # mlx - ], - layer_b3=[ - "cb3d3edafd81651eefd62894b3572deb02c5304f4b5d4f7ab8654f1fb922ecd6", # mlx - ], - layer_256=[ - "a6b9af6efc25fa77cd24046b81ee66fea09a9987d2a8e56ffca9b7a1c9c9c519" # mlx, - ], - ), - ) - repo = "tensorart/stable-diffusion-3.5-medium-turbo" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=sd3_series, - comp=tag_model_from_repo(repo)[0], - repo=repo, - pkg={ - 0: { - "precision": "ops.precision.bfloat.B16", - "generation": {"num_inference_steps": 8, "guidance_scale": 1.5, "height": 1024, "width": 768}, - } - }, - file_256=[ - "5b0530e8d71b49fa1358f1208047cd789a40bae5b44406c9524b0f0d88f8b246", # diffusers - "07119c77c3548a1d9eb30923df4dd55ec74914dc5ec81626804dcbe51ce17a5d", # sai - "3c379381344d2a2b3ee3d7a1bc97f7d1e58fa95c6b5187fb48b3ce446f99f17b", # q4km gguf - "6b3806cafdb4303ea2638e9e08eb186067b4a46a95ddf344ccdbe56537afaf6e", # q8km gguf - ], - layer_b3=[ - "873821614080a98e1ebfe56673bc96c2ac57379720d4ad2f97e4bca317571d48", # diffusers - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6", - ], - layer_256=[ - "3c324055a1ec6eb4ee0242e344bb2b6356afcbd2e215fdd9d160cda691a72fae", - "7284d2027523482af9ef47405667ca891cc518bfb6ebf1f1d4666cb0accc8cd5", - "d938ee5738c73f701760ed18acad274b074d2796123aee3f2eee1328b6c36ea4", - "c4c40056c2a77959083b5a69a1a4b205caa463ccabde057352c5c4e38b2c67b6", - ], - ), - ) - repo = "Wan-AI/Wan2.1-FLF2V-14B-720P-Diffusers" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=series, - comp=comp, - repo=repo, - file_256=[ - "", - "", - ], - layer_b3=[ - "", - ], - layer_256=[""], - ), - ) - repo = "OnomaAIResearch/Illustrious-Lumina-v0.03" - mir_db.add( - mir_entry( - domain="info", - arch="dit", - series=tag_model_from_repo("Alpha-VLLM/Lumina-Image-2.0")[0], - comp=tag_model_from_repo(repo)[0], - repo=repo, - file_256=[ - "dc6cffcfb0ccfca6332ddb5d2fe25bcb5f496f44b481627f48c42626156fa6a8", # 2b 22100 ema unified fp32 - "2ac549741fa1c6de2d6cd8be06abcdce52d472eeae2439f948e285258b66a214", # 0.03 ema - ], - layer_b3=[ - "a97b4a63e1e7678e8e7154fae55252267bd1f0ba76b03dba622d801644e657ac", - "aa6c1b2d1971cea3c4ed0963c8d68d4c50db683f8eab9f77f60ea2d04ed6ce5c", - ], - layer_256=[ - "39086c199b9ac296dcba53461ba1e113906d91fbc1b12556d92f5cc77ca11f9f", - "e51ba2ded40f1af5ca6f78c46eed8305fbd87cd6401e9d439837e10d35cc5828", - ], - ) - ) - mir_db.add( - mir_entry( - domain="ops", - arch="patch", - series="hidiffusion", - comp=sdxl_series, - pkg={ - 0: { - "hidiffusion": {"apply_hidiffusion": {"timesteps": "StableDiffusionXLTimesteps"}}, - "generation": {"height": 2048, "width": 2048, "eta": 1.0, "guidance_scale": 7.5, "num_inference_steps": 10}, - }, - }, - ) - ) - mir_db.add( - mir_entry( - domain="ops", - arch="scheduler", - series="align-your-steps", - comp=sdxl_series, - pkg={ - 0: { - "diffusers": "schedulers.scheduling_utils.AysSchedules", - "generation": {"timesteps": "StableDiffusionXLTimesteps", "num_inference_steps": 10}, - } - }, - ) - ) - # possible mixed-type architecture? - # fusion / united / universal - - -def add_mir_llm(mir_db: MIRDatabase): - base_arch, base_series, base_comp = tag_base_model(repo_path="facebook/chameleon-7b", class_name="ChameleonModel") - repo = "Alpha-VLLM/Lumina-mGPT-7B-1024" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=base_series, - comp=series, - repo=repo, - pkg={ - 0: { - "inference_solver": {"FlexARInferenceSolver": {"precision": "bf16", "target_size": 768}}, - "generation": {"images": [], "qas": [["q1", None]], "max_gen_len": 8192, "temperature": 1.0}, - }, - 1: {"inference_solver": "ChameleonXLLMXForConditionalGeneration"}, - }, - identifiers=["model.embed_tokens.weight"], - file_256=[ - "6b71408a7c574d98f00114ab770ac6addc71471770456e482e7b5ec641c02345", - "1d5d8d5532bae0f32ba35d10d411e506d61e4378dc9fc338f2b1e6af2aa322ec", # 768 - "a8fe636bbee30fef06dcd8e806ffc65b2aed0ad08a07fdc62f35717d0f851be5", # 512 multi - "6420fa13483576d46263996627ba7add2237a01f46dedd3b7750112c0cc2d95b", # 512 - ], - layer_b3=["6cd6b3caaea270feb5aff8e9fec205a27da4f48a1e740e63dc9a08f16e70a656"], - layer_256=["eaa882db6a69cf8ed0104a15b2cdbbb570a23a06ab8c8f65f4c6c21719c6ba25"], - ), - ) - repo = "openai/clip-vit-large-patch14" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="vit", - series=series, - comp=comp, - repo=repo, - pkg={0: {"transformers": "CLIPTextModel"}}, - identifiers=["text_model.encoder.layers.0.mlp.fc1.weight", "clip-l"], - file_256=[ - "cb0cba1ead482a850532ebe5ff6b5c8d4456aee32a5228acf0a31e7d9472415e", # long vit best - "39e79c916feca4ddf546d9fe923e664714b59ea61074f7228037d17c302f3d17", # vit l detail improved hit gmp - "893d67a23f4693ed42cdab4cbad7fe3e727cf59609c40da28a46b5470f9ed082", # flux/shuttle 3 aes - "778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3", # playground 2.5 - "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd", # playground 2.5 fp16 - "71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1", # sd3.5 fp16 - "5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc", # sdxl diffusers - "87c1c0b0894c9e9e10b962e597e8d64dd3a3a2d372c389922b335a53c250b2ae", # L - "bd289dd57fee86bc8816b55919a2b03f9c3c75af6025e21777325a6730872325", # jaguar mlx - "8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5", # ssd-1b - "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447", # ssd-1b fp16 - "92b998a9a64549bfa05c019bde114be6681549a0c79caee903fe30c9444d08b9", # vega - "1e090d6a828fd92401be5f83e615fd7b4fb1f4a22e9af9040a38f602e839317c", # vega fp16 - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", # flux - "d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334", # sd1 - "77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e", # sd1 fp16 - "b70c11ad5d7e9abf6109348908f599ea382f8019e1f36910bbc8ebecde936633", # hidream i1 - "fc42badf529dd83f2f7c3d20fe6bda1e22036162f37c4c668b9e130884e20561", - "e27bafa0b3029ad637ef3ace24ce1efe85b8d0dbd22e03a2e70bda6fc88963a1", # onnx - ], - layer_b3=[ - "f58a22a381f79985b6d38782f6110a52c2f319b40fdedd3b88b24945dfcbdf64", - "8faa00b8fd1dbd9286a7237df18caeb8c91af100a6813849b6bae272a01dd7b7", - "ab5bebc98299c155251a06deccde599ba0128038ee3ce021e8c59a45f58f72c0", - "c70e9d86a9dcbbbe7c269ef9dfac96ce9c96c46922577338cc1902e5fe936315", - "f285e9b7b70745df81adc8b558ec74b536b79b6fc02a453ecc61ea9d13f25f1a", - "7ab17bfa06ab8d65840997ef641f3f593d096860e20141f1eeb0169d131c1c23", - "2737d3f327e8176dbb549b9c5c4994821430a6c3b07e3bbc925d97511c802636", # jaguar mlx q8 - "58a826a4a5fe555b4df188a1ebc0d8d9c96cedae3a26ce84c247861dbb93388f", # sd1 - "1540fd8844898960e18ce8fd153e5f21a8c446bd8c4d6f536a7cf11418f02bf3", # sd1 - "c4c9caccdbec12b965d93688c521893f75e0bf9a5e0aad70a6a962b669e7b9d5", # vega - "e43fae8d5fd1e562607da172369cc0c5ec99b834e42502e682287ff7d12baacc", # vega fp16 - "c6f79f7416a882891957b815fbdfd6edfaa253c43970b1a25ef14e217599c7bc", # flux - "daf5e09f67ad09a909f58a01298fec0132324634cb8fca2a604c3a240c2c453f", # jaguar mlx q8 - "3f62bfb6bbde05f01435129326166c44aeb113ac0d9f735f31ed3f7dd04f6980", # hidream i1 - "22f866f3c96a92bc61e9965cf366d706db942ad047ba8cb82109edcd4e68fa40", # sd3 turbo - "f3fa9d7a8f15741621c1fe82f8a1bcc5c601c900d947ac09fba7016615a252a5", # shap-e - ], - layer_256=[ - "48daa3d8f939972e69f044533a4312a941971c18c78255f5e555fa26faf664c1", - "60f5734a74c342be8b0011fc704e718431839790bcfdc7d7004fc39d70f7fec6", - "6e76e25b4a55dddfa2eecf4b7ab189a8148658a9f6df165c00170f6ce661033c", - "2d5249df489fec9137cc3a5e9bda499dd9b72a957ddd8e7ad4e99ff3684bad99", - "3bf085e701713ed3e79775dafea375c3e2a43659ad1ee788b1b393c0aeff9f0e", - "efb7976800692772e449c81a739339f59394886590ff3f768b0f9ddd87d2a94c", - "9b0ac8d127c6c457b2eb8c7236f18c4e4ba9e8bbf27130aa8fe854d7c3f7b1e0", - "24a9ee3d60cdde6c967f08e4b2ec7088fe1bfe308c6896e73caa874860570a5c", - "5d6d9d0cc7943eb1b8c16862bfd5bee5c3766d0df027ec837e90fac715ac2bd3", - "68fb122f7d6c3cfbef320341b2af8f5916678e36a69ed36fa8cfcb19e7d5c43d", - "11807cb2522cfe99240e5ee2bbeb1ccb42cecca2215102ee872567c7773b28b9", - "50c46cdddbe9f0162278c69b9a1f818519330e3a91b994272e19b5c789670471", # jaguar mlx q8 - "ffe1c4f55e07c2010ace7b9cf35798bb9f431bc954a32784e5acbdc16acc0364", # hidream i1 - "146ea48d234e05a934db9d8988e9a9dd86b2ac70f535eaa550ecb0ee23ec135e", # sd3 turbo - "d97560cf9704cf71711f6121df2bf55e55a1eda4b574a6ddba074767420bc8c3", - ], - ) - ) - repo = "laion/CLIP-ViT-g-14-laion2B-s12B-b42K" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="vit", - series=series, - comp=comp, - repo=repo, - pkg={0: {"transformers": "CLIPTextModelWithProjection"}}, - identifiers=["31.self_attn.k_proj.weight", "text_model.encoder.layers.22.mlp.fc1.weight", "clip-g"], - file_256=[ - "ca18e0c67c1ef1e64cac22926266765b60688f692307ecc06283d987c5768134", # seaart furry g - "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4", # modelspec sai - "fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4", # playground 2.5 - "b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe", # ssd1b - "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d", # ssd1b fp16 - "943a2924ee888295a156dd47089d67181d633b782337890af11ef4b15af17ec5", # vega - "5b98e4a57a9292eeb819d67e2d2100f66f17db723cde4ecea27a7c3741160d0c", # vega fp16 - "4d6effa7a5e600cabf7528ed7234146a13ead1b2c151211d706b293a060b112a", # hidream i1 - "3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff", # modelspec sai - "162042ac6556e73f93d4172d4c67532c1cbe4dc7a6a8fa7e44dd2e3d7cbb772b", # onnx - ], - layer_b3=[ - "d754db276f2d89d2808abb7086b3b8eccee43ac521c128d21a071f3a631474a8", - "2eb93685b34719e1d1e0541d8902b0a592d95848f80657e32816cf3b152a0f31", - "e253a5cf3a6242c58037abd6b378bf0281f278e441f28dff7ca1bcfcd3cd6bd8", # ssd1b - "16d0eec4e55b0aa63cdca4e4d36f78f66a4b1b9605ce3b1089305026f853c3d2", # ssd1b fp16 - "f606463295ecf3bae8920d3d45bb9d180793418b3d08c3e84d4c4135c7dc2aa5", # vega - "7060993a5eb32d94d1ea8aef7a7301e7be73b199c639c63f8f7cfbfcd2abf10e", # vega fp16 - "b92af95334c657371af6051a91374a41b5455907fa6622bb66a8c112dc511600", # hidream i1 - ], - layer_256=[ - "270e998633eb22145100a3889a62ca270d5080654735e5ff8dda09a7c233af8d", - "df18800c2a9d9318c4323d991a0fb24a6a9afceb41bea203812f60517c301536", - "4c228b104f6b9b383e0808c9baa1998957f5125d8f90a4d98c1a86e71edd72dc", # ssd1b - "f7fc81d8b5ae91ec28a5106ecc0d067be9a94fd3f394c4aa4686ed131ce5a5b3", # ssd1b fp16 - "61ab42bd5c0fcb9fd3db1d4014cb844ccae8dc17fd69a108cf077a573d092946", # vega - "6c64e36cdda3bec7067e94b05619f882f5d31070792acaadac60ddbef580453a", # vega fp16 - "43c9e64995b485a7f128771c48defce128640df28e65c7f79537d472f43ebe46", # hidream i1 - ], - ) - ) - repo = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="vit", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: {"transformers": "CLIPModel"}, - }, - file_256=[ - "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d", - "0084e75319a50ad85ef45377bad5bc38f2f58824459eb690048d51c9f8863be5", # open clip - "64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161", # wan sai - ], - layer_b3=[ - "227f26ed63120b9034f4a0c90b6b37eede721a8260f2c1e8f7ea3ccc0d109e7e", - "3a38ffd1b60499cf2f451f3065079ff26efb9190a86f23ad1c8d993bbeb9af05", # open clip - "ce06cf1fd684269ee96631b2bf9334c6ecde6a84a55760dfa0d9d2a6411f28e4", # wan sai - ], - layer_256=[ - "130a94ed12569e099196a6ca27388181922e20148dee5bcb58c5e309acfc2352", - "cfdbd3fd2b90b64ba12d395a62dd7c3c3ea3e811f0a54593e91bae6516ca5061", # open clip - "9125ce5970c649d6f9368c25493d3aaa6b41e224d4cc427e955115f7b7e53d1c", # wan sai - ], - ) - ) - repo = "zai-org/chatglm3-6b" # formerly THUDM - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="aet", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: {"transformers": "AutoModel"}, - }, - file_256=[ - "0054d03310248928fdabdeef3fdc753170218dc49a1e9eb5f98323e27683f654", # kolors - "b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d", - ], - layer_b3=[ - "a45dfba6a9fa8739777c76deb845fc9589b40f88670d3ce4661646a7b7b1d481", # kolors - ], - layer_256=[ - "174924fd7a07f370bb6fcd1ad07a73eecb7de901f15eefb80f420c1042c47d44", # kolors - ], - ) - ) - base_arch, base_series, base_comp = tag_base_model(repo_path="Qwen/Qwen2-7B-beta", class_name="Qwen2Model") - repo = "ByteDance-Seed/BAGEL-7B-MoT" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=base_series, - comp=series, - repo=repo, - pkg={0: {"Bagel": "app"}}, - ) - ) - - -def add_mir_audio(mir_db: MIRDatabase): - """Create MIR audio modality entries""" - repo = "facebook/audiogen-medium" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "audiocraft": "models.AudioGen", - "generation": {"duration": 5}, - "stage_2": { - "audiocraft": ".data.audioaudio_write", - "generation": {"strategy": "loudness", "loudness_compressor": True}, - }, - } - }, - ) - ) - repo = "parler-tts/parler-tts-tiny-v1" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "parler_tts": "ParlerTTSForConditionalGeneration", - "generation": {"return_tensors": "pt"}, - }, - }, - ) - ) - repo = "Zuellni/snac-24khz-ST" - series, comp = tag_model_from_repo(repo) - ( - mir_db.add( - mir_entry( - domain="info", - arch="gan", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "snac": "SNAC", - }, - "1": { - "mlx_audio": "tts.generate.generate_audio", - }, - }, - file_256=["e61ae2f638f56ee07a37592cd5a6a9e7d642560ddc78a76ee4a7f96d6922f1be", "973ee1be4032319fd9685ec54eee1b93e79c7bc98c786e67f17c04669714f11d"], - layer_b3=["18307b00460a64cc4893f9061592ce8d7e15b70fc54065cc8ae0f0155381ec46", "d599b1bb36dee3cee4674b7922fcd69e5ec05b74413f611d21cfdfdf8f9b6119"], - layer_256=["35ba9aa1feb931010559a178fcac243673d2efdd1396a4b69d406c9853a88300", "5a22c4707ed6c928043f23b59f2d102a579db3a9af41cf6e60d7c3958f182841"], - ) - ), - ) - repo = "parler-tts/parler-tts-large-v1" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "parler_tts": "ParlerTTSForConditionalGeneration", - "generation": {"return_tensors": "pt"}, - }, - }, - ) - ) - repo = "hexgrad/Kokoro-82M" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="gan", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: {"kokoro": "KPipeline"}, - 1: { - "mlx_audio": "tts.generate.generate_audio", - "generation": {"audio_format": "wav", "join_audio": True, "verbose": False}, - }, - }, - file_256=[ - "5a5cb3d87478f2e74dfca208ee52209ccfce024095e137097fd276026506e45f", - "496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4", - ], - layer_b3=[ - "3e9b5017cfe67a7804ac717b18b6add42ffc0bd3353490df2bcc520eaaef79b6", - "379660a87a64524bab69a267e3d9580f04b5eec4f7e3fbd48c6597d164d9b17d", # safetensors - "997f154f5a78879ef3ba1a1556977c40b28b9c21076b8f583f752c57ecc36e93" # pytorch - "2dc3dba29452b85ea85266084a6248f9e0efe642d5f75b43e64f25b9f2837f92", - ], - layer_256=[ - "dbedf0e2115aa309b92689f86534be4a77b91d7900365e1717879fbb19b849f6", - "2c68574571b3f9229e015a909788116ea2251142e29c1bd5c687863192124e8b", - ], - ) - ) - repo = "freddyaboulton/silero-vad" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="stst", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "onnx": "onnx", - }, - 1: { - "mlx_audio": "tts.generate.generate_audio", - "generation": {"audio_format": "wav", "join_audio": True, "verbose": False}, - }, - }, - file_256=["591f853590d11ddde2f2a54f9e7ccecb2533a8af7716330e8adfa6f3849787a9"], - layer_b3=[ - "41ca5931452b3ffee588c6c7e5bd327c4e914141604eaf3fd05f4a790ac83bb2", - "7dc736cd5d840182792bde4edfbf5ddc5aeaf16826a9c72d1ba8166c1e3fab9b", - "6e2c1bdbad74f56663ffb5710c7cb849a2b91ba331d81acdba47a21f69107434", # onnx - "ab5ff443aece9171af5e7603d0b4309d3ecc934e3940ccedefff10f0b54b931e", # onnx vad - # "7939427700c3b4d91428a490bde1a6d893f63ee5d79b86f68de9e89c7094d3e7" # onnx # <- clip-g ?? unet? inaccurate test at layer level - ], - layer_256=[ - "2ffef1834d5fe14ad8db58fc78d769d5dc38dda5eddbfc396786f74b326215fd", - # "94ea015f5f7f65b1d8e80f7d52859535e7761d7ed2752e24d57a8d9d9da96672", # onnx lose reliability with layer search apparently - ], - ), - ) - repo = "facebook/wav2vec2-conformer-rope-large-960h-ft" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="stst", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "transformers": "Wav2Vec2ConformerForCTC", - }, - }, - file_256=["97bb9761fb71ec1225100bc81ccf7d002e0d0ba3d0604c1fd2dbda7d7d491f1d"], - layer_b3=["6c9c5642aa8dce62bcb3eb577bc519619a2d868005c767c5e65371c583a8a8eb"], - layer_256=["1afcfda68307a75caa1a1c4456cf97e20c7914e8aba828006e9fe17e8675a79d"], - ), - ) - repo = "canopylabs/orpheus-3b-0.1-ft" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: { - "orpheus_tts": "OrpheusModel", - "generation": {"max_model_len": 2048}, - }, - 1: { - "mlx_audio": "tts.generate.generate_audio", - "generation": {"audio_format": "wav", "join_audio": True, "verbose": False}, - }, - }, - ) - ) - repo = "OuteAI/OuteTTS-0.3-1B" - series, comp = tag_model_from_repo(repo) - mir_db.add( - mir_entry( - domain="info", - arch="art", - series=series, - comp=comp, - repo=repo, - pkg={ - 0: {"outetts": "InterfaceHF"}, - 1: { - "mlx_audio": "tts.generate.generate_audio", - "generation": {"audio_format": "wav", "join_audio": True, "verbose": False}, - }, - }, - ) - ) - - -def add_mir_lora(mir_db: MIRDatabase): - """Create MIR lora entries""" - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="dmd", - comp=sdxl_series, - repo="tianweiy/DMD2", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {}}, - "generation": {"num_inference_steps": 4, "guidance_scale": 0, "timesteps": [999, 749, 499, 249]}, - "scheduler": {"ops.scheduler.lcm": ""}, - } - }, - file_256=[ - "b3d9173815a4b595991c3a7a0e0e63ad821080f314a0b2a3cc31ecd7fcf2cbb8", - "a374289e9446d7f14d2037c4b3770756b7b52c292142a691377c3c755010a1bb", - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="dpo", - comp=sdxl_series, - repo="radames/sdxl-DPO-LoRA", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {}}, - "generation": {"guidance_scale": 7.5, "num_inference_steps": 4}, - "scheduler": {"ops.scheduler.dpm": {"algorithm_type": "sde-dpmsolver++", "use_karras_sigmas": True, "order": 2}}, - }, - }, - file_256=[ - "666f71a833fc41229ec7e8a264fb7b0fcb8bf47a80e366ae7486c18f38ec9fc0", - "6b1dcbfb234d7b6000948b5b95ccebc8f903450ce2ba1b50bc3456987c9087ad", - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="flash", - comp=sdxl_series, - repo="jasperai/flash-sdxl", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {}}, - "scheduler": "ops.scheduler.lcm", - } - }, - file_256=["afe2ca6e27c4c6087f50ef42772c45d7b0efbc471b76e422492403f9cae724d7"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="flash", - comp="pixart-alpha", - repo="jasperai/flash-pixart", - pkg={ - 0: {"diffusers": {"load_lora_weights": {}}}, - }, - file_256=["99ef037fe3c1fb6d6bbefdbb85ad60df434fcc0577d34c768d752d60cf69681b"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="flash", - comp=sd3_series, - repo="jasperai/flash-sd3", - pkg={ - 0: {"diffusers": {"load_lora_weights": {}}}, - }, - file_256=["85fce13c36e3739aa42930f745eb9fceb6c53d53fb17e2a687e3234c1a58ee15"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="flash", - comp=sd1_series, - repo="jasperai/flash-sd", - pkg={ - 0: {"diffusers": {"load_lora_weights": {}}, "generation": {"num_inference_steps": 4, "guidance_scale": 0}}, - }, - file_256=["99353444c1a0f40719a1b3037049dbd24800317979a73c312025c05af3574a5f"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="hyper", - comp=sdxl_series, - repo="ByteDance/Hyper-SD", - pkg={0: {"diffusers": {"load_lora_weights": {"fuse": 1.0}}}}, - file_256={ - "0b97f447b5878323a28fbe7c51ba7acebd21f4d77552ba77b04b11c8911825b6": {"num_inference_steps": 12}, - "55b51334c85061afff5eff7c550b61963c8b8607a5868bbe4f26db49374719b1": {"num_inference_steps": 8}, - "c912df184c5116792d2c604d26c6bc2aa916685f4a793755255cda1c43a3c78a": {"num_inference_steps": 1, "guidance_scale": 0.0}, - "69b25c0187ced301c3603c599c0bc509ac99b8ac34db89a2aecc3d5f77a35187": {"num_inference_steps": 2, "guidance_scale": 0.0}, - "12f81a27d00a751a40d68fd15597091896c5a90f3bd632fb6c475607cbdad76e": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "ca689190e8c46038550384b5675488526cfe5a40d35f82b27acb75c100f417c1": {"num_inference_steps": 8, "guidance_scale": 0.0}, - }, - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="hyper", - comp=dev_series, - repo="ByteDance/Hyper-SD", - pkg={0: {"diffusers": {"load_lora_weights": {"fuse": 0.125}}}}, - file_256={ - "6461f67dfc1a967ae60344c3b3f350877149ccab758c273cc37f5e8a87b5842e": {"num_inference_steps": 16, "guidance_scale": 0.0}, - "e0ab0fdf569cd01a382f19bd87681f628879dea7ad51fe5a3799b6c18c7b2d03": {"num_inference_steps": 8, "guidance_scale": 0.0}, - }, - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="hyper", - comp=sd3_series, - repo="ByteDance/Hyper-SD", - pkg={0: {"diffusers": {"load_lora_weights": {"fuse": 0.125}}}}, - file_256={ - "5b4d0b99d58deb811bdbbe521a06f4dbf56a2e9148ff3211c594e0502b656bc9": {"num_inference_steps": 16}, - "0ee4e529abd17b06d4295e3bb91c0d4ddae393afad86b2b43c4f5eeb9e401602": {"num_inference_steps": 4}, - "fc6a3e73e14ed11e21e4820e960d7befcffe7e333850ada9545f239e9aa6027e": {"num_inference_steps": 8}, - }, - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="hyper", - comp=sd1_series, - repo="ByteDance/Hyper-SD", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - file_256={ - "64b98437383537cd968fda6f87a05c33160ece9c79ff4757949a1e212ff78361": {"num_inference_steps": 12}, - "f6123d5b950d5250ab6c33600e27f4dcf71b3099ebf888685e01e9e8117ce482": {"num_inference_steps": 8}, - "a04fd9a535c1e56d38f7590ee72a13fd5ca0409853b4fff021e5a9482cf1ca3b": {"num_inference_steps": 1, "guidance_scale": 0.0}, - "2f26dcc1d883feb07557a552315baae2ca2a04ac08556b08a355a244547e8c3a": {"num_inference_steps": 2, "guidance_scale": 0.0}, - "c5dd058616461ed5053e2b14eec4dbe3fa0eea3b13688642f6d6c80ea2ba5958": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "91fc3186236e956d64dbb4357f2e120c69b968b78af7d2db9884a5ca74d3cd13": {"num_inference_steps": 8, "guidance_scale": 0.0}, - }, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="lcm", - comp=sdxl_series, - repo="latent-consistency/lcm-lora-sdxl", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {"fuse": 1.0}}, - "scheduler": {"ops.scheduler.lcm": {"timestep_spacing": "trailing"}}, - "generation": {"num_inference_steps": 8}, - }, - }, - file_256=["a764e6859b6e04047cd761c08ff0cee96413a8e004c9f07707530cd776b19141"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="lcm", - comp=ssd_series, - repo="latent-consistency/lcm-lora-ssd-1b", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "generation": {"num_inference_steps": 8}}}, - file_256=["7adaaa69db6f011058a19fd1d5315fdf19ef79fcd513cdab30e173833fd5c59b"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="lcm", - comp=vega_series, - repo="segmind/Segmind-VegaRT", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "gen_kwargs": {"num_inference_steps": 8}}}, - file_256=["9b6e8cd833fa205eaeeed391ca623a6f2546e447470bd1c5dcce3fa8d2f26afb"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="lcm", - comp=sd1_series, - repo="latent-consistency/lcm-lora-sdv1-5", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "generation": {"num_inference_steps": 8}}}, - file_256=["8f90d840e075ff588a58e22c6586e2ae9a6f7922996ee6649a7f01072333afe4"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="lightning", - comp=sdxl_series, - repo="ByteDance/SDXL-Lightning", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "generation": {"num_inference_steps": 4, "guidance_scale": 0}}}, - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="pcm", - comp=sdxl_series, - repo="wangfuyun/PCM_Weights", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - file_256={ - "0365f6107250a4fed1b83e8ae6a070065e026a2ba54bff65f55a50284232bbe6": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "04ea827435d5750e63d113dc509174b4f6e8a069ff8f91970c3d25299c10b1f8": {"num_inference_steps": 16}, - "7eb353b2abcaabab6251ba4e17d6cbe2e763feb0674b0f950555552212b44621": {"num_inference_steps": 16}, - "a85cf70ac16ed42011630a5cd6b5927722cb7c40a2107eff85e2670f9a38c893": {"num_inference_steps": 4}, # float16 - "9f7f13bb019925eacd89aeff678e4fd831f7b60245b986855dff6634aee4eba9": {"num_inference_steps": 4}, - "3b9c970a3e4c0e182931e71b3f769c1956f16c6b06db98b4d67236790d4d0b1d": {"num_inference_steps": 8}, - "7f04ba8911b4c25ef2c7cbf74abcb6daa3b4f0e4bc6a03896bdae7601f2f180b": {"num_inference_steps": 8}, - "13fb038025ce9dad93b8ee1b67fc81bac8affb59a77b67d408d286e0b0365a1d": {"num_inference_steps": 16, "guidance_scale": 0.0}, - "3442eff271aa3b60a094fd6f9169d03e49e4051044a974f6fcf690507959191f": {"num_inference_steps": 16, "guidance_scale": 0.0}, - "242cbe4695fe3f2e248faa71cf53f2ccbf248a316973e4b2f38ab9e34f35a5ab": {"num_inference_steps": 2, "guidance_scale": 0.0}, - "e1f600491bb8e0cd94f41144321e44fdb2cb346447f31e71f6e53f1c24cccfbf": {"num_inference_steps": 2, "guidance_scale": 0.0}, - "d0bf40a7f280829195563486bec7253f043a06b1f218602b20901c367641023e": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "212150d7953627fb89df99aad579d6763645a1cb2ef26b19fee8b398d5e5ff4d": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "e80fcf46d15f4d3821d3d9611bdb3022a4a8b647b2536833b168d317a91e4f74": {"num_inference_steps": 8, "guidance_scale": 0.0}, - "56ed9dc9f51f4bb0d6172e13b7947f215c347fc0da341c8951b2c12b9507d09e": {"num_inference_steps": 8, "guidance_scale": 0.0}, - }, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="pcm", - comp=sd1_series, - repo="wangfuyun/PCM_Weights", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - file_256={ - "b80b27dd6504f1c3a7637237dda86bc7e26fa5766da30c4fc853c0a1d46bad31": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "8f605ffde3616592deb37ed8c6bacb83fe98963c1fd0883c2a4f93787098aa45": {"num_inference_steps": 16}, - "fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e": {"num_inference_steps": 4}, - "bff3d4499718b61455b0757b5f8d98fe23e73a768b538c82ecf91c693b69dbcd": {"num_inference_steps": 8}, - "c7ac2fa3df3a5b7080ebe63f259ab13630014f104c93c3c706d77b05cc48506b": {"num_inference_steps": 16, "guidance_scale": 0.0}, - "4c5f27a727d12146de4b1d987cee3343bca89b085d12b03c45297af05ce88ef4": {"num_inference_steps": 2, "guidance_scale": 0.0}, - "29278bc86274fdfc840961e3c250758ff5e2dc4666d940f103e78630d5b879d3": {"num_inference_steps": 4, "guidance_scale": 0.0}, - "41a7f0b966d18f643d16c4401f0b5ef6b9ef7362c20e17128322f17874709107": {"num_inference_steps": 8, "guidance_scale": 0.0}, - }, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="pcm", - comp=sd3_series, - repo="wangfuyun/PCM_Weights", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - file_256={ - "8a45878ecc34e53855fe21146cb6ef32682053b7c4eacc013be89fb08c4c19d8": {"num_inference_steps": 2, "guidance_scale": 1.2}, - "9444a5cead551c56c4d1c455ce829ba9f96f01fbcca31294277e0862a6a15b76": {"num_inference_steps": 4, "guidance_scale": 1.2}, - "e365902c208cbc0456ca5e7c41a490f637c15f3f7b98691cbba21f96a8c960b4": {"num_inference_steps": 4, "guidance_scale": 1.2}, - "3550fa018cd0b60d9e36ac94c31b30f27e402d3855ed63e47668bb181b35a0ad": {"num_inference_steps": 4, "guidance_scale": 1.2}, - }, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="slam", - comp=sdxl_series, - repo="alimama-creative/slam-lora-sdxl", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {}}, - "scheduler": {"ops.scheduler.lcm": {"timestep_spacing": "trailing"}}, - "generation": {"num_inference_steps": 4, "guidance_scale": 1}, - } - }, - file_256=["22569a946b0db645aa3b8eb782c674c8e726a7cc0d655887c21fecf6dfe6ad91"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="slam", - comp=sd1_series, - repo="alimama-creative/slam-sd1.5", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="spo", - comp=sdxl_series, - repo="SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "generation": {"guidance_scale": 5.0}}}, - file_256=["0b9896f30d29daa5eedcfc9e7ad03304df6efc5114508f6ca9c328c0b4f057df"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="spo", - comp=sd1_series, - repo="SPO-Diffusion-Models/SPO-SD-v1-5_4k-p_10ep_LoRA", - pkg={0: {"diffusers": {"load_lora_weights": {}}, "generation": {"guidance_scale": 7.5}}}, - file_256=["1be130c5be2de0beacadd3bf0bafe3bedd7e7a380729932a1e369fb29efa86f4"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="tcd", - comp=sdxl_series, - repo="h1t/TCD-SDXL-LoRA", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {}}, - "generation": {"num_inference_steps": 4, "guidance_scale": 0, "eta": 0.3}, - "scheduler": {"ops.scheduler.tcd": {}}, - } - }, - file_256=["2c777bc60abf41d3eb0fe405d23d73c280a020eea5adf97a82a141592c33feba"], - ), - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="tcd", - comp=sd1_series, - repo="h1t/TCD-SD15-LoRA", - pkg={0: {"diffusers": {"load_lora_weights": {}}}}, - file_256=["eaecb24a1cda4411eab67275b1d991071216ac93693e8fa0c9226c9df0386232"], - layer_b3=["90158259812a89beb8874216009c799f420334aac49bbf4fa1bf0ebf4bbd256b"], - layer_256=["e9825b81bca684126ac3cc8867d2ebc655f74268bc26bea4e4b7e58a52ad6c75"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="turbo", - comp=sdxl_series, - file_256=["a599c42a9f4f7494c7f410dbc0fd432cf0242720509e9d52fa41aac7a88d1b69"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="turbo", - comp=dev_series, - repo="alimama-creative/FLUX.1-Turbo-Alpha", - pkg={ - 0: { - "diffusers": {"load_lora_weights": {"fuse": 0.125}}, - "generation": {"guidance_scale": 3.5, "num_inference_steps": 8, "max_sequence_length": 512}, - } - }, - file_256=["77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="turbo", - comp=sd3_series, - repo="tensorart/stable-diffusion-3.5-medium-turbo", - pkg={0: {"diffusers": {"load_lora_weights": {"fuse": 1.0}}, "scheduler": {"ops.scheduler.flow-match": {"shift": 5}}}}, - file_256={"bdcbdfa3ec8ed838b77b1020eea3bc7917a2d42573688a034feb921fde8b1858": {"num_inference_steps": "4"}}, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="lora", - series="turbo", - comp=sd3_series, - repo="tensorart/stable-diffusion-3.5-large-TurboX", - pkg={0: {"diffusers": {"load_lora_weights": {"fuse": 1.0}}, "scheduler": {"ops.scheduler.flow-match": {"shift": 5}}}}, - file_256={"fae59d1b749c0d14a8fd4c68cc94eaac92876cee7b91fa75cf8fde3160e09548": {"num_inference_steps": "8"}}, - ) - ) - - -def add_mir_vae(mir_db: MIRDatabase): - """Create MIR VAE missing from the database""" - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="tae", - comp=sd3_series, - repo="madebyollin/taesd3", - pkg={0: {"diffusers": "AutoencoderTiny"}}, - file_256=["6f79c1397cb9ce1dac363722dbe70147aee0ccca75e28338f8482fe515891399"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="tae", - comp=sdxl_series, - repo="madebyollin/taesdxl", - pkg={0: {"diffusers": "AutoencoderTiny"}}, - file_256=["ff4824aca94dd6111e0340fa749347fb74101060d9712cb5ef1ca8f1cf17502f"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="tae", - comp=sd1_series, - repo="madebyollin/taesd", - pkg={0: {"diffusers": "AutoencoderTiny"}}, - file_256=["db169d69145ec4ff064e49d99c95fa05d3eb04ee453de35824a6d0f325513549"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="tae", - comp=dev_series, - repo="madebyollin/taef1", - pkg={0: {"diffusers": "AutoencoderTiny"}}, - file_256=["927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449"], - ) - ) - series, comp = tag_model_from_repo("Qwen/Qwen-Image") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLQwenImage"}, - }, - file_256=[ - "0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344", # diffusers - ], - layer_b3=[ - "64af8fb08d2054c81ad2aef94965be8fb1366fcc6136cb9222ae046550af014b", # diffusers - ], - layer_256=[ - "42f255440ef1d379a8a731456bc44312a73a8568716caa6100803990cd5ea7dc", # diffusers - ], - ) - ) - series, comp = tag_model_from_repo("Wan-AI/Wan2.1-I2V-14B-480P-Diffusers") - sr_series_text2v, _ = tag_model_from_repo("Skywork/SkyReels-V2-T2V-14B-720P-Diffusers") - sr_series_image2v, _ = tag_model_from_repo("Skywork/SkyReels-V2-I2V-14B-720P-Diffusers") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="wan", - comp=series, - # no repo here, may conflict - pkg={ - 0: { - "diffusers": "AutoencoderKLWan", - "precision": "ops.precision.float.F32", - } - }, - file_256=[ - "d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793", # diffusers - "2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b", # sai - ], - layer_b3=[ - "f867543d636029ebfc05b8075e572be0b313a83b0470e56bcf4bbad07a6db010", # diffusers - "6b5b229727a2d4e37993687c62c94ff8519a371ab4103c699ff1f5969ca0b433", # sai - ], - layer_256=[ - "121b3974b39263dcca9d644d1b5c9b9251a911b6a8a8e307fcb21ca778e78ed2", - "364be43a8959012d798d3f98e17d8b5c4b99ba1e70077008dd19acca3ced395e", - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="wan", - comp=sr_series_text2v, - # no repo here, may conflict - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="wan", - comp=sr_series_image2v, - # no repo here, may conflict - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("Lightricks/LTX-Video") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLLTXVideo"}, - }, - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("rhymes-ai/Allegro") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLAllegro"}, - }, - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("zai-org/CogVideoX-5b-I2V") - series_fun, _ = tag_model_from_repo("alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose") - series_wish, _ = tag_model_from_repo("BestWishYsh/ConsisID-preview") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="cogvideox", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLCogVideoX"}, - }, - file_256=["a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e"], - layer_b3=["246addb8dc798240638bffee4546a3c5c83572139b4a2a602d68b4c4146226eb"], - layer_256=["43c7e9cb4364e55fd563817f01484ede8a09ff19a8e69eb61a32a12f93d6f66e"], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="cogvideox", - comp=series_fun, - # no repo here, may conflict - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="cogvideox", - comp=series_wish, - # no repo here, may conflict - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("nvidia/Cosmos-1.0-Diffusion-7B-Video2World") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLCosmos"}, - }, - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("alibaba-pai/EasyAnimateV5.1-7b-zh-diffusers") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLMagvit"}, - }, - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("hunyuanvideo-community/HunyuanVideo-I2V") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLHunyuanVideo"}, - }, - file_256=[ - "95d1fc707c1421ccd88ea542838ab4c5d45a5babb48205bac9ce0985525f9818", # pt, - "7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883", - "fbe5ea338431bc8ba20f7019b474e83379fe5763abfd562adcc04b1c0d35c728", - "019973c147e0c3462629d8d06bdbdbb83408f3ebd4ea4b4ae21a99c3cdcb54c0", - ], - # layer_b3=[], - # layer_256=[], - ) - ) - series, comp = tag_model_from_repo("genmo/mochi-1-preview") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLMochi"}, - }, - file_256=[], - layer_b3=[], - layer_256=[], - ) - ) - series, comp = tag_model_from_repo("rhymes-ai/Allegro") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: { - "diffusers": "AutoencoderKLAllegro", - }, - }, - file_256=["47871a698b18f92f15019d361a81cbc8af4676f8eef9a47fd2b95354a39f831a"], - layer_b3=["93654cbab7541504d2377c66e72943c7fd9947fca2eb1be01bcc8877c322c1e0"], - layer_256=["bfd496586118165a13243997101fc7cdd4f855b2d8a73ee2b771a4484c4c2f9f"], - ) - ) - series, comp = tag_model_from_repo("cvssp/audioldm-s-full-v2") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: { - "diffusers": "AutoencoderKL", - }, - }, - file_256=["42f64f7565b23eabde68c9694e39f18b8bba5f7a14f477e7ed4b51e0ea7de8a5"], - layer_b3=["00959677dae940b9cfdbe5380c8cbb5a6b4951864cd26f8211d74a3d22b4f3de"], - layer_256=["54d075953d5253a3abac651de070736c1d5510b857a8ab24c624304f428146b6"], - ) - ) - - series, comp = tag_model_from_repo("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="dc", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderDC"}, - }, - file_256=["15a4b09e56d95b768a0ec9da50b702e21d920333fc9b3480d66bb5c7fad9d87f"], - layer_b3=["cf4ecc6697d18b0663e4eac58203f1dd6d9fb689cf99adfeadbc0019de0c73d0"], - layer_256=["abfc39d1a6d71f03dde7bc40fec4a90478a97d17ae1688be9aad00e0512b9bde"], - ) - ) - series, comp = tag_model_from_repo("stabilityai/stable-audio-open-1.0") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="oobleck", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderOobleck"}, - }, - # file_256=[], - # layer_b3=[], - # layer_256=[], - ) - ) - series, comp = tag_model_from_repo("stable-video-diffusion-img2vid-xt") - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKLTemporalDecoder"}, - }, - # file_256=[], - # layer_b3=[], - # layer_256=[], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=sdxl_series, - repo="madebyollin/sdxl-vae-fp16-fix", - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - file_256=[ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", # modelspec sai - "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c", # diffusers - "78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646", # ssd1b diffusers - "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48", # ssd1b diffusers fp16 - "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68", # kolors fp16 - "1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341", # vega / lumina next sft d / auraflow - "703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4", # pixart a - "98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88", # hyd 1.1 - ], - layer_b3=[ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", # modelspec sai - "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0", # diffusers - # "245070a60a25ca080cb4951220c3fb1503da43829930d5f6f7a6770b491eafe1", - # "50e65a628b5fe379798d8956e4a4e1d4b105c84b329f088d577f7f28c22abc49", # diffusers fp16 matches sd1 - ], - layer_256=[ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", # modelspec sai - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0", # diffusers - # "35641f65ad7ea600cb931dcab556f7503279f1d8d99eda170fe7976d48502a2a", # diffusers fp16 matches sd1 (incorrect) - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=sdxl_series + sdxl_comp, - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - file_256=[ - "235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1", # modelspec sai - "27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a", # diffusers - "eb6516ab7e1104d5d1a174a4d65c57835ae38061531d0a2192103aecfb790cc1", # diffusers fp16 - "e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff", # modelspec sai vae 0.9 - ], - layer_b3=[ - "bd5b356b509814025a9cf692710b87116d4fcd0e30a8232ed1db133e908d0e74", # modelspec sai - # "9106380403dee83238af63ff1738396d2fdff9f6d78d0d9c1d0bf770ae4294d0", # diffusers - # "245070a60a25ca080cb4951220c3fb1503da43829930d5f6f7a6770b491eafe1", - # "50e65a628b5fe379798d8956e4a4e1d4b105c84b329f088d577f7f28c22abc49", # diffusers fp16 matches sd1 - ], - layer_256=[ - "c9399a4cd39a180a0bb2af96a8297b9330541e090c21e83317cebb2f7cc651da", # modelspec sai - "2240ae134a3b983abf45200c198f07e3d8068012fbbd2f658bbaa1fd6a0629c0", # diffusers - # "35641f65ad7ea600cb931dcab556f7503279f1d8d99eda170fe7976d48502a2a", # diffusers fp16 matches sd1 (incorrect) - ], - ) - ) - - repo = "shuttleai/shuttle-jaguar" - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=tag_model_from_repo(repo)[0], - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - file_256=[ - "6fdfa2add4f04d94f36157cbb0197f97966b612e3f8eff4095315aefea74b904", - ], # q8, - layer_b3=[ - "0ebf9b7010accc44e219e355dd24bf1e3128004093c0c1dfc06f88c0a39fdbdd", - "d0e7ef3c4af06fa08b4c0485a073e2df55f7b1e9e3ba8f7b261688bc562568f0", # q8 - ], - layer_256=[ - "9b28f36873ea283905094a64e1ccb7cfc2b0f0aa166201d0ca63807ac37caa7b", # q8 - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=dev_series, - # no repo here, may conflict - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - file_256=[ - "afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38", # dev - "f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3", # dev diffusers - "8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94", # lumina2 - "8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc", # sd3 turbo - ], - layer_b3=[ - "b6db93ed78c4a10d69e80831c1b8fbc1447f04e9b3d494889ee2056b98d41f17", # diffusers - "a8a3ebdec4d7b38d65b7169d3604c19b587330e5e66f69ebf0ded56a24ec6903", # lumina2 - # "245070a60a25ca080cb4951220c3fb1503da43829930d5f6f7a6770b491eafe1", - ], - layer_256=[ - "7950e4f3897c75affaa5f9f3c51c88b4d9a27bfd9b05ad41c3f71d8c1c620b89", - "79d2bfe93a2ac037cdc59ccb5576e32d00d75d4741fba49fc7e82b9724928216", # diffusers - "8f084dc91fd5b481875bc9c86a4ef05e5f176896b7d31c6a5c2ce45c2e174004", # dev diffusers - "322e01bd511e20bc2a3c27cd611f81ed85f0046b7c023b5622c2c9a5b8b34f80", # lumina2 - ], - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="eq", - comp=sdxl_series, - repo="KBlueLeaf/EQ-SDXL-VAE", - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - ) - ) - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="ms-lc-eq", - comp=sdxl_series, - repo="Anzhc/MS-LC-EQ-D-VR_VAE", - pkg={ - 0: { - "diffusers": "AutoencoderKL", - }, - }, - ) - ) - repo = "ucsd-reach/musicldm" - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=tag_model_from_repo(repo)[0], - # no repo here, may conflict - file_256=[ - "16e0c6c7c34e459c19500cc15cf538e6331db14969ea15917caa9b0966e44fd4", - ], # q8, - layer_b3=[ - "c5c32b3fb3e73799838836ccce27d883254254daecd10f86ba8ddc55214014e0", - ], - layer_256=[ - "1610c0ce39d1379091eb9ab2a4d14a8567e0f1a5dc6cca40fc0fa6f8e4e97c0f", - ], - ) - ) - - mir_db.add( - mir_entry( - domain="info", - arch="vae", - series="kl", - comp=sd1_series, - pkg={ - 0: {"diffusers": "AutoencoderKL"}, - }, - file_256=[ - "0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520", # ckpt ema original ema pruned - "95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a", # safetensors ema original ema pruned - "32db726da04f06c1b6b14c0043ce115cc87a501482945c5add89a40d838fcb46", # safetensors ema diffusers - "c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab", # ckpt mse original ema pruned - "735e4c3a447a3255760d7f86845f09f937809baa529c17370d83e4c3758f3c75", # safetensors mse original ema pruned - "a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815", # safetensors mse diffusers - "a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c", # safetensors diffusers - "4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c", # safetensors fp16 diffusers - ], - layer_b3=[ - "82e2dc440a23d78bb91df8c9fce069a8512da51f8f54ea29e3431f545808171e", # safetensors original - "2230487833925a104bee96e7ecfebaa4c3c43cc426c7a5b863f2584313dd4833", # safetensors diffusers - ], - layer_256=[ - "e43f3a227b5ecb43a6272fa92ed6011d2e9abcadadd1032dfa7ea7f875f9d5bd", # safetensors original - "2494154245becf98891be884f943276aa3f54e9b3f0ea1042903fc15fba488f3", # safetensors diffusers - ], - ) - ) diff --git a/mir/_deprecated/_extras.py b/mir/_deprecated/_extras.py deleted file mode 100644 index 39af779..0000000 --- a/mir/_deprecated/_extras.py +++ /dev/null @@ -1,242 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable, Dict, List, Optional, Union - -from mir import NFO -from mir.generate.from_module import import_object_named, show_path_for -from mir.generate.tasks import TaskAnalyzer - - -def _class_parent(code_name: str, pkg_name: str) -> Optional[List[str]]: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n - ### NOTE: in most cases `__module__` makes this redundant - :param code_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - import os - from importlib import import_module - - pkg_paths = { - "diffusers": "pipelines", - "transformers": "models", - } - folder_name = code_name.replace("-", "_") - pkg_name = pkg_name.lower() - folder_path = pkg_paths[pkg_name] - package_obj = import_module(pkg_name) - folder_path_named = [folder_path, folder_name] - pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) - # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) - if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: - import_path = [pkg_name] - import_path.extend(folder_path_named) - return import_path - - -def _trace_classes(pipe_class: str, pkg_name: str) -> Dict[str, List[str]]: - """Retrieve all compatible pipe forms\n - NOTE: Mainly for Diffusers - :param pipe_class: Origin pipe - :param pkg_name: Dependency package - :return: A dictionary of pipelines""" - - related_pipes = [] - code_name = show_path_for(pipe_class, pkg_name) - if pkg_name == "diffusers": - related_pipe_class_name = pipe_class - else: - related_pipe_class_name = None - related_pipes: list[str] = TaskAnalyzer.show_diffusers_tasks(code_name=code_name, class_name=related_pipe_class_name) - # for i in range(len(auto_tasks)): - # auto_tasks.setdefault(i, revealed_tasks[i]) - parent_folder = class_parent(code_name, pkg_name) - if pkg_name == "diffusers": - pkg_folder = import_object_named(parent_folder[0], ".".join(parent_folder)) - else: - pkg_folder = import_object_named("__init__", ".".join(parent_folder[:-1])) - if hasattr(pkg_folder, "_import_structure"): - related_pipes.extend(next(iter(x)) for x in pkg_folder._import_structure.values()) - related_pipes = set(related_pipes) - related_pipes.update(tuple(x) for x in _extract_inherited_classes(model_class=pipe_class, pkg_name=pkg_name)) - return related_pipes - - -def _show_shared_hyperparameters(parameter_filter: Optional[str] = None) -> List[str]: - """Show all config classes in the Transformer package with the specified init annotation\n - :param from_match: Narrow the classes to only those with an exact key inside - :return: A list of all Classes""" - from mir.config.constants import extract_init_parameters - from mir.inspect.metadata import find_transformers_classes - - transformers_data = find_transformers_classes() - config_data = [] - for entry in transformers_data: - if parameter_filter: - segments = extract_init_parameters(module=entry.config, package_name="transformers") - if parameter_filter in list(segments): - config_data.append(entry.config) - else: - config_data.append(entry.config) - return config_data - - -def _get_class_parent_folder(class_name: str, pkg_name: str) -> List[str]: - """Retrieve the folder path within a class. Only returns if it is a valid path in the system (formerly seek_class_path)\n - ### NOTE: in most cases `__module__` makes this redundant - :param class_name: The internal name for the model in the third-party API. - :param pkg_name: The API Package - :return: A list corresponding to the path of the model, or None if not found - :raises KeyError: for invalid pkg_name - """ - from mir.config.console import dbuq - from mir.config.constants import extract_init_parameters - from mir.inspect.classes import resolve_code_names - - pkg_name = pkg_name.lower() - if pkg_name == "diffusers": - parent_folder: List[str] = resolve_code_names(class_name=class_name, pkg_name=pkg_name, path_format=True) - if not parent_folder or not parent_folder[-1].strip(): - dbuq("Data not found for", " class_name = {class_name},pkg_name = {pkg_name},{parent_folder} = parent_folder") - return None - elif pkg_name == "transformers": - print(class_name) - module_path = extract_init_parameters(class_name, "transformers") - print(module_path) - config = str(module_path.get("config")) - print(config) - config = config.split(": ")[-1].split(".") - parent_folder = config[:3] - return parent_folder - - -def _class_to_mir_tag(mir_db: Dict[str, str], code_name: str) -> Optional[str]: - """Converts a class identifier to its corresponding MIR tag.\n - :param mir_db: A dictionary mapping series-compatibility pairs to their respective data. - :param code_name: The Transformers class identifier to convert. - :return: An optional list containing the series and compatibility if found, otherwise None.""" - - from transformers.models.auto.modeling_auto import MODEL_MAPPING_NAMES - - from mir.config.constants import TEMPLATE - - template_data = TEMPLATE["arch"]["transformer"] - - for series, compatibility_data in mir_db.database.items(): - if any([template for template in template_data if template in series.split(".")[1]]): - for compatibility, field_data in compatibility_data.items(): - if code_name == series.split(".")[2]: - return [series, compatibility] - - class_name = MODEL_MAPPING_NAMES.get(code_name, False) - if not class_name: # second pass without separators - recoded_mapping = {code.replace("-", "").replace("_", ""): model for code, model in MODEL_MAPPING_NAMES.items()} - class_name = recoded_mapping.get(code_name, False) - if not class_name: - return None - pkg_data = field_data.get("pkg") - if pkg_data: - for _, pkg_type_data in pkg_data.items(): - maybe_class = pkg_type_data.get("transformers") - if maybe_class == class_name: - return [series, compatibility] - return None - - -def tag_transformers_model(repo_path: str, class_name: str, addendum: dict | None = None) -> tuple[str, str, str | dict[str, dict]]: - """Convert model repo paths to MIR tags, classifying by feature\n - :param name: Repo path - :param class_name: The HF transformers class for the model - :return: A segmented MIR tag useful for appending index entries""" - - from mir.config.constants import extract_init_parameters - - annotations = extract_init_parameters(class_name.replace("Model", "Config"), "transformers") - if not annotations: - class_name = class_name.replace("Config", "Model") - annotations = extract_init_parameters(class_name, "transformers") - if not annotations: - raise TypeError("No mode type returned") - if "Bert" in class_name: - print(annotations) - mir_prefix = mir_prefix_from_forward_pass(True, **annotations) - base_series, base_comp = tag_model_from_repo(repo_path) - if not addendum: - return mir_prefix, base_series, base_comp - else: - mir_prefix = f"info.{mir_prefix}" - return mir_prefix, base_series, {base_comp: addendum} - - -# def extract_model_data(self,pipe_name, file_name: str) -> dict | None: -# migrated_pipes = MIGRATIONS["migrated_pipes"] -# pkg_path = f"diffusers.pipelines.{pipe_name}.{file_name}" -# pipe_file: Callable = import_object_named(file_name, pkg_path) or import_module(pkg_path) -# if pipe_file and (doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None)): #where pipe class and repo are -# docstrings= DocStringEntry(package_name=pipe_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) -# DocStringParser(doc_string=docstrings.doc_string) -# self.parsed_docs.pipe_repo = migrated_pipes.get(self.parsed_docs.pipe_class, self.parsed_docs.pipe_repo) -# model = import_object_named(parsed_data.pipe_class, docstrings.pipe_module.__name__) -# model_data = show_init_fields_for(model,"diffusers") -# return {"model_params": model_data} - - -# for pipe_name in IMPORT_STRUCTURE.keys(): -# if pipe_name not in exclusion_list and (import_name := getattr(diffusers_pipelines, str(pipe_name))): -# file_specific = uncommon_naming.get(pipe_name, pipe_name) -# file_names:list[str] = [getattr(import_name, "_import_structure", {})] or [f"pipeline_{file_specific}"] -# for file_name in file_names: -# if not file_name in exclusion_list or not (model_data := self.extract_model_data(pipe_name, file_name)): -# continue -# if not (prepared_data := PrepareData( **model_data)): -# continue -# else: -# continue - - -# def show_path_for(code_name: str, pkg_name: str) -> list[str] | str | None: -# """Retrieve the folder path within a class. Only returns if it is a valid path in the system\n -# ### NOTE: in most cases `__module__` makes this redundant -# :param code_name: The internal name for the model in the third-party API. -# :param pkg_name: The API Package -# :return: A list corresponding to the path of the model, or None if not found -# :raises KeyError: for invalid pkg_name -# """ - -# pkg_paths = { -# "diffusers": "pipelines", -# "transformers": "models", -# } -# folder_name = code_name.replace("-", "_") -# pkg_name = pkg_name.lower() -# folder_path = pkg_paths[pkg_name] -# package_obj = import_module(pkg_name) -# folder_path_named = [folder_path, folder_name] -# pkg_folder = os.path.dirname(getattr(package_obj, "__file__")) -# # dbuq(os.path.exists(os.path.join(pkg_folder, *folder_path_named))) -# if os.path.exists(os.path.join(pkg_folder, *folder_path_named)) is True: -# import_path = [pkg_name] -# import_path.extend(folder_path_named) -# return import_path - - -# def get_internal_name_for(module_name: str | Type | None = None, pkg_name: str = "transformers", path_format: bool | None = False) -> list[str] | str | None: -# """Reveal code names for class names from Diffusers or Transformers (formerly get code names)\n -# :param class_name: To return only one class, defaults to None -# :param pkg_name: optional field for library, defaults to "transformers" -# :param path_format: Retrieve just the code name, or the full module path and code name within the package -# :return: A list of all code names, or the one corresponding to the provided class""" -# from mir.generate.diffusers import IMPORT_STRUCTURE -# from mir.generate.transformers import MODEL_MAPPING_NAMES - -# package_imports = IMPORT_STRUCTURE if pkg_name == "diffusers" else MODEL_MAPPING_NAMES -# pkg_name = pkg_name.lower() -# MAPPING_NAMES: dict[str, str] = import_object_named(*package_imports[pkg_name]) -# if module_name: -# if isinstance(module_name, Type): -# module_name = module_name.__name__ -# code_name = next(iter(key for key, value in MAPPING_NAMES.items() if module_name in str(value)), "") -# return show_path_for(code_name, pkg_name) if path_format else code_name.replace("_", "-") -# return list(MAPPING_NAMES) diff --git a/mir/_deprecated/_guiders.py b/mir/_deprecated/_guiders.py deleted file mode 100644 index b791829..0000000 --- a/mir/_deprecated/_guiders.py +++ /dev/null @@ -1,88 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -# def gen_guiders(mir_db: MIRDatabase): # upstream not quite ready for this yet -# from nnll.metadata.helpers import snake_caseify -# from diffusers.guider import GuiderType - -# guider_type = GuiderType -# for comp_name in guider_type.items(): -# class_obj = comp_name.__name__ -# mir_data = {"pkg": {0: {"diffusers": class_obj}}} -# try: -# mir_db.add( -# mir_entry( -# domain="ops", -# arch="noise_prediction", -# series="guider", -# comp=snake_caseify(class_obj), -# **mir_data, -# ), -# ) -# except IndexError as error_log: -# nfo(f"Failed to create compatibility: {class_obj}") -# dbug(error_log) - - -# ( -# "info.unet", -# "stable-cascade", -# { -# "combined": { -# "pkg": { -# 0: { # decoder=decoder_unet -# "precision": "ops.precision.bfloat.B16", -# "generation": { -# "negative_prompt": "", -# "num_inference_steps": 20, -# "guidance_scale": 4.0, -# "num_images_per_prompt": 1, -# "width": 1024, -# "height": 1024, -# }, -# }, -# "pkg_alt": { -# 0: { -# "diffusers": { -# "StableCascadeCombinedPipeline": { -# "negative_prompt": "", -# "num_inference_steps": 10, -# "prior_num_inference_steps": 20, -# "prior_guidance_scale": 3.0, -# } -# }, -# } -# }, -# } -# } -# }, -# ), - - -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -# def gen_attention_processors(mir_db: MIRDatabase): # upstream not quite ready for this yet -# from diffusers.models.attention_processor import AttentionProcessor - -# mir_data -# for series, comp_name in mir_data.items(): -# id_segment = series.split(".") -# for compatibility in comp_name: -# dbug(id_segment) -# try: -# mir_db.add( -# mir_entry( -# domain=id_segment[0], -# arch=id_segment[1], -# series=id_segment[2], -# comp=compatibility, -# **mir_data[series][compatibility], -# ), -# ) -# except IndexError as error_log: -# nfo(f"Failed to create series: {series} compatibility: {comp_name} ") -# dbug(error_log) - diff --git a/mir/_deprecated/_index.py b/mir/_deprecated/_index.py deleted file mode 100644 index 813bcdd..0000000 --- a/mir/_deprecated/_index.py +++ /dev/null @@ -1,270 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -# import os -# from importlib import import_module -# from typing import Any, Generator - -# from mir import DBUQ, NFO -# from mir.data import EXCLUSIONS -# from mir.generate.diffusers import GET_TASK_CLASS, IMPORT_STRUCTURE, SUPPORTED_TASKS_MAPPINGS -# from mir.generate.from_module import import_object_named, show_init_fields_for, to_domain_tag -# from mir.generate.indexers import migrations - - -# def retrieve_diffusers_docstrings( -# package_name: str, -# file_names: list[str], -# ) -> Generator[DocStringEntry]: -# """Yield (pkg, file, EXAMPLE_DOC_STRING) from a folder or a single file.\n -# :param pkg_name: Package under ``diffusers.pipelines``.\n -# :param file_names: A list of related file names.\n -# :param use_folder: True → treat ``source`` as a folder with ``_import_structure``.\n -# :return: DocString Entry class.\n -# """ - -# module_location: str | None = import_module("diffusers.pipelines").__file__ -# module_path = os.path.dirname(module_location) - -# for file_name in file_names: -# assert isinstance(file_name, str), f"Expected path to be string, got {file_name} type {type(file_name)}" -# if file_name == "pipeline_stable_diffusion_xl_inpaint": -# continue - -# pkg_path = f"diffusers.pipelines.{package_name}.{file_name}" -# DBUQ(pkg_path) - -# if os.path.exists(os.path.join(module_path, package_name, f"{file_name}.py")): -# pipe_file = import_object_named(file_name, pkg_path) or import_module(pkg_path) or NFO(f"Failed to import {pkg_path}") -# if doc_string := getattr(pipe_file, "EXAMPLE_DOC_STRING", None): -# yield DocStringEntry(package_name=package_name, file_name=file_name, pipe_module=pipe_file, doc_string=doc_string) -# else: -# NFO(f"Doc string attribute missing for {package_name}/{file_name}") -# else: -# NFO(f"Path not found for {package_name}/{file_name}") - -# return - - -# def create_pipe_entry(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: -# """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n -# :param repo_path (str): Repository path. -# :param model_class_obj (str): The model class function -# :raises TypeError: If 'repo_path' or 'class_name' are not set. -# :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. -# """ -# import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name - -# control_net = ["Control", "Controlnet"] # -# mir_prefix = "info" -# if hasattr(diffusers, class_name): -# model_class_obj = getattr(diffusers, class_name) -# sub_segments = show_init_fields_for(model_class_obj, "diffusers") -# decoder = "decoder" in sub_segments -# if repo_path in ["kandinsky-community/kandinsky-3"]: -# mir_prefix = "info.unet" -# if repo_path in ["openai/shap-e"]: -# mir_prefix = "info.unet" -# class_name = "ShapEPipeline" -# elif class_name == "MotionAdapter": -# mir_prefix = "info.lora" -# elif class_name == "WanPipeline": -# mir_prefix = "info.dit" -# elif class_name == "CogVideoXVideoToVideoPipeline": -# class_name = "CogVideoXPipeline" -# elif any(maybe for maybe in control_net if maybe.lower() in class_name.lower()): -# mir_prefix = "info.controlnet" -# else: -# mir_prefix = to_domain_tag(**sub_segments) -# if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: -# NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") -# else: -# mir_prefix = "info." + mir_prefix -# if class_name == "StableDiffusion3InpaintPipeline" or repo_path in ["stabilityai/stable-diffusion-3-medium-diffusers"]: -# class_name = "StableDiffusion3Pipeline" -# repo_path = "stabilityai/stable-diffusion-3.5-medium" -# if class_name == "HunyuanVideoFramepackPipeline" or repo_path in ["hunyuanvideo-community/HunyuanVideo"]: -# class_name = "HunyuanVideoPipeline" -# mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) -# mir_series = mir_prefix + "." + mir_series -# repo_path = migrations(repo_path) -# # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) -# prefixed_data = { -# "repo": repo_path, -# "pkg": {0: {"diffusers": class_name}}, -# # "mode": modalities.get("mode"), -# } -# return mir_series, {mir_comp: prefixed_data} - - -# def tag_pipe(repo_path: str, class_name: str, addendum: dict) -> tuple: -# """Convert model repo pipes to MIR tags, classifying by feature\n -# :param name: Repo path -# :param class_name: The HF Diffusers class for the model -# :return: A segmented MIR tag useful for appending index entries""" -# mir_series, mir_data = create_pipe_entry(repo_path=repo_path, class_name=class_name) -# mir_prefix, mir_series = mir_series.rsplit(".", 1) -# mir_comp = list(mir_data)[0] -# return mir_prefix, mir_series, {mir_comp: addendum} - - -# def find_diffusers_docstrings() -> Generator[list[DocStringEntry]]: -# """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n -# :return: Docstrings for common diffusers models""" -# import diffusers.pipelines as diffusers_pipelines - -# docstring_patterns = EXCLUSIONS -# exclusion_list = docstring_patterns["exclusion_list"] -# uncommon_naming = docstring_patterns["uncommon_naming"] -# for pipe_name in IMPORT_STRUCTURE.keys(): -# if pipe_name not in exclusion_list: -# file_specific = uncommon_naming.get(pipe_name, pipe_name) -# if import_name := getattr(diffusers_pipelines, str(pipe_name)): -# file_names = list(getattr(import_name, "_import_structure", {}).keys()) or [f"pipeline_{file_specific}"] -# yield list(retrieve_diffusers_docstrings(pipe_name, file_names)) -# else: -# continue - - -# def diffusers_index() -> dict[str, dict[str, dict[str, Any]]]: -# """Generate diffusion model data for MIR index\n -# :return: Dictionary ready to be applied to MIR data fields -# """ -# special_repos = { -# "black-forest-labs/FLUX.1-schnell": "black-forest-labs/FLUX.1-dev", -# # "stabilityai/stable-diffusion-3-medium-diffusers": "stabilityai/stable-diffusion-3.5-medium", -# } -# special_classes = { -# # "StableDiffusion3Pipeline": "stabilityai/stable-diffusion-3.5-medium", # NOT sd3 -# "HunyuanDiTPipeline": "tencent-hunyuan/hunyuandiT-v1.2-diffusers", # NOT hyd .ckpt -# "ChromaPipeline": "lodestones/Chroma", -# } -# for class_name, swap_repo in special_classes.items(): -# if parsed_data.pipe_class == class_name: -# parsed_data.pipe_repo = swap_repo -# extracted_docstrings = find_diffusers_docstrings() -# model_info = [extract for pipeline in extracted_docstrings for extract in pipeline] -# pipe_data = {} # pipeline_stable_diffusion_xl_inpaint - -# for extracted in model_info: -# parsed_data: DocParseData = parse_docs(extracted.doc_string) -# if parsed_data is None: -# print(f"Doc string not found in '{extracted.package_name}' in {extracted.file_name}") -# continue -# for class_name, swap_repo in special_classes.items(): -# if parsed_data.pipe_class == class_name: -# parsed_data.pipe_repo = swap_repo -# break -# model_class_obj = import_object_named(parsed_data.pipe_class, extracted.pipe_module.__name__) -# if not model_class_obj: -# continue -# try: -# series, comp_data = create_pipe_entry(parsed_data.pipe_repo, parsed_data.pipe_class) -# except TypeError: -# pass # Attempt 1 -# if pipe_data.get(series): -# if "img2img" in parsed_data.pipe_class.lower(): -# continue -# pipe_data.setdefault(series, {}).update(comp_data) -# special_conditions = special_repos | special_classes -# if parsed_data.staged_class or parsed_data.pipe_repo in list(special_conditions): -# test = special_conditions.get(parsed_data.pipe_repo) -# if test: -# staged_repo = test -# parsed_data.staged_class = parsed_data.pipe_class -# try: -# series, comp_data = create_pipe_entry( -# staged_repo if parsed_data.staged_repo else parsed_data.pipe_repo, -# parsed_data.staged_class # -# if parsed_data.staged_class -# else parsed_data.pipe_class, -# ) -# except TypeError as error_log: -# NFO(series, comp_data) -# NFO(error_log) -# continue # Attempt 2, -# pipe_data.setdefault(series, {}).update(comp_data) -# return dict(pipe_data) - - -# def pull_weight_map(repo_id: str, arch: str) -> Dict[str, str]: -# from nnll.download.hub_cache import download_hub_file - -# model_file = download_hub_file( -# repo_id=f"{repo_id}/tree/main/{arch}", -# source="huggingface", -# file_name="diffusion_pytorch_model.safetensors.index.json", -# local_dir=".tmp", -# ) - - -# @MODE_DATA.decorator -# def add_mode_types(mir_tag: list[str], data: dict | None = None) -> dict[str, list[str] | str]: -# """_summary_\n -# :param mir_tag: _description_ -# :param data: _description_, defaults to None -# :return: _description_""" -# fused_tag = ".".join(mir_tag) - -# mir_details = { -# "mode": data.get(fused_tag, {}).get("pipeline_tag"), -# "pkg_type": data.get(fused_tag, {}).get("library_type"), -# "tags": data.get(fused_tag, {}).get("tags"), -# } -# return mir_details - - -# def generate_pipe_tag(repo_path: str, class_name: str, model_class_obj: Callable | None = None) -> tuple[str, dict[str, dict[Any, Any]]]: -# """Create a pipeline article and generate corresponding information according to the provided repo path and pipeline category\n -# :param repo_path (str): Repository path. -# :param model_class_obj (str): The model class function -# :raises TypeError: If 'repo_path' or 'class_name' are not set. -# :return: Tuple: The data structure containing mir_series and mir_comp is used for subsequent processing. -# """ -# import diffusers # pyright: ignore[reportMissingImports] # pylint:disable=redefined-outer-name - -# if hasattr(diffusers, class_name): -# model_class_obj = getattr(diffusers, class_name) -# sub_segments = show_init_fields_for(model_class_obj, "diffusers") - -# else: -# mir_prefix = to_domain_tag(**sub_segments) -# if mir_prefix is None and class_name not in ["AutoPipelineForImage2Image", "DiffusionPipeline"]: -# NFO(f"Failed to detect type for {class_name} {list(sub_segments)}\n") -# else: -# mir_prefix = "info." + mir_prefix - -# mir_series, mir_comp = list(tag_model_from_repo(repo_path, decoder)) -# mir_series = mir_prefix + "." + mir_series -# repo_path = migrations(repo_path) -# # modalities = add_mode_types(mir_tag=[mir_series, mir_comp]) -# prefixed_data = { -# "repo": repo_path, -# "pkg": {0: {"diffusers": class_name}}, -# # "mode": modalities.get("mode"), -# } -# return mir_series, {mir_comp: prefixed_data} - - -# def write_to_mir(new_data: dict, mir_db: MIRDatabase) -> None: -# """Generate MIR HF Hub model database -# :param new_data: Data for the MIR database -# :param mir_database: MIRDatabase instance -# """ -# for series, comp_name in new_data.items(): -# id_segment = series.split(".") -# for compatibility in comp_name: -# # dbug(id_segment) -# try: -# mir_db.add( -# mir_entry( -# domain=id_segment[0], -# arch=id_segment[1], -# series=id_segment[2], -# comp=compatibility, -# **new_data[series][compatibility], -# ), -# ) -# except IndexError: # as error_log: -# NFO(f"Failed to create series: {series} compatibility: {comp_name} ") -# # dbug(error_log) diff --git a/mir/_deprecated/_schedulers.py b/mir/_deprecated/_schedulers.py deleted file mode 100644 index e415427..0000000 --- a/mir/_deprecated/_schedulers.py +++ /dev/null @@ -1,74 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import re -from importlib import import_module - -from mir.generate.diffusers import IMPORT_STRUCTURE -from mir.maid import MIRDatabase -from mir.spec import mir_entry - - -def tag_scheduler(series_name: str) -> tuple[str, str]: - """Create a mir label from a scheduler operation\n - :param class_name: Known period-separated prefix and model type - :return: The assembled mir tag with compatibility pre-separated""" - - comp_name = None - patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] - for scheduler in patterns: - compiled = re.compile(scheduler) - match = re.search(compiled, series_name) - if match: - comp_name = match.group() - comp_name = comp_name.lower() - break - for pattern in patterns: - series_name = re.sub(pattern, "", series_name) - series_name.lower() - assert series_name is not None, "Expected series tag but got None" - assert comp_name is not None, "Expected compatibility tag but got None" - return series_name, comp_name - - -def add_schedulers(mir_db: MIRDatabase): - """Create mir info database""" - - for class_name in IMPORT_STRUCTURE["schedulers"]: - if class_name != "SchedulerMixin": - series_name, comp_name = tag_scheduler(class_name) - class_obj = import_module("diffusers.schedulers") - class_path = getattr(class_obj, class_name).__module__ - mir_db.add( - mir_entry( - domain="ops", - arch="scheduler", - series=series_name, - comp=comp_name.lower(), - pkg={ - 0: { - "diffusers": class_name, - "module_path": class_path, - }, - }, - ) - ) - - class_name = "KarrasDiffusionSchedulers" - series_name, comp_name = tag_scheduler(class_name) - class_obj = import_module("diffusers.schedulers.scheduling_utils") - class_path = getattr(class_obj, class_name).__module__ - mir_db.add( - mir_entry( - domain="ops", - arch="scheduler", - series=series_name, - comp=comp_name, - pkg={ - 0: { - "diffusers": class_name, - "module_path": class_path, - }, - }, - ), - ) diff --git a/mir/generate/_tasks.py b/mir/generate/_tasks.py index 5c746ef..32961ae 100644 --- a/mir/generate/_tasks.py +++ b/mir/generate/_tasks.py @@ -4,7 +4,6 @@ from typing import Any, Callable, List from mir.generate.diffusers.raw_data import DPrepareData -from mir.generate.diffusers.schedulers import tag_scheduler from mir import DBUQ from mir.tag import MIRTag @@ -88,6 +87,7 @@ async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str) -> :param pipe_role: Role of the class in the pipeline :param series: Series identifier for the component :return: Tuple containing MIR tag and class name""" + from mir.generate.diffusers.schedulers import tag_scheduler mir_tag = None class_name = pipe_class.__name__ diff --git a/mir/generate/diffusers/harvest.py b/mir/generate/diffusers/harvest.py index db40d91..e0a697c 100644 --- a/mir/generate/diffusers/harvest.py +++ b/mir/generate/diffusers/harvest.py @@ -3,92 +3,46 @@ from importlib import import_module from inspect import getmro -from typing import Any, Callable, get_type_hints +from typing import get_type_hints from mir.generate.diffusers.raw_data import DPrepareData -from mir.package import MIRNesting, MIRPackage -from mir.tag import MIRTag -class HarvestClasses: +class HarvestLoop: def __init__(self) -> None: """Initializes the HarvestClasses instance with an empty list to store raw class data.""" + from mir.generate.transformers.harvest import HarvestLoop + from mir.maid import MIRDatabase self.db = MIRDatabase() - self.raw_data = [] - self.find_diffusers_docstrings() - - def find_diffusers_docstrings(self) -> None: - """Pull down docstrings from 🤗Diffusers pipelines, minimizing internet requests\n - :return: Docstrings for common diffusers models""" - - # from mir.generate.tasks import TaskAnalyzer + self.harvest_tf = HarvestLoop() - subclasses = self.extract_subclass_data("diffusers", "DiffusionPipeline") - for module_path, model in subclasses.items(): - if not (base_data := self.extract_base_data(module_path)): - continue - if not (model_data := self.extract_model_class_data(model)): - continue - if not (prepared_data := DPrepareData(**base_data, **model_data)): - continue - mir_tag = MIRTag(prepared_data) - # task_analysis = TaskAnalyzer(prepared_data=prepared_data, mir_tag=mir_tag) - mir_nest = MIRNesting(mir_tag, prepared_data) - packages = {"model": MIRPackage(data=prepared_data.model)} - for component_name, component_model in prepared_data.model_params.items(): - if hasattr(prepared_data, component_name): - packages.setdefault(component_name, MIRPackage(data=component_model)) - packages.setdefault("framework", MIRPackage(data=mir_nest.framework_data)) - # print(packages) - mir_nest(packages) - - self.db.add_data(mir_nest, *mir_nest.loops) - - def extract_base_data(self, module_path: str) -> dict[str, str] | None: + def __call__(self) -> None: from mir.data import EXCLUSIONS - if module_path.rsplit(".", 1)[-1] in EXCLUSIONS["exclusion_list"]: - return None - base_path = module_path.rsplit(".", 1)[0] - model_path = import_module(base_path) - if doc_string := getattr(model_path, "EXAMPLE_DOC_STRING", None): - return { - "doc_string": doc_string, - "model_path": base_path, - } - return None - - def extract_model_class_data(self, model: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: - model_name: str = model.__name__ - library: str = model.__module__.split(".", 1)[0] - model_params: dict[str, Any] = get_type_hints(model.__init__) - for module in model_params.values(): - module_name = module.__module__ - library_path = f"{library}.models." - if library_path in module_name: - module_name = module_name.replace(library_path, "").split(".")[0] - return { - "model": model, - "model_name": model_name, - "model_params": model_params, - "library": library, - } - return None + prepared_data = {} + library = "diffusers" + subclasses = self.extract_subclass_data(library, "DiffusionPipeline") # diffusers.pipelines. + for module_path, pipeline in subclasses.items(): + if module_path.rsplit(".", 1)[-1] not in EXCLUSIONS["exclusion_list"]: + loop_parameters = get_type_hints(pipeline.__init__) + loop_parameters.setdefault("pipeline", pipeline) + for name, self.model in loop_parameters.items(): + if prepare_data := self.prepare_class_data(): + prepared_data.setdefault(name, prepare_data) + for data in prepared_data: + pass + + def prepare_class_data(self): + prepared_data = DPrepareData(model=self.model) + return prepared_data def extract_subclass_data(self, package_name: str, base_class_name: str): - """ - Return a dict mapping `.` → class object + """Return a dict mapping `.` → class object for every class in `package_name` that subclasses a class named - `base_class_name`. + `base_class_name`.""" - The implementation is intentionally defensive: it avoids - triggering `__getattr__` on lazy‑loaded submodules that might - raise a `RuntimeError`. Instead of `inspect.getmembers`, it - iterates over the module's `__dict__` which contains only - attributes that have already been imported. - """ from pkgutil import walk_packages results = {} diff --git a/mir/generate/diffusers/package.py b/mir/generate/diffusers/package.py new file mode 100644 index 0000000..9c08f39 --- /dev/null +++ b/mir/generate/diffusers/package.py @@ -0,0 +1,69 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from types import ModuleType +from typing import Callable +from dataclasses import dataclass, field + + +@dataclass +class MIRPackage: + model_type: str + model: Callable | str | dict[str, str] + model_path: ModuleType + package: dict[str, str] = field(init=False, default_factory=dict[str, str]) + + def __post_init__(self): + self.package = {} + self.model_name: str = self.model.__name__ + self.model_path: ModuleType = self.model.__module__ + if not isinstance(self.data, dict): + self.generate_package() + self.generate_repo() + + def generate_repo(self): + from mir.data import MIGRATIONS + + if self.model_type in ["unet", "transformer"] and (doc_string := getattr(self.model_path, "EXAMPLE_DOC_STRING", None)): + if repo := MIGRATIONS["migrated_pipes"].get(self.model_name, False): + self.repo = repo + elif self.model_type not in ["scheduler", "vae", "tokenizer"]: + self.process_doc_string(doc_string=doc_string) + + def generate_package(self) -> None: + """Generates package information for the MIR tag based on class. + :param pkg: A class object (model, tokenizer, etc) to build a tag from""" + model = f"{self.model_path}.{self.model_name}" + self.package: dict[str, str] = {"model": model} + + def config_to_repo(self, config_class: Callable) -> str | None: + """Extracts the repository path from the configuration class documentation.\n + :param config_class: Configuration class to extract repository path from. + :return: Repository path as a string if found, otherwise None.""" + import re + + from mir import NFO + + doc_check = [config_class] + if hasattr(config_class, "forward"): + doc_check.append(config_class.forward) # type: ignore + for pattern in doc_check: + doc_string = pattern.__doc__ + matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore + if matches: + try: + return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + NFO(f"ERROR >>{matches} : LOG >> {error_log}") + continue + + def process_doc_string(self, doc_string: str) -> None: + from mir.generate.diffusers.doc_parse import DocStringParser + + doc_parser = DocStringParser(doc_string=doc_string, model=self.model, model_path=self.model_path) + doc_parser.parse() + if repo_path := doc_parser.pipe_repo: + self.repo_path = repo_path + if staged_repo := doc_parser.staged_repo: + self.staged_repo = staged_repo diff --git a/mir/generate/diffusers/raw_data.py b/mir/generate/diffusers/raw_data.py index e86dbfb..26170e8 100644 --- a/mir/generate/diffusers/raw_data.py +++ b/mir/generate/diffusers/raw_data.py @@ -3,55 +3,22 @@ from dataclasses import dataclass, field -from typing import Callable, get_type_hints +from typing import Callable @dataclass class DPrepareData: - doc_string: str + """Represents a structured entry of the name of the class and its associated attributes.""" + model: Callable - model_path: str - library: str - model_name: str model_params: dict[str, list[str]] = field(init=True, default_factory=lambda: {"": [""]}) - repo_path: str = field(init=False, default_factory=str) - staged_repo: str | None = field(init=False, default_factory=str) - tasks: list[str] = field(init=False, default_factory=lambda: [""]) - name: str = field(init=False, default_factory=str) - - def __post_init__(self) -> None: - from mir.data import MIGRATIONS - from mir.generate.diffusers.doc_parse import DocStringParser - - doc_parser = DocStringParser(doc_string=self.doc_string, model=self.model, model_path=self.model_path) - doc_parser.parse() - if repo_path := MIGRATIONS["migrated_pipes"].get(self.model.__name__, False): - self.repo_path = repo_path - else: - if repo_path := doc_parser.pipe_repo: - self.repo_path = repo_path - if staged_repo := doc_parser.staged_repo: - self.staged_repo = staged_repo - self.show_diffusers_tasks() - for name, model in self.model_params.items(): - setattr(self, name, model) - print(name, model) - - def show_diffusers_tasks(self) -> None: - """Return Diffusers task pipes based on package-specific query\n - :param class_name: To find task pipes from a Diffusers class pipe, defaults to None - :param code_name: To find task pipes from a Transformers class pipe, defaults to None - :return: A list of alternate class pipelines derived from the specified class""" - from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS - alt_tasks = set({}) - self.internal_name = self.model_path.rsplit(".", 2)[-1] - for task_map in SUPPORTED_TASKS_MAPPINGS: - task_class = GET_TASK_CLASS(task_map, self.model, False) - if task_class: - alt_tasks.add(task_class.__name__) - for model_code, pipe_class_obj in task_map.items(): - if self.internal_name in model_code: - alt_tasks.add(pipe_class_obj.__name__) + model_name: str = field(init=False) + library: str = field(init=False) + import_path: str = field(init=False) - self.tasks = [x for x in alt_tasks] + def __post_init__(self): + """Initializes the DPrepareData instance by setting derived attributes.""" + self.model_name: str = self.model.__name__ + self.import_path: str = self.model.__module__.rsplit(".", 1)[0] + self.library: str = self.import_path.split(".")[0] diff --git a/mir/generate/diffusers/tasks.py b/mir/generate/diffusers/tasks.py new file mode 100644 index 0000000..068b126 --- /dev/null +++ b/mir/generate/diffusers/tasks.py @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from dataclasses import dataclass, field +from typing import Callable + + +@dataclass +class CollectTasks: + model: Callable + import_path: str + tasks: list[str] = field(init=False) + + def __post_init__(self) -> None: + self.model_to_tasks() + + def model_to_tasks(self) -> None: + """Return Diffusers task pipes based on package-specific query\n + :param class_name: To find task pipes from a Diffusers class pipe, defaults to None + :param code_name: To find task pipes from a Transformers class pipe, defaults to None + :return: A list of alternate class pipelines derived from the specified class""" + from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS + + alt_tasks = set({}) + self.internal_name = self.import_path.rsplit(".", 2)[-1] + for task_map in SUPPORTED_TASKS_MAPPINGS: + task_class = GET_TASK_CLASS(task_map, self.model, False) + if task_class: + alt_tasks.add(task_class.__name__) + for model_code, pipe_class_obj in task_map.items(): + if self.internal_name in model_code: + alt_tasks.add(pipe_class_obj.__name__) + + self.tasks = [x for x in alt_tasks] diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py index 90de8f6..5b8525d 100644 --- a/mir/generate/transformers/harvest.py +++ b/mir/generate/transformers/harvest.py @@ -1,108 +1,44 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import Any, Callable +from typing import Callable -from mir.package import MIRNesting, MIRPackage from mir.generate.transformers.raw_data import PrepareData -from mir.tag import MIRTag -class HarvestClasses: +class HarvestLoop: def __init__(self) -> None: """Initializes the HarvestClasses instance with an empty list to store raw class data.""" from mir.maid import MIRDatabase self.db = MIRDatabase() - self.find_transformers_classes() - def find_transformers_classes(self) -> None: - """Finds and collects PrepareData entries for all transformer classes defined in AUTO_MAP.\n - :return: List of PrepareData entries representing the transformer classes.""" + def __call__(self) -> None: from mir.generate.transformers import AUTO_MAP - - for config_class, model_class in AUTO_MAP.items(): # type: ignore - if isinstance(model_class, tuple): - model_class: Callable = model_class[0] - if not (config_data := self.extract_config_class_data(config_class)): - continue - if not (model_data := self.extract_model_class_data(model_class)): - continue - if not (prepared_data := PrepareData(**config_data, **model_data)): # type:ignore , _Lazyautomapping tuple - continue - - mir_tag = MIRTag(prepared_data) - mir_nest = MIRNesting(mir_tag, prepared_data) - - packages = {"model": MIRPackage(data=prepared_data.model)} - if hasattr(prepared_data, "tokenizer") and prepared_data.tokenizer: - packages.setdefault("tokenizer", MIRPackage(data=prepared_data.tokenizer)) # type: ignore , _Lazyautomapping tuple - packages.setdefault("framework", MIRPackage(data=mir_nest.framework_data)) - mir_nest(packages) - - self.db.add_data(mir_nest, *mir_nest.loops) - - def extract_config_class_data(self, config_class: Callable) -> dict[str, str | Callable | dict[str, Any]] | None: - """Extracts information from config classes.\n - :param config_class: Model class or callable returning model classes. - :return: dictionary of discovered elements""" - from mir.data import MIGRATIONS, PARAMETERS + from mir.generate.transformers import TOKENIZER_MAPPING + + prepared_data = {} + for config_class, model_data in AUTO_MAP.items(): + assert isinstance(config_class, Callable) + loop_parameters = {"model": (model_data, config_class)} + if tokenizer := TOKENIZER_MAPPING.get(config_class, None): + loop_parameters.setdefault("tokenizer", (tokenizer, tokenizer)) # type: ignore + for name, (self.model, self.config) in loop_parameters.items(): + if prepare_data := self.prepare_class_data(): # type: ignore + prepared_data.setdefault(name, prepare_data) + for data in prepared_data: + pass + + def prepare_class_data(self) -> PrepareData | None: + """Extract and collect information from model and config classes.\n + :return: A PrepareData entry representing the transformer class.""" + from mir.data import PARAMETERS from mir.generate.from_module import show_init_fields_for - config_name = config_class.__name__ - config_params = PARAMETERS.get(config_name, {}) - if not config_params: - config_params = show_init_fields_for(config_class) - repo_path = MIGRATIONS["config"].get(config_name, {}) - if not repo_path: - repo_path = self.config_to_repo(config_class) - if not repo_path or not config_params: - return None - elif "inspect" in config_params or "deprecated" in config_params: - return None - return { - "name": config_name, - "config": config_class, - "config_params": config_params, - "repo_path": repo_path, - } - - def extract_model_class_data(self, model_class: Callable) -> dict[str, str | Any] | None: - """Extracts information from model classes.\n - :param model_class: Model class or callable returning model classes. - :return: dictionary of discovered elements""" - from mir.generate.from_module import show_init_fields_for # Ensure it's a tuple for consistency. - - model_data: dict[str, str | Any] = {"model": model_class} - model_params = show_init_fields_for(model_class) - if "inspect" in model_params or "deprecated" in model_params: + config_name = self.config.__name__ + config_params = PARAMETERS.get(config_name, show_init_fields_for(self.config)) + if any(x in config_params for x in ["inspect", "deprecated"]): return None - else: - return model_data | { - "model_params": model_params, - } - - def config_to_repo(self, config_class: Callable) -> str | None: - """Extracts the repository path from the configuration class documentation.\n - :param config_class: Configuration class to extract repository path from. - :return: Repository path as a string if found, otherwise None.""" - import re - - from mir import NFO - - doc_check = [config_class] - if hasattr(config_class, "forward"): - doc_check.append(config_class.forward) # type: ignore - for pattern in doc_check: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore - if matches: - try: - return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - NFO(f"ERROR >>{matches} : LOG >> {error_log}") - continue - - -if __name__ == "__main__": - HarvestClasses() + if isinstance(self.model, tuple): + self.model_class: Callable = self.model[0] + return PrepareData(model=self.model, **config_params) # type: ignore diff --git a/mir/generate/transformers/package.py b/mir/generate/transformers/package.py new file mode 100644 index 0000000..148aded --- /dev/null +++ b/mir/generate/transformers/package.py @@ -0,0 +1,56 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + + +from typing import Callable, ModuleType +from dataclasses import dataclass, field + + +@dataclass +class MIRPackage: + config: Callable + model: Callable + package: dict[str, str] = field(init=False, default_factory=dict[str, str]) + + def __post_init__(self): + self.package = {} + self.model_name: str = self.model.__name__ + self.model_path: ModuleType = self.model.__module__ + if not isinstance(self.config, dict): + self.generate_package() + self.generate_repo() + + def generate_repo(self) -> None: + from mir.data import MIGRATIONS + + if repo := MIGRATIONS["config"].get(self.config.__name__, {}): + self.repo = repo + else: + self.repo = self.config_to_repo(self.config) + + def generate_package(self) -> None: + """Generates package information for the MIR tag based on class. + :param pkg: A class object (model, tokenizer, etc) to build a tag from""" + model = f"{self.model_type}.{self.model_name}" + self.package: dict[str, str] = {"model": model} + + def config_to_repo(self) -> str | None: + """Extracts the repository path from the configuration class documentation.\n + :param config_class: Configuration class to extract repository path from. + :return: Repository path as a string if found, otherwise None.""" + import re + + from mir import NFO + + doc_check = [self.config] + if hasattr(self.config, "forward"): + doc_check.append(self.config.forward) # type: ignore + for pattern in doc_check: + doc_string = pattern.__doc__ + matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore + if matches: + try: + return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + NFO(f"ERROR >>{matches} : LOG >> {error_log}") + continue diff --git a/mir/generate/transformers/raw_data.py b/mir/generate/transformers/raw_data.py index 0664c45..02bbd11 100644 --- a/mir/generate/transformers/raw_data.py +++ b/mir/generate/transformers/raw_data.py @@ -1,47 +1,24 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # - +from typing import Callable from dataclasses import dataclass, field -from typing import Callable, Any @dataclass class PrepareData: """Represents a structured entry of the name of the class and its associated attributes.""" - name: str model: Callable - config: type - repo_path: str config_params: dict[str, list[str]] - model_params: dict[str, list[str]] | None = field(init=True, default_factory=lambda: {"": [""]}) - tasks: list[str] = field(init=False, default_factory=lambda: [""]) + config: Callable | None = None + + model_name: str = field(init=False) + library: str = field(init=False) + import_path: str = field(init=False) def __post_init__(self) -> None: """Initializes the PrepareData instance by setting derived attributes.""" - from mir.generate.transformers import REVERSE_MAP, TOKENIZER_MAPPING - - self.model_name: str = self.model.__name__.split(".")[-1] - if tokenizer := TOKENIZER_MAPPING.get(self.config, None): - self.tokenizer: tuple[type[Any] | None, type[Any] | None] = tokenizer - if internal_name := REVERSE_MAP.get(self.config): - self.internal_name = internal_name - self.library = self.model.__module__.split(".")[0] - self.model_to_tasks() - - def model_to_tasks(self) -> None: - """Transform a single model class into derivative classes for specific tasks.\n - :return: A list of task classes associated with the model.""" - from pathlib import Path - from importlib import import_module - - import_path = Path(self.model.__module__).stem - parent_module = import_module(import_path) - self.tasks = [] - if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": - for module in parent_module.__all__: - if (module.lower() != module) and (module != self.model_name) and (module != self.config.__name__): - self.tasks.append(module) - else: - self.tasks = [self.model.__name__] + self.model_name: str = self.model.__name__ + self.import_path = self.model.__module__.rsplit(".", 1)[0] + self.library = self.import_path.split(".")[0] diff --git a/mir/generate/transformers/tasks.py b/mir/generate/transformers/tasks.py new file mode 100644 index 0000000..be9cf81 --- /dev/null +++ b/mir/generate/transformers/tasks.py @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from dataclasses import dataclass, field +from typing import Callable + + +@dataclass +class CollectTasks: + model: Callable + import_path: str + config: Callable + tasks: list[str] = field(init=False) + + def __post_init__(self) -> None: + self.model_to_tasks() + + def model_to_tasks(self) -> None: + """Transform a single model class into derivative classes for specific tasks.\n + :return: A list of task classes associated with the model.""" + from importlib import import_module + + model_name = self.model.__name__ + + parent_module = import_module(self.import_path) + self.tasks = [] + if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": + for module in parent_module.__all__: + if (module.lower() != module) and (module != model_name) and (module != self.config.__name__): + self.tasks.append(module) + else: + self.tasks = [model_name] diff --git a/mir/package.py b/mir/package.py index 97187e9..7269fab 100644 --- a/mir/package.py +++ b/mir/package.py @@ -8,31 +8,6 @@ from mir.tag import MIRTag -@dataclass -class MIRPackage: - data: Callable | str | dict[str, str] - package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - - def __init__(self, data: Callable | str | dict[str, str] | dict[str, Any]): - self.package = {} - self.data = data - if not isinstance(self.data, dict): - self.generate_package() - else: - self.add_framework(self.data) - - def generate_package(self) -> None: - """Generates package information for the MIR tag based on class. - :param pkg: A class object (model, tokenizer, etc) to build a tag from""" - self.domain = "ops" - model = f"{self.data.__module__}.{self.data.__name__}" - self.package: dict[str, str] = {"model": model} - - def add_framework(self, framework_data) -> None: - self.domain = "info" - self.package = framework_data - - class MIRNesting: """Build tag components from the extracted data\n :param mir_tag: An instance of MIR tag with the necessary information @@ -55,7 +30,7 @@ def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData | DPrepareData) - self.loops = [] self.framework_data = {} - def __call__(self, packages: dict[str, MIRPackage]) -> None: + def __call__(self, packages: MIRPackage) -> None: """Common routine for handling a package: store tag data, nest the package, and record the name of the newly-created attribute.\n :param name: Identification string to store data underneath @@ -64,6 +39,7 @@ def __call__(self, packages: dict[str, MIRPackage]) -> None: for name, mir_package in packages.items(): is_framework = name == "framework" is_model = name == "model" + is_tokenizer = name == "tokenizer" if is_framework: package_data = {self.prepared_data.library: mir_package.package} diff --git a/mir/tag.py b/mir/tag.py index 82f7b8b..4d49e83 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -2,9 +2,9 @@ # from dataclasses import dataclass, field - -from mir.generate.transformers.raw_data import PrepareData -from mir.generate.diffusers.raw_data import DPrepareData +from typing import Callable +# from mir.generate.transformers.raw_data import PrepareData +# from mir.generate.diffusers.raw_data import DPrepareData @dataclass @@ -18,20 +18,30 @@ class MIRTag: comp The compatibility component of the MIR tag (generated, optional). """ - raw_data: PrepareData | DPrepareData + domain: str = field(init=False) arch: str = field(init=False) series: str = field(init=False) decoder: bool = False def __post_init__(self) -> None: """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" + self.generate_domain() self.generate_arch() self.generate_series_and_comp(repo_path=self.raw_data.repo_path) + if hasattr(self, "comp"): + self.flat = f"{self.domain}.{self.arch}.{self.series}.{self.comp}" + else: + self.flat = f"{self.domain}.{self.arch}.{self.series}" + + def generate_domain(self) -> None: + if isinstance(self.raw_data.model, Callable): + self.domain = "ops" + else: + self.domain = "info" def generate_arch(self) -> None: """Generates the architecture part of the MIR tag based on prepared data.\n :raises ValueError: If no suitable tag can be determined.""" - arch = None library = self.raw_data.model.__module__.split(".")[0] if hasattr(self.raw_data, "config_params"): diff --git a/tests/old/test_class_parent.py b/tests/old/test_class_parent.py deleted file mode 100644 index cbd729d..0000000 --- a/tests/old/test_class_parent.py +++ /dev/null @@ -1,35 +0,0 @@ -# # # -# # # - -import pytest -from mir.inspect.parenting import class_parent # Replace with the actual module name - - -def test_class_parent_diffusers(): - assert class_parent("stable-diffusion", "Diffusers") == ["diffusers", "pipelines", "stable_diffusion"] - - -def test_class_parent_transformers(): - assert class_parent("albert", "Transformers") == ["transformers", "models", "albert"] - - -def test_class_parent_invalid_parent(): - with pytest.raises(KeyError): - class_parent("unknown", "Unknown") - - -def test_class_parent_empty_parent(): - with pytest.raises(KeyError): - assert class_parent("", "") == ["", "", ""] - - -def test_class_parent_bad_code_name(): - assert class_parent("diffdusers", "diffusers") is None - - -def test_class_parent_mixed_case(): - assert class_parent("sana", "DIFFusERS") == ["diffusers", "pipelines", "sana"] - - -if __name__ == "__main__": - pytest.main(["-vv", __file__]) diff --git a/tests/old/test_deconstructors_root.py b/tests/old/test_deconstructors_root.py deleted file mode 100644 index 67a0bed..0000000 --- a/tests/old/test_deconstructors_root.py +++ /dev/null @@ -1,22 +0,0 @@ -# # # -# # # - -import pytest -from mir.config.constants import extract_init_parameters - - -def test_root_class_with_builtin_types(): - class DummyInitModule: - def __init__(self): - pass - - expected_output = {} - - result = extract_init_parameters(DummyInitModule) - assert result == expected_output - - -if __name__ == "__main__": - import pytest - - pytest.main(["-vv", __file__]) diff --git a/tests/old/test_doc_parser.py b/tests/old/test_doc_parser.py deleted file mode 100644 index 3178d41..0000000 --- a/tests/old/test_doc_parser.py +++ /dev/null @@ -1,143 +0,0 @@ -import unittest -from mir.doc_parser import parse_docs - - -class TestDocParser(unittest.TestCase): - def test_parse_simple_case(self): - doc_string = """ - >>> pipe = MyPipeline.from_pretrained("model/repo") - """ - result = parse_docs(doc_string) - self.assertEqual(result.pipe_class, "MyPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "model/repo") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_with_variable_resolution(self): - doc_string = """ - model_id = "custom/model" - >>> pipe = MyPipeline.from_pretrained(model_id) - """ - result = parse_docs(doc_string) - self.assertEqual(result.pipe_class, "MyPipeline") - self.assertEqual(result.pipe_repo, "custom/model") - - def test_parse_staged_case(self): - doc_string = """ - >>> pipe = MyPipeline.from_pretrained("model/repo") - >>> prior_pipe = PriorPipeline.from_pretrain("prior/repo") - """ - result = parse_docs(doc_string) - self.assertEqual(result.pipe_class, "MyPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "model/repo") # repo_path - self.assertEqual(result.staged_class, "PriorPipeline") # staged_class - self.assertEqual(result.staged_repo, "prior/repo") # staged_repo - - def test_parse_no_match(self): - doc_string = """ - >>> something_else = SomeClass.do_something() - """ - result = parse_docs(doc_string) - self.assertIsNone(result) # pipe_class - - def test_parse_multiline_doc(self): - doc_string = """ - # model_id_or_path = "another/repo" - >>> pipe_prior = PriorPipeline.from_pretrain(model_id_or_path) - >>> pipeline = MyPipeline.from_pretrained("repo/path") - """ - result = parse_docs(doc_string) - self.assertEqual(result.pipe_class, "MyPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "repo/path") # repo_path - self.assertEqual(result.staged_class, "PriorPipeline") # staged_class - self.assertEqual(result.staged_repo, "another/repo") # staged_repo - - def test_parse_blip(self): - from diffusers.pipelines.blip_diffusion.pipeline_blip_diffusion import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "BlipDiffusionPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "Salesforce/blipdiffusion") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_pia(self): - from diffusers.pipelines.pia.pipeline_pia import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "PIAPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "openmmlab/PIA-condition-adapter") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_animatediff_xl(self): - from diffusers.pipelines.animatediff.pipeline_animatediff_sdxl import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "AnimateDiffSDXLPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_animatediff_controlnet(self): - from diffusers.pipelines.animatediff.pipeline_animatediff_controlnet import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - # TODO : This ought to return control net data but its missing in the docstring - - # self.assertEqual(result.pipe_class, "ControlNetModel") # pipe_class - # self.assertEqual(result.pipe_repo, "lllyasviel/ControlNet-v1-1") # repo_path - # self.assertIsNone(result.staged_class) # staged_class - # self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_consistency(self): - from diffusers.pipelines.consistency_models.pipeline_consistency_models import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "ConsistencyModelPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "openai/diffusers-cd_imagenet64_l2") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_pixart_sigma(self): - from diffusers.pipelines.pixart_alpha.pipeline_pixart_sigma import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "PixArtSigmaPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS") # repo_path - self.assertIsNone(result.staged_class) # staged_class - self.assertIsNone(result.staged_repo) # staged_repo - - def test_parse_cascade(self): - from diffusers.pipelines.stable_cascade.pipeline_stable_cascade import EXAMPLE_DOC_STRING - - result = parse_docs(EXAMPLE_DOC_STRING) - self.assertEqual(result.pipe_class, "StableCascadePriorPipeline") # pipe_class - self.assertEqual(result.pipe_repo, "stabilityai/stable-cascade-prior") # repo_path - self.assertEqual(result.staged_class, "StableCascadeDecoderPipeline") # staged_class - self.assertEqual(result.staged_repo, "stabilityai/stable-cascade") # staged_repo - - def test_parse_xl(self): - from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl import EXAMPLE_DOC_STRING - from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl_inpaint import EXAMPLE_DOC_STRING as EXAMPLE_DOC_STRING_INPAINT - - doc_strings = [ - EXAMPLE_DOC_STRING, - EXAMPLE_DOC_STRING_INPAINT, - ] - result = [] - for doc in doc_strings: - result.append(parse_docs(doc)) - - self.assertEqual(result[0].pipe_class, "StableDiffusionXLPipeline") # pipe_class - self.assertEqual(result[0].pipe_repo, "stabilityai/stable-diffusion-xl-base-1.0") # repo_path - self.assertIsNone(result[0].staged_class) # staged_class - self.assertIsNone(result[0].staged_repo) # staged_repo - self.assertEqual(result[1].pipe_class, "StableDiffusionXLInpaintPipeline") # pipe_class - self.assertEqual(result[1].pipe_repo, "stabilityai/stable-diffusion-xl-base-1.0") # repo_path - self.assertIsNone(result[1].staged_class) # staged_class - self.assertIsNone(result[1].staged_repo) # staged_repo - - -if __name__ == "__main__": - unittest.main() diff --git a/tests/old/test_find_docstring_run.py b/tests/old/test_find_docstring_run.py deleted file mode 100644 index 952c5a5..0000000 --- a/tests/old/test_find_docstring_run.py +++ /dev/null @@ -1,5 +0,0 @@ -from mir.inspect.metadata import find_diffusers_docstrings -from pprint import pprint - -find_diffusers_docstrings() -list(find_diffusers_docstrings()) diff --git a/tests/old/test_gather_diffusers_metadata.py b/tests/old/test_gather_diffusers_metadata.py deleted file mode 100644 index e628720..0000000 --- a/tests/old/test_gather_diffusers_metadata.py +++ /dev/null @@ -1,49 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# -import pytest -from unittest.mock import Mock - - -@pytest.fixture -def mock_import_module(mocker): - """Fixture to mock import_module and simulate different module scenarios.""" - return mocker.patch("mir.config.conversion.import_submodules") - - -@pytest.fixture -def mock_pkgutil_iter_modules(mocker): - """Fixture to mock pkgutil.iter_modules for controlled testing.""" - - return mocker.patch( - "pkgutil.iter_modules", - return_value=[ - (Mock(), "allegro", True), - (Mock(), "amused", True), - (Mock(), "animatediff", True), - (Mock(), "audioldm", True), - (Mock(), "cogvideo", True), - (Mock(), "deepfloyd_if", True), - ], - ) - - -def test_list_diffusers_models(): - from mir.inspect.metadata import find_diffusers_docstrings - - find_diffusers_docstrings() - - -def test_find_docstrings_excluded(mock_import_module, mock_pkgutil_iter_modules): - """Test that excluded modules are not processed.""" - from mir.inspect.metadata import find_diffusers_docstrings - - excluded_modules = ["ddpm"] - - def side_effect(import_name, *args, **kwargs): - if any(exc in import_name for exc in excluded_modules): - raise ImportError(f"Module {import_name} is excluded.") - return Mock() - - mock_import_module.side_effect = side_effect - results = list(find_diffusers_docstrings()) # type: ignore # noqa - assert not any("ddpm" in call_arg[0][0] for call_arg in mock_import_module.call_args_list) diff --git a/tests/old/test_json_io.py b/tests/old/test_json_io.py deleted file mode 100644 index cc68cb8..0000000 --- a/tests/old/test_json_io.py +++ /dev/null @@ -1,42 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -import os -import unittest -from tempfile import TemporaryDirectory -from mir.config.json_io import write_json_file, read_json_file - - -class TestFileOperations(unittest.TestCase): - def setUp(self): - """Create a temporary directory to store the test files""" - self.temp_dir = TemporaryDirectory() - self.file_name = "test_data.json" - self.file_path = os.path.join(self.temp_dir.name, self.file_name) - self.test_data = { - "key1": "value1", - "key2": 69, # nice - "key3": [1, 2, 3], - } - - def test_write_and_read_json_file(self): - """Write data to a JSON file, Read data back from the JSON file,Assert that the written and read data are the same""" - write_json_file(self.temp_dir.name, self.file_name, self.test_data) - read_data = read_json_file(self.file_path) - self.assertEqual(read_data, self.test_data) - - def test_read_nonexistent_file(self): - """Test reading a non-existent file should raise FileNotFoundError""" - with self.assertRaises(FileNotFoundError): - read_json_file("non_existent_file.json") - - def tearDown(self): - """Clean up the temporary directory""" - self.temp_dir.cleanup() - - -if __name__ == "__main__": - import pytest - - pytest.main(["-vv", __file__]) diff --git a/tests/old/test_mir_db_create_restore.py b/tests/old/test_mir_db_create_restore.py deleted file mode 100644 index b927cb0..0000000 --- a/tests/old/test_mir_db_create_restore.py +++ /dev/null @@ -1,160 +0,0 @@ -# # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# # - -# import os -# from pathlib import Path -# from mir.config.constants import MIR_PATH_NAMED - - -# def test_mir_creation(): -# from mir.spec import mir_entry -# from pprint import pprint - -# os.remove(MIR_PATH_NAMED) -# Path().touch() - -# entry = mir_entry( -# domain="info", -# arch="unet", -# series="stable-diffusion-xl", -# comp="base", -# repo="stabilityai/stable-diffusion-xl", -# pkg={ -# 0: { -# "diffusers": "class_name", -# "generation": {"num_inference_steps": 40, "denoising_end": 0.8, "output_type": "latent", "safety_checker": False}, -# } -# }, -# ) -# entry.update( -# mir_entry( -# domain="model", -# arch="unet", -# series="stable-diffusion-xl", -# comp="base", -# file_path="/Users/nyan/Documents/models", -# ), -# ) -# entry.update( -# mir_entry( -# domain="ops", -# arch="scheduler", -# series="align-your-steps", -# comp="stable-diffusion-xl", -# pkg={ -# 0: { -# "diffusers.schedulers.scheduling_utils": { -# "AysSchedules": {"num_inference_steps": 10, "timesteps": "StableDiffusionXLTimesteps"}, -# } -# } -# }, -# ) -# ) -# entry.update( -# mir_entry( -# domain="ops", -# arch="patch", -# series="hidiffusion", -# comp="stable-diffusion-xl", -# pkg={0: {"hidiffusion": {"apply_hidiffusion": {"generation": {"height": 2048, "width": 2048, "eta": 1.0, "guidance_scale": 7.5}}}}}, -# ) -# ) -# pprint(entry) - - -# def test_mir_maid(): -# import json -# import os -# from mir.spec.mir import mir_entry - -# entry = mir_entry( -# domain="info", -# arch="unet", -# series="stable-diffusion-xl", -# comp="base", -# repo="stabilityai/stable-diffusion-xl", -# pkg={ -# 0: { -# "diffusers": "class_name", -# "generation": {"num_inference_steps": 40, "denoising_end": 0.8, "output_type": "latent", "safety_checker": False}, -# } -# }, -# ) -# try: -# os.remove(MIR_PATH_NAMED) -# except FileNotFoundError: -# pass -# with open(MIR_PATH_NAMED, "x", encoding="UTF-8") as f: -# f.write("{}") -# folder_path_named = os.path.dirname(MIR_PATH_NAMED) -# from mir.maid import MIRDatabase - -# mir_db = MIRDatabase() -# mir_db.add(entry) -# mir_db.write_to_disk() -# print(mir_db.database) -# with open(MIR_PATH_NAMED, "r", encoding="UTF-8") as f: -# result = json.load(f) -# expected = { -# "info.unet.stable-diffusion-xl": { -# "base": { -# "pkg": { -# "0": { -# "diffusers": "class_name", -# "generation": { -# "denoising_end": 0.8, -# "num_inference_steps": 40, -# "output_type": "latent", -# "safety_checker": False, -# }, -# }, -# }, -# "repo": "stabilityai/stable-diffusion-xl", -# }, -# }, -# } - -# assert mir_db.database == expected -# assert result == expected - - -# def test_restore_mir(): -# import json -# import os - -# from mir.config.json_io import write_json_file -# from mir.config.constants import MIR_PATH_NAMED -# from mir.maid import MIRDatabase, main - -# database = {"expecting": "data"} -# try: -# os.remove(MIR_PATH_NAMED) -# except FileNotFoundError: -# pass -# folder_path_named = os.path.dirname(MIR_PATH_NAMED) -# write_json_file(folder_path_named, file_name="mir.json", data=database, mode="w") -# database.pop("expecting", {}) -# mir_db = MIRDatabase() -# mir_db.database.pop("empty", {}) -# main(mir_db) -# with open(MIR_PATH_NAMED, "r", encoding="UTF-8") as f: -# result = json.load(f) -# mir_db = MIRDatabase() -# expected = mir_db.database -# for tag, compatibility in result.items(): -# for comp, field in compatibility.items(): -# for header, definition in field.items(): -# if isinstance(definition, dict): -# for key in definition: -# if len(key) > 1: -# assert field[header][key] == expected[tag][comp][header][key] -# # else: -# # assert field[header][key] == expected[tag][comp][header][key] -# else: -# assert field[header] == expected[tag][comp][header] - -# print(mir_db.database) - - -# if __name__ == "__main__": -# test_mir_creation() diff --git a/tests/old/test_mir_merge.py b/tests/old/test_mir_merge.py deleted file mode 100644 index 3d14ac9..0000000 --- a/tests/old/test_mir_merge.py +++ /dev/null @@ -1,122 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -# test_merge_data.py -import pytest - -from mir.automata import assimilate - - -class MIRDatabase: - def __init__(self): - self.database = { - "info.unet.stable-diffusion-xl": { - "base": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": {0: {"diffusers": "StableDiffusionXLPipeline"}}, - "layer_256": ["62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef"], - }, - } - } - - -def test_merge_data_simple_case(): - mir_db = MIRDatabase() - mir_db.database["arch1.series1"] = {"component1": {}} - - data_tuple = [("arch1", "series1", {"component1": {"field1": {"key1": "value1"}}})] - - assimilate(mir_db, data_tuple) - assert mir_db.database["arch1.series1"]["component1"]["field1"]["key1"] == "value1" - - -# Test case -@pytest.fixture -def mock_mir_db(): - return MIRDatabase() - - -def test_merge_data(mock_mir_db): - """TEST DATAAAAA 測試資料 - Call the function to test & Check if the data was merged correctly""" - from pprint import pprint - - data_tuple = [ - ( - "info.unet", - "stable-diffusion-xl", - { - "base": { - "pkg": { - 0: { - "generation": { - "denoising_end": 0.8, - "output_type": "latent", - "safety_checker": False, - "width": 1024, - "height": 1024, - }, - }, - 1: {"diffusers": "DiffusionPipeline"}, - }, - "layer_256": ["62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef"], - } - }, - ), - ] - - assimilate(mock_mir_db, data_tuple) - expected_result = { - "base": { - "repo": "stabilityai/stable-diffusion-xl-base-1.0", - "pkg": { - 0: { - "diffusers": "StableDiffusionXLPipeline", - "generation": { - "denoising_end": 0.8, - "output_type": "latent", - "safety_checker": False, - "width": 1024, - "height": 1024, - }, - }, - 1: {"diffusers": "DiffusionPipeline"}, - }, - "layer_256": ["62a5ab1b5fdfa4fedb32323841298c6effe1af25be94a8583350b0a7641503ef"], - } - } - pprint(mock_mir_db.database) - assert mock_mir_db.database["info.unet.stable-diffusion-xl"] == expected_result - - -def test_merge_data_nested_case(): - mir_db = MIRDatabase() - mir_db.database = {"arch2.series2": {"base": {"pkg": {0: {"module": {}}}}}} - print(mir_db.database) - assert mir_db.database["arch2.series2"]["base"]["pkg"][0] == {"module": {}} - data_tuple = [("arch2", "series2", {"base": {"pkg": {0: {"extra": {"x": {"key2": "value2"}}}}}})] - assimilate(mir_db, data_tuple) - print(mir_db.database) - - assert mir_db.database["arch2.series2"]["base"]["pkg"][0]["module"] == {} - assert mir_db.database["arch2.series2"]["base"]["pkg"][0]["extra"] == {"x": {"key2": "value2"}} - - -def test_merge_data_multiple_levels(): - mir_db = MIRDatabase() - mir_db.database["arch3.series3"] = {"component3": {"field3": {"definition3": {"sub_def3": {}}}}} - - data_tuple = [("arch3", "series3", {"component3": {"field3": {"definition3": {"sub_def3": {"key3": "value3"}}}}})] - - assimilate(mir_db, data_tuple) - assert mir_db.database["arch3.series3"]["component3"]["field3"]["definition3"]["sub_def3"]["key3"] == "value3" - - -def test_merge_data_type_error(): - mir_db = MIRDatabase() - mir_db.database["arch4.series4"] = {"component4": {}} - - data_tuple = [("arch4", "series4", {"component4": "not a dict"})] - - with pytest.raises(TypeError): - assimilate(mir_db, data_tuple) diff --git a/tests/old/test_mir_search.py b/tests/old/test_mir_search.py deleted file mode 100644 index 6bfd64c..0000000 --- a/tests/old/test_mir_search.py +++ /dev/null @@ -1,98 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import pytest - - -@pytest.fixture -def mock_test_database(): - from mir.maid import MIRDatabase # , main - - mir_db = MIRDatabase() - # main(mir_db) - return mir_db - - -def test_grade_maybes_fail(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="table-cascade") - assert result is None - - -def test_grade_similar_fail_again(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="able-cascade-") - assert result is None - - -def test_grade_cascade_decoder_match(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="stabilityai/stable-cascade") - assert result == ["info.unet.stable-cascade", "decoder"] - - -def test_grade_cascade_match(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="stabilityai/stable-cascade", domain="info.unet") - assert result == ["info.unet.stable-cascade", "decoder"] - - -def test_grade_field_change(mock_test_database): - result = mock_test_database.find_tag(field="pkg", target="parler_tts", domain="info.") - assert result == ["info.art.parler-tts-v1", "*"] - - -def test_grade_letter_case_change(mock_test_database): - result = mock_test_database.find_tag(field="pkg", target="AuDiOCrAfT") - assert result == ["info.art.audiogen", "*"] - - -def test_repo_case_change(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="outeAI/OuteTTS-0.3-1b") - assert result == ["info.art.outetts-0", "*"] - - -def test_sub_module_detection(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="PixArt-alpha/PixArt-Sigma-XL-2-1024-Ms") - assert result == ["info.dit.pixart-sigma-xl-2-1024-ms", "*"] - - -def test_find_tag_truncated(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="UsefulSenso") - assert result is None - - -def test_find_tag_truncated_2(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="UsefulSensors") - assert result is None - - -def test_find_tag_truncated_4(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="UsefulSensors/moon") - assert result is None - - -def test_find_tag_decent(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="UsefulSensors/moonshine") - assert result == ["info.stst.moonshine", "*"] - - -def test_find_tag_truncated_6(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="UsefulSensors/moonshine-") - assert result == ["info.stst.moonshine", "*"] - - -def test_find_qwen_2_vl(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="Qwen/Qwen2-VL-7B-Instruct", domain="info.vit") - assert result == ["info.vit.qwen2-vl", "*"] - - -def test_find_qwen_2_vl_2(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="Qwen/Qwen2-VL-Instruct".lower(), domain="info.vit") - assert result == ["info.vit.qwen2-vl", "*"] - - -def test_grade_similar_fail_umt5(mock_test_database): - result = mock_test_database.find_tag(field="task", target="UMT5EncoderModel") - assert result is None - - -def test_find_gpt_oss(mock_test_database): - result = mock_test_database.find_tag(field="repo", target="openai/gpt-oss-120b".lower(), domain="info.moe") - assert result == ["info.moe.gpt-oss", "*"] diff --git a/tests/old/test_mir_tagging.py b/tests/old/test_mir_tagging.py deleted file mode 100644 index 272f157..0000000 --- a/tests/old/test_mir_tagging.py +++ /dev/null @@ -1,44 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# -from mir.tag import tag_model_from_repo - - -# def test_param_no_delimiter_version():BAH -# result = make_mir_tag("xyz1b") -# assert result == ("xyz", "*") -# print(result) - - -def test_split_hyphenated(): - result = tag_model_from_repo("xyz-15b") - assert result == ("xyz", "*") - print(result) - - -# def test_split_dot(): BAH -# result = make_mir_tag("xyz.15b") -# assert result == ("xyz", "*") - - -def test_split_dot_version(): - assert tag_model_from_repo("xyz1.0") == ("xyz1", "*") - - -def test_split_hyphen_version(): - assert tag_model_from_repo("xyz1-0") == ("xyz1-0", "*") - - -def test_split_hyphen_v_version(): - assert tag_model_from_repo("xyzv1-0") == ("xyzv1-0", "*") - - -def test_no_split(): - assert tag_model_from_repo("flux.1-dev") == ("flux1-dev", "*") - - -def test_no_split_again(): - assert tag_model_from_repo("blipdiffusion") == ("blipdiffusion", "*") - - -def test_no_version_dot_numeric_and_diffusers(): - assert tag_model_from_repo("EasyAnimateV5.1-7b-zh-diffusers") == ("easyanimatev5-zh", "diffusers") diff --git a/tests/old/test_regex_constants.py b/tests/old/test_regex_constants.py deleted file mode 100644 index 70820a8..0000000 --- a/tests/old/test_regex_constants.py +++ /dev/null @@ -1,27 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from mir.config.constants import PARAMETERS_SUFFIX -from mir.tag import tag_model_from_repo - - -def test_constants(): - import re - - data_tests = { - "mlx-community/Kokoro-82M-4bit": ["kokoro", "*"], - "RuadaptQwen2.5-32B-Pro-Beta:latest": ["ruadaptqwen2", "*"], - "microsoft/Phi-4-mini-instruct": ["phi-4", "*"], - "tiiuae/falcon-mamba-7b": ["falcon-mamba", "*"], - "ijepa-vith14-1k": ["ijepa-vith14", "*"], - "arcee-ai/AFM-4.5B": ["afm", "*"], - "ibm-research/PowerMoE-3b": ["powermoe", "*"], - "qwen1-5-moe-a2-7b": ["qwen1-5-moe-a2", "*"], - "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers": ["sana-sprint-1024px", "diffusers"], - "Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers": ["hunyuandit-v1", "diffusers"], - "parler-tts/parler-tts-large-v1": ["parler-tts-v1", "*"], - } - # regex = PARAMETERS_SUFFIX - for test, expected in data_tests.items(): - mir_tag = list(tag_model_from_repo(test)) - assert mir_tag == expected diff --git a/tests/old/test_resolve_code_names.py b/tests/old/test_resolve_code_names.py deleted file mode 100644 index fa875a1..0000000 --- a/tests/old/test_resolve_code_names.py +++ /dev/null @@ -1,44 +0,0 @@ -# # # -# # # - -import pytest -from mir.inspect.classes import resolve_code_names - - -def test_diffusers_name(): - assert resolve_code_names("StableDiffusionPipeline", "diffusers") == "stable-diffusion" - - -def test_transformers_name(): - assert resolve_code_names("BertModel", "transformers") == "bert" - - -def test_no_class(): - result = resolve_code_names() - assert isinstance(result, list) is True - assert len(result) > 300 - - -def test_invalid_package(): - with pytest.raises(KeyError): - assert resolve_code_names("EBertModel", "invalid_package") == "" - - -def test_mixed_search(): - assert resolve_code_names("EBertModel", "transformers") == "" - - -def test_difficult_search(): - assert resolve_code_names("AllegroPipeline", "diffusers") == "allegro" - - -def test_diff_folder_search(): - assert resolve_code_names("AllegroPipeline", "diffusers", path_format=True) == ["diffusers", "pipelines", "allegro"] - - -def test_tf_folder_search(): - assert resolve_code_names("Wav2Vec2Model", "transformers", path_format=True) == ["transformers", "models", "wav2vec2"] - - -if __name__ == "__main__": - pytest.main(["-vv", __file__]) diff --git a/tests/old/test_seek_class.py b/tests/old/test_seek_class.py deleted file mode 100644 index 4d3a1de..0000000 --- a/tests/old/test_seek_class.py +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from mir.config.conversion import import_submodules -from mir.inspect.pipes import get_class_parent_folder - - -def test_seek_diffusers_path(): - assert get_class_parent_folder(import_submodules("AllegroPipeline", "diffusers"), "diffusers") == ["diffusers", "pipelines", "allegro"] - - -def test_seek_transformers_path(): - module = import_submodules("AlbertModel", "transformers") - assert get_class_parent_folder(module, "transformers") == ["transformers", "models", "albert"] - - -def test_seek_class_attention(): - assert get_class_parent_folder("CogVideoXAttnProcessor2_0", "diffusers") is None diff --git a/tests/old/test_task.py b/tests/old/test_task.py deleted file mode 100644 index 2c527b9..0000000 --- a/tests/old/test_task.py +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -# from mir.__main__ import main -# from mir.maid import MIRDatabase - - -# def test_task_and_pipe(): -# mir_db = MIRDatabase() -# assert main(mir_db) is not None diff --git a/tests/old/test_taskanalyzer.py b/tests/old/test_taskanalyzer.py deleted file mode 100644 index 77adb96..0000000 --- a/tests/old/test_taskanalyzer.py +++ /dev/null @@ -1,320 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import types -from typing import OrderedDict -import pytest -import pytest_asyncio -import sys - -from mir.inspect.tasks import TaskAnalyzer - - -def test_show_transformers_tasks_by_code_name(): - """Test that show_transformers_tasks returns a list of class names when code_name is provided.""" - tasks = TaskAnalyzer.show_transformers_tasks(code_name="bert") - - # Should return a list (not a type object) - assert isinstance(tasks, list), f"Expected list, got {tasks} type {type(tasks)}" - - # Should contain string class names - if tasks: - assert all(isinstance(task, str) for task in tasks), f"Expected list of strings, got {tasks} type {type(tasks)}" - print(f"show_transformers_tasks('bert') returned: {tasks}") - - -class DummyDiffusersTaskMap(OrderedDict): - """Mimic a SUPPORTED_TASKS_MAPPINGS entry.""" - - pass - - -def make_dummy_diffusers_modules(monkeypatch): - """Create minimal diffusers package structure required by AutoPkg. - ie diffusers.pipelines.auto_pipeline""" - auto_pipeline = types.SimpleNamespace() - task_map_norm = DummyDiffusersTaskMap() - task_map_i2i = DummyDiffusersTaskMap() - - # - class CoronaPipeline: - """Fake model code mapped to fake pipe class""" - - __name__ = "CoronaPipeline" - - class CoronaImg2ImgPipeline: - __name__ = "CoronaImg2ImgPipeline" - - task_map_norm["corona-model"] = CoronaPipeline - task_map_i2i["corona-model"] = CoronaImg2ImgPipeline - auto_pipeline.SUPPORTED_TASKS_MAPPINGS = [ - task_map_norm, - task_map_i2i, - ] - - def _get_task_class(task_map, class_name, _): - """Return a dummy class if class_name matches""" - - return task_map.get("corona-model") - # return None - - auto_pipeline._get_task_class = _get_task_class - monkeypatch.setitem(sys.modules, "diffusers.pipelines.auto_pipeline", auto_pipeline) - - -def make_dummy_transformers_modules(monkeypatch): - """Create minimal transformers package structure required by AutoPkg.""" - utils_fx = types.SimpleNamespace() - - def _generate_supported_model_class_names(code_name): - """Return a list based on the code_name""" - return [f"{code_name}_TaskA", f"{code_name}_TaskB"] - - utils_fx._generate_supported_model_class_names = _generate_supported_model_class_names - monkeypatch.setitem(sys.modules, "transformers.utils.fx", utils_fx) - - # nnll.metadata.helpers.make_callable stub - helpers = types.SimpleNamespace() - - def make_callable(name, pkg): - # Return a dummy class with __module__ and __all__ - class Dummy: - __module__ = f"{pkg}.dummy_module" - - Dummy.__all__ = ["DummyClass"] - return Dummy - - helpers.make_callable = make_callable - monkeypatch.setitem(sys.modules, "nnll.metadata.helpers", helpers) - - -def make_dummy_nnll_modules(monkeypatch): - """Create minimal nnll package structure required by AutoPkg.""" - # nnll.tensor_pipe.deconstructors.get_code_names - deconstructors = types.SimpleNamespace() - - def get_code_names(class_name, package_name): - """Return a deterministic code name""" - return f"{class_name}_code" - - deconstructors.get_code_names = get_code_names - monkeypatch.setitem(sys.modules, "nnll.tensor_pipe.deconstructors", deconstructors) - - # nnll.mir.tag.make_scheduler_tag - mir_tag = types.SimpleNamespace() - - def make_scheduler_tag(class_name): - """Return dummy series and component""" - return ("scheduler_series", "scheduler_component") - - mir_tag.make_scheduler_tag = make_scheduler_tag - monkeypatch.setitem(sys.modules, "nnll.mir.tag", mir_tag) - - -class DummyMIRDatabase: - """A very small in‑memory stand‑in for the real MIRDatabase.""" - - def __init__(self): - """# DB Structure: {series: {compatibility: {field_name: {"0": pkg:{ : ...}}}}}""" - self.database = {} - - def add_entry(self, series, compatibility, field_name, pkg_tree): - self.database.setdefault(series, {}) - self.database[series].setdefault(compatibility, {}) - self.database[series][compatibility][field_name] = {"0": pkg_tree} - - def find_tag(self, *, field, target, sub_field=None, domain=None): - """Simplified: return a fake tag if target contains "Known""" - tree = { - "IPNDMScheduler": ["ops.scheduler.dummy", "ipndmscheduler"], - "EQvae": ["info.vae.dummy", "AutoencoderKL"], - "DummyOther": ["info.dummy.OtherClass", "*"], - "CLIPTokenizer": [ - "info.encoder.tokenizer", - "CLIPDummy", - ], - } - return tree.get(target) - - -@pytest.fixture(autouse=True) -def stub_external_modules(monkeypatch): - """Patch all external imports used by AutoPkg.""" - - make_dummy_diffusers_modules(monkeypatch) - make_dummy_transformers_modules(monkeypatch) - make_dummy_nnll_modules(monkeypatch) - - -def test_show_diffusers_tasks(): - tasks = TaskAnalyzer.show_diffusers_tasks( - code_name="corona-model", - class_name="CoronaModel", - ) - assert "CoronaPipeline" in tasks - assert "CoronaImg2ImgPipeline" in tasks - - -# def test_show_transformers_tasks_by_class(): -# """When code_name is None, make_callable returns a dummy with __all__""" -# tasks = TaskAnalyzer.show_transformers_tasks(class_name="AnyClass") -# assert tasks == ["DummyClass"] # from Dummy.__all__ - - -# def test_show_transformers_tasks_by_code(): -# tasks = TaskAnalyzer.show_transformers_tasks(code_name="bert") -# assert tasks == ["bert_TaskA", "bert_TaskB"] - - -# @pytest.mark.asyncio -# async def test_trace_tasks_filters_and_sorts(): -# """Package entry should be processed (not in `skip_auto` list) -# show_transformers_tasks should return ["DummyClass"]; no snip words, so unchanged""" -# ap = TaskAnalyzer() - -# pkg_tree = {"transformers": "SomeModel"} -# tasks = await ap.trace_tasks(pkg_tree) - -# assert tasks == ["DummyClass"] - - -@pytest.mark.asyncio -async def test_trace_finds_map_with_code_name(): - ap = TaskAnalyzer() - pkg_tree = {"diffusers": "CoronaPipeline"} - tasks = await ap.trace_tasks(pkg_tree) - assert tasks == [ - "CoronaImg2ImgPipeline", - "CoronaPipeline", - ] - - -@pytest.mark.asyncio -async def test_mflux_path_returns_static_list(): - ap = TaskAnalyzer() - pkg_tree = {"mflux": "any"} - tasks = await ap.trace_tasks(pkg_tree) - assert tasks == ap.mflux_tasks - - -@pytest.mark.asyncio -async def test_skip_automode_return_none(): - ap = TaskAnalyzer() - pkg_tree = {"transformers": "AutoModel"} - tasks = await ap.trace_tasks(pkg_tree) - assert tasks is None - - -@pytest.mark.asyncio -async def test_hyperlink_and_tag_class(): - """Populate a known tag for a scheduler class\n""" - ap = TaskAnalyzer() - mir_db = DummyMIRDatabase() - - mir_db.add_entry( - series="ops.scheduler.scheduler_series", - compatibility="any", - field_name="pkg", - pkg_tree={"diffusers": "IPNDMScheduler"}, - ) - - class IPNDMScheduler: - __name__ = "IPNDM" - __module__ = "schedulers.ipndm.IPNDMScheduler" - - class EQvae: - __name__ = "EQ-VAE" - __module__ = "autoencoders.AutoencoderKL" - - class DummyOther: - __name__ = "OtherClass" - __module__ = "other_pkg.OtherClass" - - class CLIPTokenizer: - __name__ = "CLIPTokenizer" - __module__ = "tokenizers.CLIPTokenizer" - - pipe_args = { - "scheduler": IPNDMScheduler, - "vae": EQvae, - "unrelated": DummyOther, - "tokenizer": CLIPTokenizer, # should be mapped to encoder tokenizers - } - - links = await ap.hyperlink_to_mir(pipe_args, "info.test_series", mir_db) - - assert "scheduler" in links["pipe_names"] # Scheduler should be resolved via make_scheduler_tag -> find_tag fallback\n - scheduler_tag = links["pipe_names"]["scheduler"] - assert scheduler_tag == ["ops.scheduler.dummy", "ipndmscheduler"] - - assert "vae" in links["pipe_names"] # VAE should be resolved via find_tag (since not in dummy DB) - assert links["pipe_names"]["vae"] == ["info.vae.dummy", "AutoencoderKL"] - - assert links["pipe_names"]["unrelated"] == ["info.dummy.OtherClass", "*"] # Unrelated should just return the class name - - assert links["pipe_names"]["tokenizer"] == ["info.encoder.tokenizer", "test_series"] # Tokenizer role is *special‑cased* - - -@pytest.mark.asyncio -async def test_detect_tasks_and_pipes(): - ap = TaskAnalyzer() - mir_db = DummyMIRDatabase() - - mir_db.add_entry( - series="info.art.modelA", # Add a series that passes the skip filters - compatibility="compat1", - field_name="pkg", - pkg_tree={"transformers": "SomeModel"}, - ) - - mir_db.add_entry( - series="info.lora.modelB", # Add a series (".lora") that should be ignored (skip_series) - compatibility="compat2", - field_name="pkg", - pkg_tree={"transformers": "SomeModel"}, - ) - - async def fake_trace_tasks(pkg_tree): - """Patch trace_tasks to return a predictable list""" - return ["TaskX", "TaskY"] - - ap.trace_tasks = fake_trace_tasks - - tasks = await ap.detect_tasks(mir_db) - print(tasks) - assert any("modelA" in series for prefix, series, _ in tasks) - assert not any("lora" in prefix for prefix, series, _ in tasks) - - class DummyPipe: - """diffusers entry with a pipe class for detect_pipes""" - - def __init__(arg1: int, arg2: str): - """Exists purely for annotation reading!""" - pass - - def fake_make_callable(name, pkg): - """Stub make_callable to return DummyPipe for the module name""" - return DummyPipe - - # Monkeypatch the helper used inside detect_pipes - from mir.config.conversion import import_submodules - - import_submodules = fake_make_callable # type: ignore - - mir_db.add_entry( - series="info.vit.modelC", - compatibility="compat3", - field_name="pkg", - pkg_tree={"diffusers": "DummyPipe"}, - ) - - async def fake_hyperlink(pipe_args, series, db): - """Patch hyperlink_to_mir to return a simple marker""" - return {"pipe_names": {"dummy": ["OK"]}} - - ap.hyperlink_to_mir = fake_hyperlink - - pipes = await ap.detect_pipes(mir_db) # Should contain the non‑skipped diffusers entry - assert any("modelC" in series for prefix, series, _ in pipes) - for _, _, data in pipes: # Ensure the returned structure matches the fake hyperlink output - assert data["compat3"]["pipe_names"]["dummy"] == ["OK"] diff --git a/tests/test_harvest_transformers.py b/tests/test_harvest_transformers.py new file mode 100644 index 0000000..1d86502 --- /dev/null +++ b/tests/test_harvest_transformers.py @@ -0,0 +1,6 @@ +from mir.generate.transformers.harvest import HarvestLoop + + +def test_harvest(): + harvest_classes = HarvestLoop() + harvest_classes() diff --git a/tests/test_inspect.py b/tests/test_inspect.py new file mode 100644 index 0000000..57e4689 --- /dev/null +++ b/tests/test_inspect.py @@ -0,0 +1,7 @@ +from diffusers import CosmosTransformer3DModel + + +model = CosmosTransformer3DModel() +print(type(model.transformer_blocks[0])) +for i in model.transformer_blocks[0]: + print(type(i)) diff --git a/tests/test_mir_generate_diffusers.py b/tests/test_mir_generate_diffusers.py index 2db66d0..4cbfb8f 100644 --- a/tests/test_mir_generate_diffusers.py +++ b/tests/test_mir_generate_diffusers.py @@ -1,6 +1,6 @@ def test_info_key_exists_and_library_is_not_nested(): - from mir.generate.diffusers.harvest import HarvestClasses + from mir.generate.diffusers.harvest import HarvestLoop - Mir = HarvestClasses().db.db + Mir = HarvestLoop().db.db # print(Mir) diff --git a/tests/test_mir_generate_transformers.py b/tests/test_mir_generate_transformers.py index 2fd0a11..47bdb13 100644 --- a/tests/test_mir_generate_transformers.py +++ b/tests/test_mir_generate_transformers.py @@ -1,7 +1,7 @@ def test_info_key_exists_and_library_is_not_nested(): - from mir.generate.transformers.harvest import HarvestClasses + from mir.generate.transformers.harvest import HarvestLoop - Mir = HarvestClasses().db.db + Mir = HarvestLoop().db.db print(Mir.info.cnn.yolos) result = Mir.info.cnn.yolos["transformers"] # should not throw @@ -9,9 +9,9 @@ def test_info_key_exists_and_library_is_not_nested(): def test_ops_key_exists_and_library_is_not_tested(): - from mir.generate.transformers.harvest import HarvestClasses + from mir.generate.transformers.harvest import HarvestLoop - Mir = HarvestClasses().db.db + Mir = HarvestLoop().db.db print(Mir.ops.cnn.yolos) result = Mir.ops.cnn.yolos["transformers"] # should not throw @@ -26,9 +26,9 @@ def test_ops_key_exists_and_library_is_not_tested(): def test_ops_tokenizer_created(): - from mir.generate.transformers.harvest import HarvestClasses + from mir.generate.transformers.harvest import HarvestLoop - Mir = HarvestClasses().db.db + Mir = HarvestLoop().db.db result = Mir.ops.encoder.tokenizer.zamba2["transformers"] assert result == {"model": "transformers.models.llama.tokenization_llama.LlamaTokenizer"} From 193522f6170634f0337ece7741eb5796013112f5 Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Wed, 21 Jan 2026 20:25:31 -0500 Subject: [PATCH 14/16] ~eeby sleeeby --- mir/generate/_tasks.py | 6 +- .../diffusers/{harvest.py => gather.py} | 43 +- mir/generate/diffusers/package.py | 69 - mir/generate/diffusers/raw_data.py | 24 - mir/generate/diffusers/tasks.py | 34 - mir/generate/from_module.py | 2 +- mir/generate/test.json | 4549 +++++++++++++++++ mir/generate/transformers/gather.py | 24 + mir/generate/transformers/harvest.py | 44 - mir/generate/transformers/package.py | 56 - mir/generate/transformers/raw_data.py | 24 - mir/generate/transformers/tasks.py | 32 - mir/maid.py | 2 +- mir/model.py | 50 + mir/nesting.py | 85 + mir/package.py | 188 +- mir/tag.py | 53 +- tests/test_gather_diffusers.py | 10 + tests/test_gather_transformers.py | 10 + tests/test_harvest_transformers.py | 6 - 20 files changed, 4873 insertions(+), 438 deletions(-) rename mir/generate/diffusers/{harvest.py => gather.py} (55%) delete mode 100644 mir/generate/diffusers/package.py delete mode 100644 mir/generate/diffusers/raw_data.py delete mode 100644 mir/generate/diffusers/tasks.py create mode 100644 mir/generate/test.json create mode 100644 mir/generate/transformers/gather.py delete mode 100644 mir/generate/transformers/harvest.py delete mode 100644 mir/generate/transformers/package.py delete mode 100644 mir/generate/transformers/raw_data.py delete mode 100644 mir/generate/transformers/tasks.py create mode 100644 mir/model.py create mode 100644 mir/nesting.py create mode 100644 tests/test_gather_diffusers.py create mode 100644 tests/test_gather_transformers.py delete mode 100644 tests/test_harvest_transformers.py diff --git a/mir/generate/_tasks.py b/mir/generate/_tasks.py index 32961ae..2745598 100644 --- a/mir/generate/_tasks.py +++ b/mir/generate/_tasks.py @@ -3,7 +3,7 @@ from typing import Any, Callable, List -from mir.generate.diffusers.raw_data import DPrepareData +from mir.generate.diffusers.raw_data import ModelAttributes from mir import DBUQ from mir.tag import MIRTag @@ -12,11 +12,11 @@ class TaskAnalyzer: - prepared_data: DPrepareData + prepared_data: ModelAttributes mir_tag: MIRTag tasks: dict[str, str] | None = None - def __init__(self, prepared_data: DPrepareData, mir_tag: MIRTag) -> None: + def __init__(self, prepared_data: ModelAttributes, mir_tag: MIRTag) -> None: self.prepared_data = prepared_data self.mir_tag = mir_tag self.skip_series = [ diff --git a/mir/generate/diffusers/harvest.py b/mir/generate/diffusers/gather.py similarity index 55% rename from mir/generate/diffusers/harvest.py rename to mir/generate/diffusers/gather.py index e0a697c..43a68ca 100644 --- a/mir/generate/diffusers/harvest.py +++ b/mir/generate/diffusers/gather.py @@ -1,49 +1,36 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from importlib import import_module -from inspect import getmro from typing import get_type_hints -from mir.generate.diffusers.raw_data import DPrepareData - -class HarvestLoop: +class GatherLoop: def __init__(self) -> None: - """Initializes the HarvestClasses instance with an empty list to store raw class data.""" - from mir.generate.transformers.harvest import HarvestLoop - + """Loops through diffusers packages to harvest class data.""" from mir.maid import MIRDatabase self.db = MIRDatabase() - self.harvest_tf = HarvestLoop() - - def __call__(self) -> None: from mir.data import EXCLUSIONS + from mir.build_entry import BuildEntry - prepared_data = {} - library = "diffusers" - subclasses = self.extract_subclass_data(library, "DiffusionPipeline") # diffusers.pipelines. + build_entries = [] + subclasses = self.extract_subclass_data("diffusers", "DiffusionPipeline") for module_path, pipeline in subclasses.items(): if module_path.rsplit(".", 1)[-1] not in EXCLUSIONS["exclusion_list"]: - loop_parameters = get_type_hints(pipeline.__init__) - loop_parameters.setdefault("pipeline", pipeline) - for name, self.model in loop_parameters.items(): - if prepare_data := self.prepare_class_data(): - prepared_data.setdefault(name, prepare_data) - for data in prepared_data: - pass - - def prepare_class_data(self): - prepared_data = DPrepareData(model=self.model) - return prepared_data + build_entries.extend([BuildEntry(model_type=model_type, model=model) for model_type, model in get_type_hints(pipeline.__init__).items()]) + build_entries.append(BuildEntry(model_type="pipeline", model=pipeline)) + print([x.attributes for x in build_entries]) + # TODO: for data in prepared_data: def extract_subclass_data(self, package_name: str, base_class_name: str): - """Return a dict mapping `.` → class object - for every class in `package_name` that subclasses a class named - `base_class_name`.""" + """Extracts subclasses from a package that inherit from a specified base class.\n + :param package_name: Name of the package to search + :param base_class_name: Name of the base class to inherit from + :return: Dictionary mapping fully qualified class names to class objects""" from pkgutil import walk_packages + from inspect import getmro + from importlib import import_module results = {} root_pkg = import_module(package_name) diff --git a/mir/generate/diffusers/package.py b/mir/generate/diffusers/package.py deleted file mode 100644 index 9c08f39..0000000 --- a/mir/generate/diffusers/package.py +++ /dev/null @@ -1,69 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from types import ModuleType -from typing import Callable -from dataclasses import dataclass, field - - -@dataclass -class MIRPackage: - model_type: str - model: Callable | str | dict[str, str] - model_path: ModuleType - package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - - def __post_init__(self): - self.package = {} - self.model_name: str = self.model.__name__ - self.model_path: ModuleType = self.model.__module__ - if not isinstance(self.data, dict): - self.generate_package() - self.generate_repo() - - def generate_repo(self): - from mir.data import MIGRATIONS - - if self.model_type in ["unet", "transformer"] and (doc_string := getattr(self.model_path, "EXAMPLE_DOC_STRING", None)): - if repo := MIGRATIONS["migrated_pipes"].get(self.model_name, False): - self.repo = repo - elif self.model_type not in ["scheduler", "vae", "tokenizer"]: - self.process_doc_string(doc_string=doc_string) - - def generate_package(self) -> None: - """Generates package information for the MIR tag based on class. - :param pkg: A class object (model, tokenizer, etc) to build a tag from""" - model = f"{self.model_path}.{self.model_name}" - self.package: dict[str, str] = {"model": model} - - def config_to_repo(self, config_class: Callable) -> str | None: - """Extracts the repository path from the configuration class documentation.\n - :param config_class: Configuration class to extract repository path from. - :return: Repository path as a string if found, otherwise None.""" - import re - - from mir import NFO - - doc_check = [config_class] - if hasattr(config_class, "forward"): - doc_check.append(config_class.forward) # type: ignore - for pattern in doc_check: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore - if matches: - try: - return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - NFO(f"ERROR >>{matches} : LOG >> {error_log}") - continue - - def process_doc_string(self, doc_string: str) -> None: - from mir.generate.diffusers.doc_parse import DocStringParser - - doc_parser = DocStringParser(doc_string=doc_string, model=self.model, model_path=self.model_path) - doc_parser.parse() - if repo_path := doc_parser.pipe_repo: - self.repo_path = repo_path - if staged_repo := doc_parser.staged_repo: - self.staged_repo = staged_repo diff --git a/mir/generate/diffusers/raw_data.py b/mir/generate/diffusers/raw_data.py deleted file mode 100644 index 26170e8..0000000 --- a/mir/generate/diffusers/raw_data.py +++ /dev/null @@ -1,24 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from dataclasses import dataclass, field -from typing import Callable - - -@dataclass -class DPrepareData: - """Represents a structured entry of the name of the class and its associated attributes.""" - - model: Callable - model_params: dict[str, list[str]] = field(init=True, default_factory=lambda: {"": [""]}) - - model_name: str = field(init=False) - library: str = field(init=False) - import_path: str = field(init=False) - - def __post_init__(self): - """Initializes the DPrepareData instance by setting derived attributes.""" - self.model_name: str = self.model.__name__ - self.import_path: str = self.model.__module__.rsplit(".", 1)[0] - self.library: str = self.import_path.split(".")[0] diff --git a/mir/generate/diffusers/tasks.py b/mir/generate/diffusers/tasks.py deleted file mode 100644 index 068b126..0000000 --- a/mir/generate/diffusers/tasks.py +++ /dev/null @@ -1,34 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from dataclasses import dataclass, field -from typing import Callable - - -@dataclass -class CollectTasks: - model: Callable - import_path: str - tasks: list[str] = field(init=False) - - def __post_init__(self) -> None: - self.model_to_tasks() - - def model_to_tasks(self) -> None: - """Return Diffusers task pipes based on package-specific query\n - :param class_name: To find task pipes from a Diffusers class pipe, defaults to None - :param code_name: To find task pipes from a Transformers class pipe, defaults to None - :return: A list of alternate class pipelines derived from the specified class""" - from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS - - alt_tasks = set({}) - self.internal_name = self.import_path.rsplit(".", 2)[-1] - for task_map in SUPPORTED_TASKS_MAPPINGS: - task_class = GET_TASK_CLASS(task_map, self.model, False) - if task_class: - alt_tasks.add(task_class.__name__) - for model_code, pipe_class_obj in task_map.items(): - if self.internal_name in model_code: - alt_tasks.add(pipe_class_obj.__name__) - - self.tasks = [x for x in alt_tasks] diff --git a/mir/generate/from_module.py b/mir/generate/from_module.py index fffb820..586c46d 100644 --- a/mir/generate/from_module.py +++ b/mir/generate/from_module.py @@ -9,7 +9,7 @@ from typing import Callable -def migrations(repo_path: str): +def migrations(repo_path: str) -> str: """Replaces old organization names in repository paths with new ones.\n :param repo_path: Original repository path containing old organization names :return: Updated repository path with new organization names""" diff --git a/mir/generate/test.json b/mir/generate/test.json new file mode 100644 index 0000000..2e8091a --- /dev/null +++ b/mir/generate/test.json @@ -0,0 +1,4549 @@ +model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'hidden_sizes': 'hidden_sizes=[ + 256, + 512, + 1024, + 2048 + ]', 'depths': 'depths=[ + 3, + 4, + 6, + 3 + ]', 'layer_type': "layer_type='preactivation'", 'hidden_act': "hidden_act='relu'", 'global_padding': 'global_padding=None', 'num_groups': 'num_groups=32', 'drop_path_rate': 'drop_path_rate=0.0', 'embedding_dynamic_padding': 'embedding_dynamic_padding=False', 'output_stride': 'output_stride=32', 'width_factor': 'width_factor=1', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, +model_name='BitModel', library='transformers', import_path='transformers.models.bit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 128256', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int + ] = 6912', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 30', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 5', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int + ] = 128001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[str + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='BitNetModel', library='transformers', import_path='transformers.models.bitnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=8008', 'max_position_embeddings': 'max_position_embeddings=128', 'encoder_layers': 'encoder_layers=2', 'encoder_ffn_dim': 'encoder_ffn_dim=10240', 'encoder_attention_heads': 'encoder_attention_heads=32', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=10240', 'decoder_attention_heads': 'decoder_attention_heads=32', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=2560', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=1', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'encoder_no_repeat_ngram_size': 'encoder_no_repeat_ngram_size=3', 'forced_eos_token_id': 'forced_eos_token_id=2' +}, model_name='BlenderbotModel', library='transformers', import_path='transformers.models.blenderbot'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=True', 'vocab': 'vocab=None', 'merges': 'merges=None' +}, model_name='BlenderbotTokenizer', library='transformers', import_path='transformers.models.blenderbot'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=512', 'encoder_layers': 'encoder_layers=8', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=8', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=512', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=1', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' +}, model_name='BlenderbotSmallModel', library='transformers', import_path='transformers.models.blenderbot_small'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'bos_token': "bos_token='__start__'", 'eos_token': "eos_token='__end__'", 'unk_token': "unk_token='__unk__'", 'pad_token': "pad_token='__null__'" +}, model_name='BlenderbotSmallTokenizer', library='transformers', import_path='transformers.models.blenderbot_small'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'image_text_hidden_size': 'image_text_hidden_size=256', 'label_smoothing': 'label_smoothing=0.0' +}, model_name='BlipModel', library='transformers', import_path='transformers.models.blip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'image_text_hidden_size': 'image_text_hidden_size=256', 'image_token_index': 'image_token_index=None' +}, model_name='Blip2Model', library='transformers', import_path='transformers.models.blip_2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'cross_attention_frequency': 'cross_attention_frequency=2', 'encoder_hidden_size': 'encoder_hidden_size=1408', 'use_qformer_text_input': 'use_qformer_text_input=False' +}, model_name='Blip2QFormerModel', library='transformers', import_path='transformers.models.blip_2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250880', 'hidden_size': 'hidden_size=64', 'n_layer': 'n_layer=2', 'n_head': 'n_head=8', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'apply_residual_connection_post_layernorm': 'apply_residual_connection_post_layernorm=False', 'hidden_dropout': 'hidden_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'pretraining_tp': 'pretraining_tp=1', 'slow_but_exact': 'slow_but_exact=False' +}, model_name='BloomModel', library='transformers', import_path='transformers.models.bloom'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 260', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'patch_in_forward': 'patch_in_forward: Optional[bool + ] = True', 'patch_size': 'patch_size: Optional[int + ] = 4', 'patching_mode': "patching_mode: Optional[str] = 'entropy'", 'patching_threshold': 'patching_threshold: Optional[float + ] = 1.335442066192627', 'patching_batch_size': 'patching_batch_size: Optional[int + ] = 1', 'max_patch_length': 'max_patch_length: Optional[int + ] = None', 'cross_attn_k': 'cross_attn_k: Optional[int + ] = 2', 'encoder_hash_byte_group_size': 'encoder_hash_byte_group_size: Optional[int + ] = None', 'encoder_hash_byte_group_vocab': 'encoder_hash_byte_group_vocab: Optional[int + ] = 500002', 'encoder_hash_byte_group_nb_functions': 'encoder_hash_byte_group_nb_functions: Optional[int + ] = 1', 'patcher_config': 'patcher_config: Optional[dict + ] = None', 'encoder_config': 'encoder_config: Optional[dict + ] = None', 'decoder_config': 'decoder_config: Optional[dict + ] = None', 'global_config': 'global_config: Optional[dict + ] = None', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='BltModel', library='transformers', import_path='transformers.models.blt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'share_cross_modal_transformer_layers': 'share_cross_modal_transformer_layers=True', 'hidden_act': "hidden_act='gelu'", 'hidden_size': 'hidden_size=768', 'initializer_factor': 'initializer_factor=1', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'share_link_tower_layers': 'share_link_tower_layers=False', 'link_tower_type': "link_tower_type='add'", 'num_attention_heads': 'num_attention_heads=12', 'num_hidden_layers': 'num_hidden_layers=6', 'tie_word_embeddings': 'tie_word_embeddings=False', 'init_layernorm_from_vision_encoder': 'init_layernorm_from_vision_encoder=False', 'text_config': 'text_config=None', 'vision_config': 'vision_config=None' +}, model_name='BridgeTowerModel', library='transformers', import_path='transformers.models.bridgetower'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'dim_bbox': 'dim_bbox=8', 'bbox_scale': 'bbox_scale=100.0', 'n_relations': 'n_relations=1', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1' +}, model_name='BrosModel', library='transformers', import_path='transformers.models.bros'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='CamembertModel', library='transformers', import_path='transformers.models.camembert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': 'additional_special_tokens=None', 'add_prefix_space': 'add_prefix_space=True', 'vocab_file': 'vocab_file=None', 'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None' +}, model_name='CamembertTokenizer', library='transformers', import_path='transformers.models.camembert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=16384', 'type_vocab_size': 'type_vocab_size=16', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=57344', 'eos_token_id': 'eos_token_id=57345', 'downsampling_rate': 'downsampling_rate=4', 'upsampling_kernel_size': 'upsampling_kernel_size=4', 'num_hash_functions': 'num_hash_functions=8', 'num_hash_buckets': 'num_hash_buckets=16384', 'local_transformer_stride': 'local_transformer_stride=128' +}, model_name='CanineModel', library='transformers', import_path='transformers.models.canine'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token='\\ue000'", 'eos_token': "eos_token='\\ue001'", 'sep_token': "sep_token='\\ue001'", 'cls_token': "cls_token='\\ue000'", 'pad_token': "pad_token='\\x00'", 'mask_token': "mask_token='\\ue003'", 'add_prefix_space': 'add_prefix_space=False', 'model_max_length': 'model_max_length=2048' +}, model_name='CanineTokenizer', library='transformers', import_path='transformers.models.canine'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 65536', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'hidden_act': "hidden_act: Optional[int] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[int + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'model_parallel_size': 'model_parallel_size: Optional[int + ] = 1', 'swin_norm': 'swin_norm: Optional[bool + ] = False', 'vq_config': 'vq_config: Optional[dict + ] = None', 'vocabulary_map': 'vocabulary_map: Optional[dict + ] = None', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False' +}, model_name='ChameleonModel', library='transformers', import_path='transformers.models.chameleon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='ChineseCLIPModel', library='transformers', import_path='transformers.models.chinese_clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' +}, model_name='ChineseCLIPVisionModel', library='transformers', import_path='transformers.models.chinese_clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_config': 'audio_config=None', 'logit_scale_init_value': 'logit_scale_init_value=14.285714285714285', 'projection_dim': 'projection_dim=512', 'projection_hidden_act': "projection_hidden_act='relu'", 'initializer_factor': 'initializer_factor=1.0' +}, model_name='ClapModel', library='transformers', import_path='transformers.models.clap'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='CLIPModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=49408', 'hidden_size': 'hidden_size=512', 'intermediate_size': 'intermediate_size=2048', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=8', 'max_position_embeddings': 'max_position_embeddings=77', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=49406', 'eos_token_id': 'eos_token_id=49407' +}, model_name='CLIPTextModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' +}, model_name='CLIPVisionModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'extract_layers': 'extract_layers=[ + 3, + 6, + 9 + ]', 'reduce_dim': 'reduce_dim=64', 'decoder_num_attention_heads': 'decoder_num_attention_heads=4', 'decoder_attention_dropout': 'decoder_attention_dropout=0.0', 'decoder_hidden_act': "decoder_hidden_act='quick_gelu'", 'decoder_intermediate_size': 'decoder_intermediate_size=2048', 'conditional_layer': 'conditional_layer=0', 'use_complex_transposed_convolution': 'use_complex_transposed_convolution=False' +}, model_name='CLIPSegModel', library='transformers', import_path='transformers.models.clipseg'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'speech_config': 'speech_config=None', 'decoder_config': 'decoder_config=None', 'projection_dim': 'projection_dim=768', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'initializer_factor': 'initializer_factor=1.0' +}, model_name='ClvpModelForConditionalGeneration', library='transformers', import_path='transformers.models.clvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'errors': "errors='replace'", 'unk_token': "unk_token='[UNK]'", 'bos_token': "bos_token='<|endoftext|>'", 'eos_token': "eos_token='[STOP]'", 'pad_token': "pad_token='[STOP]'", 'add_prefix_space': 'add_prefix_space=False' +}, model_name='ClvpTokenizer', library='transformers', import_path='transformers.models.clvp'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='LlamaModel', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50400', 'n_positions': 'n_positions=2048', 'n_ctx': 'n_ctx=2048', 'n_embd': 'n_embd=4096', 'n_layer': 'n_layer=28', 'n_head': 'n_head=16', 'rotary_dim': 'rotary_dim=64', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.0', 'embd_pdrop': 'embd_pdrop=0.0', 'attn_pdrop': 'attn_pdrop=0.0', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='CodeGenModel', library='transformers', import_path='transformers.models.codegen'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int + ] = 22528', 'logit_scale': 'logit_scale: Optional[float + ] = 0.0625', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 5', 'eos_token_id': 'eos_token_id: Optional[int + ] = 255001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'use_qk_norm': 'use_qk_norm: Optional[bool + ] = False' +}, model_name='CohereModel', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = '<|END_OF_TURN_TOKEN|>'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'sep_token': "sep_token: str = ''", 'mask_token': "mask_token: str = ''", 'use_default_system_prompt': 'use_default_system_prompt: bool = False', 'add_prefix_space': 'add_prefix_space: bool = False' +}, model_name='CohereTokenizer', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int + ] = 22528', 'logit_scale': 'logit_scale: Optional[float + ] = 0.0625', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 5', 'eos_token_id': 'eos_token_id: Optional[int + ] = 255001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Cohere2Model', library='transformers', import_path='transformers.models.cohere2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = '<|END_OF_TURN_TOKEN|>'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'sep_token': "sep_token: str = ''", 'mask_token': "mask_token: str = ''", 'use_default_system_prompt': 'use_default_system_prompt: bool = False', 'add_prefix_space': 'add_prefix_space: bool = False' +}, model_name='CohereTokenizer', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'downsample_factor': 'downsample_factor=2', 'image_token_id': 'image_token_id=255036', 'alignment_intermediate_size': 'alignment_intermediate_size=36864' +}, model_name='Cohere2VisionModel', library='transformers', import_path='transformers.models.cohere2_vision'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=300', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=2', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'cls_loss_coefficient': 'cls_loss_coefficient=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'focal_alpha': 'focal_alpha=0.25' +}, model_name='ConditionalDetrModel', library='transformers', import_path='transformers.models.conditional_detr'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'embedding_size': 'embedding_size=768', 'head_ratio': 'head_ratio=2', 'conv_kernel_size': 'conv_kernel_size=9', 'num_groups': 'num_groups=1', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='ConvBertModel', library='transformers', import_path='transformers.models.convbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=4', 'num_stages': 'num_stages=4', 'hidden_sizes': 'hidden_sizes=None', 'depths': 'depths=None', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'layer_scale_init_value': 'layer_scale_init_value=1e-06', 'drop_path_rate': 'drop_path_rate=0.0', 'image_size': 'image_size=224', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='ConvNextModel', library='transformers', import_path='transformers.models.convnext'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=4', 'num_stages': 'num_stages=4', 'hidden_sizes': 'hidden_sizes=None', 'depths': 'depths=None', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'drop_path_rate': 'drop_path_rate=0.0', 'image_size': 'image_size=224', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='ConvNextV2Model', library='transformers', import_path='transformers.models.convnextv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 30720', 'hidden_size': 'hidden_size: int = 4096', 'num_attention_heads': 'num_attention_heads: int = 32', 'dim_head': 'dim_head: int = 128', 'dim_ff': 'dim_ff: int = 10240', 'num_hidden_layers': 'num_hidden_layers: int = 48', 'dropout_p': 'dropout_p: int = 0.0', 'position_bias_num_buckets': 'position_bias_num_buckets: int = 512', 'position_bias_max_distance': 'position_bias_max_distance: int = 2048', 'eps': 'eps: int = 1e-06', 'init_std': 'init_std: float = 1.0', 'prompt_types': 'prompt_types: int = 32', 'prompt_length': 'prompt_length: int = 32', 'segment_types': 'segment_types: int = 32' +}, model_name='CpmAntModel', library='transformers', import_path='transformers.models.cpmant'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bod_token': "bod_token=''", 'eod_token': "eod_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'line_token': "line_token=''", 'space_token': "space_token=''", 'padding_side': "padding_side='left'" +}, model_name='CpmAntTokenizer', library='transformers', import_path='transformers.models.cpmant'), ModelAttributes(model=, model_type='model', model_parameters={'num_codebooks': 'num_codebooks: Optional[int + ] = 32', 'vocab_size': 'vocab_size: Optional[int + ] = 2051', 'text_vocab_size': 'text_vocab_size: Optional[int + ] = 128256', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 128002', 'codebook_pad_token_id': 'codebook_pad_token_id: Optional[int + ] = 2050', 'codebook_eos_token_id': 'codebook_eos_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int + ] = None', 'audio_token_id': 'audio_token_id: Optional[int + ] = 128002', 'audio_eos_token_id': 'audio_eos_token_id: Optional[int + ] = 128003', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'head_dim': 'head_dim: Optional[int + ] = None', 'tie_codebooks_embeddings': 'tie_codebooks_embeddings: Optional[bool + ] = True', 'depth_decoder_config': 'depth_decoder_config: Optional[dict + ] = None', 'codec_config': 'codec_config: Optional[dict + ] = None' +}, model_name='CsmForConditionalGeneration', library='transformers', import_path='transformers.models.csm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=246534', 'n_positions': 'n_positions=256', 'n_embd': 'n_embd=1280', 'dff': 'dff=8192', 'n_layer': 'n_layer=48', 'n_head': 'n_head=16', 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_range': 'initializer_range=0.02' +}, model_name='CTRLModel', library='transformers', import_path='transformers.models.ctrl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'unk_token': "unk_token=''" +}, model_name='CTRLTokenizer', library='transformers', import_path='transformers.models.ctrl'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_sizes': 'patch_sizes=[ + 7, + 3, + 3 + ]', 'patch_stride': 'patch_stride=[ + 4, + 2, + 2 + ]', 'patch_padding': 'patch_padding=[ + 2, + 1, + 1 + ]', 'embed_dim': 'embed_dim=[ + 64, + 192, + 384 + ]', 'num_heads': 'num_heads=[ + 1, + 3, + 6 + ]', 'depth': 'depth=[ + 1, + 2, + 10 + ]', 'mlp_ratio': 'mlp_ratio=[ + 4.0, + 4.0, + 4.0 + ]', 'attention_drop_rate': 'attention_drop_rate=[ + 0.0, + 0.0, + 0.0 + ]', 'drop_rate': 'drop_rate=[ + 0.0, + 0.0, + 0.0 + ]', 'drop_path_rate': 'drop_path_rate=[ + 0.0, + 0.0, + 0.1 + ]', 'qkv_bias': 'qkv_bias=[True, True, True + ]', 'cls_token': 'cls_token=[False, False, True + ]', 'qkv_projection_method': "qkv_projection_method=['dw_bn', 'dw_bn', 'dw_bn']", 'kernel_qkv': 'kernel_qkv=[ + 3, + 3, + 3 + ]', 'padding_kv': 'padding_kv=[ + 1, + 1, + 1 + ]', 'stride_kv': 'stride_kv=[ + 2, + 2, + 2 + ]', 'padding_q': 'padding_q=[ + 1, + 1, + 1 + ]', 'stride_q': 'stride_q=[ + 1, + 1, + 1 + ]', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12' +}, model_name='CvtModel', library='transformers', import_path='transformers.models.cvt'), ModelAttributes(model=, model_type='model', model_parameters={'n_head': ['' + ] +}, model_name='CwmModel', library='transformers', import_path='transformers.models.cwm'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ + 512, + 1024, + 2048 + ]', 'feat_strides': 'feat_strides=[ + 8, + 16, + 32 + ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ + 2 + ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ + 256, + 256, + 256 + ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'weight_loss_fgl': 'weight_loss_fgl=0.15', 'weight_loss_ddf': 'weight_loss_ddf=1.5', 'eos_coefficient': 'eos_coefficient=0.0001', 'eval_idx': 'eval_idx=-1', 'layer_scale': 'layer_scale=1', 'max_num_bins': 'max_num_bins=32', 'reg_scale': 'reg_scale=4.0', 'depth_mult': 'depth_mult=1.0', 'top_prob_values': 'top_prob_values=4', 'lqe_hidden_dim': 'lqe_hidden_dim=64', 'lqe_layers': 'lqe_layers=2', 'decoder_offset_scale': 'decoder_offset_scale=0.5', 'decoder_method': "decoder_method='default'", 'up': 'up=0.5' +}, model_name='DFineModel', library='transformers', import_path='transformers.models.d_fine'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'num_queries': 'num_queries=300', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='prelu'", 'hidden_size': 'hidden_size=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'dilation': 'dilation=False', 'class_cost': 'class_cost=2', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'cls_loss_coefficient': 'cls_loss_coefficient=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'focal_alpha': 'focal_alpha=0.25', 'temperature_height': 'temperature_height=20', 'temperature_width': 'temperature_width=20', 'query_dim': 'query_dim=4', 'random_refpoints_xy': 'random_refpoints_xy=False', 'keep_query_pos': 'keep_query_pos=False', 'num_patterns': 'num_patterns=0', 'normalize_before': 'normalize_before=False', 'sine_position_embedding_scale': 'sine_position_embedding_scale=None', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None' +}, model_name='DabDetrModel', library='transformers', import_path='transformers.models.dab_detr'), ModelAttributes(model=, model_type='model', model_parameters={'encoder_hidden_size': 'encoder_hidden_size=64', 'downsampling_ratios': 'downsampling_ratios=[ + 2, + 4, + 8, + 8 + ]', 'decoder_hidden_size': 'decoder_hidden_size=1536', 'n_codebooks': 'n_codebooks=9', 'codebook_size': 'codebook_size=1024', 'codebook_dim': 'codebook_dim=8', 'quantizer_dropout': 'quantizer_dropout=0', 'commitment_loss_weight': 'commitment_loss_weight=0.25', 'codebook_loss_weight': 'codebook_loss_weight=1.0', 'sampling_rate': 'sampling_rate=16000' +}, model_name='DacModel', library='transformers', import_path='transformers.models.dac'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'conv_pos_kernel_size': 'conv_pos_kernel_size=19', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=5', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None' +}, model_name='Data2VecAudioModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' +}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='Data2VecTextModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'use_mask_token': 'use_mask_token=False', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=False', 'use_relative_position_bias': 'use_relative_position_bias=False', 'use_shared_relative_position_bias': 'use_shared_relative_position_bias=False', 'layer_scale_init_value': 'layer_scale_init_value=0.1', 'drop_path_rate': 'drop_path_rate=0.1', 'use_mean_pooling': 'use_mean_pooling=True', 'out_indices': 'out_indices=[ + 3, + 5, + 7, + 11 + ]', 'pool_scales': 'pool_scales=[ + 1, + 2, + 3, + 6 + ]', 'use_auxiliary_head': 'use_auxiliary_head=True', 'auxiliary_loss_weight': 'auxiliary_loss_weight=0.4', 'auxiliary_channels': 'auxiliary_channels=256', 'auxiliary_num_convs': 'auxiliary_num_convs=1', 'auxiliary_concat_input': 'auxiliary_concat_input=False', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' +}, model_name='Data2VecVisionModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='model', model_parameters={'d_model': 'd_model: Optional[int + ] = 2048', 'n_heads': 'n_heads: Optional[int + ] = 16', 'n_layers': 'n_layers: Optional[int + ] = 24', 'max_seq_len': 'max_seq_len: Optional[int + ] = 2048', 'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'resid_pdrop': 'resid_pdrop: Optional[float + ] = 0.0', 'emb_pdrop': 'emb_pdrop: Optional[float + ] = 0.0', 'attn_config': 'attn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxAttentionConfig + ] = None', 'ffn_config': 'ffn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxFFNConfig + ] = None', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='DbrxModel', library='transformers', import_path='transformers.models.dbrx'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'relative_attention': 'relative_attention=False', 'max_relative_positions': 'max_relative_positions=-1', 'pad_token_id': 'pad_token_id=0', 'position_biased_input': 'position_biased_input=True', 'pos_att_type': 'pos_att_type=None', 'pooler_dropout': 'pooler_dropout=0', 'pooler_hidden_act': "pooler_hidden_act='gelu'", 'legacy': 'legacy=True' +}, model_name='DebertaModel', library='transformers', import_path='transformers.models.deberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors='replace'", 'bos_token': "bos_token='[CLS]'", 'eos_token': "eos_token='[SEP]'", 'sep_token': "sep_token='[SEP]'", 'cls_token': "cls_token='[CLS]'", 'unk_token': "unk_token='[UNK]'", 'pad_token': "pad_token='[PAD]'", 'mask_token': "mask_token='[MASK]'", 'add_prefix_space': 'add_prefix_space=False' +}, model_name='DebertaTokenizer', library='transformers', import_path='transformers.models.deberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128100', 'hidden_size': 'hidden_size=1536', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=24', 'intermediate_size': 'intermediate_size=6144', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'relative_attention': 'relative_attention=False', 'max_relative_positions': 'max_relative_positions=-1', 'pad_token_id': 'pad_token_id=0', 'position_biased_input': 'position_biased_input=True', 'pos_att_type': 'pos_att_type=None', 'pooler_dropout': 'pooler_dropout=0', 'pooler_hidden_act': "pooler_hidden_act='gelu'", 'legacy': 'legacy=True' +}, model_name='DebertaV2Model', library='transformers', import_path='transformers.models.deberta_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'do_lower_case': 'do_lower_case=False', 'split_by_punct': 'split_by_punct=False', 'bos_token': "bos_token='[CLS]'", 'eos_token': "eos_token='[SEP]'", 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'add_prefix_space': 'add_prefix_space=True', 'unk_id': 'unk_id=1' +}, model_name='DebertaV2Tokenizer', library='transformers', import_path='transformers.models.deberta_v2'), ModelAttributes(model=, model_type='model', model_parameters={'state_dim': 'state_dim=17', 'act_dim': 'act_dim=4', 'hidden_size': 'hidden_size=128', 'max_ep_len': 'max_ep_len=4096', 'action_tanh': 'action_tanh=True', 'vocab_size': 'vocab_size=1', 'n_positions': 'n_positions=1024', 'n_layer': 'n_layer=3', 'n_head': 'n_head=1', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='relu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' +}, model_name='DecisionTransformerModel', library='transformers', import_path='transformers.models.decision_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int + ] = 0', 'kv_lora_rank': 'kv_lora_rank: Optional[int + ] = 512', 'q_lora_rank': 'q_lora_rank: Optional[int + ] = 1536', 'n_group': 'n_group: Optional[int + ] = None', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = 64', 'n_shared_experts': 'n_shared_experts: Optional[int + ] = 2', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int + ] = 128', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int + ] = 64', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 1.0', 'topk_group': 'topk_group: Optional[int + ] = None', 'topk_method': "topk_method: Optional[str] = 'greedy'", 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False', 'v_head_dim': 'v_head_dim: Optional[int + ] = 128', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = None', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1407' +}, model_name='DeepseekV2Model', library='transformers', import_path='transformers.models.deepseek_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 129280', 'hidden_size': 'hidden_size: Optional[int + ] = 7168', 'intermediate_size': 'intermediate_size: Optional[int + ] = 18432', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 61', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 128', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 128', 'n_shared_experts': 'n_shared_experts: Optional[int + ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = 256', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 2.5', 'kv_lora_rank': 'kv_lora_rank: Optional[int + ] = 512', 'q_lora_rank': 'q_lora_rank: Optional[int + ] = 1536', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int + ] = 64', 'v_head_dim': 'v_head_dim: Optional[int + ] = 128', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int + ] = 128', 'n_group': 'n_group: Optional[int + ] = 8', 'topk_group': 'topk_group: Optional[int + ] = 4', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 8', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int + ] = 3', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = True', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'rope_interleave': 'rope_interleave: Optional[bool + ] = True', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='DeepseekV3Model', library='transformers', import_path='transformers.models.deepseek_v3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig + ] = None', 'vision_config': 'vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig + ] = None', 'image_token_id': 'image_token_id: int = 100015' +}, model_name='DeepseekVLModel', library='transformers', import_path='transformers.models.deepseek_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig + ] = None', 'vision_config': 'vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig + ] = None', 'high_res_vision_config': 'high_res_vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig + ] = None', 'image_token_id': 'image_token_id: int = 100015' +}, model_name='DeepseekVLHybridModel', library='transformers', import_path='transformers.models.deepseek_vl_hybrid'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=300', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'return_intermediate': 'return_intermediate=True', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=False', 'two_stage_num_proposals': 'two_stage_num_proposals=300', 'with_box_refine': 'with_box_refine=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False' +}, model_name='DeformableDetrModel', library='transformers', import_path='transformers.models.deformable_detr'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'encoder_stride': 'encoder_stride=16', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" +}, model_name='DeiTModel', library='transformers', import_path='transformers.models.deit'), ModelAttributes(model=, model_type='model', model_parameters={'fusion_hidden_size': 'fusion_hidden_size=256', 'patch_size': 'patch_size=384', 'initializer_range': 'initializer_range=0.02', 'intermediate_hook_ids': 'intermediate_hook_ids=[ + 11, + 5 + ]', 'intermediate_feature_dims': 'intermediate_feature_dims=[ + 256, + 256 + ]', 'scaled_images_ratios': 'scaled_images_ratios=[ + 0.25, + 0.5, + 1 + ]', 'scaled_images_overlap_ratios': 'scaled_images_overlap_ratios=[ + 0.0, + 0.5, + 0.25 + ]', 'scaled_images_feature_dims': 'scaled_images_feature_dims=[ + 1024, + 1024, + 512 + ]', 'merge_padding_value': 'merge_padding_value=3', 'use_batch_norm_in_fusion_residual': 'use_batch_norm_in_fusion_residual=False', 'use_bias_in_fusion_residual': 'use_bias_in_fusion_residual=True', 'use_fov_model': 'use_fov_model=False', 'num_fov_head_layers': 'num_fov_head_layers=2', 'image_model_config': 'image_model_config=None', 'patch_model_config': 'patch_model_config=None', 'fov_model_config': 'fov_model_config=None' +}, model_name='DepthProModel', library='transformers', import_path='transformers.models.depth_pro'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=100', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' +}, model_name='DetrModel', library='transformers', import_path='transformers.models.detr'), ModelAttributes(model=, model_type='model', model_parameters={'encoder_config': 'encoder_config: Optional[transformers.models.dia.configuration_dia.DiaEncoderConfig + ] = None', 'decoder_config': 'decoder_config: Optional[transformers.models.dia.configuration_dia.DiaDecoderConfig + ] = None', 'norm_eps': 'norm_eps: float = 1e-05', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'pad_token_id': 'pad_token_id: int = 1025', 'eos_token_id': 'eos_token_id: int = 1024', 'bos_token_id': 'bos_token_id: int = 1026', 'delay_pattern': 'delay_pattern: Optional[list[int + ] + ] = None', 'initializer_range': 'initializer_range: float = 0.02' +}, model_name='DiaModel', library='transformers', import_path='transformers.models.dia'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'pad_token': "pad_token: Optional[str] = ''", 'unk_token': "unk_token: Optional[str] = ''", 'max_length': 'max_length: Optional[int + ] = 1024', 'offset': 'offset: int = 0' +}, model_name='DiaTokenizer', library='transformers', import_path='transformers.models.dia'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'lambda_std_dev': 'lambda_std_dev: Optional[float + ] = 0.1', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='DiffLlamaModel', library='transformers', import_path='transformers.models.diffllama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=64', 'depths': 'depths=[ + 3, + 4, + 6, + 5 + ]', 'num_heads': 'num_heads=[ + 2, + 4, + 8, + 16 + ]', 'kernel_size': 'kernel_size=7', 'dilations': 'dilations=[ + [ + 1, + 8, + 1 + ], + [ + 1, + 4, + 1, + 4 + ], + [ + 1, + 2, + 1, + 2, + 1, + 2 + ], + [ + 1, + 1, + 1, + 1, + 1 + ] + ]', 'mlp_ratio': 'mlp_ratio=3.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'layer_scale_init_value': 'layer_scale_init_value=0.0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='DinatModel', library='transformers', import_path='transformers.models.dinat'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=14', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'layerscale_value': 'layerscale_value=1.0', 'drop_path_rate': 'drop_path_rate=0.0', 'use_swiglu_ffn': 'use_swiglu_ffn=False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True', 'use_mask_token': 'use_mask_token=True' +}, model_name='Dinov2Model', library='transformers', import_path='transformers.models.dinov2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'layerscale_value': 'layerscale_value=1.0', 'drop_path_rate': 'drop_path_rate=0.0', 'use_swiglu_ffn': 'use_swiglu_ffn=False', 'num_register_tokens': 'num_register_tokens=4', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True' +}, model_name='Dinov2WithRegistersModel', library='transformers', import_path='transformers.models.dinov2_with_registers'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels: int = 3', 'hidden_sizes': 'hidden_sizes: Optional[list[int + ] + ] = None', 'depths': 'depths: Optional[list[int + ] + ] = None', 'hidden_act': "hidden_act: str = 'gelu'", 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'layer_scale_init_value': 'layer_scale_init_value: float = 1e-06', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'image_size': 'image_size: int = 224', 'out_features': 'out_features: Optional[list[str + ] + ] = None', 'out_indices': 'out_indices: Optional[list[int + ] + ] = None' +}, model_name='DINOv3ConvNextModel', library='transformers', import_path='transformers.models.dinov3_convnext'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size: int = 16', 'hidden_size': 'hidden_size: int = 384', 'intermediate_size': 'intermediate_size: int = 1536', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 6', 'hidden_act': "hidden_act: str = 'gelu'", 'attention_dropout': 'attention_dropout: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-05', 'rope_theta': 'rope_theta: float = 100.0', 'image_size': 'image_size: int = 224', 'num_channels': 'num_channels: int = 3', 'query_bias': 'query_bias: bool = True', 'key_bias': 'key_bias: bool = False', 'value_bias': 'value_bias: bool = True', 'proj_bias': 'proj_bias: bool = True', 'mlp_bias': 'mlp_bias: bool = True', 'layerscale_value': 'layerscale_value: float = 1.0', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'use_gated_mlp': 'use_gated_mlp: bool = False', 'num_register_tokens': 'num_register_tokens: int = 0', 'pos_embed_shift': 'pos_embed_shift: Optional[float + ] = None', 'pos_embed_jitter': 'pos_embed_jitter: Optional[float + ] = None', 'pos_embed_rescale': 'pos_embed_rescale: Optional[float + ] = 2.0', 'out_features': 'out_features: Optional[list[str + ] + ] = None', 'out_indices': 'out_indices: Optional[list[int + ] + ] = None', 'apply_layernorm': 'apply_layernorm: bool = True', 'reshape_hidden_states': 'reshape_hidden_states: bool = True' +}, model_name='DINOv3ViTModel', library='transformers', import_path='transformers.models.dinov3_vit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'max_position_embeddings': 'max_position_embeddings=512', 'sinusoidal_pos_embds': 'sinusoidal_pos_embds=False', 'n_layers': 'n_layers=6', 'n_heads': 'n_heads=12', 'dim': 'dim=768', 'hidden_dim': 'hidden_dim=3072', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation': "activation='gelu'", 'initializer_range': 'initializer_range=0.02', 'qa_dropout': 'qa_dropout=0.1', 'seq_classif_dropout': 'seq_classif_dropout=0.2', 'pad_token_id': 'pad_token_id=0' +}, model_name='DistilBertModel', library='transformers', import_path='transformers.models.distilbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32768', 'hidden_size': 'hidden_size: Optional[int + ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int + ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'keep_window_size': 'keep_window_size: Optional[int + ] = 2048', 'is_moe': 'is_moe: Optional[bool + ] = False', 'num_experts': 'num_experts: Optional[int + ] = 16384', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 64', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001' +}, model_name='DogeModel', library='transformers', import_path='transformers.models.doge'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'num_heads': 'num_heads=[ + 3, + 6, + 12, + 24 + ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' +}, model_name='DonutSwinModel', library='transformers', import_path='transformers.models.donut'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 152064', 'hidden_size': 'hidden_size: Optional[int + ] = 4608', 'intermediate_size': 'intermediate_size: Optional[int + ] = 10944', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1408', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 62', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'n_shared_experts': 'n_shared_experts: Optional[int + ] = None', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = None', 'n_group': 'n_group: Optional[int + ] = 1', 'topk_group': 'topk_group: Optional[int + ] = 1', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = None', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int + ] = 0', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 1.0', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 62', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Dots1Model', library='transformers', import_path='transformers.models.dots1'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'projection_dim': 'projection_dim: int = 0' +}, model_name='DPRQuestionEncoder', library='transformers', import_path='transformers.models.dpr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='DPRQuestionEncoderTokenizerFast', library='transformers', import_path='transformers.models.dpr'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=384', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'is_hybrid': 'is_hybrid=False', 'qkv_bias': 'qkv_bias=True', 'backbone_out_indices': 'backbone_out_indices=[ + 2, + 5, + 8, + 11 + ]', 'readout_type': "readout_type='project'", 'reassemble_factors': 'reassemble_factors=[ + 4, + 2, + 1, + 0.5 + ]', 'neck_hidden_sizes': 'neck_hidden_sizes=[ + 96, + 192, + 384, + 768 + ]', 'fusion_hidden_size': 'fusion_hidden_size=256', 'head_in_index': 'head_in_index=-1', 'use_batch_norm_in_fusion_residual': 'use_batch_norm_in_fusion_residual=False', 'use_bias_in_fusion_residual': 'use_bias_in_fusion_residual=None', 'add_projection': 'add_projection=False', 'use_auxiliary_head': 'use_auxiliary_head=True', 'auxiliary_loss_weight': 'auxiliary_loss_weight=0.4', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255', 'semantic_classifier_dropout': 'semantic_classifier_dropout=0.1', 'backbone_featmap_shape': 'backbone_featmap_shape=[ + 1, + 1024, + 24, + 24 + ]', 'neck_ignore_stages': 'neck_ignore_stages=[ + 0, + 1 + ]', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" +}, model_name='DPTModel', library='transformers', import_path='transformers.models.dpt'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='EdgeTamModel', library='transformers', import_path='transformers.models.edgetam'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1024', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=-1', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=2', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_mlp_hidden_size': 'memory_attention_mlp_hidden_size=2048', 'memory_attention_mlp_hidden_act': "memory_attention_mlp_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_k_sizes': 'memory_attention_rope_k_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'perceiver_resampler_num_latents': 'perceiver_resampler_num_latents=256', 'perceiver_resampler_num_latents_2d': 'perceiver_resampler_num_latents_2d=256', 'perceiver_resampler_hidden_size': 'perceiver_resampler_hidden_size=64', 'perceiver_resampler_mlp_intermediate_size': 'perceiver_resampler_mlp_intermediate_size=256', 'perceiver_resampler_num_attention_heads': 'perceiver_resampler_num_attention_heads=1', 'perceiver_resampler_attention_head_dim': 'perceiver_resampler_attention_head_dim=64', 'perceiver_resampler_num_layers': 'perceiver_resampler_num_layers=2', 'perceiver_resampler_hidden_dropout': 'perceiver_resampler_hidden_dropout=0.0', 'perceiver_resampler_attention_dropout': 'perceiver_resampler_attention_dropout=0.0', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" +}, model_name='EdgeTamVideoModel', library='transformers', import_path='transformers.models.edgetam_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone_channel_list': 'backbone_channel_list=None', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'fpn_kernel_size': 'fpn_kernel_size=1', 'fpn_stride': 'fpn_stride=1', 'fpn_padding': 'fpn_padding=0', 'fpn_top_down_levels': 'fpn_top_down_levels=None', 'num_feature_levels': 'num_feature_levels=3', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' +}, model_name='EdgeTamVisionModel', library='transformers', import_path='transformers.models.edgetam'), ModelAttributes(model=, model_type='model', model_parameters={'stage_num_blocks': 'stage_num_blocks: Optional[list[int + ] + ] = None', 'out_features': 'out_features: Optional[list[int + ] + ] = None', 'stage_stride': 'stage_stride: Optional[list[int + ] + ] = None', 'hidden_size': 'hidden_size: int = 256', 'activation_function': "activation_function: str = 'relu'", 'q_aggregation_kernel_size': 'q_aggregation_kernel_size: int = 4', 'kv_aggregation_kernel_size': 'kv_aggregation_kernel_size: int = 4', 'q_aggregation_stride': 'q_aggregation_stride: int = 4', 'kv_aggregation_stride': 'kv_aggregation_stride: int = 4', 'num_attention_layers': 'num_attention_layers: int = 4', 'num_attention_heads': 'num_attention_heads: int = 8', 'attention_dropout': 'attention_dropout: float = 0.0', 'attention_bias': 'attention_bias: bool = False', 'mlp_activation_function': "mlp_activation_function: str = 'leaky_relu'", 'coarse_matching_skip_softmax': 'coarse_matching_skip_softmax: bool = False', 'coarse_matching_threshold': 'coarse_matching_threshold: float = 0.2', 'coarse_matching_temperature': 'coarse_matching_temperature: float = 0.1', 'coarse_matching_border_removal': 'coarse_matching_border_removal: int = 2', 'fine_kernel_size': 'fine_kernel_size: int = 8', 'batch_norm_eps': 'batch_norm_eps: float = 1e-05', 'rope_parameters': 'rope_parameters: Optional[dict + ] = None', 'fine_matching_slice_dim': 'fine_matching_slice_dim: int = 8', 'fine_matching_regress_temperature': 'fine_matching_regress_temperature: float = 10.0', 'initializer_range': 'initializer_range: float = 0.02' +}, model_name='EfficientLoFTRModel', library='transformers', import_path='transformers.models.efficientloftr'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels: int = 3', 'image_size': 'image_size: int = 600', 'width_coefficient': 'width_coefficient: float = 2.0', 'depth_coefficient': 'depth_coefficient: float = 3.1', 'depth_divisor': 'depth_divisor: int = 8', 'kernel_sizes': 'kernel_sizes: list[int + ] = [ + 3, + 3, + 5, + 3, + 5, + 5, + 3 + ]', 'in_channels': 'in_channels: list[int + ] = [ + 32, + 16, + 24, + 40, + 80, + 112, + 192 + ]', 'out_channels': 'out_channels: list[int + ] = [ + 16, + 24, + 40, + 80, + 112, + 192, + 320 + ]', 'depthwise_padding': 'depthwise_padding: list[int + ] = []', 'strides': 'strides: list[int + ] = [ + 1, + 2, + 2, + 2, + 1, + 2, + 1 + ]', 'num_block_repeats': 'num_block_repeats: list[int + ] = [ + 1, + 2, + 2, + 3, + 3, + 4, + 1 + ]', 'expand_ratios': 'expand_ratios: list[int + ] = [ + 1, + 6, + 6, + 6, + 6, + 6, + 6 + ]', 'squeeze_expansion_ratio': 'squeeze_expansion_ratio: float = 0.25', 'hidden_act': "hidden_act: str = 'swish'", 'hidden_dim': 'hidden_dim: int = 2560', 'pooling_type': "pooling_type: str = 'mean'", 'initializer_range': 'initializer_range: float = 0.02', 'batch_norm_eps': 'batch_norm_eps: float = 0.001', 'batch_norm_momentum': 'batch_norm_momentum: float = 0.99', 'dropout_rate': 'dropout_rate: float = 0.5', 'drop_connect_rate': 'drop_connect_rate: float = 0.2' +}, model_name='EfficientNetModel', library='transformers', import_path='transformers.models.efficientnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'embedding_size': 'embedding_size=128', 'hidden_size': 'hidden_size=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=4', 'intermediate_size': 'intermediate_size=1024', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': "summary_activation='gelu'", 'summary_last_dropout': 'summary_last_dropout=0.1', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='ElectraModel', library='transformers', import_path='transformers.models.electra'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vq_config': 'vq_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3VQVAEConfig + ] = None', 'text_config': 'text_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3TextConfig + ] = None', 'vocabulary_map': 'vocabulary_map: Optional[dict[int, int + ] + ] = None' +}, model_name='Emu3Model', library='transformers', import_path='transformers.models.emu3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'target_bandwidths': 'target_bandwidths=[ + 1.5, + 3.0, + 6.0, + 12.0, + 24.0 + ]', 'sampling_rate': 'sampling_rate=24000', 'audio_channels': 'audio_channels=1', 'normalize': 'normalize=False', 'chunk_length_s': 'chunk_length_s=None', 'overlap': 'overlap=None', 'hidden_size': 'hidden_size=128', 'num_filters': 'num_filters=32', 'num_residual_layers': 'num_residual_layers=1', 'upsampling_ratios': 'upsampling_ratios=[ + 8, + 5, + 4, + 2 + ]', 'norm_type': "norm_type='weight_norm'", 'kernel_size': 'kernel_size=7', 'last_kernel_size': 'last_kernel_size=7', 'residual_kernel_size': 'residual_kernel_size=3', 'dilation_growth_rate': 'dilation_growth_rate=2', 'use_causal_conv': 'use_causal_conv=True', 'pad_mode': "pad_mode='reflect'", 'compress': 'compress=2', 'num_lstm_layers': 'num_lstm_layers=2', 'trim_right_ratio': 'trim_right_ratio=1.0', 'codebook_size': 'codebook_size=1024', 'codebook_dim': 'codebook_dim=None', 'use_conv_shortcut': 'use_conv_shortcut=True' +}, model_name='EncodecModel', library='transformers', import_path='transformers.models.encodec'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'task_type_vocab_size': 'task_type_vocab_size=3', 'use_task_id': 'use_task_id=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='ErnieModel', library='transformers', import_path='transformers.models.ernie'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 103424', 'hidden_size': 'hidden_size: Optional[int + ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int + ] = 3072', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 18', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_bias': 'use_bias: Optional[bool + ] = False', 'head_dim': 'head_dim: Optional[int + ] = 128' +}, model_name='Ernie4_5Model', library='transformers', import_path='transformers.models.ernie4_5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 103424', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int + ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_bias': 'use_bias: Optional[int + ] = False', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1536', 'moe_k': 'moe_k: Optional[int + ] = 6', 'moe_num_experts': 'moe_num_experts: Optional[int + ] = 64', 'moe_num_shared_experts': 'moe_num_shared_experts: Optional[int + ] = 2', 'moe_layer_start_index': 'moe_layer_start_index: Optional[int + ] = 1', 'moe_layer_end_index': 'moe_layer_end_index: Optional[int + ] = -1', 'moe_layer_interval': 'moe_layer_interval: Optional[int + ] = 1', 'moe_norm_min': 'moe_norm_min: Optional[int + ] = 1e-12', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001' +}, model_name='Ernie4_5_MoeModel', library='transformers', import_path='transformers.models.ernie4_5_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_start_token_id': 'image_start_token_id=101304', 'image_end_token_id': 'image_end_token_id=101305', 'image_token_id': 'image_token_id=100295', 'video_start_token_id': 'video_start_token_id=101306', 'video_end_token_id': 'video_end_token_id=101307', 'video_token_id': 'video_token_id=103367' +}, model_name='Ernie4_5_VL_MoeModel', library='transformers', import_path='transformers.models.ernie4_5_vl_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'mask_token_id': 'mask_token_id=None', 'pad_token_id': 'pad_token_id=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1026', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'position_embedding_type': "position_embedding_type='absolute'", 'emb_layer_norm_before': 'emb_layer_norm_before=None', 'token_dropout': 'token_dropout=False', 'is_folding_model': 'is_folding_model=False', 'esmfold_config': 'esmfold_config=None', 'vocab_list': 'vocab_list=None' +}, model_name='EsmModel', library='transformers', import_path='transformers.models.esm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'unk_token': "unk_token=''", 'cls_token': "cls_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'eos_token': "eos_token=''" +}, model_name='EsmTokenizer', library='transformers', import_path='transformers.models.esm'), ModelAttributes(model=, model_type='model', model_parameters={'protein_encoder_config': 'protein_encoder_config: Optional[dict + ] = None', 'vocab_size': 'vocab_size: Optional[int + ] = 128256', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'aligner_ffn_mult': 'aligner_ffn_mult: Optional[int + ] = 4', 'aligner_enable_bias': 'aligner_enable_bias: Optional[bool + ] = True', 'aligner_attention_probs_dropout_prob': 'aligner_attention_probs_dropout_prob: Optional[float + ] = 0.1', 'aligner_num_add_layers': 'aligner_num_add_layers: Optional[int + ] = 8', 'resampler_depth': 'resampler_depth: Optional[int + ] = 6', 'resampler_dim_head': 'resampler_dim_head: Optional[int + ] = 64', 'resampler_heads': 'resampler_heads: Optional[int + ] = 8', 'resampler_num_latents': 'resampler_num_latents: Optional[int + ] = 64', 'resampler_ff_mult': 'resampler_ff_mult: Optional[int + ] = 4', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int + ] = 128009', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False' +}, model_name='EvollaModel', library='transformers', import_path='transformers.models.evolla'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 102400', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'sliding_window_pattern': 'sliding_window_pattern: Optional[int + ] = 4', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Exaone4Model', library='transformers', import_path='transformers.models.exaone4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 65024', 'hidden_size': 'hidden_size: Optional[int + ] = 4544', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 71', 'num_ln_in_parallel_attn': 'num_ln_in_parallel_attn: Optional[int + ] = None', 'layer_norm_epsilon': 'layer_norm_epsilon: Optional[int + ] = 1e-05', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_kv_heads': 'num_kv_heads: Optional[int + ] = None', 'alibi': 'alibi: Optional[bool + ] = False', 'new_decoder_architecture': 'new_decoder_architecture: Optional[bool + ] = False', 'multi_query': 'multi_query: Optional[bool + ] = True', 'parallel_attn': 'parallel_attn: Optional[bool + ] = True', 'bias': 'bias: Optional[bool + ] = False', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 11', 'eos_token_id': 'eos_token_id: Optional[int + ] = 11', 'ffn_hidden_size': 'ffn_hidden_size: Optional[int + ] = None', 'activation': "activation: Optional[str] = 'gelu'" +}, model_name='FalconModel', library='transformers', import_path='transformers.models.falcon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 128000', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'num_logits_to_keep': 'num_logits_to_keep: Optional[int + ] = 1', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mamba_d_ssm': 'mamba_d_ssm: Optional[int + ] = 1024', 'mamba_n_heads': 'mamba_n_heads: Optional[int + ] = 128', 'mamba_d_head': "mamba_d_head: Optional[str] = 'auto'", 'mamba_n_groups': 'mamba_n_groups: Optional[int + ] = 1', 'mamba_d_state': 'mamba_d_state: Optional[int + ] = 256', 'mamba_d_conv': 'mamba_d_conv: Optional[int + ] = 4', 'mamba_expand': 'mamba_expand: Optional[int + ] = 2', 'mamba_chunk_size': 'mamba_chunk_size: Optional[int + ] = 256', 'mamba_conv_bias': 'mamba_conv_bias: Optional[bool + ] = True', 'mamba_proj_bias': 'mamba_proj_bias: Optional[bool + ] = False', 'mamba_norm_before_gate': 'mamba_norm_before_gate: Optional[bool + ] = True', 'mamba_rms_norm': 'mamba_rms_norm: Optional[bool + ] = False', 'projectors_bias': 'projectors_bias: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'lm_head_multiplier': 'lm_head_multiplier: Optional[float + ] = 1.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float + ] = 1.0', 'mlp_multipliers': 'mlp_multipliers: Optional[int + ] = None', 'key_multiplier': 'key_multiplier: Optional[int + ] = None', 'attention_out_multiplier': 'attention_out_multiplier: Optional[int + ] = None', 'attention_in_multiplier': 'attention_in_multiplier: Optional[int + ] = None', 'ssm_multipliers': 'ssm_multipliers: Optional[int + ] = None', 'ssm_in_multiplier': 'ssm_in_multiplier: Optional[int + ] = None', 'ssm_out_multiplier': 'ssm_out_multiplier: Optional[int + ] = None' +}, model_name='FalconH1Model', library='transformers', import_path='transformers.models.falcon_h1'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50280', 'hidden_size': 'hidden_size=768', 'state_size': 'state_size=16', 'num_hidden_layers': 'num_hidden_layers=32', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_scale': 'time_step_scale=1.0', 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_init_scheme': "time_step_init_scheme='random'", 'time_step_floor': 'time_step_floor=0.0001', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'use_falcon_mambapy': 'use_falcon_mambapy=False', 'mixer_rms_eps': 'mixer_rms_eps=1e-06' +}, model_name='FalconMambaModel', library='transformers', import_path='transformers.models.falcon_mamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151646', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='full'", 'vision_feature_layer': 'vision_feature_layer=-1', 'multimodal_projector_bias': 'multimodal_projector_bias=True' +}, model_name='FastVlmModel', library='transformers', import_path='transformers.models.fast_vlm'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=384', 'vocab_size': 'vocab_size=78', 'num_mel_bins': 'num_mel_bins=80', 'encoder_num_attention_heads': 'encoder_num_attention_heads=2', 'encoder_layers': 'encoder_layers=4', 'encoder_linear_units': 'encoder_linear_units=1536', 'decoder_layers': 'decoder_layers=4', 'decoder_num_attention_heads': 'decoder_num_attention_heads=2', 'decoder_linear_units': 'decoder_linear_units=1536', 'speech_decoder_postnet_layers': 'speech_decoder_postnet_layers=5', 'speech_decoder_postnet_units': 'speech_decoder_postnet_units=256', 'speech_decoder_postnet_kernel': 'speech_decoder_postnet_kernel=5', 'positionwise_conv_kernel_size': 'positionwise_conv_kernel_size=3', 'encoder_normalize_before': 'encoder_normalize_before=False', 'decoder_normalize_before': 'decoder_normalize_before=False', 'encoder_concat_after': 'encoder_concat_after=False', 'decoder_concat_after': 'decoder_concat_after=False', 'reduction_factor': 'reduction_factor=1', 'speaking_speed': 'speaking_speed=1.0', 'use_macaron_style_in_conformer': 'use_macaron_style_in_conformer=True', 'use_cnn_in_conformer': 'use_cnn_in_conformer=True', 'encoder_kernel_size': 'encoder_kernel_size=7', 'decoder_kernel_size': 'decoder_kernel_size=31', 'duration_predictor_layers': 'duration_predictor_layers=2', 'duration_predictor_channels': 'duration_predictor_channels=256', 'duration_predictor_kernel_size': 'duration_predictor_kernel_size=3', 'energy_predictor_layers': 'energy_predictor_layers=2', 'energy_predictor_channels': 'energy_predictor_channels=256', 'energy_predictor_kernel_size': 'energy_predictor_kernel_size=3', 'energy_predictor_dropout': 'energy_predictor_dropout=0.5', 'energy_embed_kernel_size': 'energy_embed_kernel_size=1', 'energy_embed_dropout': 'energy_embed_dropout=0.0', 'stop_gradient_from_energy_predictor': 'stop_gradient_from_energy_predictor=False', 'pitch_predictor_layers': 'pitch_predictor_layers=5', 'pitch_predictor_channels': 'pitch_predictor_channels=256', 'pitch_predictor_kernel_size': 'pitch_predictor_kernel_size=5', 'pitch_predictor_dropout': 'pitch_predictor_dropout=0.5', 'pitch_embed_kernel_size': 'pitch_embed_kernel_size=1', 'pitch_embed_dropout': 'pitch_embed_dropout=0.0', 'stop_gradient_from_pitch_predictor': 'stop_gradient_from_pitch_predictor=True', 'encoder_dropout_rate': 'encoder_dropout_rate=0.2', 'encoder_positional_dropout_rate': 'encoder_positional_dropout_rate=0.2', 'encoder_attention_dropout_rate': 'encoder_attention_dropout_rate=0.2', 'decoder_dropout_rate': 'decoder_dropout_rate=0.2', 'decoder_positional_dropout_rate': 'decoder_positional_dropout_rate=0.2', 'decoder_attention_dropout_rate': 'decoder_attention_dropout_rate=0.2', 'duration_predictor_dropout_rate': 'duration_predictor_dropout_rate=0.2', 'speech_decoder_postnet_dropout': 'speech_decoder_postnet_dropout=0.5', 'max_source_positions': 'max_source_positions=5000', 'use_masking': 'use_masking=True', 'use_weighted_masking': 'use_weighted_masking=False', 'num_speakers': 'num_speakers=None', 'num_languages': 'num_languages=None', 'speaker_embed_dim': 'speaker_embed_dim=None', 'is_encoder_decoder': 'is_encoder_decoder=True', 'convolution_bias': 'convolution_bias=True' +}, model_name='FastSpeech2ConformerModel', library='transformers', import_path='transformers.models.fastspeech2_conformer'), ModelAttributes(model=, model_type='model', model_parameters={'model_config': 'model_config: Optional[dict + ] = None', 'vocoder_config': 'vocoder_config: Optional[dict + ] = None' +}, model_name='FastSpeech2ConformerWithHifiGan', library='transformers', import_path='transformers.models.fastspeech2_conformer'), ModelAttributes(model=, model_type='model', model_parameters={'pre_norm': 'pre_norm=False', 'layerdrop': 'layerdrop=0.0', 'vocab_size': 'vocab_size=30145', 'emb_dim': 'emb_dim=2048', 'n_layers': 'n_layers=12', 'n_heads': 'n_heads=16', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'gelu_activation': 'gelu_activation=True', 'sinusoidal_embeddings': 'sinusoidal_embeddings=False', 'causal': 'causal=False', 'asm': 'asm=False', 'n_langs': 'n_langs=1', 'use_lang_emb': 'use_lang_emb=True', 'max_position_embeddings': 'max_position_embeddings=512', 'embed_init_std': 'embed_init_std=0.02209708691207961', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'init_std': 'init_std=0.02', 'bos_index': 'bos_index=0', 'eos_index': 'eos_index=1', 'pad_index': 'pad_index=2', 'unk_index': 'unk_index=3', 'mask_index': 'mask_index=5', 'is_encoder': 'is_encoder=True', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'mask_token_id': 'mask_token_id=0', 'lang_id': 'lang_id=0', 'pad_token_id': 'pad_token_id=2', 'bos_token_id': 'bos_token_id=0' +}, model_name='FlaubertModel', library='transformers', import_path='transformers.models.flaubert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'do_lowercase': 'do_lowercase=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", 'lang2id': 'lang2id=None', 'id2lang': 'id2lang=None' +}, model_name='FlaubertTokenizer', library='transformers', import_path='transformers.models.flaubert'), ModelAttributes(model=, model_type='model', model_parameters={'image_config': 'image_config: Optional[dict[str, Any + ] + ] = None', 'text_config': 'text_config: Optional[dict[str, Any + ] + ] = None', 'multimodal_config': 'multimodal_config: Optional[dict[str, Any + ] + ] = None', 'image_codebook_config': 'image_codebook_config: Optional[dict[str, Any + ] + ] = None', 'hidden_size': 'hidden_size: int = 768', 'layer_norm_eps': 'layer_norm_eps: float = 1e-12', 'projection_dim': 'projection_dim: int = 768', 'init_codebook': 'init_codebook: bool = True', 'logit_scale_init_value': 'logit_scale_init_value: float = 2.6592', 'initializer_range': 'initializer_range: float = 0.02', 'ce_ignore_index': 'ce_ignore_index: int = -100', 'mim_weight': 'mim_weight: float = 1.0', 'mlm_weight': 'mlm_weight: float = 1.0', 'global_contrastive_weight': 'global_contrastive_weight: float = 1.0', 'itm_weight': 'itm_weight: float = 1.0', 'mmm_image_weight': 'mmm_image_weight: float = 1.0', 'mmm_text_weight': 'mmm_text_weight: float = 1.0', 'global_backprop_contrastive': 'global_backprop_contrastive: bool = True', 'skip_unmasked_multimodal_encoder': 'skip_unmasked_multimodal_encoder: bool = True', 'return_loss': 'return_loss: bool = True' +}, model_name='FlavaModel', library='transformers', import_path='transformers.models.flava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 100352', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 100277', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'eos_token_id': 'eos_token_id: Optional[int + ] = 100257', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 5', 'num_experts': 'num_experts: Optional[int + ] = 7', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.01', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False' +}, model_name='FlexOlmoModel', library='transformers', import_path='transformers.models.flex_olmo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=51289', 'is_encoder_decoder': 'is_encoder_decoder=True' +}, model_name='Florence2Model', library='transformers', import_path='transformers.models.florence2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_new'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=4', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_tpu_fourier_optimizations': 'use_tpu_fourier_optimizations=False', 'tpu_short_seq_length': 'tpu_short_seq_length=512', 'pad_token_id': 'pad_token_id=3', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' +}, model_name='FNetModel', library='transformers', import_path='transformers.models.fnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='FNetTokenizer', library='transformers', import_path='transformers.models.fnet'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'use_conv_embed': 'use_conv_embed=False', 'hidden_sizes': 'hidden_sizes=[ + 192, + 384, + 768, + 768 + ]', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'focal_levels': 'focal_levels=[ + 2, + 2, + 2, + 2 + ]', 'focal_windows': 'focal_windows=[ + 3, + 3, + 3, + 3 + ]', 'hidden_act': "hidden_act='gelu'", 'mlp_ratio': 'mlp_ratio=4.0', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'use_layerscale': 'use_layerscale=False', 'layerscale_value': 'layerscale_value=0.0001', 'use_post_layernorm': 'use_post_layernorm=False', 'use_post_layernorm_in_modulation': 'use_post_layernorm_in_modulation=False', 'normalize_modulator': 'normalize_modulator=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='FocalNetModel', library='transformers', import_path='transformers.models.focalnet'), ModelAttributes(model=, model_type='model', model_parameters={'langs': "langs=['en', 'de']", 'src_vocab_size': 'src_vocab_size=42024', 'tgt_vocab_size': 'tgt_vocab_size=42024', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'max_length': 'max_length=200', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_layers': 'encoder_layers=12', 'encoder_attention_heads': 'encoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_layers': 'decoder_layers=12', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'attention_dropout': 'attention_dropout=0.0', 'dropout': 'dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'is_encoder_decoder': 'is_encoder_decoder=True', 'scale_embedding': 'scale_embedding=True', 'tie_word_embeddings': 'tie_word_embeddings=False', 'num_beams': 'num_beams=5', 'length_penalty': 'length_penalty=1.0', 'early_stopping': 'early_stopping=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2', 'common_kwargs': '**common_kwargs' +}, model_name='FSMTModel', library='transformers', import_path='transformers.models.fsmt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'langs': 'langs=None', 'src_vocab_file': 'src_vocab_file=None', 'tgt_vocab_file': 'tgt_vocab_file=None', 'merges_file': 'merges_file=None', 'do_lower_case': 'do_lower_case=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''" +}, model_name='FSMTTokenizer', library='transformers', import_path='transformers.models.fsmt'), ModelAttributes(model=, model_type='model', model_parameters=None, model_name='FunnelModel', library='transformers', import_path='transformers.models.funnel'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = ''", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'mask_token': "mask_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'clean_text': 'clean_text: bool = True', 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None', 'wordpieces_prefix': "wordpieces_prefix: str = '##'" +}, model_name='FunnelTokenizer', library='transformers', import_path='transformers.models.funnel'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 262144', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 16384', 'image_size': 'image_size: Optional[int + ] = 300', 'patch_size': 'patch_size: Optional[int + ] = 30', 'num_channels': 'num_channels: Optional[int + ] = 3', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool + ] = True', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'image_token_id': 'image_token_id: Optional[int + ] = 71011', 'text_config': 'text_config: Optional[dict + ] = None' +}, model_name='FuyuModel', library='transformers', import_path='transformers.models.fuyu'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int + ] = 24576', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 16', 'head_dim': 'head_dim: Optional[int + ] = 256', 'hidden_act': "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool + ] = None' +}, model_name='GemmaModel', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int + ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'head_dim': 'head_dim: Optional[int + ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int + ] = 256', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float + ] = 30.0', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float + ] = 50.0', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool + ] = None' +}, model_name='Gemma2Model', library='transformers', import_path='transformers.models.gemma2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Union[transformers.models.gemma3.configuration_gemma3.Gemma3TextConfig, dict[str, Any + ], NoneType + ] = None', 'vision_config': 'vision_config: Union[transformers.models.siglip.configuration_siglip.SiglipVisionConfig, dict[str, Any + ], NoneType + ] = None', 'mm_tokens_per_image': 'mm_tokens_per_image: int = 256', 'boi_token_index': 'boi_token_index: int = 255999', 'eoi_token_index': 'eoi_token_index: int = 256000', 'image_token_index': 'image_token_index: int = 262144', 'initializer_range': 'initializer_range: float = 0.02' +}, model_name='Gemma3Model', library='transformers', import_path='transformers.models.gemma3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 262208', 'hidden_size': 'hidden_size: Optional[int + ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int + ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'head_dim': 'head_dim: Optional[int + ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int + ] = 256', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float + ] = None', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float + ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool + ] = False' +}, model_name='Gemma3TextModel', library='transformers', import_path='transformers.models.gemma3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nTextConfig, dict[str, Any + ], NoneType + ] = None', 'vision_config': 'vision_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nVisionConfig, dict[str, Any + ], NoneType + ] = None', 'audio_config': 'audio_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nAudioConfig, dict[str, Any + ], NoneType + ] = None', 'audio_soft_tokens_per_image': 'audio_soft_tokens_per_image: int = 188', 'vision_soft_tokens_per_image': 'vision_soft_tokens_per_image: int = 256', 'boi_token_id': 'boi_token_id: int = 255999', 'eoi_token_id': 'eoi_token_id: int = 262144', 'image_token_id': 'image_token_id: int = 262145', 'boa_token_id': 'boa_token_id: int = 256000', 'eoa_token_id': 'eoa_token_id: int = 262272', 'audio_token_id': 'audio_token_id: int = 262273', 'initializer_range': 'initializer_range: float = 0.02' +}, model_name='Gemma3nModel', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 128', 'vocab_offset': 'vocab_offset: int = 262272', 'input_feat_size': 'input_feat_size: int = 128', 'hidden_size': 'hidden_size: int = 1536', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'gradient_clipping': 'gradient_clipping: float = 10000000000.0', 'conf_attention_chunk_size': 'conf_attention_chunk_size: int = 12', 'conf_attention_context_left': 'conf_attention_context_left: int = 13', 'conf_attention_context_right': 'conf_attention_context_right: int = 0', 'conf_attention_logit_cap': 'conf_attention_logit_cap: float = 50.0', 'conf_num_attention_heads': 'conf_num_attention_heads: int = 8', 'conf_num_hidden_layers': 'conf_num_hidden_layers: int = 12', 'conf_conv_kernel_size': 'conf_conv_kernel_size: int = 5', 'conf_reduction_factor': 'conf_reduction_factor: int = 4', 'conf_residual_weight': 'conf_residual_weight: float = 0.5', 'sscp_conv_channel_size': 'sscp_conv_channel_size: tuple[int, int + ] = (128, + 32)', 'sscp_conv_group_norm_eps': 'sscp_conv_group_norm_eps: float = 0.001', 'sscp_conv_kernel_size': 'sscp_conv_kernel_size: tuple[tuple[int, int + ], tuple[int, int + ] + ] = ((3, + 3), (3, + 3))', 'sscp_conv_stride_size': 'sscp_conv_stride_size: tuple[tuple[int, int + ], tuple[int, int + ] + ] = ((2, + 2), (2, + 2))' +}, model_name='Gemma3nAudioEncoder', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 262400', 'vocab_size_per_layer_input': 'vocab_size_per_layer_input: int = 262144', 'hidden_size': 'hidden_size: int = 2048', 'hidden_size_per_layer_input': 'hidden_size_per_layer_input: int = 256', 'intermediate_size': 'intermediate_size: Union[int, collections.abc.Sequence[int + ] + ] = 16384', 'num_hidden_layers': 'num_hidden_layers: int = 35', 'num_attention_heads': 'num_attention_heads: int = 8', 'num_key_value_heads': 'num_key_value_heads: int = 2', 'head_dim': 'head_dim: int = 256', 'hidden_activation': "hidden_activation: str = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: int = 32768', 'initializer_range': 'initializer_range: float = 0.02', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'pad_token_id': 'pad_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 2', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: bool = False', 'attention_dropout': 'attention_dropout: float = 0.0', 'sliding_window': 'sliding_window: int = 512', 'layer_types': 'layer_types: Optional[collections.abc.Sequence[str + ] + ] = None', 'final_logit_softcapping': 'final_logit_softcapping: float = 30.0', 'altup_active_idx': 'altup_active_idx: int = 0', 'altup_coef_clip': 'altup_coef_clip: float = 120.0', 'altup_correct_scale': 'altup_correct_scale: bool = True', 'altup_num_inputs': 'altup_num_inputs: int = 4', 'num_kv_shared_layers': 'num_kv_shared_layers: int = 15', 'laurel_rank': 'laurel_rank: int = 64', 'activation_sparsity_pattern': 'activation_sparsity_pattern: Union[float, collections.abc.Sequence[float + ], NoneType + ] = None' +}, model_name='Gemma3nTextModel', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'_resnet_': ['' + ] +}, model_name='TimmWrapperModel', library='transformers', import_path='transformers.models.timm_wrapper'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=6', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'tie_word_embeddings': 'tie_word_embeddings=False', 'bos_token_id': 'bos_token_id=101', 'eos_token_id': 'eos_token_id=102', 'num_image_with_embedding': 'num_image_with_embedding=None' +}, model_name='GitModel', library='transformers', import_path='transformers.models.git'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151552', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1.5625e-07', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'pad_token_id': 'pad_token_id: Optional[int + ] = 151329', 'eos_token_id': 'eos_token_id: Optional[list[int + ] + ] = [ + 151329, + 151336, + 151338 + ]', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = True' +}, model_name='GlmModel', library='transformers', import_path='transformers.models.glm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151552', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1.5625e-07', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'pad_token_id': 'pad_token_id: Optional[int + ] = 151329', 'eos_token_id': 'eos_token_id: Optional[list[int + ] + ] = [ + 151329, + 151336, + 151338 + ]', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = True' +}, model_name='Glm4Model', library='transformers', import_path='transformers.models.glm4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151343', 'video_token_id': 'video_token_id=151344', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151361', 'video_end_token_id': 'video_end_token_id=151362' +}, model_name='Glm46VModel', library='transformers', import_path='transformers.models.glm46v'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151552', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 10944', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 46', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 96', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 8', 'n_shared_experts': 'n_shared_experts: Optional[int + ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = 128', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 1.0', 'n_group': 'n_group: Optional[int + ] = 1', 'topk_group': 'topk_group: Optional[int + ] = 1', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int + ] = 1', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = True', 'use_qk_norm': 'use_qk_norm: Optional[bool + ] = False' +}, model_name='Glm4MoeModel', library='transformers', import_path='transformers.models.glm4_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151343', 'video_token_id': 'video_token_id=151344', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151341', 'video_end_token_id': 'video_end_token_id=151342' +}, model_name='Glm4vModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151363', 'video_token_id': 'video_token_id=151364', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151341', 'video_end_token_id': 'video_end_token_id=151342' +}, model_name='Glm4vMoeModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151424', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 10944', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 46', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 96', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 65536', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = True', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 8', 'n_shared_experts': 'n_shared_experts: Optional[int + ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = 128', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 1.0', 'n_group': 'n_group: Optional[int + ] = 1', 'topk_group': 'topk_group: Optional[int + ] = 1', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int + ] = 1', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = True', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.0001' +}, model_name='Glm4vMoeTextModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='model', model_parameters={'depth': 'depth=24', 'hidden_size': 'hidden_size=1536', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'attention_dropout': 'attention_dropout=0.0', 'num_heads': 'num_heads=12', 'in_channels': 'in_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'spatial_merge_size': 'spatial_merge_size=2', 'temporal_patch_size': 'temporal_patch_size=2', 'out_hidden_size': 'out_hidden_size=4096', 'intermediate_size': 'intermediate_size=13696', 'initializer_range': 'initializer_range=0.02' +}, model_name='Glm4vMoeVisionModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151552', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='Glm4vTextModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='model', model_parameters={'depth': 'depth=24', 'hidden_size': 'hidden_size=1536', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'attention_dropout': 'attention_dropout=0.0', 'num_heads': 'num_heads=12', 'in_channels': 'in_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'spatial_merge_size': 'spatial_merge_size=2', 'temporal_patch_size': 'temporal_patch_size=2', 'out_hidden_size': 'out_hidden_size=4096', 'intermediate_size': 'intermediate_size=13696', 'initializer_range': 'initializer_range=0.02' +}, model_name='Glm4vVisionModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config=None', 'text_config': 'text_config=None', 'audio_token_id': 'audio_token_id=59260', 'projector_hidden_act': "projector_hidden_act='gelu'" +}, model_name='GlmAsrForConditionalGeneration', library='transformers', import_path='transformers.models.glmasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1280', 'intermediate_size': 'intermediate_size=5120', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=20', 'num_key_value_heads': 'num_key_value_heads=None', 'hidden_act': "hidden_act='gelu'", 'max_position_embeddings': 'max_position_embeddings=1500', 'initializer_range': 'initializer_range=0.02', 'rope_parameters': 'rope_parameters=None', 'attention_dropout': 'attention_dropout=0.0', 'num_mel_bins': 'num_mel_bins=128' +}, model_name='GlmAsrEncoder', library='transformers', import_path='transformers.models.glmasr'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'num_encoder_blocks': 'num_encoder_blocks=4', 'depths': 'depths=[ + 2, + 2, + 2, + 2 + ]', 'sr_ratios': 'sr_ratios=[ + 8, + 4, + 2, + 1 + ]', 'hidden_sizes': 'hidden_sizes=[ + 32, + 64, + 160, + 256 + ]', 'patch_sizes': 'patch_sizes=[ + 7, + 3, + 3, + 3 + ]', 'strides': 'strides=[ + 4, + 2, + 2, + 2 + ]', 'num_attention_heads': 'num_attention_heads=[ + 1, + 2, + 5, + 8 + ]', 'mlp_ratios': 'mlp_ratios=[ + 4, + 4, + 4, + 4 + ]', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'drop_path_rate': 'drop_path_rate=0.1', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=64', 'max_depth': 'max_depth=10', 'head_in_index': 'head_in_index=-1' +}, model_name='GLPNModel', library='transformers', import_path='transformers.models.glpn'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config: Optional[dict + ] = None', 'text_config': 'text_config: Optional[dict + ] = None', 'image_token_index': 'image_token_index: Optional[int + ] = 151859', 'image_seq_length': 'image_seq_length: Optional[int + ] = 576', 'pad_token_id': 'pad_token_id: Optional[int + ] = -1' +}, model_name='GotOcr2Model', library='transformers', import_path='transformers.models.got_ocr2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' +}, model_name='GPT2Model', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' +}, model_name='GPT2Model', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_pytorch_tanh'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'attention_softmax_in_fp32': 'attention_softmax_in_fp32=True', 'scale_attention_softmax_in_fp32': 'scale_attention_softmax_in_fp32=True', 'multi_query': 'multi_query=True' +}, model_name='GPTBigCodeModel', library='transformers', import_path='transformers.models.gpt_bigcode'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'max_position_embeddings': 'max_position_embeddings=2048', 'hidden_size': 'hidden_size=2048', 'num_layers': 'num_layers=24', 'attention_types': "attention_types=[[['global', 'local'], 12]]", 'num_heads': 'num_heads=16', 'intermediate_size': 'intermediate_size=None', 'window_size': 'window_size=256', 'activation_function': "activation_function='gelu_new'", 'resid_dropout': 'resid_dropout=0.0', 'embed_dropout': 'embed_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'classifier_dropout': 'classifier_dropout=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256' +}, model_name='GPTNeoModel', library='transformers', import_path='transformers.models.gpt_neo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50432', 'hidden_size': 'hidden_size: Optional[int + ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 44', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'intermediate_size': 'intermediate_size: Optional[int + ] = 24576', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'classifier_dropout': 'classifier_dropout: Optional[float + ] = 0.1', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'use_parallel_residual': 'use_parallel_residual: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = True' +}, model_name='GPTNeoXModel', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'intermediate_multiple_size': 'intermediate_multiple_size: Optional[int + ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int + ] = 31996', 'eos_token_id': 'eos_token_id: Optional[int + ] = 31999', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.1', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0' +}, model_name='GPTNeoXJapaneseModel', library='transformers', import_path='transformers.models.gpt_neox_japanese'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'emoji_file': 'emoji_file', 'unk_token': "unk_token='<|endoftext|>'", 'pad_token': "pad_token='<|endoftext|>'", 'bos_token': "bos_token='<|startoftext|>'", 'eos_token': "eos_token='<|endoftext|>'", 'do_clean_text': 'do_clean_text=False' +}, model_name='GPTNeoXJapaneseTokenizer', library='transformers', import_path='transformers.models.gpt_neox_japanese'), ModelAttributes(model=, model_type='model', model_parameters={'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 36', 'num_local_experts': 'num_local_experts: Optional[int + ] = 128', 'vocab_size': 'vocab_size: Optional[int + ] = 201088', 'hidden_size': 'hidden_size: Optional[int + ] = 2880', 'intermediate_size': 'intermediate_size: Optional[int + ] = 2880', 'head_dim': 'head_dim: Optional[int + ] = 64', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'sliding_window': 'sliding_window: Optional[int + ] = 128', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'rope_parameters': "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = {'rope_type': 'yarn', 'factor': 32.0, 'beta_fast': 32.0, 'beta_slow': 1.0, 'truncate': False, 'original_max_position_embeddings': 4096}", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 4', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.9', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='GptOssModel', library='transformers', import_path='transformers.models.gpt_oss'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50400', 'n_positions': 'n_positions=2048', 'n_embd': 'n_embd=4096', 'n_layer': 'n_layer=28', 'n_head': 'n_head=16', 'rotary_dim': 'rotary_dim=64', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.0', 'embd_pdrop': 'embd_pdrop=0.0', 'attn_pdrop': 'attn_pdrop=0.0', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='GPTJModel', library='transformers', import_path='transformers.models.gptj'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'embedding_multiplier': 'embedding_multiplier: Optional[float + ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float + ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float + ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float + ] = 1.0' +}, model_name='GraniteModel', library='transformers', import_path='transformers.models.granite'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float + ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float + ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float + ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float + ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001' +}, model_name='GraniteMoeModel', library='transformers', import_path='transformers.models.granitemoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float + ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float + ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float + ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float + ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'shared_intermediate_size': 'shared_intermediate_size: Optional[int + ] = 1024', 'position_embedding_type': 'position_embedding_type: Optional[str + ] = None', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'mamba_n_heads': 'mamba_n_heads: Optional[int + ] = 128', 'mamba_n_groups': 'mamba_n_groups: Optional[int + ] = 1', 'mamba_d_state': 'mamba_d_state: Optional[int + ] = 256', 'mamba_d_head': "mamba_d_head: Optional[str] = 'auto'", 'mamba_d_conv': 'mamba_d_conv: Optional[int + ] = 4', 'mamba_expand': 'mamba_expand: Optional[int + ] = 2', 'mamba_chunk_size': 'mamba_chunk_size: Optional[int + ] = 256', 'mamba_conv_bias': 'mamba_conv_bias: Optional[bool + ] = True', 'mamba_proj_bias': 'mamba_proj_bias: Optional[bool + ] = False' +}, model_name='GraniteMoeHybridModel', library='transformers', import_path='transformers.models.granitemoehybrid'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float + ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float + ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float + ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float + ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'shared_intermediate_size': 'shared_intermediate_size: Optional[int + ] = 0' +}, model_name='GraniteMoeSharedModel', library='transformers', import_path='transformers.models.granitemoeshared'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'text_config': 'text_config=None', 'num_queries': 'num_queries=900', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=True', 'class_cost': 'class_cost=1.0', 'bbox_cost': 'bbox_cost=5.0', 'giou_cost': 'giou_cost=2.0', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5.0', 'giou_loss_coefficient': 'giou_loss_coefficient=2.0', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False', 'max_text_len': 'max_text_len=256', 'text_enhancer_dropout': 'text_enhancer_dropout=0.0', 'fusion_droppath': 'fusion_droppath=0.1', 'fusion_dropout': 'fusion_dropout=0.0', 'embedding_init_target': 'embedding_init_target=True', 'query_dim': 'query_dim=4', 'decoder_bbox_embed_share': 'decoder_bbox_embed_share=True', 'two_stage_bbox_embed_share': 'two_stage_bbox_embed_share=False', 'positional_embedding_temperature': 'positional_embedding_temperature=20', 'init_std': 'init_std=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' +}, model_name='GroundingDinoModel', library='transformers', import_path='transformers.models.grounding_dino'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=256', 'projection_intermediate_dim': 'projection_intermediate_dim=4096', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='GroupViTModel', library='transformers', import_path='transformers.models.groupvit'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 48000', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int + ] = 7040', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 20', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-08', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'pad_token_id': 'pad_token_id: Optional[int + ] = 3', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False' +}, model_name='HeliumModel', library='transformers', import_path='transformers.models.helium'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'depths': 'depths=[ + 3, + 4, + 6, + 3 + ]', 'hidden_sizes': 'hidden_sizes=[ + 256, + 512, + 1024, + 2048 + ]', 'hidden_act': "hidden_act='relu'", 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'stem_channels': 'stem_channels=[ + 3, + 32, + 48 + ]', 'stage_in_channels': 'stage_in_channels=[ + 48, + 128, + 512, + 1024 + ]', 'stage_mid_channels': 'stage_mid_channels=[ + 48, + 96, + 192, + 384 + ]', 'stage_out_channels': 'stage_out_channels=[ + 128, + 512, + 1024, + 2048 + ]', 'stage_num_blocks': 'stage_num_blocks=[ + 1, + 1, + 3, + 1 + ]', 'stage_downsample': 'stage_downsample=[False, True, True, True + ]', 'stage_light_block': 'stage_light_block=[False, False, True, True + ]', 'stage_kernel_size': 'stage_kernel_size=[ + 3, + 3, + 5, + 5 + ]', 'stage_numb_of_layers': 'stage_numb_of_layers=[ + 6, + 6, + 6, + 6 + ]', 'use_learnable_affine_block': 'use_learnable_affine_block=False', 'initializer_range': 'initializer_range=0.02' +}, model_name='HGNetV2Backbone', library='transformers', import_path='transformers.models.hgnet_v2'), ModelAttributes(model=, model_type='model', model_parameters={'embed_dim': 'embed_dim=96', 'image_size': 'image_size=[ + 224, + 224 + ]', 'patch_size': 'patch_size=[ + 7, + 7 + ]', 'patch_stride': 'patch_stride=[ + 4, + 4 + ]', 'patch_padding': 'patch_padding=[ + 3, + 3 + ]', 'mlp_ratio': 'mlp_ratio=4.0', 'depths': 'depths=[ + 2, + 3, + 16, + 3 + ]', 'num_heads': 'num_heads=[ + 1, + 2, + 4, + 8 + ]', 'embed_dim_multiplier': 'embed_dim_multiplier=2.0', 'num_query_pool': 'num_query_pool=3', 'query_stride': 'query_stride=[ + 2, + 2 + ]', 'masked_unit_size': 'masked_unit_size=[ + 8, + 8 + ]', 'masked_unit_attention': 'masked_unit_attention=[True, True, False, False + ]', 'drop_path_rate': 'drop_path_rate=0.0', 'num_channels': 'num_channels=3', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_init': 'layer_norm_init=1.0', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=None', 'decoder_depth': 'decoder_depth=None', 'decoder_num_heads': 'decoder_num_heads=None', 'normalize_pixel_loss': 'normalize_pixel_loss=True', 'mask_ratio': 'mask_ratio=0.6', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='HieraModel', library='transformers', import_path='transformers.models.hiera'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_layer_norm': 'feat_proj_layer_norm=True', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'conv_pos_batch_norm': 'conv_pos_batch_norm=False', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' +}, model_name='HubertModel', library='transformers', import_path='transformers.models.hubert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' +}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 290943', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'eod_token_id': 'eod_token_id: Optional[int + ] = 3', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='HunYuanDenseV1Model', library='transformers', import_path='transformers.models.hunyuan_v1_dense'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 290943', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'eod_token_id': 'eod_token_id: Optional[int + ] = 3', 'sep_token_id': 'sep_token_id: Optional[int + ] = 4', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts': 'num_experts: Union[int, list + ] = 1', 'moe_topk': 'moe_topk: Union[int, list + ] = 1', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='HunYuanMoEV1Model', library='transformers', import_path='transformers.models.hunyuan_v1_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'quant_mode': 'quant_mode=False', 'force_dequant': "force_dequant='none'" +}, model_name='IBertModel', library='transformers', import_path='transformers.models.ibert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'additional_vocab_size': 'additional_vocab_size=0', 'hidden_size': 'hidden_size=4096', 'intermediate_size': 'intermediate_size=11008', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=32', 'dropout': 'dropout=0.0', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.02', 'alpha_initializer': "alpha_initializer='zeros'", 'alphas_initializer_range': 'alphas_initializer_range=0.0', 'alpha_type': "alpha_type='float'", 'rms_norm_eps': 'rms_norm_eps=1e-06', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'tie_word_embeddings': 'tie_word_embeddings=False', 'cross_layer_interval': 'cross_layer_interval=1', 'qk_layer_norms': 'qk_layer_norms=False', 'freeze_text_layers': 'freeze_text_layers=True', 'freeze_text_module_exceptions': 'freeze_text_module_exceptions=[]', 'freeze_lm_head': 'freeze_lm_head=False', 'freeze_vision_layers': 'freeze_vision_layers=True', 'freeze_vision_module_exceptions': 'freeze_vision_module_exceptions=[]', 'use_resampler': 'use_resampler=False', 'vision_config': 'vision_config=None', 'perceiver_config': 'perceiver_config=None' +}, model_name='IdeficsModel', library='transformers', import_path='transformers.models.idefics'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=32001', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'perceiver_config': 'perceiver_config=None', 'text_config': 'text_config=None' +}, model_name='Idefics2Model', library='transformers', import_path='transformers.models.idefics2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=128257', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'scale_factor': 'scale_factor=2', 'pad_token_id': 'pad_token_id=128002' +}, model_name='Idefics3Model', library='transformers', import_path='transformers.models.idefics3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1152', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' +}, model_name='Idefics3VisionTransformer', library='transformers', import_path='transformers.models.idefics3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" +}, model_name='IJepaModel', library='transformers', import_path='transformers.models.ijepa'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=513', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=512', 'n_layer': 'n_layer=24', 'n_head': 'n_head=8', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='quick_gelu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'tie_word_embeddings': 'tie_word_embeddings=False', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' +}, model_name='ImageGPTModel', library='transformers', import_path='transformers.models.imagegpt'), ModelAttributes(model=, model_type='model', model_parameters={'prediction_length': 'prediction_length: Optional[int + ] = None', 'context_length': 'context_length: Optional[int + ] = None', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'nll'", 'input_size': 'input_size: int = 1', 'lags_sequence': 'lags_sequence: Optional[list[int + ] + ] = None', 'scaling': "scaling: Union[str, bool, NoneType] = 'mean'", 'num_dynamic_real_features': 'num_dynamic_real_features: int = 0', 'num_static_real_features': 'num_static_real_features: int = 0', 'num_static_categorical_features': 'num_static_categorical_features: int = 0', 'num_time_features': 'num_time_features: int = 0', 'cardinality': 'cardinality: Optional[list[int + ] + ] = None', 'embedding_dimension': 'embedding_dimension: Optional[list[int + ] + ] = None', 'd_model': 'd_model: int = 64', 'encoder_ffn_dim': 'encoder_ffn_dim: int = 32', 'decoder_ffn_dim': 'decoder_ffn_dim: int = 32', 'encoder_attention_heads': 'encoder_attention_heads: int = 2', 'decoder_attention_heads': 'decoder_attention_heads: int = 2', 'encoder_layers': 'encoder_layers: int = 2', 'decoder_layers': 'decoder_layers: int = 2', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'dropout': 'dropout: float = 0.05', 'encoder_layerdrop': 'encoder_layerdrop: float = 0.1', 'decoder_layerdrop': 'decoder_layerdrop: float = 0.1', 'attention_dropout': 'attention_dropout: float = 0.1', 'activation_dropout': 'activation_dropout: float = 0.1', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'init_std': 'init_std: float = 0.02', 'attention_type': "attention_type: str = 'prob'", 'sampling_factor': 'sampling_factor: int = 5', 'distil': 'distil: bool = True' +}, model_name='InformerModel', library='transformers', import_path='transformers.models.informer'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'image_token_index': 'image_token_index=None' +}, model_name='InstructBlipModel', library='transformers', import_path='transformers.models.instructblip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'video_token_index': 'video_token_index=None' +}, model_name='InstructBlipVideoModel', library='transformers', import_path='transformers.models.instructblipvideo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151667', 'image_seq_length': 'image_seq_length=256', 'downsample_ratio': 'downsample_ratio=0.5', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_layer': 'vision_feature_layer=-1', 'vision_feature_select_strategy': "vision_feature_select_strategy='default'" +}, model_name='InternVLModel', library='transformers', import_path='transformers.models.internvl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'attention_bias': 'attention_bias=False', 'use_qk_norm': 'use_qk_norm=False', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_dropout': 'attention_dropout=0.0', 'projection_dropout': 'projection_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'norm_type': "norm_type='layer_norm'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=[ + 448, + 448 + ]', 'patch_size': 'patch_size=[ + 14, + 14 + ]', 'num_channels': 'num_channels=3', 'use_mask_token': 'use_mask_token=False', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=True', 'layer_scale_init_value': 'layer_scale_init_value=0.1', 'use_mean_pooling': 'use_mean_pooling=True' +}, model_name='InternVLVisionModel', library='transformers', import_path='transformers.models.internvl'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 150272', 'hidden_size': 'hidden_size: Optional[int + ] = 3328', 'intermediate_size': 'intermediate_size: Optional[int + ] = 26624', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 26', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 150024', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'attention_bias': 'attention_bias: Optional[bool + ] = True', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = True', 'head_dim': 'head_dim: Optional[int + ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='Jais2Model', library='transformers', import_path='transformers.models.jais2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=65536', 'tie_word_embeddings': 'tie_word_embeddings=False', 'hidden_size': 'hidden_size=4096', 'intermediate_size': 'intermediate_size=14336', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=32', 'num_key_value_heads': 'num_key_value_heads=8', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-06', 'output_router_logits': 'output_router_logits=False', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'max_position_embeddings': 'max_position_embeddings=262144', 'attention_dropout': 'attention_dropout=0.0', 'num_experts_per_tok': 'num_experts_per_tok=2', 'num_experts': 'num_experts=16', 'expert_layer_period': 'expert_layer_period=2', 'expert_layer_offset': 'expert_layer_offset=1', 'attn_layer_period': 'attn_layer_period=8', 'attn_layer_offset': 'attn_layer_offset=4', 'use_mamba_kernels': 'use_mamba_kernels=True', 'mamba_d_state': 'mamba_d_state=16', 'mamba_d_conv': 'mamba_d_conv=4', 'mamba_expand': 'mamba_expand=2', 'mamba_dt_rank': "mamba_dt_rank='auto'", 'mamba_conv_bias': 'mamba_conv_bias=True', 'mamba_proj_bias': 'mamba_proj_bias=False' +}, model_name='JambaModel', library='transformers', import_path='transformers.models.jamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'vq_config': 'vq_config=None', 'image_token_id': 'image_token_id=100581' +}, model_name='JanusModel', library='transformers', import_path='transformers.models.janus'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 12', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 16', 'kv_channels': 'kv_channels: Optional[int + ] = 128', 'intermediate_size': 'intermediate_size: Optional[int + ] = 5632', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'activation_function': "activation_function: Optional[str] = 'silu'", 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'aux_loss_coef': 'aux_loss_coef: Optional[float + ] = 0.01', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'initializer_range': 'initializer_range: Optional[float + ] = 0.01', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='JetMoeModel', library='transformers', import_path='transformers.models.jetmoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'latent_query_num': 'latent_query_num=64' +}, model_name='Kosmos2Model', library='transformers', import_path='transformers.models.kosmos2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'latent_query_num': 'latent_query_num=2048' +}, model_name='Kosmos2_5Model', library='transformers', import_path='transformers.models.kosmos2_5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'codebook_vocab_size': 'codebook_vocab_size: Optional[int + ] = 2049', 'vocab_size': 'vocab_size: Optional[int + ] = 4001', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 48', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 750', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'head_dim': 'head_dim: Optional[int + ] = None', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'sliding_window': 'sliding_window: Optional[int + ] = 375', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'ffn_dim': 'ffn_dim: Optional[int + ] = 11264', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-08', 'num_codebooks': 'num_codebooks: Optional[int + ] = 32', 'audio_bos_token_id': 'audio_bos_token_id: Optional[int + ] = 2048', 'audio_pad_token_id': 'audio_pad_token_id: Optional[int + ] = 69569', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'pad_token_id': 'pad_token_id: Optional[int + ] = 3', 'bos_token_id': 'bos_token_id: Optional[int + ] = 48000', 'codec_config': 'codec_config: Optional[dict + ] = None' +}, model_name='KyutaiSpeechToTextModel', library='transformers', import_path='transformers.models.kyutai_speech_to_text'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=512', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=True', 'encoder_config': 'encoder_config: Union[dict, transformers.models.lasr.configuration_lasr.LasrEncoderConfig + ] = None', 'pad_token_id': 'pad_token_id=0' +}, model_name='LasrForCTC', library='transformers', import_path='transformers.models.lasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='ParakeetTokenizerFast', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=512', 'num_hidden_layers': 'num_hidden_layers=17', 'num_attention_heads': 'num_attention_heads=8', 'intermediate_size': 'intermediate_size=2048', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'convolution_bias': 'convolution_bias=False', 'conv_kernel_size': 'conv_kernel_size=32', 'subsampling_conv_channels': 'subsampling_conv_channels=256', 'subsampling_conv_kernel_size': 'subsampling_conv_kernel_size=5', 'subsampling_conv_stride': 'subsampling_conv_stride=2', 'num_mel_bins': 'num_mel_bins=128', 'dropout': 'dropout=0.1', 'dropout_positions': 'dropout_positions=0.0', 'layerdrop': 'layerdrop=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'max_position_embeddings': 'max_position_embeddings=10000', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'feed_forward_residual_weights': 'feed_forward_residual_weights=[ + 1.5, + 0.5 + ]', 'conv_residual_weights': 'conv_residual_weights=[ + 2.0, + 1.0 + ]', 'batch_norm_momentum': 'batch_norm_momentum=0.01', 'rope_parameters': 'rope_parameters=None' +}, model_name='LasrEncoder', library='transformers', import_path='transformers.models.lasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='ParakeetTokenizerFast', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024' +}, model_name='LayoutLMModel', library='transformers', import_path='transformers.models.layoutlm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'max_rel_pos': 'max_rel_pos=128', 'rel_pos_bins': 'rel_pos_bins=32', 'fast_qkv': 'fast_qkv=True', 'max_rel_2d_pos': 'max_rel_2d_pos=256', 'rel_2d_pos_bins': 'rel_2d_pos_bins=64', 'convert_sync_batchnorm': 'convert_sync_batchnorm=True', 'image_feature_pool_shape': 'image_feature_pool_shape=[ + 7, + 7, + 256 + ]', 'coordinate_size': 'coordinate_size=128', 'shape_size': 'shape_size=128', 'has_relative_attention_bias': 'has_relative_attention_bias=True', 'has_spatial_attention_bias': 'has_spatial_attention_bias=True', 'has_visual_segment_embedding': 'has_visual_segment_embedding=False', 'detectron2_config_args': 'detectron2_config_args=None' +}, model_name='LayoutLMv2Model', library='transformers', import_path='transformers.models.layoutlmv2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case=True', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'cls_token_box': 'cls_token_box=[ + 0, + 0, + 0, + 0 + ]', 'sep_token_box': 'sep_token_box=[ + 1000, + 1000, + 1000, + 1000 + ]', 'pad_token_box': 'pad_token_box=[ + 0, + 0, + 0, + 0 + ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' +}, model_name='LayoutLMv2Tokenizer', library='transformers', import_path='transformers.models.layoutlmv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'coordinate_size': 'coordinate_size=128', 'shape_size': 'shape_size=128', 'has_relative_attention_bias': 'has_relative_attention_bias=True', 'rel_pos_bins': 'rel_pos_bins=32', 'max_rel_pos': 'max_rel_pos=128', 'rel_2d_pos_bins': 'rel_2d_pos_bins=64', 'max_rel_2d_pos': 'max_rel_2d_pos=256', 'has_spatial_attention_bias': 'has_spatial_attention_bias=True', 'text_embed': 'text_embed=True', 'visual_embed': 'visual_embed=True', 'input_size': 'input_size=224', 'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='LayoutLMv3Model', library='transformers', import_path='transformers.models.layoutlmv3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'errors': "errors='replace'", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=True', 'cls_token_box': 'cls_token_box=[ + 0, + 0, + 0, + 0 + ]', 'sep_token_box': 'sep_token_box=[ + 0, + 0, + 0, + 0 + ]', 'pad_token_box': 'pad_token_box=[ + 0, + 0, + 0, + 0 + ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None' +}, model_name='LayoutLMv3Tokenizer', library='transformers', import_path='transformers.models.layoutlmv3'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_encoder_position_embeddings': 'max_encoder_position_embeddings=16384', 'max_decoder_position_embeddings': 'max_decoder_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'classifier_dropout': 'classifier_dropout=0.0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'attention_window': 'attention_window: Union[list[int + ], int + ] = 512' +}, model_name='LEDModel', library='transformers', import_path='transformers.models.led'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_channels': 'num_channels=3', 'kernel_size': 'kernel_size=3', 'stride': 'stride=2', 'padding': 'padding=1', 'patch_size': 'patch_size=16', 'hidden_sizes': 'hidden_sizes=[ + 128, + 256, + 384 + ]', 'num_attention_heads': 'num_attention_heads=[ + 4, + 8, + 12 + ]', 'depths': 'depths=[ + 4, + 4, + 4 + ]', 'key_dim': 'key_dim=[ + 16, + 16, + 16 + ]', 'drop_path_rate': 'drop_path_rate=0', 'mlp_ratio': 'mlp_ratio=[ + 2, + 2, + 2 + ]', 'attention_ratio': 'attention_ratio=[ + 2, + 2, + 2 + ]', 'initializer_range': 'initializer_range=0.02' +}, model_name='LevitModel', library='transformers', import_path='transformers.models.levit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 65536', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int + ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 128000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'norm_eps': 'norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'conv_bias': 'conv_bias: Optional[bool + ] = False', 'conv_L_cache': 'conv_L_cache: Optional[int + ] = 3', 'block_multiple_of': 'block_multiple_of: Optional[int + ] = 256', 'block_ffn_dim_multiplier': 'block_ffn_dim_multiplier: Optional[float + ] = 1.0', 'block_auto_adjust_ff_dim': 'block_auto_adjust_ff_dim: Optional[bool + ] = True', 'full_attn_idxs': 'full_attn_idxs: Optional[list[int + ] + ] = None', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Lfm2Model', library='transformers', import_path='transformers.models.lfm2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 65536', 'hidden_size': 'hidden_size: int = 2048', 'intermediate_size': 'intermediate_size: int = 7168', 'moe_intermediate_size': 'moe_intermediate_size: int = 1792', 'num_hidden_layers': 'num_hidden_layers: int = 32', 'pad_token_id': 'pad_token_id: int = 0', 'bos_token_id': 'bos_token_id: int = 1', 'eos_token_id': 'eos_token_id: int = 2', 'tie_word_embeddings': 'tie_word_embeddings: bool = True', 'rope_parameters': 'rope_parameters: transformers.modeling_rope_utils.RopeParameters = None', 'max_position_embeddings': 'max_position_embeddings: int = 128000', 'initializer_range': 'initializer_range: float = 0.02', 'norm_eps': 'norm_eps: float = 1e-05', 'num_attention_heads': 'num_attention_heads: int = 32', 'num_key_value_heads': 'num_key_value_heads: int = 8', 'conv_bias': 'conv_bias: bool = False', 'conv_L_cache': 'conv_L_cache: int = 3', 'num_dense_layers': 'num_dense_layers: int = 2', 'num_experts_per_tok': 'num_experts_per_tok: int = 4', 'num_experts': 'num_experts: int = 32', 'use_expert_bias': 'use_expert_bias: bool = True', 'routed_scaling_factor': 'routed_scaling_factor: float = 1.0', 'norm_topk_prob': 'norm_topk_prob: bool = True', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Lfm2MoeModel', library='transformers', import_path='transformers.models.lfm2_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=396', 'projector_hidden_act': "projector_hidden_act='gelu'", 'projector_hidden_size': 'projector_hidden_size=2560', 'projector_bias': 'projector_bias=True', 'projector_use_layernorm': 'projector_use_layernorm=True', 'downsample_factor': 'downsample_factor=2' +}, model_name='Lfm2VlModel', library='transformers', import_path='transformers.models.lfm2_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'keypoint_detector_config': 'keypoint_detector_config: transformers.models.superpoint.configuration_superpoint.SuperPointConfig = None', 'descriptor_dim': 'descriptor_dim: int = 256', 'num_hidden_layers': 'num_hidden_layers: int = 9', 'num_attention_heads': 'num_attention_heads: int = 4', 'num_key_value_heads': 'num_key_value_heads=None', 'depth_confidence': 'depth_confidence: float = 0.95', 'width_confidence': 'width_confidence: float = 0.99', 'filter_threshold': 'filter_threshold: float = 0.1', 'initializer_range': 'initializer_range: float = 0.02', 'hidden_act': "hidden_act: str = 'gelu'", 'attention_dropout': 'attention_dropout=0.0', 'attention_bias': 'attention_bias=True', 'trust_remote_code': 'trust_remote_code: bool = False' +}, model_name='LightGlueForKeypointMatching', library='transformers', import_path='transformers.models.lightglue'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None', 'channel_shrink_ratio': 'channel_shrink_ratio=4', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024' +}, model_name='LiltModel', library='transformers', import_path='transformers.models.lilt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='LlamaModel', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'boi_token_index': 'boi_token_index=200080', 'eoi_token_index': 'eoi_token_index=200081', 'image_token_index': 'image_token_index=200092', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='Llama4ForConditionalGeneration', library='transformers', import_path='transformers.models.llama4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=202048', 'hidden_size': 'hidden_size=5120', 'intermediate_size': 'intermediate_size=8192', 'intermediate_size_mlp': 'intermediate_size_mlp=16384', 'num_hidden_layers': 'num_hidden_layers=48', 'num_attention_heads': 'num_attention_heads=40', 'num_key_value_heads': 'num_key_value_heads=8', 'head_dim': 'head_dim=128', 'hidden_act': "hidden_act='silu'", 'max_position_embeddings': 'max_position_embeddings=131072', 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=None', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'tie_word_embeddings': 'tie_word_embeddings=False', 'attention_dropout': 'attention_dropout=0.0', 'num_experts_per_tok': 'num_experts_per_tok=1', 'num_local_experts': 'num_local_experts=16', 'moe_layers': 'moe_layers=None', 'interleave_moe_layer_step': 'interleave_moe_layer_step=1', 'use_qk_norm': 'use_qk_norm=True', 'output_router_logits': 'output_router_logits=False', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'router_jitter_noise': 'router_jitter_noise=0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'no_rope_layers': 'no_rope_layers=None', 'no_rope_layer_interval': 'no_rope_layer_interval=4', 'attention_chunk_size': 'attention_chunk_size=8192', 'layer_types': 'layer_types=None', 'attn_temperature_tuning': 'attn_temperature_tuning=True', 'floor_scale': 'floor_scale=8192', 'attn_scale': 'attn_scale=0.1' +}, model_name='Llama4TextModel', library='transformers', import_path='transformers.models.llama4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_seq_length': 'image_seq_length=576', 'multimodal_projector_bias': 'multimodal_projector_bias=True' +}, model_name='LlavaModel', library='transformers', import_path='transformers.models.llava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'tie_word_embeddings': 'tie_word_embeddings=False', 'image_seq_length': 'image_seq_length=576', 'multimodal_projector_bias': 'multimodal_projector_bias=True' +}, model_name='LlavaNextModel', library='transformers', import_path='transformers.models.llava_next'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32001', 'projector_hidden_act': "projector_hidden_act='gelu'", 'multimodal_projector_bias': 'multimodal_projector_bias=True', 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'video_token_index': 'video_token_index=32000', 'spatial_pool_mode': "spatial_pool_mode='average'", 'spatial_pool_stride': 'spatial_pool_stride=2', 'image_seq_length': 'image_seq_length=576', 'video_seq_length': 'video_seq_length=288' +}, model_name='LlavaNextVideoModel', library='transformers', import_path='transformers.models.llava_next_video'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=151646', 'video_token_index': 'video_token_index=151647', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='full'", 'vision_feature_layer': 'vision_feature_layer=-1', 'vision_aspect_ratio': "vision_aspect_ratio='anyres_max_9'", 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'multimodal_projector_bias': 'multimodal_projector_bias=True' +}, model_name='LlavaOnevisionModel', library='transformers', import_path='transformers.models.llava_onevision'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 131072', 'hidden_size': 'hidden_size: Optional[int + ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 56', 'num_layers': 'num_layers: Optional[int + ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'ffn_hidden_size': 'ffn_hidden_size: Optional[int + ] = 12288', 'q_lora_rank': 'q_lora_rank: Optional[int + ] = 1536', 'kv_lora_rank': 'kv_lora_rank: Optional[int + ] = 512', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int + ] = 128', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int + ] = 64', 'head_dim': 'head_dim: Optional[int + ] = 64', 'v_head_dim': 'v_head_dim: Optional[int + ] = 128', 'qk_head_dim': 'qk_head_dim: Optional[int + ] = None', 'moe_topk': 'moe_topk: Optional[int + ] = 12', 'n_routed_experts': 'n_routed_experts: Optional[int + ] = 512', 'zero_expert_num': 'zero_expert_num: Optional[int + ] = 256', 'expert_ffn_hidden_size': 'expert_ffn_hidden_size: Optional[int + ] = 2048', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float + ] = 6.0' +}, model_name='LongcatFlashModel', library='transformers', import_path='transformers.models.longcat_flash'), ModelAttributes(model=, model_type='model', model_parameters={'attention_window': 'attention_window: Union[list[int + ], int + ] = 512', 'sep_token_id': 'sep_token_id: int = 2', 'pad_token_id': 'pad_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 2', 'vocab_size': 'vocab_size: int = 30522', 'hidden_size': 'hidden_size: int = 768', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 12', 'intermediate_size': 'intermediate_size: int = 3072', 'hidden_act': "hidden_act: str = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.1', 'max_position_embeddings': 'max_position_embeddings: int = 512', 'type_vocab_size': 'type_vocab_size: int = 2', 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-12', 'onnx_export': 'onnx_export: bool = False' +}, model_name='LongformerModel', library='transformers', import_path='transformers.models.longformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'num_layers': 'num_layers=6', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=8', 'local_radius': 'local_radius=127', 'global_block_size': 'global_block_size=16', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_attention_type': "encoder_attention_type='local'", 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1' +}, model_name='LongT5Model', library='transformers', import_path='transformers.models.longt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50267', 'entity_vocab_size': 'entity_vocab_size=500000', 'hidden_size': 'hidden_size=768', 'entity_emb_size': 'entity_emb_size=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_entity_aware_attention': 'use_entity_aware_attention=True', 'classifier_dropout': 'classifier_dropout=None', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='LukeModel', library='transformers', import_path='transformers.models.luke'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'entity_vocab': 'entity_vocab: Union[str, dict, list, NoneType + ] = None', 'errors': "errors='replace'", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=False', 'task': 'task=None', 'max_entity_length': 'max_entity_length=32', 'max_mention_length': 'max_mention_length=30', 'entity_token_1': "entity_token_1=''", 'entity_token_2': "entity_token_2=''", 'entity_unk_token': "entity_unk_token='[UNK]'", 'entity_pad_token': "entity_pad_token='[PAD]'", 'entity_mask_token': "entity_mask_token='[MASK]'", 'entity_mask2_token': "entity_mask2_token='[MASK2]'" +}, model_name='LukeTokenizer', library='transformers', import_path='transformers.models.luke'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_attention_heads': 'num_attention_heads=12', 'num_qa_labels': 'num_qa_labels=9500', 'num_object_labels': 'num_object_labels=1600', 'num_attr_labels': 'num_attr_labels=400', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'l_layers': 'l_layers=9', 'x_layers': 'x_layers=5', 'r_layers': 'r_layers=5', 'visual_feat_dim': 'visual_feat_dim=2048', 'visual_pos_dim': 'visual_pos_dim=4', 'visual_loss_normalizer': 'visual_loss_normalizer=6.67', 'task_matched': 'task_matched=True', 'task_mask_lm': 'task_mask_lm=True', 'task_obj_predict': 'task_obj_predict=True', 'task_qa': 'task_qa=True', 'visual_obj_loss': 'visual_obj_loss=True', 'visual_attr_loss': 'visual_attr_loss=True', 'visual_feat_loss': 'visual_feat_loss=True' +}, model_name='LxmertModel', library='transformers', import_path='transformers.models.lxmert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128112', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='M2M100Model', library='transformers', import_path='transformers.models.m2m_100'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'spm_file': 'spm_file', 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'language_codes': "language_codes='m2m100'", 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None', 'num_madeup_words': 'num_madeup_words=8' +}, model_name='M2M100Tokenizer', library='transformers', import_path='transformers.models.m2m_100'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50280', 'hidden_size': 'hidden_size=768', 'state_size': 'state_size=16', 'num_hidden_layers': 'num_hidden_layers=32', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_scale': 'time_step_scale=1.0', 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_init_scheme': "time_step_init_scheme='random'", 'time_step_floor': 'time_step_floor=0.0001', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'use_mambapy': 'use_mambapy=False' +}, model_name='MambaModel', library='transformers', import_path='transformers.models.mamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'num_heads': 'num_heads=128', 'head_dim': 'head_dim=64', 'vocab_size': 'vocab_size=32768', 'hidden_size': 'hidden_size=4096', 'state_size': 'state_size=128', 'num_hidden_layers': 'num_hidden_layers=64', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'n_groups': 'n_groups=8', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_floor': 'time_step_floor=0.0001', 'time_step_limit': 'time_step_limit=(0.0, inf)', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'rms_norm': 'rms_norm=True', 'chunk_size': 'chunk_size=256', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='Mamba2Model', library='transformers', import_path='transformers.models.mamba2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=58101', 'decoder_vocab_size': 'decoder_vocab_size=None', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=58100', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=58100', 'eos_token_id': 'eos_token_id=0', 'forced_eos_token_id': 'forced_eos_token_id=0', 'share_encoder_decoder_embeddings': 'share_encoder_decoder_embeddings=True' +}, model_name='MarianModel', library='transformers', import_path='transformers.models.marian'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'source_spm': 'source_spm', 'target_spm': 'target_spm', 'vocab': 'vocab', 'target_vocab_file': 'target_vocab_file=None', 'source_lang': 'source_lang=None', 'target_lang': 'target_lang=None', 'unk_token': "unk_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'model_max_length': 'model_max_length=512', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None', 'separate_vocabs': 'separate_vocabs=False' +}, model_name='MarianTokenizer', library='transformers', import_path='transformers.models.marian'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_xpath_tag_unit_embeddings': 'max_xpath_tag_unit_embeddings=256', 'max_xpath_subs_unit_embeddings': 'max_xpath_subs_unit_embeddings=1024', 'tag_pad_id': 'tag_pad_id=216', 'subs_pad_id': 'subs_pad_id=1001', 'xpath_unit_hidden_size': 'xpath_unit_hidden_size=32', 'max_depth': 'max_depth=50', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='MarkupLMModel', library='transformers', import_path='transformers.models.markuplm'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'feature_size': 'feature_size: int = 256', 'mask_feature_size': 'mask_feature_size: int = 256', 'hidden_dim': 'hidden_dim: int = 256', 'encoder_feedforward_dim': 'encoder_feedforward_dim: int = 1024', 'activation_function': "activation_function: str = 'relu'", 'encoder_layers': 'encoder_layers: int = 6', 'decoder_layers': 'decoder_layers: int = 10', 'num_attention_heads': 'num_attention_heads: int = 8', 'dropout': 'dropout: float = 0.0', 'dim_feedforward': 'dim_feedforward: int = 2048', 'pre_norm': 'pre_norm: bool = False', 'enforce_input_projection': 'enforce_input_projection: bool = False', 'common_stride': 'common_stride: int = 4', 'ignore_value': 'ignore_value: int = 255', 'num_queries': 'num_queries: int = 100', 'no_object_weight': 'no_object_weight: float = 0.1', 'class_weight': 'class_weight: float = 2.0', 'mask_weight': 'mask_weight: float = 5.0', 'dice_weight': 'dice_weight: float = 5.0', 'train_num_points': 'train_num_points: int = 12544', 'oversample_ratio': 'oversample_ratio: float = 3.0', 'importance_sample_ratio': 'importance_sample_ratio: float = 0.75', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = True', 'feature_strides': 'feature_strides: list[int + ] = [ + 4, + 8, + 16, + 32 + ]', 'output_auxiliary_logits': 'output_auxiliary_logits: Optional[bool + ] = None', 'backbone': 'backbone: Optional[str + ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict + ] = None' +}, model_name='Mask2FormerModel', library='transformers', import_path='transformers.models.mask2former'), ModelAttributes(model=, model_type='model', model_parameters={'fpn_feature_size': 'fpn_feature_size: int = 256', 'mask_feature_size': 'mask_feature_size: int = 256', 'no_object_weight': 'no_object_weight: float = 0.1', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = False', 'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'decoder_config': 'decoder_config: Optional[dict + ] = None', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'dice_weight': 'dice_weight: float = 1.0', 'cross_entropy_weight': 'cross_entropy_weight: float = 1.0', 'mask_weight': 'mask_weight: float = 20.0', 'output_auxiliary_logits': 'output_auxiliary_logits: Optional[bool + ] = None', 'backbone': 'backbone: Optional[str + ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict + ] = None' +}, model_name='MaskFormerModel', library='transformers', import_path='transformers.models.maskformer'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'num_heads': 'num_heads=[ + 3, + 6, + 12, + 24 + ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='MaskFormerSwinModel', library='transformers', import_path='transformers.models.maskformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' +}, model_name='MBartModel', library='transformers', import_path='transformers.models.mbart'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='MBartTokenizer', library='transformers', import_path='transformers.models.mbart'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=29056', 'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0' +}, model_name='MegatronBertModel', library='transformers', import_path='transformers.models.megatron_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='MetaClip2Model', library='transformers', import_path='transformers.models.metaclip_2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=[ + 32, + 128 + ]', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'max_token_length': 'max_token_length=27', 'num_character_labels': 'num_character_labels=38', 'num_bpe_labels': 'num_bpe_labels=50257', 'num_wordpiece_labels': 'num_wordpiece_labels=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'distilled': 'distilled=False', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'drop_rate': 'drop_rate=0.0', 'attn_drop_rate': 'attn_drop_rate=0.0', 'drop_path_rate': 'drop_path_rate=0.0', 'output_a3_attentions': 'output_a3_attentions=False', 'initializer_range': 'initializer_range=0.02' +}, model_name='MgpstrForSceneTextRecognition', library='transformers', import_path='transformers.models.mgp_str'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'unk_token': "unk_token='[GO]'", 'bos_token': "bos_token='[GO]'", 'eos_token': "eos_token='[s]'", 'pad_token': "pad_token='[GO]'" +}, model_name='MgpstrTokenizer', library='transformers', import_path='transformers.models.mgp_str'), ModelAttributes(model=, model_type='model', model_parameters={'sampling_rate': 'sampling_rate: Optional[int + ] = 24000', 'frame_rate': 'frame_rate: Optional[int + ] = None', 'audio_channels': 'audio_channels: Optional[int + ] = 1', 'hidden_size': 'hidden_size: Optional[int + ] = 512', 'num_filters': 'num_filters: Optional[int + ] = 64', 'num_residual_layers': 'num_residual_layers: Optional[int + ] = 1', 'upsampling_ratios': 'upsampling_ratios: Optional[list[int + ] + ] = None', 'kernel_size': 'kernel_size: Optional[int + ] = 7', 'last_kernel_size': 'last_kernel_size: Optional[int + ] = 3', 'residual_kernel_size': 'residual_kernel_size: Optional[int + ] = 3', 'dilation_growth_rate': 'dilation_growth_rate: Optional[int + ] = 2', 'use_causal_conv': 'use_causal_conv: Optional[bool + ] = True', 'pad_mode': "pad_mode: Optional[str] = 'constant'", 'compress': 'compress: Optional[int + ] = 2', 'trim_right_ratio': 'trim_right_ratio: Optional[float + ] = 1.0', 'codebook_size': 'codebook_size: Optional[int + ] = 2048', 'codebook_dim': 'codebook_dim: Optional[int + ] = 256', 'num_quantizers': 'num_quantizers: Optional[int + ] = 32', 'use_conv_shortcut': 'use_conv_shortcut: Optional[bool + ] = False', 'vector_quantization_hidden_dimension': 'vector_quantization_hidden_dimension: Optional[int + ] = 256', 'num_semantic_quantizers': 'num_semantic_quantizers: Optional[int + ] = 1', 'upsample_groups': 'upsample_groups: Optional[int + ] = 512', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 8', 'intermediate_size': 'intermediate_size: Optional[int + ] = 2048', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'norm_eps': 'norm_eps: Optional[int + ] = 1e-05', 'use_streaming': 'use_streaming: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = 250', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'layer_scale_initial_scale': 'layer_scale_initial_scale: Optional[float + ] = 0.01', 'attention_bias': 'attention_bias: Optional[bool + ] = False' +}, model_name='MimiModel', library='transformers', import_path='transformers.models.mimi'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'block_size': 'block_size: Optional[int + ] = 256', 'full_attn_alpha_factor': 'full_attn_alpha_factor: Optional[int + ] = 1', 'full_attn_beta_factor': 'full_attn_beta_factor: Optional[int + ] = 1', 'linear_attn_alpha_factor': 'linear_attn_alpha_factor: Optional[int + ] = 1', 'linear_attn_beta_factor': 'linear_attn_beta_factor: Optional[int + ] = 1', 'mlp_alpha_factor': 'mlp_alpha_factor: Optional[int + ] = 1', 'mlp_beta_factor': 'mlp_beta_factor: Optional[int + ] = 1' +}, model_name='MiniMaxModel', library='transformers', import_path='transformers.models.minimax'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='MinistralModel', library='transformers', import_path='transformers.models.ministral'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 131072', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 34', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 262144', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 11', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='Ministral3Model', library='transformers', import_path='transformers.models.ministral3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='MistralModel', library='transformers', import_path='transformers.models.mistral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=10', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_layer': 'vision_feature_layer=-1', 'multimodal_projector_bias': 'multimodal_projector_bias=False', 'spatial_merge_size': 'spatial_merge_size=2' +}, model_name='Mistral3Model', library='transformers', import_path='transformers.models.mistral3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'head_dim': 'head_dim: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'num_local_experts': 'num_local_experts: Optional[int + ] = 8', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='MixtralModel', library='transformers', import_path='transformers.models.mixtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1664', 'intermediate_size': 'intermediate_size=8192', 'num_hidden_layers': 'num_hidden_layers=48', 'num_attention_heads': 'num_attention_heads=16', 'num_key_value_groups': 'num_key_value_groups=1', 'num_channels': 'num_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' +}, model_name='MLCDVisionModel', library='transformers', import_path='transformers.models.mlcd'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=128256' +}, model_name='MllamaModel', library='transformers', import_path='transformers.models.mllama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'text_config': 'text_config=None', 'num_queries': 'num_queries=900', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=True', 'class_cost': 'class_cost=1.0', 'bbox_cost': 'bbox_cost=5.0', 'giou_cost': 'giou_cost=2.0', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5.0', 'giou_loss_coefficient': 'giou_loss_coefficient=2.0', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False', 'max_text_len': 'max_text_len=256', 'text_enhancer_dropout': 'text_enhancer_dropout=0.0', 'fusion_droppath': 'fusion_droppath=0.1', 'fusion_dropout': 'fusion_dropout=0.0', 'embedding_init_target': 'embedding_init_target=True', 'query_dim': 'query_dim=4', 'positional_embedding_temperature': 'positional_embedding_temperature=20', 'init_std': 'init_std=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' +}, model_name='MMGroundingDinoModel', library='transformers', import_path='transformers.models.mm_grounding_dino'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=512', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=4', 'intermediate_size': 'intermediate_size=512', 'hidden_act': "hidden_act='relu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'embedding_size': 'embedding_size=128', 'trigram_input': 'trigram_input=True', 'use_bottleneck': 'use_bottleneck=True', 'intra_bottleneck_size': 'intra_bottleneck_size=128', 'use_bottleneck_attention': 'use_bottleneck_attention=False', 'key_query_shared_bottleneck': 'key_query_shared_bottleneck=True', 'num_feedforward_networks': 'num_feedforward_networks=4', 'normalization_type': "normalization_type='no_norm'", 'classifier_activation': 'classifier_activation=True', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='MobileBertModel', library='transformers', import_path='transformers.models.mobilebert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'depth_multiplier': 'depth_multiplier=1.0', 'min_depth': 'min_depth=8', 'hidden_act': "hidden_act='relu6'", 'tf_padding': 'tf_padding=True', 'classifier_dropout_prob': 'classifier_dropout_prob=0.999', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=0.001' +}, model_name='MobileNetV1Model', library='transformers', import_path='transformers.models.mobilenet_v1'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'depth_multiplier': 'depth_multiplier=1.0', 'depth_divisible_by': 'depth_divisible_by=8', 'min_depth': 'min_depth=8', 'expand_ratio': 'expand_ratio=6.0', 'output_stride': 'output_stride=32', 'first_layer_is_expansion': 'first_layer_is_expansion=True', 'finegrained_output': 'finegrained_output=True', 'hidden_act': "hidden_act='relu6'", 'tf_padding': 'tf_padding=True', 'classifier_dropout_prob': 'classifier_dropout_prob=0.8', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=0.001', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' +}, model_name='MobileNetV2Model', library='transformers', import_path='transformers.models.mobilenet_v2'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=256', 'patch_size': 'patch_size=2', 'hidden_sizes': 'hidden_sizes=[ + 144, + 192, + 240 + ]', 'neck_hidden_sizes': 'neck_hidden_sizes=[ + 16, + 32, + 64, + 96, + 128, + 160, + 640 + ]', 'num_attention_heads': 'num_attention_heads=4', 'mlp_ratio': 'mlp_ratio=2.0', 'expand_ratio': 'expand_ratio=4.0', 'hidden_act': "hidden_act='silu'", 'conv_kernel_size': 'conv_kernel_size=3', 'output_stride': 'output_stride=32', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'qkv_bias': 'qkv_bias=True', 'aspp_out_channels': 'aspp_out_channels=256', 'atrous_rates': 'atrous_rates=[ + 6, + 12, + 18 + ]', 'aspp_dropout_prob': 'aspp_dropout_prob=0.1', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' +}, model_name='MobileViTModel', library='transformers', import_path='transformers.models.mobilevit'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=256', 'patch_size': 'patch_size=2', 'expand_ratio': 'expand_ratio=2.0', 'hidden_act': "hidden_act='swish'", 'conv_kernel_size': 'conv_kernel_size=3', 'output_stride': 'output_stride=32', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'aspp_out_channels': 'aspp_out_channels=512', 'atrous_rates': 'atrous_rates=[ + 6, + 12, + 18 + ]', 'aspp_dropout_prob': 'aspp_dropout_prob=0.1', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255', 'n_attn_blocks': 'n_attn_blocks=[ + 2, + 4, + 3 + ]', 'base_attn_unit_dims': 'base_attn_unit_dims=[ + 128, + 192, + 256 + ]', 'width_multiplier': 'width_multiplier=1.0', 'ffn_multiplier': 'ffn_multiplier=2', 'attn_dropout': 'attn_dropout=0.0', 'ffn_dropout': 'ffn_dropout=0.0' +}, model_name='MobileViTV2Model', library='transformers', import_path='transformers.models.mobilevitv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50368', 'hidden_size': 'hidden_size: Optional[int + ] = 768', 'intermediate_size': 'intermediate_size: Optional[int + ] = 1152', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 22', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 12', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'initializer_cutoff_factor': 'initializer_cutoff_factor: Optional[float + ] = 2.0', 'norm_eps': 'norm_eps: Optional[int + ] = 1e-05', 'norm_bias': 'norm_bias: Optional[bool + ] = False', 'pad_token_id': 'pad_token_id: Optional[int + ] = 50283', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50282', 'bos_token_id': 'bos_token_id: Optional[int + ] = 50281', 'cls_token_id': 'cls_token_id: Optional[int + ] = 50281', 'sep_token_id': 'sep_token_id: Optional[int + ] = 50282', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'local_attention': 'local_attention: Optional[int + ] = 128', 'embedding_dropout': 'embedding_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'mlp_dropout': 'mlp_dropout: Optional[float + ] = 0.0', 'decoder_bias': 'decoder_bias: Optional[bool + ] = True', 'classifier_pooling': "classifier_pooling: Literal['cls', 'mean'] = 'cls'", 'classifier_dropout': 'classifier_dropout: Optional[float + ] = 0.0', 'classifier_bias': 'classifier_bias: Optional[bool + ] = False', 'classifier_activation': "classifier_activation: Optional[str] = 'gelu'", 'deterministic_flash_attn': 'deterministic_flash_attn: Optional[bool + ] = False', 'sparse_prediction': 'sparse_prediction: Optional[bool + ] = False', 'sparse_pred_ignore_index': 'sparse_pred_ignore_index: Optional[int + ] = -100', 'reference_compile': 'reference_compile: Optional[bool + ] = None', 'repad_logits_with_grad': 'repad_logits_with_grad: Optional[bool + ] = False' +}, model_name='ModernBertModel', library='transformers', import_path='transformers.models.modernbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50368', 'hidden_size': 'hidden_size: Optional[int + ] = 768', 'intermediate_size': 'intermediate_size: Optional[int + ] = 1152', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 22', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 12', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'initializer_cutoff_factor': 'initializer_cutoff_factor: Optional[float + ] = 2.0', 'norm_eps': 'norm_eps: Optional[int + ] = 1e-05', 'norm_bias': 'norm_bias: Optional[bool + ] = False', 'pad_token_id': 'pad_token_id: Optional[int + ] = 50283', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50282', 'bos_token_id': 'bos_token_id: Optional[int + ] = 50281', 'cls_token_id': 'cls_token_id: Optional[int + ] = 50281', 'sep_token_id': 'sep_token_id: Optional[int + ] = 50282', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'embedding_dropout': 'embedding_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'mlp_dropout': 'mlp_dropout: Optional[float + ] = 0.0', 'decoder_bias': 'decoder_bias: Optional[bool + ] = True', 'classifier_dropout': 'classifier_dropout: Optional[float + ] = 0.0', 'classifier_bias': 'classifier_bias: Optional[bool + ] = False', 'classifier_activation': "classifier_activation: Optional[str] = 'gelu'", 'local_attention': 'local_attention: Optional[int + ] = 128', 'global_attn_every_n_layers': 'global_attn_every_n_layers: Optional[int + ] = 3', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None' +}, model_name='ModernBertDecoderModel', library='transformers', import_path='transformers.models.modernbert_decoder'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32768', 'hidden_size': 'hidden_size: Optional[int + ] = 288', 'intermediate_size': 'intermediate_size: Optional[int + ] = 1152', 'encoder_num_hidden_layers': 'encoder_num_hidden_layers: Optional[int + ] = 6', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers: Optional[int + ] = 6', 'encoder_num_attention_heads': 'encoder_num_attention_heads: Optional[int + ] = 8', 'decoder_num_attention_heads': 'decoder_num_attention_heads: Optional[int + ] = 8', 'encoder_num_key_value_heads': 'encoder_num_key_value_heads: Optional[int + ] = None', 'decoder_num_key_value_heads': 'decoder_num_key_value_heads: Optional[int + ] = None', 'pad_head_dim_to_multiple_of': 'pad_head_dim_to_multiple_of: Optional[int + ] = None', 'encoder_hidden_act': "encoder_hidden_act: Optional[str] = 'gelu'", 'decoder_hidden_act': "decoder_hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 512', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'decoder_start_token_id': 'decoder_start_token_id: Optional[int + ] = 1', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool + ] = True', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2' +}, model_name='MoonshineModel', library='transformers', import_path='transformers.models.moonshine'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'audio_vocab_size': 'audio_vocab_size: Optional[int + ] = None', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 3000', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'head_dim': 'head_dim: Optional[int + ] = None', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'sliding_window': 'sliding_window: Optional[int + ] = 3000', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'ffn_dim': 'ffn_dim: Optional[int + ] = 22528', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-08', 'num_codebooks': 'num_codebooks: Optional[int + ] = 8', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False' +}, model_name='MoshiModel', library='transformers', import_path='transformers.models.moshi'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30527', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='MPNetModel', library='transformers', import_path='transformers.models.mpnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case=True', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token='[UNK]'", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' +}, model_name='MPNetTokenizer', library='transformers', import_path='transformers.models.mpnet'), ModelAttributes(model=, model_type='model', model_parameters={'d_model': 'd_model: int = 2048', 'n_heads': 'n_heads: int = 16', 'n_layers': 'n_layers: int = 24', 'expansion_ratio': 'expansion_ratio: int = 4', 'max_seq_len': 'max_seq_len: int = 2048', 'vocab_size': 'vocab_size: int = 50368', 'resid_pdrop': 'resid_pdrop: float = 0.0', 'layer_norm_epsilon': 'layer_norm_epsilon: float = 1e-05', 'emb_pdrop': 'emb_pdrop: float = 0.0', 'learned_pos_emb': 'learned_pos_emb: bool = True', 'attn_config': 'attn_config: transformers.models.mpt.configuration_mpt.MptAttentionConfig = None', 'init_device': "init_device: str = 'cpu'", 'logit_scale': 'logit_scale: Union[float, str, NoneType + ] = None', 'no_bias': 'no_bias: bool = True', 'verbose': 'verbose: int = 0', 'embedding_fraction': 'embedding_fraction: float = 1.0', 'norm_type': "norm_type: str = 'low_precision_layernorm'", 'initializer_range': 'initializer_range=0.02' +}, model_name='MptModel', library='transformers', import_path='transformers.models.mpt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'block_per_row': 'block_per_row=4', 'approx_mode': "approx_mode='full'", 'initial_prior_first_n_blocks': 'initial_prior_first_n_blocks=0', 'initial_prior_diagonal_n_blocks': 'initial_prior_diagonal_n_blocks=0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='MraModel', library='transformers', import_path='transformers.models.mra'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250112', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=1024', 'num_layers': 'num_layers=8', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=6', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='gated-gelu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'tokenizer_class': "tokenizer_class='T5Tokenizer'", 'tie_word_embeddings': 'tie_word_embeddings=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'decoder_start_token_id': 'decoder_start_token_id=0', 'classifier_dropout': 'classifier_dropout=0.0' +}, model_name='MT5Model', library='transformers', import_path='transformers.models.mt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'text_encoder': 'text_encoder', 'audio_encoder': 'audio_encoder', 'decoder': 'decoder' +}, model_name='MusicgenModel', library='transformers', import_path='transformers.models.musicgen'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'text_encoder': 'text_encoder', 'audio_encoder': 'audio_encoder', 'decoder': 'decoder', 'num_chroma': 'num_chroma=12', 'chroma_length': 'chroma_length=235' +}, model_name='MusicgenMelodyModel', library='transformers', import_path='transformers.models.musicgen_melody'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50267', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'is_encoder_decoder': 'is_encoder_decoder=True', 'decoder_start_token_id': 'decoder_start_token_id=2', 'use_prompt': 'use_prompt=False', 'prompt_length': 'prompt_length=100', 'prompt_mid_dim': 'prompt_mid_dim=800' +}, model_name='MvpModel', library='transformers', import_path='transformers.models.mvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 50304', 'hidden_size': 'hidden_size: int = 768', 'intermediate_size': 'intermediate_size: int | None = 8192', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 6', 'num_key_value_heads': 'num_key_value_heads: int | None = None', 'max_position_embeddings': 'max_position_embeddings: int = 2048', 'hidden_act': "hidden_act: str = 'relu2'", 'attention_dropout': 'attention_dropout: float = 0.0', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'initializer_range': 'initializer_range: float = 0.02', 'rope_parameters': 'rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None', 'final_logit_softcapping': 'final_logit_softcapping: float | None = 15.0', 'attention_bias': 'attention_bias: bool = False', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 1', 'pad_token_id': 'pad_token_id: int = 1', 'tie_word_embeddings': 'tie_word_embeddings: bool = False' +}, model_name='NanoChatModel', library='transformers', import_path='transformers.models.nanochat'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 6144', 'intermediate_size': 'intermediate_size: Optional[int + ] = 24576', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 48', 'head_dim': 'head_dim: Optional[int + ] = None', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.0134', 'norm_eps': 'norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'eos_token_id': 'eos_token_id: Optional[int + ] = 3', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False' +}, model_name='NemotronModel', library='transformers', import_path='transformers.models.nemotron'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128112', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'router_bias': 'router_bias=False', 'router_dtype': "router_dtype='float32'", 'router_ignore_padding_tokens': 'router_ignore_padding_tokens=False', 'num_experts': 'num_experts=128', 'expert_capacity': 'expert_capacity=64', 'encoder_sparse_step': 'encoder_sparse_step=4', 'decoder_sparse_step': 'decoder_sparse_step=4', 'router_z_loss_coef': 'router_z_loss_coef=0.001', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'second_expert_policy': "second_expert_policy='all'", 'normalize_router_prob_before_dropping': 'normalize_router_prob_before_dropping=False', 'batch_prioritized_routing': 'batch_prioritized_routing=False', 'moe_eval_capacity_token_fraction': 'moe_eval_capacity_token_fraction=1.0', 'moe_token_dropout': 'moe_token_dropout=0.2', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'output_router_logits': 'output_router_logits=False' +}, model_name='NllbMoeModel', library='transformers', import_path='transformers.models.nllb_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'additional_special_tokens': 'additional_special_tokens=None', 'legacy_behaviour': 'legacy_behaviour=False' +}, model_name='NllbTokenizer', library='transformers', import_path='transformers.models.nllb'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30000', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_new'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=510', 'type_vocab_size': 'type_vocab_size=2', 'segment_means_seq_len': 'segment_means_seq_len=64', 'num_landmarks': 'num_landmarks=64', 'conv_kernel_size': 'conv_kernel_size=65', 'inv_coeff_init_option': 'inv_coeff_init_option=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='NystromformerModel', library='transformers', import_path='transformers.models.nystromformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='AlbertTokenizer', library='transformers', import_path='transformers.models.albert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50304', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'clip_qkv': 'clip_qkv: Optional[bool + ] = None' +}, model_name='OlmoModel', library='transformers', import_path='transformers.models.olmo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50304', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05' +}, model_name='Olmo2Model', library='transformers', import_path='transformers.models.olmo2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50304', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Olmo3Model', library='transformers', import_path='transformers.models.olmo3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50304', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = None', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'clip_qkv': 'clip_qkv: Optional[bool + ] = None', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 8', 'num_experts': 'num_experts: Optional[int + ] = 64', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.01', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False' +}, model_name='OlmoeModel', library='transformers', import_path='transformers.models.olmoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'backbone_config': 'backbone_config=None', 'use_timm_backbone': 'use_timm_backbone=True', 'backbone': "backbone='swin_tiny_patch4_window7_224'", 'backbone_kwargs': 'backbone_kwargs=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'apply_layernorm_after_vision_backbone': 'apply_layernorm_after_vision_backbone=True', 'image_size': 'image_size=640', 'disable_custom_kernels': 'disable_custom_kernels=False', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'init_std': 'init_std=0.02', 'text_projection_in_dim': 'text_projection_in_dim=512', 'text_projection_out_dim': 'text_projection_out_dim=512', 'task_encoder_hidden_dim': 'task_encoder_hidden_dim=1024', 'class_embed_dim': 'class_embed_dim=512', 'class_distance_type': "class_distance_type='cosine'", 'num_queries': 'num_queries=900', 'csp_activation': "csp_activation='silu'", 'conv_norm_activation': "conv_norm_activation='gelu'", 'encoder_feedforward_activation': "encoder_feedforward_activation='relu'", 'encoder_feedforward_dropout': 'encoder_feedforward_dropout=0.0', 'encoder_dropout': 'encoder_dropout=0.0', 'hidden_expansion': 'hidden_expansion=1', 'vision_features_channels': 'vision_features_channels=[ + 256, + 256, + 256 + ]', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ + 192, + 384, + 768 + ]', 'encoder_projection_indices': 'encoder_projection_indices=[ + 2 + ]', 'encoder_attention_heads': 'encoder_attention_heads=8', 'encoder_dim_feedforward': 'encoder_dim_feedforward=2048', 'encoder_layers': 'encoder_layers=1', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'num_feature_levels': 'num_feature_levels=3', 'decoder_hidden_dim': 'decoder_hidden_dim=256', 'decoder_num_heads': 'decoder_num_heads=8', 'decoder_num_layers': 'decoder_num_layers=6', 'decoder_activation': "decoder_activation='relu'", 'decoder_dim_feedforward': 'decoder_dim_feedforward=2048', 'decoder_num_points': 'decoder_num_points=4', 'decoder_dropout': 'decoder_dropout=0.0', 'eval_size': 'eval_size=None', 'learn_initial_query': 'learn_initial_query=False', 'cache_size': 'cache_size=100', 'is_encoder_decoder': 'is_encoder_decoder=True' +}, model_name='OmDetTurboForObjectDetection', library='transformers', import_path='transformers.models.omdet_turbo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'backbone': 'backbone: Optional[str + ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict + ] = None', 'ignore_value': 'ignore_value: int = 255', 'num_queries': 'num_queries: int = 150', 'no_object_weight': 'no_object_weight: int = 0.1', 'class_weight': 'class_weight: float = 2.0', 'mask_weight': 'mask_weight: float = 5.0', 'dice_weight': 'dice_weight: float = 5.0', 'contrastive_weight': 'contrastive_weight: float = 0.5', 'contrastive_temperature': 'contrastive_temperature: float = 0.07', 'train_num_points': 'train_num_points: int = 12544', 'oversample_ratio': 'oversample_ratio: float = 3.0', 'importance_sample_ratio': 'importance_sample_ratio: float = 0.75', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-05', 'is_training': 'is_training: bool = False', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = True', 'output_auxiliary_logits': 'output_auxiliary_logits: bool = True', 'strides': 'strides: Optional[list + ] = [ + 4, + 8, + 16, + 32 + ]', 'task_seq_len': 'task_seq_len: int = 77', 'text_encoder_width': 'text_encoder_width: int = 256', 'text_encoder_context_length': 'text_encoder_context_length: int = 77', 'text_encoder_num_layers': 'text_encoder_num_layers: int = 6', 'text_encoder_vocab_size': 'text_encoder_vocab_size: int = 49408', 'text_encoder_proj_layers': 'text_encoder_proj_layers: int = 2', 'text_encoder_n_ctx': 'text_encoder_n_ctx: int = 16', 'conv_dim': 'conv_dim: int = 256', 'mask_dim': 'mask_dim: int = 256', 'hidden_dim': 'hidden_dim: int = 256', 'encoder_feedforward_dim': 'encoder_feedforward_dim: int = 1024', 'norm': "norm: str = 'GN'", 'encoder_layers': 'encoder_layers: int = 6', 'decoder_layers': 'decoder_layers: int = 10', 'use_task_norm': 'use_task_norm: bool = True', 'num_attention_heads': 'num_attention_heads: int = 8', 'dropout': 'dropout: float = 0.1', 'dim_feedforward': 'dim_feedforward: int = 2048', 'pre_norm': 'pre_norm: bool = False', 'enforce_input_proj': 'enforce_input_proj: bool = False', 'query_dec_layers': 'query_dec_layers: int = 2', 'common_stride': 'common_stride: int = 4' +}, model_name='OneFormerModel', library='transformers', import_path='transformers.models.oneformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=40478', 'n_positions': 'n_positions=512', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'afn': "afn='gelu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1' +}, model_name='OpenAIGPTModel', library='transformers', import_path='transformers.models.openai'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''" +}, model_name='OpenAIGPTTokenizer', library='transformers', import_path='transformers.models.openai'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50272', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'ffn_dim': 'ffn_dim=3072', 'max_position_embeddings': 'max_position_embeddings=2048', 'do_layer_norm_before': 'do_layer_norm_before=True', '_remove_final_layer_norm': '_remove_final_layer_norm=False', 'word_embed_proj_dim': 'word_embed_proj_dim=None', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'num_attention_heads': 'num_attention_heads=12', 'activation_function': "activation_function='relu'", 'layerdrop': 'layerdrop=0.0', 'init_std': 'init_std=0.02', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=2', 'enable_bias': 'enable_bias=True', 'layer_norm_elementwise_affine': 'layer_norm_elementwise_affine=True' +}, model_name='OPTModel', library='transformers', import_path='transformers.models.opt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151665', 'visual_indicator_token_ids': 'visual_indicator_token_ids=[ + 151666, + 151667, + 151668, + 151669, + 151670 + ]', 'vocab_size': 'vocab_size=151643', 'hidden_size': 'hidden_size=1536' +}, model_name='Ovis2Model', library='transformers', import_path='transformers.models.ovis2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'return_dict': 'return_dict=True' +}, model_name='Owlv2Model', library='transformers', import_path='transformers.models.owlv2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'return_dict': 'return_dict=True' +}, model_name='OwlViTModel', library='transformers', import_path='transformers.models.owlvit'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=256000', 'vocab_size': 'vocab_size=257152', 'projection_dim': 'projection_dim=2048', 'hidden_size': 'hidden_size=2048' +}, model_name='PaliGemmaModel', library='transformers', import_path='transformers.models.paligemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=1025', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=True', 'encoder_config': 'encoder_config: Union[dict, transformers.models.parakeet.configuration_parakeet.ParakeetEncoderConfig + ] = None', 'pad_token_id': 'pad_token_id=1024' +}, model_name='ParakeetForCTC', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=8', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=True', 'convolution_bias': 'convolution_bias=True', 'conv_kernel_size': 'conv_kernel_size=9', 'subsampling_factor': 'subsampling_factor=8', 'subsampling_conv_channels': 'subsampling_conv_channels=256', 'num_mel_bins': 'num_mel_bins=80', 'subsampling_conv_kernel_size': 'subsampling_conv_kernel_size=3', 'subsampling_conv_stride': 'subsampling_conv_stride=2', 'dropout': 'dropout=0.1', 'dropout_positions': 'dropout_positions=0.0', 'layerdrop': 'layerdrop=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'max_position_embeddings': 'max_position_embeddings=5000', 'scale_input': 'scale_input=True', 'initializer_range': 'initializer_range=0.02' +}, model_name='ParakeetEncoder', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'context_length': 'context_length: int = 32', 'patch_length': 'patch_length: int = 8', 'num_input_channels': 'num_input_channels: int = 1', 'patch_stride': 'patch_stride: int = 8', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'd_model': 'd_model: int = 8', 'expansion_factor': 'expansion_factor: int = 2', 'num_layers': 'num_layers: int = 3', 'dropout': 'dropout: float = 0.2', 'mode': "mode: str = 'common_channel'", 'gated_attn': 'gated_attn: bool = True', 'norm_mlp': "norm_mlp: str = 'LayerNorm'", 'self_attn': 'self_attn: bool = False', 'self_attn_heads': 'self_attn_heads: int = 1', 'use_positional_encoding': 'use_positional_encoding: bool = False', 'positional_encoding_type': "positional_encoding_type: str = 'sincos'", 'scaling': "scaling: Union[str, bool, NoneType] = 'std'", 'loss': "loss: str = 'mse'", 'init_std': 'init_std: float = 0.02', 'post_init': 'post_init: bool = False', 'norm_eps': 'norm_eps: float = 1e-05', 'mask_type': "mask_type: str = 'random'", 'random_mask_ratio': 'random_mask_ratio: float = 0.5', 'num_forecast_mask_patches': 'num_forecast_mask_patches: Union[int, list[int + ], NoneType + ] = [ + 2 + ]', 'mask_value': 'mask_value: int = 0', 'masked_loss': 'masked_loss: bool = True', 'channel_consistent_masking': 'channel_consistent_masking: bool = True', 'unmasked_channel_indices': 'unmasked_channel_indices: Optional[list[int + ] + ] = None', 'head_dropout': 'head_dropout: float = 0.2', 'distribution_output': "distribution_output: str = 'student_t'", 'prediction_length': 'prediction_length: int = 16', 'prediction_channel_indices': 'prediction_channel_indices: Optional[list + ] = None', 'num_targets': 'num_targets: int = 3', 'output_range': 'output_range: Optional[list + ] = None', 'head_aggregation': "head_aggregation: str = 'max_pool'" +}, model_name='PatchTSMixerModel', library='transformers', import_path='transformers.models.patchtsmixer'), ModelAttributes(model=, model_type='model', model_parameters={'num_input_channels': 'num_input_channels: int = 1', 'context_length': 'context_length: int = 32', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'mse'", 'patch_length': 'patch_length: int = 1', 'patch_stride': 'patch_stride: int = 1', 'num_hidden_layers': 'num_hidden_layers: int = 3', 'd_model': 'd_model: int = 128', 'num_attention_heads': 'num_attention_heads: int = 4', 'share_embedding': 'share_embedding: bool = True', 'channel_attention': 'channel_attention: bool = False', 'ffn_dim': 'ffn_dim: int = 512', 'norm_type': "norm_type: str = 'batchnorm'", 'norm_eps': 'norm_eps: float = 1e-05', 'attention_dropout': 'attention_dropout: float = 0.0', 'positional_dropout': 'positional_dropout: float = 0.0', 'path_dropout': 'path_dropout: float = 0.0', 'ff_dropout': 'ff_dropout: float = 0.0', 'bias': 'bias: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'pre_norm': 'pre_norm: bool = True', 'positional_encoding_type': "positional_encoding_type: str = 'sincos'", 'use_cls_token': 'use_cls_token: bool = False', 'init_std': 'init_std: float = 0.02', 'share_projection': 'share_projection: bool = True', 'scaling': "scaling: Union[str, bool, NoneType] = 'std'", 'do_mask_input': 'do_mask_input: Optional[bool + ] = None', 'mask_type': "mask_type: str = 'random'", 'random_mask_ratio': 'random_mask_ratio: float = 0.5', 'num_forecast_mask_patches': 'num_forecast_mask_patches: Union[int, list[int + ], NoneType + ] = [ + 2 + ]', 'channel_consistent_masking': 'channel_consistent_masking: Optional[bool + ] = False', 'unmasked_channel_indices': 'unmasked_channel_indices: Optional[list[int + ] + ] = None', 'mask_value': 'mask_value: int = 0', 'pooling_type': "pooling_type: str = 'mean'", 'head_dropout': 'head_dropout: float = 0.0', 'prediction_length': 'prediction_length: int = 24', 'num_targets': 'num_targets: int = 1', 'output_range': 'output_range: Optional[list + ] = None', 'num_parallel_samples': 'num_parallel_samples: int = 100' +}, model_name='PatchTSTModel', library='transformers', import_path='transformers.models.patchtst'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_config': 'audio_config=None' +}, model_name='PeAudioModel', library='transformers', import_path='transformers.models.pe_audio'), ModelAttributes(model=, model_type='model', model_parameters={'dac_config': 'dac_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'hidden_size': 'hidden_size: Optional[int + ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int + ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 10000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='PeAudioEncoder', library='transformers', import_path='transformers.models.pe_audio'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_video_config': 'audio_video_config=None' +}, model_name='PeAudioVideoModel', library='transformers', import_path='transformers.models.pe_audio_video'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'video_config': 'video_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'hidden_size': 'hidden_size: Optional[int + ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int + ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 10000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='PeAudioVideoEncoder', library='transformers', import_path='transformers.models.pe_audio_video'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'video_config': 'video_config=None' +}, model_name='PeVideoModel', library='transformers', import_path='transformers.models.pe_video'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType + ] = None', 'hidden_size': 'hidden_size: Optional[int + ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int + ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 10000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='PeVideoEncoder', library='transformers', import_path='transformers.models.pe_video'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'forced_eos_token_id': 'forced_eos_token_id=1' +}, model_name='PegasusModel', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'pad_token': "pad_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'mask_token': "mask_token=''", 'mask_token_sent': "mask_token_sent=''", 'additional_special_tokens': 'additional_special_tokens=None', 'offset': 'offset=103' +}, model_name='PegasusTokenizer', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=96103', 'max_position_embeddings': 'max_position_embeddings=16384', 'encoder_layers': 'encoder_layers=16', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=16', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=0', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'forced_eos_token_id': 'forced_eos_token_id=1', 'num_global_tokens': 'num_global_tokens=32', 'block_size': 'block_size=512', 'stagger_local_blocks': 'stagger_local_blocks=True' +}, model_name='PegasusXModel', library='transformers', import_path='transformers.models.pegasus_x'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'pad_token': "pad_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'mask_token': "mask_token=''", 'mask_token_sent': "mask_token_sent=''", 'additional_special_tokens': 'additional_special_tokens=None', 'offset': 'offset=103' +}, model_name='PegasusTokenizer', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='model', model_parameters={'num_latents': 'num_latents=256', 'd_latents': 'd_latents=1280', 'd_model': 'd_model=768', 'num_blocks': 'num_blocks=1', 'num_self_attends_per_block': 'num_self_attends_per_block=26', 'num_self_attention_heads': 'num_self_attention_heads=8', 'num_cross_attention_heads': 'num_cross_attention_heads=8', 'qk_channels': 'qk_channels=None', 'v_channels': 'v_channels=None', 'cross_attention_shape_for_attention': "cross_attention_shape_for_attention='kv'", 'self_attention_widening_factor': 'self_attention_widening_factor=1', 'cross_attention_widening_factor': 'cross_attention_widening_factor=1', 'hidden_act': "hidden_act='gelu'", 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_query_residual': 'use_query_residual=True', 'vocab_size': 'vocab_size=262', 'max_position_embeddings': 'max_position_embeddings=2048', 'image_size': 'image_size=56', 'train_size': 'train_size=[ + 368, + 496 + ]', 'num_frames': 'num_frames=16', 'audio_samples_per_frame': 'audio_samples_per_frame=1920', 'samples_per_patch': 'samples_per_patch=16', 'output_shape': 'output_shape=[ + 1, + 16, + 224, + 224 + ]', 'output_num_channels': 'output_num_channels=512', '_label_trainable_num_channels': '_label_trainable_num_channels=1024' +}, model_name='PerceiverModel', library='transformers', import_path='transformers.models.perceiver'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'pad_token': "pad_token='[PAD]'", 'bos_token': "bos_token='[BOS]'", 'eos_token': "eos_token='[EOS]'", 'mask_token': "mask_token='[MASK]'", 'cls_token': "cls_token='[CLS]'", 'sep_token': "sep_token='[SEP]'", 'model_max_length': 'model_max_length=2048' +}, model_name='PerceiverTokenizer', library='transformers', import_path='transformers.models.perceiver'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'vision_use_cls_token': 'vision_use_cls_token=True', 'projector_pooling_ratio': 'projector_pooling_ratio=1', 'image_token_id': 'image_token_id=128002', 'video_token_id': 'video_token_id=128003' +}, model_name='PerceptionLMModel', library='transformers', import_path='transformers.models.perception_lm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 262144', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 16384', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool + ] = True', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2' +}, model_name='PersimmonModel', library='transformers', import_path='transformers.models.persimmon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 51200', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'resid_pdrop': 'resid_pdrop: Optional[float + ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'gelu_new'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 2048', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool + ] = False', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2' +}, model_name='PhiModel', library='transformers', import_path='transformers.models.phi'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32064', 'hidden_size': 'hidden_size: Optional[int + ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int + ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'resid_pdrop': 'resid_pdrop: Optional[float + ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'original_max_position_embeddings': 'original_max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 32000', 'pad_token_id': 'pad_token_id: Optional[int + ] = 32000', 'sliding_window': 'sliding_window: Optional[int + ] = None' +}, model_name='Phi3Model', library='transformers', import_path='transformers.models.phi3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 200064', 'hidden_size': 'hidden_size: Optional[int + ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int + ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'resid_pdrop': 'resid_pdrop: Optional[float + ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 199999', 'eos_token_id': 'eos_token_id: Optional[list[int + ] + ] = [ + 199999, + 200020 + ]', 'pad_token_id': 'pad_token_id: Optional[int + ] = 199999', 'original_max_position_embeddings': 'original_max_position_embeddings: Optional[int + ] = 4096', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'vision_config': 'vision_config: Optional[dict + ] = None', 'audio_config': 'audio_config: Optional[dict + ] = None' +}, model_name='Phi4MultimodalModel', library='transformers', import_path='transformers.models.phi4_multimodal'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32064', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 6400', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 131072', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 2', 'num_local_experts': 'num_local_experts: Optional[int + ] = 16', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float + ] = 0.01', 'input_jitter_noise': 'input_jitter_noise: Optional[float + ] = 0.0', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'lm_head_bias': 'lm_head_bias: Optional[bool + ] = False' +}, model_name='PhimoeModel', library='transformers', import_path='transformers.models.phimoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1280', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=16', 'mlp_ratio': 'mlp_ratio=4', 'n_cls_tokens': 'n_cls_tokens=8', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=256', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'drop_path_rate': 'drop_path_rate=0.0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True' +}, model_name='PixioModel', library='transformers', import_path='transformers.models.pixio'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size: Optional[int + ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int + ] = 4096', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_channels': 'num_channels: Optional[int + ] = 3', 'image_size': 'image_size: Optional[int + ] = 1024', 'patch_size': 'patch_size: Optional[int + ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02' +}, model_name='PixtralVisionModel', library='transformers', import_path='transformers.models.pixtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50005', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=3072', 'encoder_attention_heads': 'encoder_attention_heads=12', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=3072', 'decoder_attention_heads': 'decoder_attention_heads=12', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=768', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' +}, model_name='PLBartModel', library='transformers', import_path='transformers.models.plbart'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'language_codes': "language_codes='base'", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None', 'additional_special_tokens': 'additional_special_tokens=None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=True' +}, model_name='PLBartTokenizer', library='transformers', import_path='transformers.models.plbart'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'stride': 'stride=16', 'pool_size': 'pool_size=3', 'mlp_ratio': 'mlp_ratio=4.0', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'hidden_sizes': 'hidden_sizes=[ + 64, + 128, + 320, + 512 + ]', 'patch_sizes': 'patch_sizes=[ + 7, + 3, + 3, + 3 + ]', 'strides': 'strides=[ + 4, + 2, + 2, + 2 + ]', 'padding': 'padding=[ + 2, + 1, + 1, + 1 + ]', 'num_encoder_blocks': 'num_encoder_blocks=4', 'drop_path_rate': 'drop_path_rate=0.0', 'hidden_act': "hidden_act='gelu'", 'use_layer_scale': 'use_layer_scale=True', 'layer_scale_init_value': 'layer_scale_init_value=1e-05', 'initializer_range': 'initializer_range=0.02' +}, model_name='PoolFormerModel', library='transformers', import_path='transformers.models.poolformer'), ModelAttributes(model=, model_type='model', model_parameters={'activation_dropout': 'activation_dropout: Optional[float + ] = 0.1', 'activation_function': "activation_function: Union[str, collections.abc.Callable, NoneType] = 'gelu'", 'vocab_size': 'vocab_size: Optional[int + ] = 30522', 'hidden_size': 'hidden_size: Optional[int + ] = 1024', 'encoder_ffn_dim': 'encoder_ffn_dim: Optional[int + ] = 4096', 'num_encoder_layers': 'num_encoder_layers: Optional[int + ] = 12', 'num_encoder_attention_heads': 'num_encoder_attention_heads: Optional[int + ] = 16', 'decoder_ffn_dim': 'decoder_ffn_dim: Optional[int + ] = 4096', 'num_decoder_layers': 'num_decoder_layers: Optional[int + ] = 12', 'num_decoder_attention_heads': 'num_decoder_attention_heads: Optional[int + ] = 16', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.1', 'dropout': 'dropout: Optional[float + ] = 0.1', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 512', 'init_std': 'init_std: Optional[float + ] = 0.02', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool + ] = True', 'add_cross_attention': 'add_cross_attention: Optional[bool + ] = True', 'decoder_start_token_id': 'decoder_start_token_id: Optional[int + ] = 0', 'ngram': 'ngram: Optional[int + ] = 2', 'num_buckets': 'num_buckets: Optional[int + ] = 32', 'relative_max_distance': 'relative_max_distance: Optional[int + ] = 128', 'disable_ngram_loss': 'disable_ngram_loss: Optional[bool + ] = False', 'eps': 'eps: Optional[float + ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2' +}, model_name='ProphetNetModel', library='transformers', import_path='transformers.models.prophetnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file: str', 'do_lower_case': 'do_lower_case: Optional[bool + ] = True', 'do_basic_tokenize': 'do_basic_tokenize: Optional[bool + ] = True', 'never_split': 'never_split: Optional[collections.abc.Iterable + ] = None', 'unk_token': "unk_token: Optional[str] = '[UNK]'", 'sep_token': "sep_token: Optional[str] = '[SEP]'", 'x_sep_token': "x_sep_token: Optional[str] = '[X_SEP]'", 'pad_token': "pad_token: Optional[str] = '[PAD]'", 'mask_token': "mask_token: Optional[str] = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: Optional[bool + ] = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces: bool = True' +}, model_name='ProphetNetTokenizer', library='transformers', import_path='transformers.models.prophetnet'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size: int = 224', 'num_channels': 'num_channels: int = 3', 'num_encoder_blocks': 'num_encoder_blocks: int = 4', 'depths': 'depths: list[int + ] = [ + 2, + 2, + 2, + 2 + ]', 'sequence_reduction_ratios': 'sequence_reduction_ratios: list[int + ] = [ + 8, + 4, + 2, + 1 + ]', 'hidden_sizes': 'hidden_sizes: list[int + ] = [ + 64, + 128, + 320, + 512 + ]', 'patch_sizes': 'patch_sizes: list[int + ] = [ + 4, + 2, + 2, + 2 + ]', 'strides': 'strides: list[int + ] = [ + 4, + 2, + 2, + 2 + ]', 'num_attention_heads': 'num_attention_heads: list[int + ] = [ + 1, + 2, + 5, + 8 + ]', 'mlp_ratios': 'mlp_ratios: list[int + ] = [ + 8, + 8, + 4, + 4 + ]', 'hidden_act': "hidden_act: collections.abc.Mapping[str, collections.abc.Callable] = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'qkv_bias': 'qkv_bias: bool = True', 'num_labels': 'num_labels: int = 1000' +}, model_name='PvtModel', library='transformers', import_path='transformers.models.pvt'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size: Union[int, tuple[int, int + ] + ] = 224', 'num_channels': 'num_channels: int = 3', 'num_encoder_blocks': 'num_encoder_blocks: int = 4', 'depths': 'depths: list[int + ] = [ + 2, + 2, + 2, + 2 + ]', 'sr_ratios': 'sr_ratios: list[int + ] = [ + 8, + 4, + 2, + 1 + ]', 'hidden_sizes': 'hidden_sizes: list[int + ] = [ + 32, + 64, + 160, + 256 + ]', 'patch_sizes': 'patch_sizes: list[int + ] = [ + 7, + 3, + 3, + 3 + ]', 'strides': 'strides: list[int + ] = [ + 4, + 2, + 2, + 2 + ]', 'num_attention_heads': 'num_attention_heads: list[int + ] = [ + 1, + 2, + 5, + 8 + ]', 'mlp_ratios': 'mlp_ratios: list[int + ] = [ + 8, + 8, + 4, + 4 + ]', 'hidden_act': "hidden_act: Union[str, collections.abc.Callable] = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'qkv_bias': 'qkv_bias: bool = True', 'linear_attention': 'linear_attention: bool = False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='PvtV2Model', library='transformers', import_path='transformers.models.pvt_v2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 28', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='Qwen2Model', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653' +}, model_name='Qwen2_5_VLModel', library='transformers', import_path='transformers.models.qwen2_5_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 152064', 'hidden_size': 'hidden_size: Optional[int + ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int + ] = 29568', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 80', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 80', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 151643', 'eos_token_id': 'eos_token_id: Optional[int + ] = 151645', 'pad_token_id': 'pad_token_id: Optional[int + ] = None' +}, model_name='Qwen2_5_VLTextModel', library='transformers', import_path='transformers.models.qwen2_5_vl'), ModelAttributes(model=, model_type='model', model_parameters={'num_mel_bins': 'num_mel_bins=128', 'encoder_layers': 'encoder_layers=32', 'encoder_attention_heads': 'encoder_attention_heads=20', 'encoder_ffn_dim': 'encoder_ffn_dim=5120', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'd_model': 'd_model=1280', 'dropout': 'dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'activation_function': "activation_function='gelu'", 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'initializer_range': 'initializer_range=0.02', 'max_source_positions': 'max_source_positions=1500' +}, model_name='Qwen2AudioEncoder', library='transformers', import_path='transformers.models.qwen2_audio'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 28', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int + ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1408', 'shared_expert_intermediate_size': 'shared_expert_intermediate_size: Optional[int + ] = 5632', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 4', 'num_experts': 'num_experts: Optional[int + ] = 60', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[bool + ] = None', 'qkv_bias': 'qkv_bias: Optional[bool + ] = True', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Qwen2MoeModel', library='transformers', import_path='transformers.models.qwen2_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653' +}, model_name='Qwen2VLModel', library='transformers', import_path='transformers.models.qwen2_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 152064', 'hidden_size': 'hidden_size: Optional[int + ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int + ] = 29568', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 80', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 80', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'bos_token_id': 'bos_token_id: Optional[int + ] = 151643', 'eos_token_id': 'eos_token_id: Optional[int + ] = 151645', 'pad_token_id': 'pad_token_id: Optional[int + ] = None' +}, model_name='Qwen2VLTextModel', library='transformers', import_path='transformers.models.qwen2_vl'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int + ] = 28', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='Qwen3Model', library='transformers', import_path='transformers.models.qwen3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int + ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 768', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 8', 'num_experts': 'num_experts: Optional[int + ] = 128', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = False', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[bool + ] = None' +}, model_name='Qwen3MoeModel', library='transformers', import_path='transformers.models.qwen3_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 48', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'head_dim': 'head_dim: Optional[int + ] = 256', 'linear_conv_kernel_dim': 'linear_conv_kernel_dim: Optional[int + ] = 4', 'linear_key_head_dim': 'linear_key_head_dim: Optional[int + ] = 128', 'linear_value_head_dim': 'linear_value_head_dim: Optional[int + ] = 128', 'linear_num_key_heads': 'linear_num_key_heads: Optional[int + ] = 16', 'linear_num_value_heads': 'linear_num_value_heads: Optional[int + ] = 32', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int + ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 512', 'shared_expert_intermediate_size': 'shared_expert_intermediate_size: Optional[int + ] = 512', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 10', 'num_experts': 'num_experts: Optional[int + ] = 512', 'norm_topk_prob': 'norm_topk_prob: Optional[bool + ] = True', 'output_router_logits': 'output_router_logits: Optional[bool + ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float + ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[list[int + ] + ] = []', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None' +}, model_name='Qwen3NextModel', library='transformers', import_path='transformers.models.qwen3_next'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='Qwen3VLModel', library='transformers', import_path='transformers.models.qwen3_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='Qwen3VLMoeModel', library='transformers', import_path='transformers.models.qwen3_vl_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' +}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 128000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int + ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int + ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int + ] = 4', 'num_experts': 'num_experts: Optional[int + ] = 60', 'mlp_only_layers': 'mlp_only_layers: Optional[list[int + ] + ] = None', 'rope_parameters': 'rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters + ] = None', 'head_dim': 'head_dim: Optional[int + ] = None' +}, model_name='Qwen3VLMoeTextModel', library='transformers', import_path='transformers.models.qwen3_vl_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 151936', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'head_dim': 'head_dim: Optional[int + ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 128000', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0' +}, model_name='Qwen3VLTextModel', library='transformers', import_path='transformers.models.qwen3_vl'), ModelAttributes(model=, model_type='model', model_parameters={'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 26', 'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int + ] = 7680', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 10', 'lru_width': 'lru_width: Optional[int + ] = None', 'attention_window_size': 'attention_window_size: Optional[int + ] = 2048', 'conv1d_width': 'conv1d_width: Optional[int + ] = 4', 'logits_soft_cap': 'logits_soft_cap: Optional[float + ] = 30.0', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'block_types': "block_types: Optional[list[str]] = ('recurrent', 'recurrent', 'attention')", 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'attention_bias': 'attention_bias: Optional[str + ] = False', 'w_init_variance_scale': 'w_init_variance_scale: Optional[float + ] = 0.01' +}, model_name='RecurrentGemmaModel', library='transformers', import_path='transformers.models.recurrent_gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'attention_head_size': 'attention_head_size=64', 'attn_layers': "attn_layers=['local', 'lsh', 'local', 'lsh', 'local', 'lsh']", 'axial_norm_std': 'axial_norm_std=1.0', 'axial_pos_embds': 'axial_pos_embds=True', 'axial_pos_shape': 'axial_pos_shape=[ + 64, + 64 + ]', 'axial_pos_embds_dim': 'axial_pos_embds_dim=[ + 64, + 192 + ]', 'chunk_size_lm_head': 'chunk_size_lm_head=0', 'eos_token_id': 'eos_token_id=2', 'feed_forward_size': 'feed_forward_size=512', 'hash_seed': 'hash_seed=None', 'hidden_act': "hidden_act='relu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.05', 'hidden_size': 'hidden_size=256', 'initializer_range': 'initializer_range=0.02', 'is_decoder': 'is_decoder=False', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'local_num_chunks_before': 'local_num_chunks_before=1', 'local_num_chunks_after': 'local_num_chunks_after=0', 'local_attention_probs_dropout_prob': 'local_attention_probs_dropout_prob=0.05', 'local_attn_chunk_length': 'local_attn_chunk_length=64', 'lsh_attn_chunk_length': 'lsh_attn_chunk_length=64', 'lsh_attention_probs_dropout_prob': 'lsh_attention_probs_dropout_prob=0.0', 'lsh_num_chunks_before': 'lsh_num_chunks_before=1', 'lsh_num_chunks_after': 'lsh_num_chunks_after=0', 'max_position_embeddings': 'max_position_embeddings=4096', 'num_attention_heads': 'num_attention_heads=12', 'num_buckets': 'num_buckets=None', 'num_hashes': 'num_hashes=1', 'pad_token_id': 'pad_token_id=0', 'vocab_size': 'vocab_size=320', 'tie_word_embeddings': 'tie_word_embeddings=False', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='ReformerModel', library='transformers', import_path='transformers.models.reformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'eos_token': "eos_token: str = ''", 'unk_token': "unk_token: str = ''", 'additional_special_tokens': 'additional_special_tokens: Optional[list + ] = None' +}, model_name='ReformerTokenizer', library='transformers', import_path='transformers.models.reformer'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=32', 'hidden_sizes': 'hidden_sizes=[ + 128, + 192, + 512, + 1088 + ]', 'depths': 'depths=[ + 2, + 6, + 12, + 2 + ]', 'groups_width': 'groups_width=64', 'layer_type': "layer_type='y'", 'hidden_act': "hidden_act='relu'" +}, model_name='RegNetModel', library='transformers', import_path='transformers.models.regnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250300', 'hidden_size': 'hidden_size=1152', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=18', 'input_embedding_size': 'input_embedding_size=256', 'output_embedding_size': 'output_embedding_size=1664', 'intermediate_size': 'intermediate_size=4608', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=312', 'eos_token_id': 'eos_token_id=313' +}, model_name='RemBertModel', library='transformers', import_path='transformers.models.rembert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'remove_space': 'remove_space: bool = True' +}, model_name='RemBertTokenizer', library='transformers', import_path='transformers.models.rembert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'hidden_sizes': 'hidden_sizes=[ + 256, + 512, + 1024, + 2048 + ]', 'depths': 'depths=[ + 3, + 4, + 6, + 3 + ]', 'layer_type': "layer_type='bottleneck'", 'hidden_act': "hidden_act='relu'", 'downsample_in_first_stage': 'downsample_in_first_stage=False', 'downsample_in_bottleneck': 'downsample_in_bottleneck=False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='ResNetModel', library='transformers', import_path='transformers.models.resnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='RobertaModel', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='RobertaPreLayerNormModel', library='transformers', import_path='transformers.models.roberta_prelayernorm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None', 'enable_pronunciation': 'enable_pronunciation=True', 'enable_shape': 'enable_shape=True', 'pronunciation_embed_dim': 'pronunciation_embed_dim=768', 'pronunciation_vocab_size': 'pronunciation_vocab_size=910', 'shape_embed_dim': 'shape_embed_dim=512', 'shape_vocab_size': 'shape_vocab_size=24858', 'concat_input': 'concat_input=True' +}, model_name='RoCBertModel', library='transformers', import_path='transformers.models.roc_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'word_shape_file': 'word_shape_file', 'word_pronunciation_file': 'word_pronunciation_file', 'do_lower_case': 'do_lower_case=True', 'do_basic_tokenize': 'do_basic_tokenize=True', 'never_split': 'never_split=None', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' +}, model_name='RoCBertTokenizer', library='transformers', import_path='transformers.models.roc_bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50000', 'embedding_size': 'embedding_size=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1536', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'rotary_value': 'rotary_value=False' +}, model_name='RoFormerModel', library='transformers', import_path='transformers.models.roformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Optional[dict[str, int + ] + ] = None', 'do_lower_case': 'do_lower_case=True', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' +}, model_name='RoFormerTokenizer', library='transformers', import_path='transformers.models.roformer'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ + 512, + 1024, + 2048 + ]', 'feat_strides': 'feat_strides=[ + 8, + 16, + 32 + ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ + 2 + ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ + 256, + 256, + 256 + ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'disable_custom_kernels': 'disable_custom_kernels=True', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'eos_coefficient': 'eos_coefficient=0.0001' +}, model_name='RTDetrModel', library='transformers', import_path='transformers.models.rt_detr'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ + 512, + 1024, + 2048 + ]', 'feat_strides': 'feat_strides=[ + 8, + 16, + 32 + ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ + 2 + ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ + 256, + 256, + 256 + ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'eos_coefficient': 'eos_coefficient=0.0001', 'decoder_n_levels': 'decoder_n_levels=3', 'decoder_offset_scale': 'decoder_offset_scale=0.5', 'decoder_method': "decoder_method='default'" +}, model_name='RTDetrV2Model', library='transformers', import_path='transformers.models.rt_detr_v2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50277', 'context_length': 'context_length=1024', 'hidden_size': 'hidden_size=4096', 'num_hidden_layers': 'num_hidden_layers=32', 'attention_hidden_size': 'attention_hidden_size=None', 'intermediate_size': 'intermediate_size=None', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'rescale_every': 'rescale_every=6', 'tie_word_embeddings': 'tie_word_embeddings=False' +}, model_name='RwkvModel', library='transformers', import_path='transformers.models.rwkv'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='SamModel', library='transformers', import_path='transformers.models.sam'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam2Model', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=96', 'num_attention_heads': 'num_attention_heads=1', 'num_channels': 'num_channels=3', 'image_size': 'image_size=None', 'patch_kernel_size': 'patch_kernel_size=None', 'patch_stride': 'patch_stride=None', 'patch_padding': 'patch_padding=None', 'query_stride': 'query_stride=None', 'window_positional_embedding_background_size': 'window_positional_embedding_background_size=None', 'num_query_pool_stages': 'num_query_pool_stages=3', 'blocks_per_stage': 'blocks_per_stage=None', 'embed_dim_per_stage': 'embed_dim_per_stage=None', 'num_attention_heads_per_stage': 'num_attention_heads_per_stage=None', 'window_size_per_stage': 'window_size_per_stage=None', 'global_attention_blocks': 'global_attention_blocks=None', 'mlp_ratio': 'mlp_ratio=4.0', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam2HieraDetModel', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1024', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=-1', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=4', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_feed_forward_hidden_size': 'memory_attention_feed_forward_hidden_size=2048', 'memory_attention_feed_forward_hidden_act': "memory_attention_feed_forward_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" +}, model_name='Sam2VideoModel', library='transformers', import_path='transformers.models.sam2_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone_channel_list': 'backbone_channel_list=None', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'fpn_kernel_size': 'fpn_kernel_size=1', 'fpn_stride': 'fpn_stride=1', 'fpn_padding': 'fpn_padding=0', 'fpn_top_down_levels': 'fpn_top_down_levels=None', 'num_feature_levels': 'num_feature_levels=3', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam2VisionModel', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'geometry_encoder_config': 'geometry_encoder_config=None', 'detr_encoder_config': 'detr_encoder_config=None', 'detr_decoder_config': 'detr_decoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam3Model', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam3TrackerModel', library='transformers', import_path='transformers.models.sam3_tracker'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1008', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=4', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=4', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_feed_forward_hidden_size': 'memory_attention_feed_forward_hidden_size=2048', 'memory_attention_feed_forward_hidden_act': "memory_attention_feed_forward_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" +}, model_name='Sam3TrackerVideoModel', library='transformers', import_path='transformers.models.sam3_tracker_video'), ModelAttributes(model=, model_type='model', model_parameters={'detector_config': 'detector_config=None', 'tracker_config': 'tracker_config=None', 'initializer_range': 'initializer_range=0.02', 'low_res_mask_size': 'low_res_mask_size=288', 'score_threshold_detection': 'score_threshold_detection=0.5', 'det_nms_thresh': 'det_nms_thresh=0.1', 'assoc_iou_thresh': 'assoc_iou_thresh=0.1', 'trk_assoc_iou_thresh': 'trk_assoc_iou_thresh=0.5', 'new_det_thresh': 'new_det_thresh=0.7', 'recondition_on_trk_masks': 'recondition_on_trk_masks=True', 'hotstart_delay': 'hotstart_delay=15', 'hotstart_unmatch_thresh': 'hotstart_unmatch_thresh=8', 'hotstart_dup_thresh': 'hotstart_dup_thresh=8', 'suppress_unmatched_only_within_hotstart': 'suppress_unmatched_only_within_hotstart=True', 'init_trk_keep_alive': 'init_trk_keep_alive=30', 'max_trk_keep_alive': 'max_trk_keep_alive=30', 'min_trk_keep_alive': 'min_trk_keep_alive=-1', 'suppress_overlapping_based_on_recent_occlusion_threshold': 'suppress_overlapping_based_on_recent_occlusion_threshold=0.7', 'decrease_trk_keep_alive_for_empty_masklets': 'decrease_trk_keep_alive_for_empty_masklets=False', 'fill_hole_area': 'fill_hole_area=16', 'max_num_objects': 'max_num_objects=10000', 'recondition_every_nth_frame': 'recondition_every_nth_frame=16', 'high_conf_thresh': 'high_conf_thresh=0.8', 'high_iou_thresh': 'high_iou_thresh=0.8' +}, model_name='Sam3VideoModel', library='transformers', import_path='transformers.models.sam3_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'scale_factors': 'scale_factors=None', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam3VisionModel', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'intermediate_size': 'intermediate_size=4736', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1008', 'patch_size': 'patch_size=14', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'rope_theta': 'rope_theta=10000.0', 'window_size': 'window_size=24', 'global_attn_indexes': 'global_attn_indexes=None', 'layer_scale_init_value': 'layer_scale_init_value=None', 'pretrain_image_size': 'pretrain_image_size=336', 'hidden_dropout': 'hidden_dropout=0.0', 'initializer_range': 'initializer_range=0.02' +}, model_name='Sam3ViTModel', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' +}, model_name='SamHQModel', library='transformers', import_path='transformers.models.sam_hq'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'output_channels': 'output_channels=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1024', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=1e-10', 'qkv_bias': 'qkv_bias=True', 'mlp_ratio': 'mlp_ratio=4.0', 'use_abs_pos': 'use_abs_pos=True', 'use_rel_pos': 'use_rel_pos=True', 'window_size': 'window_size=14', 'global_attn_indexes': 'global_attn_indexes=[ + 2, + 5, + 8, + 11 + ]', 'num_pos_feats': 'num_pos_feats=128', 'mlp_dim': 'mlp_dim=None' +}, model_name='SamHQVisionModel', library='transformers', import_path='transformers.models.sam_hq'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'output_channels': 'output_channels=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1024', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=1e-10', 'qkv_bias': 'qkv_bias=True', 'mlp_ratio': 'mlp_ratio=4.0', 'use_abs_pos': 'use_abs_pos=True', 'use_rel_pos': 'use_rel_pos=True', 'window_size': 'window_size=14', 'global_attn_indexes': 'global_attn_indexes=[ + 2, + 5, + 8, + 11 + ]', 'num_pos_feats': 'num_pos_feats=128', 'mlp_dim': 'mlp_dim=None' +}, model_name='SamVisionModel', library='transformers', import_path='transformers.models.sam'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256102', 't2u_vocab_size': 't2u_vocab_size=10082', 'hidden_size': 'hidden_size=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'max_position_embeddings': 'max_position_embeddings=1024', 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'activation_function': "activation_function='relu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'encoder_layers': 'encoder_layers=24', 'encoder_ffn_dim': 'encoder_ffn_dim=8192', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=8192', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_start_token_id': 'decoder_start_token_id=3', 'max_new_tokens': 'max_new_tokens=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=3', 'speech_encoder_layers': 'speech_encoder_layers=24', 'speech_encoder_attention_heads': 'speech_encoder_attention_heads=16', 'speech_encoder_intermediate_size': 'speech_encoder_intermediate_size=4096', 'speech_encoder_hidden_act': "speech_encoder_hidden_act='swish'", 'speech_encoder_dropout': 'speech_encoder_dropout=0.0', 'add_adapter': 'add_adapter=True', 'speech_encoder_layerdrop': 'speech_encoder_layerdrop=0.1', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'adaptor_kernel_size': 'adaptor_kernel_size=8', 'adaptor_stride': 'adaptor_stride=8', 'adaptor_dropout': 'adaptor_dropout=0.1', 'num_adapter_layers': 'num_adapter_layers=1', 'position_embeddings_type': "position_embeddings_type='relative'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=4096', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 't2u_bos_token_id': 't2u_bos_token_id=0', 't2u_pad_token_id': 't2u_pad_token_id=1', 't2u_eos_token_id': 't2u_eos_token_id=2', 't2u_decoder_start_token_id': 't2u_decoder_start_token_id=2', 't2u_max_new_tokens': 't2u_max_new_tokens=1024', 't2u_encoder_layers': 't2u_encoder_layers=6', 't2u_encoder_ffn_dim': 't2u_encoder_ffn_dim=8192', 't2u_encoder_attention_heads': 't2u_encoder_attention_heads=16', 't2u_decoder_layers': 't2u_decoder_layers=6', 't2u_decoder_ffn_dim': 't2u_decoder_ffn_dim=8192', 't2u_decoder_attention_heads': 't2u_decoder_attention_heads=16', 't2u_max_position_embeddings': 't2u_max_position_embeddings=2048', 'sampling_rate': 'sampling_rate=16000', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ + 5, + 4, + 4, + 2, + 2 + ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ + 11, + 8, + 8, + 4, + 4 + ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ + 3, + 7, + 11 + ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ] + ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'unit_hifi_gan_vocab_size': 'unit_hifi_gan_vocab_size=10000', 'unit_embed_dim': 'unit_embed_dim=1280', 'lang_embed_dim': 'lang_embed_dim=256', 'spkr_embed_dim': 'spkr_embed_dim=256', 'vocoder_num_langs': 'vocoder_num_langs=36', 'vocoder_num_spkrs': 'vocoder_num_spkrs=200', 'variance_predictor_kernel_size': 'variance_predictor_kernel_size=3', 'var_pred_dropout': 'var_pred_dropout=0.5', 'vocoder_offset': 'vocoder_offset=4' +}, model_name='SeamlessM4TModel', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'src_lang': "src_lang='eng'", 'tgt_lang': "tgt_lang='fra'", 'additional_special_tokens': 'additional_special_tokens=None', 'keep_accents': 'keep_accents=None', 'vocab_file': 'vocab_file=None' +}, model_name='SeamlessM4TTokenizer', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256102', 't2u_vocab_size': 't2u_vocab_size=10082', 'char_vocab_size': 'char_vocab_size=10943', 'hidden_size': 'hidden_size=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'max_position_embeddings': 'max_position_embeddings=4096', 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'activation_function': "activation_function='relu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'encoder_layers': 'encoder_layers=24', 'encoder_ffn_dim': 'encoder_ffn_dim=8192', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=8192', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_start_token_id': 'decoder_start_token_id=3', 'max_new_tokens': 'max_new_tokens=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=3', 'speech_encoder_layers': 'speech_encoder_layers=24', 'speech_encoder_attention_heads': 'speech_encoder_attention_heads=16', 'speech_encoder_intermediate_size': 'speech_encoder_intermediate_size=4096', 'speech_encoder_hidden_act': "speech_encoder_hidden_act='swish'", 'speech_encoder_dropout': 'speech_encoder_dropout=0.0', 'add_adapter': 'add_adapter=True', 'speech_encoder_layerdrop': 'speech_encoder_layerdrop=0.1', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'adaptor_kernel_size': 'adaptor_kernel_size=8', 'adaptor_stride': 'adaptor_stride=8', 'adaptor_dropout': 'adaptor_dropout=0.1', 'num_adapter_layers': 'num_adapter_layers=1', 'position_embeddings_type': "position_embeddings_type='relative_key'", 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'left_max_position_embeddings': 'left_max_position_embeddings=64', 'right_max_position_embeddings': 'right_max_position_embeddings=8', 'speech_encoder_chunk_size': 'speech_encoder_chunk_size=20000', 'speech_encoder_left_chunk_num': 'speech_encoder_left_chunk_num=128', 't2u_bos_token_id': 't2u_bos_token_id=0', 't2u_pad_token_id': 't2u_pad_token_id=1', 't2u_eos_token_id': 't2u_eos_token_id=2', 't2u_encoder_layers': 't2u_encoder_layers=6', 't2u_encoder_ffn_dim': 't2u_encoder_ffn_dim=8192', 't2u_encoder_attention_heads': 't2u_encoder_attention_heads=16', 't2u_decoder_layers': 't2u_decoder_layers=6', 't2u_decoder_ffn_dim': 't2u_decoder_ffn_dim=8192', 't2u_decoder_attention_heads': 't2u_decoder_attention_heads=16', 't2u_max_position_embeddings': 't2u_max_position_embeddings=4096', 't2u_variance_predictor_embed_dim': 't2u_variance_predictor_embed_dim=1024', 't2u_variance_predictor_hidden_dim': 't2u_variance_predictor_hidden_dim=256', 't2u_variance_predictor_kernel_size': 't2u_variance_predictor_kernel_size=3', 't2u_variance_pred_dropout': 't2u_variance_pred_dropout=0.5', 'sampling_rate': 'sampling_rate=16000', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ + 5, + 4, + 4, + 2, + 2 + ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ + 11, + 8, + 8, + 4, + 4 + ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ + 3, + 7, + 11 + ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ] + ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'unit_hifi_gan_vocab_size': 'unit_hifi_gan_vocab_size=10000', 'unit_embed_dim': 'unit_embed_dim=1280', 'lang_embed_dim': 'lang_embed_dim=256', 'spkr_embed_dim': 'spkr_embed_dim=256', 'vocoder_num_langs': 'vocoder_num_langs=36', 'vocoder_num_spkrs': 'vocoder_num_spkrs=200', 'variance_predictor_kernel_size': 'variance_predictor_kernel_size=3', 'var_pred_dropout': 'var_pred_dropout=0.5', 'vocoder_offset': 'vocoder_offset=4' +}, model_name='SeamlessM4Tv2Model', library='transformers', import_path='transformers.models.seamless_m4t_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'src_lang': "src_lang='eng'", 'tgt_lang': "tgt_lang='fra'", 'additional_special_tokens': 'additional_special_tokens=None', 'keep_accents': 'keep_accents=None', 'vocab_file': 'vocab_file=None' +}, model_name='SeamlessM4TTokenizer', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 155136', 'hidden_size': 'hidden_size: Optional[int + ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int + ] = 27648', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 64', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 80', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 524288', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int + ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = True', 'attention_out_bias': 'attention_out_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.1', 'residual_dropout': 'residual_dropout: Optional[float + ] = 0.1', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False', 'head_dim': 'head_dim: Optional[int + ] = 128' +}, model_name='SeedOssModel', library='transformers', import_path='transformers.models.seed_oss'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'num_encoder_blocks': 'num_encoder_blocks=4', 'depths': 'depths=[ + 2, + 2, + 2, + 2 + ]', 'sr_ratios': 'sr_ratios=[ + 8, + 4, + 2, + 1 + ]', 'hidden_sizes': 'hidden_sizes=[ + 32, + 64, + 160, + 256 + ]', 'patch_sizes': 'patch_sizes=[ + 7, + 3, + 3, + 3 + ]', 'strides': 'strides=[ + 4, + 2, + 2, + 2 + ]', 'num_attention_heads': 'num_attention_heads=[ + 1, + 2, + 5, + 8 + ]', 'mlp_ratios': 'mlp_ratios=[ + 4, + 4, + 4, + 4 + ]', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'drop_path_rate': 'drop_path_rate=0.1', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=256', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' +}, model_name='SegformerModel', library='transformers', import_path='transformers.models.segformer'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=[ + 896, + 448 + ]', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'mlp_dim': 'mlp_dim=None', 'drop_path_rate': 'drop_path_rate=0.1', 'pretrain_image_size': 'pretrain_image_size=224', 'decoder_hidden_size': 'decoder_hidden_size=64', 'use_relative_position_embeddings': 'use_relative_position_embeddings=True', 'merge_index': 'merge_index=2', 'intermediate_hidden_state_indices': 'intermediate_hidden_state_indices=[ + 5, + 11, + 17, + 23 + ]', 'beta': 'beta=0.01' +}, model_name='SegGptModel', library='transformers', import_path='transformers.models.seggpt'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'squeeze_factor': 'squeeze_factor=2', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(64, + 128, + 128, + 128, + 128, + 256, + 256, + 256, + 256, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1)', 'conv_kernel': 'conv_kernel=(10, + 3, + 1, + 3, + 1, + 3, + 1, + 3, + 1, + 2, + 1, + 2, + 1)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' +}, model_name='SEWModel', library='transformers', import_path='transformers.models.sew'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'squeeze_factor': 'squeeze_factor=2', 'max_position_embeddings': 'max_position_embeddings=512', 'position_buckets': 'position_buckets=256', 'share_att_key': 'share_att_key=True', 'relative_attention': 'relative_attention=True', 'pos_att_type': "pos_att_type=('p2c', 'c2p')", 'norm_rel_ebd': "norm_rel_ebd='layer_norm'", 'hidden_act': "hidden_act='gelu_python'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'feature_layer_norm_eps': 'feature_layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(64, + 128, + 128, + 128, + 128, + 256, + 256, + 256, + 256, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1, + 2, + 1)', 'conv_kernel': 'conv_kernel=(10, + 3, + 1, + 3, + 1, + 3, + 1, + 3, + 1, + 2, + 1, + 2, + 1)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' +}, model_name='SEWDModel', library='transformers', import_path='transformers.models.sew_d'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None' +}, model_name='SiglipModel', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'additional_special_tokens': 'additional_special_tokens=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None', 'model_max_length': 'model_max_length=64', 'do_lower_case': 'do_lower_case=True' +}, model_name='SiglipTokenizer', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None' +}, model_name='Siglip2Model', library='transformers', import_path='transformers.models.siglip2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'num_patches': 'num_patches=256', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0' +}, model_name='Siglip2VisionModel', library='transformers', import_path='transformers.models.siglip2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0' +}, model_name='SiglipVisionModel', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 128256', 'hidden_size': 'hidden_size: Optional[int + ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int + ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 32768', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 128004', 'bos_token_id': 'bos_token_id: Optional[int + ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int + ] = 128001', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool + ] = False', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'no_rope_layers': 'no_rope_layers: Optional[int + ] = None', 'no_rope_layer_interval': 'no_rope_layer_interval: Optional[int + ] = 4', 'layer_types': 'layer_types: Optional[int + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool + ] = False' +}, model_name='SmolLM3Model', library='transformers', import_path='transformers.models.smollm3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' +}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=128257', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'scale_factor': 'scale_factor=2', 'pad_token_id': 'pad_token_id=128002' +}, model_name='SmolVLMModel', library='transformers', import_path='transformers.models.smolvlm'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1152', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' +}, model_name='SmolVLMVisionTransformer', library='transformers', import_path='transformers.models.smolvlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=10000', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=4', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=4', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_source_positions': 'max_source_positions=6000', 'max_target_positions': 'max_target_positions=1024', 'num_conv_layers': 'num_conv_layers=2', 'conv_kernel_sizes': 'conv_kernel_sizes=(5, + 5)', 'conv_channels': 'conv_channels=1024', 'input_feat_per_channel': 'input_feat_per_channel=80', 'input_channels': 'input_channels=1' +}, model_name='Speech2TextModel', library='transformers', import_path='transformers.models.speech_to_text'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'spm_file': 'spm_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'do_upper_case': 'do_upper_case=False', 'do_lower_case': 'do_lower_case=False', 'tgt_lang': 'tgt_lang=None', 'lang_codes': 'lang_codes=None', 'additional_special_tokens': 'additional_special_tokens=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None' +}, model_name='Speech2TextTokenizer', library='transformers', import_path='transformers.models.speech_to_text'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=81', 'hidden_size': 'hidden_size=768', 'encoder_layers': 'encoder_layers=12', 'encoder_attention_heads': 'encoder_attention_heads=12', 'encoder_ffn_dim': 'encoder_ffn_dim=3072', 'encoder_layerdrop': 'encoder_layerdrop=0.1', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=3072', 'decoder_attention_heads': 'decoder_attention_heads=12', 'decoder_layerdrop': 'decoder_layerdrop=0.1', 'hidden_act': "hidden_act='gelu'", 'positional_dropout': 'positional_dropout=0.1', 'hidden_dropout': 'hidden_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'scale_embedding': 'scale_embedding=False', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'decoder_start_token_id': 'decoder_start_token_id=2', 'num_mel_bins': 'num_mel_bins=80', 'speech_decoder_prenet_layers': 'speech_decoder_prenet_layers=2', 'speech_decoder_prenet_units': 'speech_decoder_prenet_units=256', 'speech_decoder_prenet_dropout': 'speech_decoder_prenet_dropout=0.5', 'speaker_embedding_dim': 'speaker_embedding_dim=512', 'speech_decoder_postnet_layers': 'speech_decoder_postnet_layers=5', 'speech_decoder_postnet_units': 'speech_decoder_postnet_units=256', 'speech_decoder_postnet_kernel': 'speech_decoder_postnet_kernel=5', 'speech_decoder_postnet_dropout': 'speech_decoder_postnet_dropout=0.5', 'reduction_factor': 'reduction_factor=2', 'max_speech_positions': 'max_speech_positions=4000', 'max_text_positions': 'max_text_positions=450', 'encoder_max_relative_position': 'encoder_max_relative_position=160', 'use_guided_attention_loss': 'use_guided_attention_loss=True', 'guided_attention_loss_num_heads': 'guided_attention_loss_num_heads=2', 'guided_attention_loss_sigma': 'guided_attention_loss_sigma=0.4', 'guided_attention_loss_scale': 'guided_attention_loss_scale=10.0', 'is_encoder_decoder': 'is_encoder_decoder=True' +}, model_name='SpeechT5Model', library='transformers', import_path='transformers.models.speecht5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'normalize': 'normalize=False', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any + ] + ] = None' +}, model_name='SpeechT5Tokenizer', library='transformers', import_path='transformers.models.speecht5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'question_token_id': 'question_token_id=104' +}, model_name='SplinterModel', library='transformers', import_path='transformers.models.splinter'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'question_token': "question_token: str = '[QUESTION]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='SplinterTokenizer', library='transformers', import_path='transformers.models.splinter'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'embedding_size': 'embedding_size=768', 'q_groups': 'q_groups=4', 'k_groups': 'k_groups=4', 'v_groups': 'v_groups=4', 'post_attention_groups': 'post_attention_groups=1', 'intermediate_groups': 'intermediate_groups=4', 'output_groups': 'output_groups=4' +}, model_name='SqueezeBertModel', library='transformers', import_path='transformers.models.squeezebert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 50304', 'intermediate_size': 'intermediate_size: Optional[int + ] = 6912', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[float + ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'use_qkv_bias': 'use_qkv_bias: Optional[bool + ] = False', 'qk_layernorm': 'qk_layernorm: Optional[bool + ] = False', 'use_parallel_residual': 'use_parallel_residual: Optional[bool + ] = False', 'hidden_dropout': 'hidden_dropout: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 0' +}, model_name='StableLmModel', library='transformers', import_path='transformers.models.stablelm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 49152', 'hidden_size': 'hidden_size: Optional[int + ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int + ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 30', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 24', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'initializer_range': 'initializer_range: Optional[float + ] = 0.018042', 'norm_epsilon': 'norm_epsilon: Optional[int + ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int + ] = 50256', 'eos_token_id': 'eos_token_id: Optional[int + ] = 50256', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'sliding_window': 'sliding_window: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'residual_dropout': 'residual_dropout: Optional[float + ] = 0.0', 'embedding_dropout': 'embedding_dropout: Optional[float + ] = 0.0', 'use_bias': 'use_bias: Optional[bool + ] = True' +}, model_name='Starcoder2Model', library='transformers', import_path='transformers.models.starcoder2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType + ] = None', 'add_prefix_space': 'add_prefix_space=False' +}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_channels': 'num_channels=3', 'depths': 'depths=[ + 3, + 3, + 6, + 4 + ]', 'embed_dims': 'embed_dims=[ + 48, + 56, + 112, + 220 + ]', 'mlp_ratio': 'mlp_ratio=4', 'downsamples': 'downsamples=[True, True, True, True + ]', 'hidden_act': "hidden_act='gelu'", 'down_patch_size': 'down_patch_size=3', 'down_stride': 'down_stride=2', 'down_pad': 'down_pad=1', 'drop_path_rate': 'drop_path_rate=0.0', 'drop_mlp_rate': 'drop_mlp_rate=0.0', 'drop_conv_encoder_rate': 'drop_conv_encoder_rate=0.0', 'use_layer_scale': 'use_layer_scale=True', 'layer_scale_init_value': 'layer_scale_init_value=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05' +}, model_name='SwiftFormerModel', library='transformers', import_path='transformers.models.swiftformer'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'num_heads': 'num_heads=[ + 3, + 6, + 12, + 24 + ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='SwinModel', library='transformers', import_path='transformers.models.swin'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=64', 'patch_size': 'patch_size=1', 'num_channels': 'num_channels=3', 'num_channels_out': 'num_channels_out=None', 'embed_dim': 'embed_dim=180', 'depths': 'depths=[ + 6, + 6, + 6, + 6, + 6, + 6 + ]', 'num_heads': 'num_heads=[ + 6, + 6, + 6, + 6, + 6, + 6 + ]', 'window_size': 'window_size=8', 'mlp_ratio': 'mlp_ratio=2.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'upscale': 'upscale=2', 'img_range': 'img_range=1.0', 'resi_connection': "resi_connection='1conv'", 'upsampler': "upsampler='pixelshuffle'" +}, model_name='Swin2SRModel', library='transformers', import_path='transformers.models.swin2sr'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ + 2, + 2, + 6, + 2 + ]', 'num_heads': 'num_heads=[ + 3, + 6, + 12, + 24 + ]', 'window_size': 'window_size=7', 'pretrained_window_sizes': 'pretrained_window_sizes=[ + 0, + 0, + 0, + 0 + ]', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='Swinv2Model', library='transformers', import_path='transformers.models.swinv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=768', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'expert_capacity': 'expert_capacity=64', 'num_layers': 'num_layers=12', 'num_sparse_encoder_layers': 'num_sparse_encoder_layers=3', 'num_decoder_layers': 'num_decoder_layers=12', 'num_sparse_decoder_layers': 'num_sparse_decoder_layers=3', 'num_heads': 'num_heads=12', 'num_experts': 'num_experts=8', 'router_bias': 'router_bias=False', 'router_jitter_noise': 'router_jitter_noise=0.01', 'router_dtype': "router_dtype='float32'", 'router_ignore_padding_tokens': 'router_ignore_padding_tokens=False', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'router_z_loss_coef': 'router_z_loss_coef=0.001', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'initializer_factor': 'initializer_factor=1.0', 'dense_act_fn': "dense_act_fn='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'add_router_probs': 'add_router_probs=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1' +}, model_name='SwitchTransformersModel', library='transformers', import_path='transformers.models.switch_transformers'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'num_layers': 'num_layers=6', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=8', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'classifier_dropout': 'classifier_dropout=0.0' +}, model_name='T5Model', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'encoder': 'encoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any + ], NoneType + ] = None', 'decoder': 'decoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any + ], NoneType + ] = None', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool + ] = True', 'dropout_rate': 'dropout_rate: Optional[float + ] = 0.0', 'classifier_dropout_rate': 'classifier_dropout_rate: Optional[float + ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'vocab_size': 'vocab_size: Optional[int + ] = 256000' +}, model_name='T5GemmaModel', library='transformers', import_path='transformers.models.t5gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'encoder': 'encoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2EncoderConfig, dict[str, Any + ], NoneType + ] = None', 'decoder': 'decoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2DecoderConfig, dict[str, Any + ], NoneType + ] = None', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'dropout_rate': 'dropout_rate: float = 0.0', 'attention_dropout': 'attention_dropout: float = 0.0', 'classifier_dropout_rate': 'classifier_dropout_rate: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'image_token_index': 'image_token_index: int = 256001' +}, model_name='T5Gemma2Model', library='transformers', import_path='transformers.models.t5gemma2'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=100', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' +}, model_name='TableTransformerModel', library='transformers', import_path='transformers.models.table_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1024', 'type_vocab_sizes': 'type_vocab_sizes=[ + 3, + 256, + 256, + 2, + 256, + 256, + 10 + ]', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'positive_label_weight': 'positive_label_weight=10.0', 'num_aggregation_labels': 'num_aggregation_labels=0', 'aggregation_loss_weight': 'aggregation_loss_weight=1.0', 'use_answer_as_supervision': 'use_answer_as_supervision=None', 'answer_loss_importance': 'answer_loss_importance=1.0', 'use_normalized_answer_loss': 'use_normalized_answer_loss=False', 'huber_loss_delta': 'huber_loss_delta=None', 'temperature': 'temperature=1.0', 'aggregation_temperature': 'aggregation_temperature=1.0', 'use_gumbel_for_cells': 'use_gumbel_for_cells=False', 'use_gumbel_for_aggregation': 'use_gumbel_for_aggregation=False', 'average_approximation_function': "average_approximation_function='ratio'", 'cell_selection_preference': 'cell_selection_preference=None', 'answer_loss_cutoff': 'answer_loss_cutoff=None', 'max_num_rows': 'max_num_rows=64', 'max_num_columns': 'max_num_columns=32', 'average_logits_per_cell': 'average_logits_per_cell=False', 'select_one_column': 'select_one_column=True', 'allow_empty_column_selection': 'allow_empty_column_selection=False', 'init_cell_selection_weights_to_zero': 'init_cell_selection_weights_to_zero=False', 'reset_position_index_per_cell': 'reset_position_index_per_cell=True', 'disable_per_token_loss': 'disable_per_token_loss=False', 'aggregation_labels': 'aggregation_labels=None', 'no_aggregation_label_index': 'no_aggregation_label_index=None' +}, model_name='TapasModel', library='transformers', import_path='transformers.models.tapas'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'do_lower_case': 'do_lower_case=True', 'do_basic_tokenize': 'do_basic_tokenize=True', 'never_split': 'never_split=None', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'empty_token': "empty_token='[EMPTY]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None', 'cell_trim_length': 'cell_trim_length: int = -1', 'max_column_id': 'max_column_id: Optional[int + ] = None', 'max_row_id': 'max_row_id: Optional[int + ] = None', 'strip_column_names': 'strip_column_names: bool = False', 'update_answer_coordinates': 'update_answer_coordinates: bool = False', 'min_question_length': 'min_question_length=None', 'max_question_length': 'max_question_length=None', 'model_max_length': 'model_max_length: int = 512', 'additional_special_tokens': 'additional_special_tokens: Optional[list[str + ] + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=True' +}, model_name='TapasTokenizer', library='transformers', import_path='transformers.models.tapas'), ModelAttributes(model=, model_type='model', model_parameters={'stem_kernel_size': 'stem_kernel_size=3', 'stem_stride': 'stem_stride=2', 'stem_num_channels': 'stem_num_channels=3', 'stem_out_channels': 'stem_out_channels=64', 'stem_act_func': "stem_act_func='relu'", 'image_size': 'image_size=[ + 640, + 640 + ]', 'conv_layer_kernel_sizes': 'conv_layer_kernel_sizes=None', 'conv_layer_strides': 'conv_layer_strides=None', 'hidden_sizes': 'hidden_sizes=[ + 64, + 64, + 128, + 256, + 512 + ]', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'initializer_range': 'initializer_range=0.02', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='TextNetModel', library='transformers', import_path='transformers.models.textnet'), ModelAttributes(model=, model_type='model', model_parameters={'prediction_length': 'prediction_length: Optional[int + ] = None', 'context_length': 'context_length: Optional[int + ] = None', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'nll'", 'input_size': 'input_size: int = 1', 'lags_sequence': 'lags_sequence: list[int + ] = [ + 1, + 2, + 3, + 4, + 5, + 6, + 7 + ]', 'scaling': "scaling: Union[str, bool, NoneType] = 'mean'", 'num_dynamic_real_features': 'num_dynamic_real_features: int = 0', 'num_static_categorical_features': 'num_static_categorical_features: int = 0', 'num_static_real_features': 'num_static_real_features: int = 0', 'num_time_features': 'num_time_features: int = 0', 'cardinality': 'cardinality: Optional[list[int + ] + ] = None', 'embedding_dimension': 'embedding_dimension: Optional[list[int + ] + ] = None', 'encoder_ffn_dim': 'encoder_ffn_dim: int = 32', 'decoder_ffn_dim': 'decoder_ffn_dim: int = 32', 'encoder_attention_heads': 'encoder_attention_heads: int = 2', 'decoder_attention_heads': 'decoder_attention_heads: int = 2', 'encoder_layers': 'encoder_layers: int = 2', 'decoder_layers': 'decoder_layers: int = 2', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'd_model': 'd_model: int = 64', 'dropout': 'dropout: float = 0.1', 'encoder_layerdrop': 'encoder_layerdrop: float = 0.1', 'decoder_layerdrop': 'decoder_layerdrop: float = 0.1', 'attention_dropout': 'attention_dropout: float = 0.1', 'activation_dropout': 'activation_dropout: float = 0.1', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'init_std': 'init_std: float = 0.02' +}, model_name='TimeSeriesTransformerModel', library='transformers', import_path='transformers.models.time_series_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'patch_length': 'patch_length: int = 32', 'context_length': 'context_length: int = 512', 'horizon_length': 'horizon_length: int = 128', 'freq_size': 'freq_size: int = 3', 'num_hidden_layers': 'num_hidden_layers: int = 50', 'hidden_size': 'hidden_size: int = 1280', 'intermediate_size': 'intermediate_size: int = 1280', 'head_dim': 'head_dim: int = 80', 'num_attention_heads': 'num_attention_heads: int = 16', 'tolerance': 'tolerance: float = 1e-06', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'quantiles': 'quantiles: list[float + ] = [ + 0.1, + 0.2, + 0.3, + 0.4, + 0.5, + 0.6, + 0.7, + 0.8, + 0.9 + ]', 'pad_val': 'pad_val: float = 1123581321.0', 'attention_dropout': 'attention_dropout: float = 0.0', 'use_positional_embedding': 'use_positional_embedding: bool = False', 'initializer_range': 'initializer_range: float = 0.02', 'min_timescale': 'min_timescale: int = 1', 'max_timescale': 'max_timescale: int = 10000' +}, model_name='TimesFmModel', library='transformers', import_path='transformers.models.timesfm'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'num_frames': 'num_frames=8', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True', 'attention_type': "attention_type='divided_space_time'", 'drop_path_rate': 'drop_path_rate=0' +}, model_name='TimesformerModel', library='transformers', import_path='transformers.models.timesformer'), ModelAttributes(model=, model_type='model', model_parameters={'backbone': 'backbone=None', 'num_channels': 'num_channels=3', 'features_only': 'features_only=True', 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'out_indices': 'out_indices=None', 'freeze_batch_norm_2d': 'freeze_batch_norm_2d=False' +}, model_name='TimmBackbone', library='transformers', import_path='transformers.models.timm_backbone'), ModelAttributes(model=, model_type='model', model_parameters={'_resnet_': ['' + ] +}, model_name='TimmWrapperModel', library='transformers', import_path='transformers.models.timm_wrapper'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'distance_loss_weight': 'distance_loss_weight=1.0', 'duration_loss_weight': 'duration_loss_weight=0.1', 'visual_prompter_type': "visual_prompter_type='framepad'", 'visual_prompter_apply': "visual_prompter_apply='replace'", 'visual_prompt_size': 'visual_prompt_size=96', 'max_img_size': 'max_img_size=448', 'num_frames': 'num_frames=48', 'vocab_size': 'vocab_size=30522', 'type_vocab_size': 'type_vocab_size=2', 'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'max_position_embeddings': 'max_position_embeddings=512', 'max_grid_col_position_embeddings': 'max_grid_col_position_embeddings=100', 'max_grid_row_position_embeddings': 'max_grid_row_position_embeddings=100', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-12', 'initializer_range': 'initializer_range=0.02', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1' +}, model_name='TvpModel', library='transformers', import_path='transformers.models.tvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=33201', 'd_model': 'd_model=1024', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=4096', 'num_layers': 'num_layers=24', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=16', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'relative_bias_args': "relative_bias_args=[{'type': '1d'}, {'type': 'horizontal'}, {'type': 'vertical'}]", 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3' +}, model_name='UdopModel', library='transformers', import_path='transformers.models.udop'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'sep_token_box': 'sep_token_box=[ + 1000, + 1000, + 1000, + 1000 + ]', 'pad_token_box': 'pad_token_box=[ + 0, + 0, + 0, + 0 + ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'extra_special_tokens': 'extra_special_tokens=None' +}, model_name='UdopTokenizer', library='transformers', import_path='transformers.models.udop'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250112', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=1024', 'num_layers': 'num_layers=8', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=6', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='gated-gelu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'tokenizer_class': "tokenizer_class='T5Tokenizer'", 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'decoder_start_token_id': 'decoder_start_token_id=0', 'classifier_dropout': 'classifier_dropout=0.0' +}, model_name='UMT5Model', library='transformers', import_path='transformers.models.umt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'num_ctc_classes': 'num_ctc_classes=80', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'replace_prob': 'replace_prob=0.5' +}, model_name='UniSpeechModel', library='transformers', import_path='transformers.models.unispeech'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'num_clusters': 'num_clusters=504' +}, model_name='UniSpeechSatModel', library='transformers', import_path='transformers.models.unispeech_sat'), ModelAttributes(model=, model_type='model', model_parameters={'model_in_channels': 'model_in_channels=64', 'model_hidden_channels': 'model_hidden_channels=32', 'num_mel_bins': 'num_mel_bins=100', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ + 3, + 3, + 3 + ]', 'resblock_stride_sizes': 'resblock_stride_sizes=[ + 8, + 8, + 4 + ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ + [ + 1, + 3, + 9, + 27 + ], + [ + 1, + 3, + 9, + 27 + ], + [ + 1, + 3, + 9, + 27 + ] + ]', 'kernel_predictor_num_blocks': 'kernel_predictor_num_blocks=3', 'kernel_predictor_hidden_channels': 'kernel_predictor_hidden_channels=64', 'kernel_predictor_conv_size': 'kernel_predictor_conv_size=3', 'kernel_predictor_dropout': 'kernel_predictor_dropout=0.0', 'initializer_range': 'initializer_range=0.01', 'leaky_relu_slope': 'leaky_relu_slope=0.2' +}, model_name='UnivNetModel', library='transformers', import_path='transformers.models.univnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 256000', 'hidden_size': 'hidden_size: Optional[int + ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int + ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = 4', 'head_dim': 'head_dim: Optional[int + ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 8192', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'eos_token_id': 'eos_token_id: Optional[int + ] = 1', 'bos_token_id': 'bos_token_id: Optional[int + ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool + ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'attention_bias': 'attention_bias: Optional[bool + ] = False', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int + ] = 256', 'sliding_window': 'sliding_window: Optional[int + ] = 4096', 'layer_types': 'layer_types: Optional[list[str + ] + ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float + ] = 30.0', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float + ] = 50.0' +}, model_name='VaultGemmaModel', library='transformers', import_path='transformers.models.vaultgemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656' +}, model_name='VideoLlama3Model', library='transformers', import_path='transformers.models.video_llama_3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' +}, model_name='VideoLlama3VisionModel', library='transformers', import_path='transformers.models.video_llama_3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'video_token_index': 'video_token_index=32001', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_seq_length': 'image_seq_length=256', 'video_seq_length': 'video_seq_length=2056', 'multimodal_projector_bias': 'multimodal_projector_bias=True' +}, model_name='VideoLlavaModel', library='transformers', import_path='transformers.models.video_llava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'num_frames': 'num_frames=16', 'tubelet_size': 'tubelet_size=2', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'qkv_bias': 'qkv_bias=True', 'use_mean_pooling': 'use_mean_pooling=True', 'decoder_num_attention_heads': 'decoder_num_attention_heads=6', 'decoder_hidden_size': 'decoder_hidden_size=384', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers=4', 'decoder_intermediate_size': 'decoder_intermediate_size=1536', 'norm_pix_loss': 'norm_pix_loss=True' +}, model_name='VideoMAEModel', library='transformers', import_path='transformers.models.videomae'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'type_vocab_size': 'type_vocab_size=2', 'modality_type_vocab_size': 'modality_type_vocab_size=2', 'max_position_embeddings': 'max_position_embeddings=40', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=384', 'patch_size': 'patch_size=32', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'max_image_length': 'max_image_length=-1', 'tie_word_embeddings': 'tie_word_embeddings=True', 'num_images': 'num_images=-1' +}, model_name='ViltModel', library='transformers', import_path='transformers.models.vilt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'projector_layernorm_eps': 'projector_layernorm_eps=1e-05', 'vision_feature_layers': 'vision_feature_layers=[ + -2, + -5, + -8, + -11, + 6 + ]', 'image_seq_length': 'image_seq_length=576' +}, model_name='VipLlavaModel', library='transformers', import_path='transformers.models.vipllava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='VisionTextDualEncoderModel', library='transformers', import_path='transformers.models.vision_text_dual_encoder'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'visual_embedding_dim': 'visual_embedding_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'bypass_transformer': 'bypass_transformer=False', 'special_visual_initialize': 'special_visual_initialize=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='VisualBertModel', library='transformers', import_path='transformers.models.visual_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool + ] = None' +}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'encoder_stride': 'encoder_stride=16', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" +}, model_name='ViTModel', library='transformers', import_path='transformers.models.vit'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'decoder_num_attention_heads': 'decoder_num_attention_heads=16', 'decoder_hidden_size': 'decoder_hidden_size=512', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers=8', 'decoder_intermediate_size': 'decoder_intermediate_size=2048', 'mask_ratio': 'mask_ratio=0.75', 'norm_pix_loss': 'norm_pix_loss=False' +}, model_name='ViTMAEModel', library='transformers', import_path='transformers.models.vit_mae'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True' +}, model_name='ViTMSNModel', library='transformers', import_path='transformers.models.vit_msn'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'dropout_prob': 'dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'pretrain_image_size': 'pretrain_image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'drop_path_rate': 'drop_path_rate=0.0', 'window_block_indices': 'window_block_indices=[]', 'residual_block_indices': 'residual_block_indices=[]', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=True', 'use_relative_position_embeddings': 'use_relative_position_embeddings=False', 'window_size': 'window_size=0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' +}, model_name='VitDetModel', library='transformers', import_path='transformers.models.vitdet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=38', 'hidden_size': 'hidden_size=192', 'num_hidden_layers': 'num_hidden_layers=6', 'num_attention_heads': 'num_attention_heads=2', 'window_size': 'window_size=4', 'use_bias': 'use_bias=True', 'ffn_dim': 'ffn_dim=768', 'layerdrop': 'layerdrop=0.1', 'ffn_kernel_size': 'ffn_kernel_size=3', 'flow_size': 'flow_size=192', 'spectrogram_bins': 'spectrogram_bins=513', 'hidden_act': "hidden_act='relu'", 'hidden_dropout': 'hidden_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'use_stochastic_duration_prediction': 'use_stochastic_duration_prediction=True', 'num_speakers': 'num_speakers=1', 'speaker_embedding_size': 'speaker_embedding_size=0', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ + 8, + 8, + 2, + 2 + ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ + 16, + 16, + 4, + 4 + ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ + 3, + 7, + 11 + ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ], + [ + 1, + 3, + 5 + ] + ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'depth_separable_channels': 'depth_separable_channels=2', 'depth_separable_num_layers': 'depth_separable_num_layers=3', 'duration_predictor_flow_bins': 'duration_predictor_flow_bins=10', 'duration_predictor_tail_bound': 'duration_predictor_tail_bound=5.0', 'duration_predictor_kernel_size': 'duration_predictor_kernel_size=3', 'duration_predictor_dropout': 'duration_predictor_dropout=0.5', 'duration_predictor_num_flows': 'duration_predictor_num_flows=4', 'duration_predictor_filter_channels': 'duration_predictor_filter_channels=256', 'prior_encoder_num_flows': 'prior_encoder_num_flows=4', 'prior_encoder_num_wavenet_layers': 'prior_encoder_num_wavenet_layers=4', 'posterior_encoder_num_wavenet_layers': 'posterior_encoder_num_wavenet_layers=16', 'wavenet_kernel_size': 'wavenet_kernel_size=5', 'wavenet_dilation_rate': 'wavenet_dilation_rate=1', 'wavenet_dropout': 'wavenet_dropout=0.0', 'speaking_rate': 'speaking_rate=1.0', 'noise_scale': 'noise_scale=0.667', 'noise_scale_duration': 'noise_scale_duration=0.8', 'sampling_rate': 'sampling_rate=16000' +}, model_name='VitsModel', library='transformers', import_path='transformers.models.vits'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'language': 'language=None', 'add_blank': 'add_blank=True', 'normalize': 'normalize=True', 'phonemize': 'phonemize=True', 'is_uroman': 'is_uroman=False' +}, model_name='VitsTokenizer', library='transformers', import_path='transformers.models.vits'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_frames': 'num_frames=32', 'tubelet_size': 'tubelet_size=[ + 2, + 16, + 16 + ]', 'num_channels': 'num_channels=3', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_fast'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True' +}, model_name='VivitModel', library='transformers', import_path='transformers.models.vivit'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size=16', 'crop_size': 'crop_size=256', 'frames_per_clip': 'frames_per_clip=64', 'tubelet_size': 'tubelet_size=2', 'hidden_size': 'hidden_size=1024', 'in_chans': 'in_chans=3', 'num_attention_heads': 'num_attention_heads=16', 'num_hidden_layers': 'num_hidden_layers=24', 'drop_path_rate': 'drop_path_rate=0.0', 'mlp_ratio': 'mlp_ratio=4.0', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'attention_dropout': 'attention_dropout=0.0', 'num_pooler_layers': 'num_pooler_layers=3', 'pred_hidden_size': 'pred_hidden_size=384', 'pred_num_attention_heads': 'pred_num_attention_heads=12', 'pred_num_hidden_layers': 'pred_num_hidden_layers=12', 'pred_num_mask_tokens': 'pred_num_mask_tokens=10', 'pred_zero_init_mask_tokens': 'pred_zero_init_mask_tokens=True', 'pred_mlp_ratio': 'pred_mlp_ratio=4.0' +}, model_name='VJEPA2Model', library='transformers', import_path='transformers.models.vjepa2'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config=None', 'text_config': 'text_config=None', 'audio_token_id': 'audio_token_id=None', 'projector_hidden_act': "projector_hidden_act='gelu'" +}, model_name='VoxtralForConditionalGeneration', library='transformers', import_path='transformers.models.voxtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=51866', 'hidden_size': 'hidden_size=1280', 'intermediate_size': 'intermediate_size=5120', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=20', 'scale_embedding': 'scale_embedding=False', 'activation_function': "activation_function='gelu'", 'num_mel_bins': 'num_mel_bins=128', 'max_source_positions': 'max_source_positions=1500', 'initializer_range': 'initializer_range=0.02', 'attention_dropout': 'attention_dropout=0.0' +}, model_name='VoxtralEncoder', library='transformers', import_path='transformers.models.voxtral'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None', 'adapter_attn_dim': 'adapter_attn_dim=None' +}, model_name='Wav2Vec2Model', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' +}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'intermediate_size': 'intermediate_size=4096', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'hidden_act': "hidden_act='swish'", 'hidden_dropout': 'hidden_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=768', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=1', 'adapter_act': "adapter_act='relu'", 'use_intermediate_ffn_before_adapter': 'use_intermediate_ffn_before_adapter=False', 'output_hidden_size': 'output_hidden_size=None', 'position_embeddings_type': "position_embeddings_type='relative_key'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=5000', 'left_max_position_embeddings': 'left_max_position_embeddings=64', 'right_max_position_embeddings': 'right_max_position_embeddings=8', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'conformer_conv_dropout': 'conformer_conv_dropout=0.1' +}, model_name='Wav2Vec2BertModel', library='transformers', import_path='transformers.models.wav2vec2_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' +}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None', 'position_embeddings_type': "position_embeddings_type='relative'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=5000', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'conformer_conv_dropout': 'conformer_conv_dropout=0.1' +}, model_name='Wav2Vec2ConformerModel', library='transformers', import_path='transformers.models.wav2vec2_conformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' +}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, + 512, + 512, + 512, + 512, + 512, + 512)', 'conv_stride': 'conv_stride=(5, + 2, + 2, + 2, + 2, + 2, + 2)', 'conv_kernel': 'conv_kernel=(10, + 3, + 3, + 3, + 3, + 2, + 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'num_buckets': 'num_buckets=320', 'max_bucket_distance': 'max_bucket_distance=800', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, + 512, + 512, + 512, + 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, + 3, + 3, + 1, + 1)', 'tdnn_dilation': 'tdnn_dilation=(1, + 2, + 3, + 1, + 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'num_ctc_classes': 'num_ctc_classes=80', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None' +}, model_name='WavLMModel', library='transformers', import_path='transformers.models.wavlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=51865', 'num_mel_bins': 'num_mel_bins=80', 'encoder_layers': 'encoder_layers=4', 'encoder_attention_heads': 'encoder_attention_heads=6', 'decoder_layers': 'decoder_layers=4', 'decoder_attention_heads': 'decoder_attention_heads=6', 'decoder_ffn_dim': 'decoder_ffn_dim=1536', 'encoder_ffn_dim': 'encoder_ffn_dim=1536', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'decoder_start_token_id': 'decoder_start_token_id=50257', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=384', 'dropout': 'dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'scale_embedding': 'scale_embedding=False', 'max_source_positions': 'max_source_positions=1500', 'max_target_positions': 'max_target_positions=448', 'pad_token_id': 'pad_token_id=50256', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'suppress_tokens': 'suppress_tokens=None', 'begin_suppress_tokens': 'begin_suppress_tokens=[ + 220, + 50256 + ]', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'apply_spec_augment': 'apply_spec_augment=False', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'median_filter_width': 'median_filter_width=7' +}, model_name='WhisperModel', library='transformers', import_path='transformers.models.whisper'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges=None', 'normalizer_file': 'normalizer_file=None', 'unk_token': "unk_token='<|endoftext|>'", 'bos_token': "bos_token='<|endoftext|>'", 'eos_token': "eos_token='<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=False', 'language': 'language=None', 'task': 'task=None', 'predict_timestamps': 'predict_timestamps=False' +}, model_name='WhisperTokenizer', library='transformers', import_path='transformers.models.whisper'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'prompt_layers': 'prompt_layers=2', 'prompt_alpha': 'prompt_alpha=0.1', 'prompt_hidden_act': "prompt_hidden_act='quick_gelu'", 'prompt_num_attention_heads': 'prompt_num_attention_heads=8', 'prompt_attention_dropout': 'prompt_attention_dropout=0.0', 'prompt_projection_dropout': 'prompt_projection_dropout=0.0', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' +}, model_name='XCLIPModel', library='transformers', import_path='transformers.models.x_clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" +}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'target_bandwidths': 'target_bandwidths: Optional[list[float + ] + ] = None', 'sample_rate': 'sample_rate: int = 16000', 'kernel_size': 'kernel_size: int = 3', 'channel_ratios': 'channel_ratios: list[float + ] = [ + 1, + 1 + ]', 'strides': 'strides: list[int + ] = [ + 1, + 1 + ]', 'block_dilations': 'block_dilations: list[int + ] = [ + 1, + 1 + ]', 'unit_kernel_size': 'unit_kernel_size: int = 3', 'codebook_size': 'codebook_size: int = 1024', 'codebook_dim': 'codebook_dim: Optional[int + ] = None', 'initializer_range': 'initializer_range: float = 0.02', 'acoustic_model_config': 'acoustic_model_config: Union[dict, transformers.models.dac.configuration_dac.DacConfig, NoneType + ] = None', 'semantic_model_config': 'semantic_model_config: Union[dict, transformers.models.hubert.configuration_hubert.HubertConfig, NoneType + ] = None' +}, model_name='XcodecModel', library='transformers', import_path='transformers.models.xcodec'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256008', 'max_position_embeddings': 'max_position_embeddings=2048', 'd_model': 'd_model=1024', 'ffn_dim': 'ffn_dim=4096', 'num_layers': 'num_layers=24', 'attention_heads': 'attention_heads=16', 'activation_function': "activation_function='gelu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'layerdrop': 'layerdrop=0.0', 'init_std': 'init_std=0.02', 'scale_embedding': 'scale_embedding=True', 'decoder_start_token_id': 'decoder_start_token_id=2', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='XGLMModel', library='transformers', import_path='transformers.models.xglm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = True' +}, model_name='XGLMTokenizer', library='transformers', import_path='transformers.models.xglm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30145', 'emb_dim': 'emb_dim=2048', 'n_layers': 'n_layers=12', 'n_heads': 'n_heads=16', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'gelu_activation': 'gelu_activation=True', 'sinusoidal_embeddings': 'sinusoidal_embeddings=False', 'causal': 'causal=False', 'asm': 'asm=False', 'n_langs': 'n_langs=1', 'use_lang_emb': 'use_lang_emb=True', 'max_position_embeddings': 'max_position_embeddings=512', 'embed_init_std': 'embed_init_std=0.02209708691207961', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'init_std': 'init_std=0.02', 'bos_index': 'bos_index=0', 'eos_index': 'eos_index=1', 'pad_index': 'pad_index=2', 'unk_index': 'unk_index=3', 'mask_index': 'mask_index=5', 'is_encoder': 'is_encoder=True', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'mask_token_id': 'mask_token_id=0', 'lang_id': 'lang_id=0', 'pad_token_id': 'pad_token_id=2', 'bos_token_id': 'bos_token_id=0' +}, model_name='XLMModel', library='transformers', import_path='transformers.models.xlm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", 'lang2id': 'lang2id=None', 'id2lang': 'id2lang=None', 'do_lowercase_and_remove_accent': 'do_lowercase_and_remove_accent=True' +}, model_name='XLMTokenizer', library='transformers', import_path='transformers.models.xlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='XLMRobertaModel', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250880', 'hidden_size': 'hidden_size=2560', 'num_hidden_layers': 'num_hidden_layers=36', 'num_attention_heads': 'num_attention_heads=32', 'intermediate_size': 'intermediate_size=10240', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=514', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' +}, model_name='XLMRobertaXLModel', library='transformers', import_path='transformers.models.xlm_roberta_xl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'd_model': 'd_model=1024', 'n_layer': 'n_layer=24', 'n_head': 'n_head=16', 'd_inner': 'd_inner=4096', 'ff_activation': "ff_activation='gelu'", 'attn_type': "attn_type='bi'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'dropout': 'dropout=0.1', 'mem_len': 'mem_len=512', 'reuse_len': 'reuse_len=None', 'use_mems_eval': 'use_mems_eval=True', 'use_mems_train': 'use_mems_train=False', 'bi_data': 'bi_data=False', 'clamp_len': 'clamp_len=-1', 'same_length': 'same_length=False', 'summary_type': "summary_type='last'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': "summary_activation='tanh'", 'summary_last_dropout': 'summary_last_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'pad_token_id': 'pad_token_id=5', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' +}, model_name='XLNetModel', library='transformers', import_path='transformers.models.xlnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'unk_id': 'unk_id: int = 0', 'do_lower_case': 'do_lower_case=False', 'remove_space': 'remove_space=True', 'keep_accents': 'keep_accents=False', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': 'additional_special_tokens=None' +}, model_name='XLNetTokenizer', library='transformers', import_path='transformers.models.xlnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 50304', 'hidden_size': 'hidden_size: int = 4096', 'embedding_dim': 'embedding_dim: Optional[int + ] = None', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 32', 'num_blocks': 'num_blocks: Optional[int + ] = None', 'num_heads': 'num_heads: int = 8', 'use_bias': 'use_bias: bool = False', 'norm_reduction_force_float32': 'norm_reduction_force_float32: bool = True', 'tie_word_embeddings': 'tie_word_embeddings: bool = False', 'add_out_norm': 'add_out_norm: bool = True', 'norm_eps': 'norm_eps: float = 1e-06', 'qk_dim_factor': 'qk_dim_factor: float = 0.5', 'v_dim_factor': 'v_dim_factor: float = 1.0', 'chunkwise_kernel': "chunkwise_kernel: Literal['chunkwise--native_autograd', 'parallel--native_autograd'] = 'chunkwise--native_autograd'", 'sequence_kernel': "sequence_kernel: Literal['native_sequence__native'] = 'native_sequence__native'", 'step_kernel': "step_kernel: Literal['native'] = 'native'", 'mode': "mode: Literal['train', 'train_with_padding', 'inference'] = 'inference'", 'chunk_size': 'chunk_size: int = 64', 'return_last_states': 'return_last_states: bool = True', 'autocast_kernel_dtype': "autocast_kernel_dtype: Literal['float32', 'bfloat16', 'float16'] = 'bfloat16'", 'eps': 'eps: float = 1e-06', 'inference_state_dtype': "inference_state_dtype: Literal['float32', 'bfloat16', 'float16'] = 'float32'", 'ffn_proj_factor': 'ffn_proj_factor: float = 2.667', 'ffn_round_up_to_multiple_of': 'ffn_round_up_to_multiple_of: int = 64', 'gate_soft_cap': 'gate_soft_cap: float = 15.0', 'output_logit_soft_cap': 'output_logit_soft_cap: float = 30.0', 'weight_mode': "weight_mode: Literal['single', 'fused'] = 'single'", 'pad_token_id': 'pad_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 2', 'max_inference_chunksize': 'max_inference_chunksize: int = 16384' +}, model_name='xLSTMModel', library='transformers', import_path='transformers.models.xlstm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int + ], NoneType + ] = None', 'merges': 'merges: Union[str, list[str + ], NoneType + ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None', 'pre_norm': 'pre_norm=False', 'adapter_reduction_factor': 'adapter_reduction_factor=2', 'adapter_layer_norm': 'adapter_layer_norm=False', 'adapter_reuse_layer_norm': 'adapter_reuse_layer_norm=True', 'ln_before_adapter': 'ln_before_adapter=True', 'languages': "languages=('en_XX',)", 'default_language': 'default_language=None' +}, model_name='XmodModel', library='transformers', import_path='transformers.models.xmod'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" +}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=[ + 512, + 864 + ]', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'num_detection_tokens': 'num_detection_tokens=100', 'use_mid_position_embeddings': 'use_mid_position_embeddings=True', 'auxiliary_loss': 'auxiliary_loss=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' +}, model_name='YolosModel', library='transformers', import_path='transformers.models.yolos'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=4096', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_expectation': 'use_expectation=True', 'hash_code_len': 'hash_code_len=9', 'num_hash': 'num_hash=64', 'conv_window': 'conv_window=None', 'use_fast_hash': 'use_fast_hash=True', 'lsh_backward': 'lsh_backward=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' +}, model_name='YosoModel', library='transformers', import_path='transformers.models.yoso'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float + ] + ], NoneType + ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' +}, model_name='AlbertTokenizer', library='transformers', import_path='transformers.models.albert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'tie_word_embeddings': 'tie_word_embeddings=True', 'hidden_size': 'hidden_size=3712', 'attention_hidden_size': 'attention_hidden_size=None', 'intermediate_size': 'intermediate_size=14848', 'num_hidden_layers': 'num_hidden_layers=76', 'num_attention_heads': 'num_attention_heads=16', 'attention_head_dim': 'attention_head_dim=None', 'num_key_value_heads': 'num_key_value_heads=16', 'n_mamba_heads': 'n_mamba_heads=2', 'hidden_act': "hidden_act='gelu'", 'hidden_mamba_act': "hidden_mamba_act='silu'", 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'num_logits_to_keep': 'num_logits_to_keep=1', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'max_position_embeddings': 'max_position_embeddings=4096', 'attention_dropout': 'attention_dropout=0.0', 'attn_layer_period': 'attn_layer_period=6', 'attn_layer_offset': 'attn_layer_offset=4', 'use_mamba_kernels': 'use_mamba_kernels=True', 'mamba_d_state': 'mamba_d_state=16', 'mamba_d_conv': 'mamba_d_conv=4', 'mamba_expand': 'mamba_expand=2', 'mamba_dt_rank': "mamba_dt_rank='auto'", 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_floor': 'time_step_floor=0.0001', 'mamba_conv_bias': 'mamba_conv_bias=True', 'mamba_proj_bias': 'mamba_proj_bias=False' +}, model_name='ZambaModel', library='transformers', import_path='transformers.models.zamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int + ] = 32000', 'max_position_embeddings': 'max_position_embeddings: Optional[int + ] = 4096', 'hidden_size': 'hidden_size: Optional[int + ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int + ] = 54', 'layers_block_type': 'layers_block_type: Optional[list[str + ] + ] = None', 'mamba_d_state': 'mamba_d_state: Optional[int + ] = 64', 'mamba_d_conv': 'mamba_d_conv: Optional[int + ] = 4', 'mamba_expand': 'mamba_expand: Optional[int + ] = 2', 'mamba_ngroups': 'mamba_ngroups: Optional[int + ] = 1', 'time_step_min': 'time_step_min: Optional[float + ] = 0.001', 'time_step_max': 'time_step_max: Optional[float + ] = 0.1', 'time_step_floor': 'time_step_floor: Optional[int + ] = 0.0001', 'time_step_limit': 'time_step_limit: Optional[int + ] = None', 'n_mamba_heads': 'n_mamba_heads: Optional[int + ] = 8', 'use_conv_bias': 'use_conv_bias: Optional[bool + ] = True', 'chunk_size': 'chunk_size: Optional[int + ] = 256', 'use_mem_eff_path': 'use_mem_eff_path: Optional[bool + ] = False', 'add_bias_linear': 'add_bias_linear: Optional[bool + ] = False', 'intermediate_size': 'intermediate_size: Optional[int + ] = None', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'num_attention_heads': 'num_attention_heads: Optional[int + ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int + ] = None', 'attention_dropout': 'attention_dropout: Optional[float + ] = 0.0', 'num_mem_blocks': 'num_mem_blocks: Optional[int + ] = 1', 'use_shared_attention_adapter': 'use_shared_attention_adapter: Optional[bool + ] = False', 'adapter_rank': 'adapter_rank: Optional[int + ] = 128', 'use_mem_rope': 'use_mem_rope: Optional[bool + ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters + ], NoneType + ] = None', 'initializer_range': 'initializer_range: Optional[float + ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int + ] = 1e-05', 'num_logits_to_keep': 'num_logits_to_keep: Optional[int + ] = 1', 'pad_token_id': 'pad_token_id: Optional[int + ] = 0', 'bos_token_id': 'bos_token_id: Optional[int + ] = 1', 'eos_token_id': 'eos_token_id: Optional[int + ] = 2', 'use_long_context': 'use_long_context: Optional[bool + ] = False' +}, model_name='Zamba2Model', library='transformers', import_path='transformers.models.zamba2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType + ] = None', 'merges': 'merges: Union[str, list, NoneType + ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' +}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama') +] \ No newline at end of file diff --git a/mir/generate/transformers/gather.py b/mir/generate/transformers/gather.py new file mode 100644 index 0000000..812d8f1 --- /dev/null +++ b/mir/generate/transformers/gather.py @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Callable + + +class GatherLoop: + def __init__(self) -> None: + """Loops through transformers packages to harvest class data.""" + from mir.generate.transformers import AUTO_MAP + from mir.generate.transformers import TOKENIZER_MAPPING + from mir.build_entry import BuildEntry + from mir.maid import MIRDatabase + + self.db = MIRDatabase() + + build_entries = [] + for config, model in AUTO_MAP.items(): # type: ignore + if isinstance(model, tuple): + model: Callable = model[0] # type: ignore + build_entries.append(BuildEntry("model", model)) + if tokenizer := TOKENIZER_MAPPING.get(config, None): + build_entries.append(BuildEntry("tokenizer", tokenizer)) + print([x.attributes for x in build_entries]) # type: ignore diff --git a/mir/generate/transformers/harvest.py b/mir/generate/transformers/harvest.py deleted file mode 100644 index 5b8525d..0000000 --- a/mir/generate/transformers/harvest.py +++ /dev/null @@ -1,44 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable - -from mir.generate.transformers.raw_data import PrepareData - - -class HarvestLoop: - def __init__(self) -> None: - """Initializes the HarvestClasses instance with an empty list to store raw class data.""" - from mir.maid import MIRDatabase - - self.db = MIRDatabase() - - def __call__(self) -> None: - from mir.generate.transformers import AUTO_MAP - from mir.generate.transformers import TOKENIZER_MAPPING - - prepared_data = {} - for config_class, model_data in AUTO_MAP.items(): - assert isinstance(config_class, Callable) - loop_parameters = {"model": (model_data, config_class)} - if tokenizer := TOKENIZER_MAPPING.get(config_class, None): - loop_parameters.setdefault("tokenizer", (tokenizer, tokenizer)) # type: ignore - for name, (self.model, self.config) in loop_parameters.items(): - if prepare_data := self.prepare_class_data(): # type: ignore - prepared_data.setdefault(name, prepare_data) - for data in prepared_data: - pass - - def prepare_class_data(self) -> PrepareData | None: - """Extract and collect information from model and config classes.\n - :return: A PrepareData entry representing the transformer class.""" - from mir.data import PARAMETERS - from mir.generate.from_module import show_init_fields_for - - config_name = self.config.__name__ - config_params = PARAMETERS.get(config_name, show_init_fields_for(self.config)) - if any(x in config_params for x in ["inspect", "deprecated"]): - return None - if isinstance(self.model, tuple): - self.model_class: Callable = self.model[0] - return PrepareData(model=self.model, **config_params) # type: ignore diff --git a/mir/generate/transformers/package.py b/mir/generate/transformers/package.py deleted file mode 100644 index 148aded..0000000 --- a/mir/generate/transformers/package.py +++ /dev/null @@ -1,56 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from typing import Callable, ModuleType -from dataclasses import dataclass, field - - -@dataclass -class MIRPackage: - config: Callable - model: Callable - package: dict[str, str] = field(init=False, default_factory=dict[str, str]) - - def __post_init__(self): - self.package = {} - self.model_name: str = self.model.__name__ - self.model_path: ModuleType = self.model.__module__ - if not isinstance(self.config, dict): - self.generate_package() - self.generate_repo() - - def generate_repo(self) -> None: - from mir.data import MIGRATIONS - - if repo := MIGRATIONS["config"].get(self.config.__name__, {}): - self.repo = repo - else: - self.repo = self.config_to_repo(self.config) - - def generate_package(self) -> None: - """Generates package information for the MIR tag based on class. - :param pkg: A class object (model, tokenizer, etc) to build a tag from""" - model = f"{self.model_type}.{self.model_name}" - self.package: dict[str, str] = {"model": model} - - def config_to_repo(self) -> str | None: - """Extracts the repository path from the configuration class documentation.\n - :param config_class: Configuration class to extract repository path from. - :return: Repository path as a string if found, otherwise None.""" - import re - - from mir import NFO - - doc_check = [self.config] - if hasattr(self.config, "forward"): - doc_check.append(self.config.forward) # type: ignore - for pattern in doc_check: - doc_string = pattern.__doc__ - matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore - if matches: - try: - return next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) - except StopIteration as error_log: - NFO(f"ERROR >>{matches} : LOG >> {error_log}") - continue diff --git a/mir/generate/transformers/raw_data.py b/mir/generate/transformers/raw_data.py deleted file mode 100644 index 02bbd11..0000000 --- a/mir/generate/transformers/raw_data.py +++ /dev/null @@ -1,24 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable -from dataclasses import dataclass, field - - -@dataclass -class PrepareData: - """Represents a structured entry of the name of the class and its associated attributes.""" - - model: Callable - config_params: dict[str, list[str]] - config: Callable | None = None - - model_name: str = field(init=False) - library: str = field(init=False) - import_path: str = field(init=False) - - def __post_init__(self) -> None: - """Initializes the PrepareData instance by setting derived attributes.""" - self.model_name: str = self.model.__name__ - self.import_path = self.model.__module__.rsplit(".", 1)[0] - self.library = self.import_path.split(".")[0] diff --git a/mir/generate/transformers/tasks.py b/mir/generate/transformers/tasks.py deleted file mode 100644 index be9cf81..0000000 --- a/mir/generate/transformers/tasks.py +++ /dev/null @@ -1,32 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from dataclasses import dataclass, field -from typing import Callable - - -@dataclass -class CollectTasks: - model: Callable - import_path: str - config: Callable - tasks: list[str] = field(init=False) - - def __post_init__(self) -> None: - self.model_to_tasks() - - def model_to_tasks(self) -> None: - """Transform a single model class into derivative classes for specific tasks.\n - :return: A list of task classes associated with the model.""" - from importlib import import_module - - model_name = self.model.__name__ - - parent_module = import_module(self.import_path) - self.tasks = [] - if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": - for module in parent_module.__all__: - if (module.lower() != module) and (module != model_name) and (module != self.config.__name__): - self.tasks.append(module) - else: - self.tasks = [model_name] diff --git a/mir/maid.py b/mir/maid.py index 14ef49f..cda9a01 100644 --- a/mir/maid.py +++ b/mir/maid.py @@ -8,7 +8,7 @@ from typing import Any, List, Optional from mir import MIR_PATH_NAMED -from mir.package import MIRNesting +from mir.nesting import MIRNesting from mir.json_io import read_json_file, write_json_file diff --git a/mir/model.py b/mir/model.py new file mode 100644 index 0000000..ac8da16 --- /dev/null +++ b/mir/model.py @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Callable +from dataclasses import dataclass, field + + +@dataclass +class ModelAttributes: + """Represents a structured entry of the class and its associated attributes.\n + + model_type: The kind of model. + model: The model function. + model_parameters: Dictionary mapping configuration parameter fields. + model_name: Name of the model function. + config: The config function for the model. + library: Name of the library containing the model. + import_path: Import path of the model module (excluding the package name).""" + + model: Callable + model_type: str + model_parameters: dict[str, list[str]] | None = None + + model_name: str = field(init=False) + library: str = field(init=False) + import_path: str = field(init=False) + + def __post_init__(self) -> None: + """Initializes the instance by setting derived attributes.""" + self.model_name: str = self.model.__name__ + self.import_path = self.model.__module__.rsplit(".", 1)[0] + self.library = self.import_path.split(".")[0] + if not hasattr(self, "config") and any(x in self.model_type for x in ["tokenizer", "prior_tokenizer"]): + self.config = self.model + elif not hasattr(self, "config") and self.library == "transformers" and "model" in self.model_type: + from mir.generate.transformers import AUTO_MAP + + config: dict = {model: config for config, model in AUTO_MAP.items() if model == self.model} + self.config = config.get(self.model, None) # type:ignore + if getattr(self, "config", None) and self.library == "transformers": + from mir.data import PARAMETERS + from mir.generate.from_module import show_init_fields_for + + config_name = self.config.__name__ + config_parameters = PARAMETERS.get(config_name, show_init_fields_for(self.config)) + if not any(x in config_parameters for x in ["inspect", "deprecated"]): + self.config = self.config + self.model_parameters = config_parameters + else: + self.model_parameters = None diff --git a/mir/nesting.py b/mir/nesting.py new file mode 100644 index 0000000..c038d97 --- /dev/null +++ b/mir/nesting.py @@ -0,0 +1,85 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Any +from dataclasses import dataclass, field +from mir.model import ModelAttributes +from mir.tag import MIRTag +from mir.package import MIRPackage + + +class MIRNesting: + """Build tag components from the extracted data\n + :param mir_tag: An instance of MIR tag with the necessary information + :param prepared_data: Instance of PrepareData to attribute the final information + :returns: The final, assembled MIR tag""" + + loops: list[str] + framework_data: dict[str, str | dict[str, Any]] = {} + repo: str | None = field(default_factory=str | None) + framework: dict[str, str] = field(init=False) + tokenizer: str | None = field(default_factory=str) + + def __init__(self, mir_tag: MIRTag, prepared_data: ModelAttributes | ModelAttributes) -> None: + """\nInitialize the framework with MIR tag and prepared data.\n + :param mir_tag : The MIR tag instance. + :param prepared_data : The prepared data for processing.""" + self.mir_tag = mir_tag + + self.prepared_data = prepared_data + self.loops = [] + self.framework_data = {} + + def __call__(self, packages: MIRPackage) -> None: + """Common routine for handling a package: store tag data, nest the package, + and record the name of the newly-created attribute.\n + :param name: Identification string to store data underneath + :param mir_package: An instance of MIRPackage with the requisite data""" + + for name, mir_package in packages.items(): + is_framework = name == "framework" + is_model = name == "model" + is_tokenizer = name == "tokenizer" + + if is_framework: + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + tag_data += comp + self.framework_data.setdefault("repo", self.prepared_data.repo_path) + elif is_model: + package_data = {self.prepared_data.library: mir_package.package} + if hasattr(self.prepared_data, "tasks") and self.prepared_data.tasks: + package_data[self.prepared_data.library].setdefault("tasks", self.prepared_data.tasks) + tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" + if comp := getattr(self.mir_tag, "comp", None): + tag_data += comp + self.framework_data.setdefault(name, tag_data) + elif is_tokenizer: # tokenizer case + package_data = {self.prepared_data.library: mir_package.package} + tag_data = f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}" + self.framework_data.setdefault(name, tag_data) + + self.nest_data(name=name, tag_data=tag_data, package_data=package_data) + self.loops.append(name) + + def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: + """Nest data into a hierarchical attribute structure.\n + :param name: Attribute name to store the nested data + :param tag_data: Dotted path string for nesting + :param package_data: Data to be stored in the nested structure""" + + from chanfig import NestedDict + + tag_parts = tuple(x for x in tag_data.split(".")) + + if len(tag_parts) == 4: + domain, arch, series, comp = tag_parts + nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) + nest[domain][arch][series][comp] = package_data + else: + domain, arch, series = tag_parts + nest = NestedDict({f"{domain}.{arch}": {series: ""}}) + nest[domain][arch][series] = package_data + + setattr(self, name, nest) diff --git a/mir/package.py b/mir/package.py index 7269fab..20f0750 100644 --- a/mir/package.py +++ b/mir/package.py @@ -1,85 +1,111 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # -from typing import Any, Callable -from dataclasses import dataclass, field -from mir.generate.diffusers.raw_data import DPrepareData -from mir.generate.transformers.raw_data import PrepareData -from mir.tag import MIRTag - - -class MIRNesting: - """Build tag components from the extracted data\n - :param mir_tag: An instance of MIR tag with the necessary information - :param prepared_data: Instance of PrepareData to attribute the final information - :returns: The final, assembled MIR tag""" - - loops: list[str] - framework_data: dict[str, str | dict[str, Any]] = {} - repo: str | None = field(default_factory=str | None) - framework: dict[str, str] = field(init=False) - tokenizer: str | None = field(default_factory=str) - - def __init__(self, mir_tag: MIRTag, prepared_data: PrepareData | DPrepareData) -> None: - """\nInitialize the framework with MIR tag and prepared data.\n - :param mir_tag : The MIR tag instance. - :param prepared_data : The prepared data for processing.""" - self.mir_tag = mir_tag - - self.prepared_data = prepared_data - self.loops = [] - self.framework_data = {} - - def __call__(self, packages: MIRPackage) -> None: - """Common routine for handling a package: store tag data, nest the package, - and record the name of the newly-created attribute.\n - :param name: Identification string to store data underneath - :param mir_package: An instance of MIRPackage with the requisite data""" - - for name, mir_package in packages.items(): - is_framework = name == "framework" - is_model = name == "model" - is_tokenizer = name == "tokenizer" - - if is_framework: - package_data = {self.prepared_data.library: mir_package.package} - tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" - if comp := getattr(self.mir_tag, "comp", None): - tag_data += comp - self.framework_data.setdefault("repo", self.prepared_data.repo_path) - elif is_model: - package_data = {self.prepared_data.library: mir_package.package} - if hasattr(self.prepared_data, "tasks") and self.prepared_data.tasks: - package_data[self.prepared_data.library].setdefault("tasks", self.prepared_data.tasks) - tag_data = f"{mir_package.domain}.{self.mir_tag.arch}.{self.mir_tag.series}" - if comp := getattr(self.mir_tag, "comp", None): - tag_data += comp - self.framework_data.setdefault(name, tag_data) - elif is_tokenizer: # tokenizer case - package_data = {self.prepared_data.library: mir_package.package} - tag_data = f"{mir_package.domain}.encoder.tokenizer.{self.mir_tag.series}" - self.framework_data.setdefault(name, tag_data) - - self.nest_data(name=name, tag_data=tag_data, package_data=package_data) - self.loops.append(name) - - def nest_data(self, name: str, tag_data: str, package_data: dict) -> None: - """Nest data into a hierarchical attribute structure.\n - :param name: Attribute name to store the nested data - :param tag_data: Dotted path string for nesting - :param package_data: Data to be stored in the nested structure""" - - from chanfig import NestedDict - - tag_parts = tuple(x for x in tag_data.split(".")) - - if len(tag_parts) == 4: - domain, arch, series, comp = tag_parts - nest = NestedDict({f"{domain}.{arch}.{series}": {comp: ""}}) - nest[domain][arch][series][comp] = package_data - else: - domain, arch, series = tag_parts - nest = NestedDict({f"{domain}.{arch}": {series: ""}}) - nest[domain][arch][series] = package_data +from dataclasses import dataclass +from mir.model import ModelAttributes +from mir.data import MIGRATIONS + + +@dataclass +class MIRPackage: + attributes: ModelAttributes + + def __post_init__(self): + self.package = {} + if self.attributes.model_type == "model": + if self.attributes.library == "transformers": + self.package_transformers() + elif self.attributes.library == "diffusers": + self.package_diffusers() + model = f"{self.attributes.import_path}.{self.attributes.model_name}" + self.package: dict[str, str] = {"model": model} + + def package_transformers(self) -> None: + """Generates package information for the MIR tag based on class.""" + + if hasattr(self.attributes, "config"): + config_name = self.attributes.config.__name__ + if repo := MIGRATIONS["config"].get(config_name, {}): + self.repo = repo + else: + self.repo_from_config() + self.tasks_from_model() + + def package_diffusers(self) -> None: + """Generates package information for the MIR tag based on class.""" + + if repo := MIGRATIONS["migrated_pipes"].get(self.attributes.model_name, False): + self.repo = repo + elif doc_string := getattr(self.attributes.import_path, "EXAMPLE_DOC_STRING", None) and not any(x in self.attributes.model_type for x in ["tokenizer", "scheduler"]): + self.repo_from_doc_string(doc_string=doc_string) # type: ignore + self.tasks_from_internal_name() + + def repo_from_config(self) -> None: + """Extracts the repository path from the configuration class documentation.\n + :param config_class: Configuration class to extract repository path from. + :return: Repository path as a string if found, otherwise None.""" + import re - setattr(self, name, nest) + from mir import NFO + + doc_check = [self.attributes.config] + if hasattr(self.attributes.config, "forward"): + doc_check.append(self.config.forward) # type: ignore + for pattern in doc_check: + doc_string = pattern.__doc__ + matches = re.findall(r"\[([^\]]+)\]", doc_string) # type: ignore + if matches: + try: + self.repo = next(iter(snip.strip('"').strip() for snip in matches if "/" in snip)) + except StopIteration as error_log: + NFO(f"ERROR >>{matches} : LOG >> {error_log}") + continue + + def repo_from_doc_string(self, doc_string: str) -> None: + from mir.generate.diffusers.doc_parse import DocStringParser + + doc_parser = DocStringParser( + doc_string=doc_string, + model=self.attributes.model, + model_path=self.attributes.import_path, + ) + doc_parser.parse() + if repo_path := doc_parser.pipe_repo: + self.repo = repo_path + if staged_repo := doc_parser.staged_repo: + self.staged_repo = staged_repo + + def tasks_from_internal_name(self) -> None: + """Return Diffusers task pipes based on package-specific query\n + :param class_name: To find task pipes from a Diffusers class pipe, defaults to None + :param code_name: To find task pipes from a Transformers class pipe, defaults to None + :return: A list of alternate class pipelines derived from the specified class""" + from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS + + alt_tasks = set({}) + self.internal_name = self.attributes.import_path.rsplit(".", 2)[-1] + for task_map in SUPPORTED_TASKS_MAPPINGS: + task_class = GET_TASK_CLASS(task_map, self.attributes.model, False) + if task_class: + alt_tasks.add(task_class.__name__) + for model_code, pipe_class_obj in task_map.items(): + if self.internal_name in model_code: + alt_tasks.add(pipe_class_obj.__name__) + if alt_tasks: + self.tasks = [x for x in alt_tasks] + + def tasks_from_model(self) -> None: + """Transform a single model class into derivative classes for specific tasks.\n + :return: A list of task classes associated with the model.""" + from importlib import import_module + + model_name = self.attributes.model_name + + parent_module = import_module(self.attributes.import_path) + self.tasks = [] + if hasattr(parent_module, "__all__") and parent_module.__name__ != "DummyPipe": + for module in parent_module.__all__: + if (module.lower() != module) and (module != model_name) and (module != self.attributes.config.__name__): + self.tasks.append(module) + else: + self.tasks = [model_name] diff --git a/mir/tag.py b/mir/tag.py index 4d49e83..c6c5408 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -2,9 +2,9 @@ # from dataclasses import dataclass, field -from typing import Callable -# from mir.generate.transformers.raw_data import PrepareData -# from mir.generate.diffusers.raw_data import DPrepareData + +from mir.model import ModelAttributes +from mir.package import MIRPackage @dataclass @@ -18,44 +18,30 @@ class MIRTag: comp The compatibility component of the MIR tag (generated, optional). """ - domain: str = field(init=False) + attributes: ModelAttributes + package: MIRPackage + decoder: bool = False arch: str = field(init=False) series: str = field(init=False) - decoder: bool = False def __post_init__(self) -> None: """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" - self.generate_domain() self.generate_arch() - self.generate_series_and_comp(repo_path=self.raw_data.repo_path) + self.generate_series_and_comp() if hasattr(self, "comp"): - self.flat = f"{self.domain}.{self.arch}.{self.series}.{self.comp}" + self.flat = f"{self.arch}.{self.series}.{self.comp}" else: - self.flat = f"{self.domain}.{self.arch}.{self.series}" - - def generate_domain(self) -> None: - if isinstance(self.raw_data.model, Callable): - self.domain = "ops" - else: - self.domain = "info" + self.flat = f"{self.arch}.{self.series}" def generate_arch(self) -> None: """Generates the architecture part of the MIR tag based on prepared data.\n :raises ValueError: If no suitable tag can be determined.""" - arch = None - library = self.raw_data.model.__module__.split(".")[0] - if hasattr(self.raw_data, "config_params"): - arch = self.tag_architecture(library, **self.raw_data.config_params) # type: ignore - elif hasattr(self.raw_data, "model_params"): - arch = None - self.decoder = "decoder" in [self.raw_data.model_params] - arch = self.tag_architecture(library, **self.raw_data.model_params) # type: ignore - if not arch: - print(f"Unrecognized model type, no tag matched {self.raw_data.name} with {self.raw_data.model_name}") - else: - self.arch = arch - def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: + arch = self.tag_architecture() # type: ignore + assert arch is not None, f"Unrecognized model type, no tag matched {self.attributes.model_name} with {self.attributes}" + self.arch = arch + + def generate_series_and_comp(self, base_model_label="*") -> None: """Generates the MIR tag components from a repository title.\n :param repo_title: The title of the repository from which to derive the MIR tag. :param decoder: Boolean flag indicating if the model is a decoder. @@ -65,8 +51,7 @@ def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: from mir import BREAKING, PARAMETERS - root = "decoder" if decoder else "*" - repo_path = repo_path.split(":latest")[0] + repo_path = self.package.repo.split(":latest")[0] repo_path = repo_path.split(":Q")[0] repo_path = repo_path.split(r"/")[-1].lower() pattern = r"^.*[v]?(\d{1}+\.\d).*" @@ -90,7 +75,9 @@ def generate_series_and_comp(self, repo_path: str, decoder=decoder) -> None: suffix = next(iter(suffix for suffix in suffix_match[0] if suffix)) cleaned_string = re.sub(suffix.lower(), "-", cleaned_string).rstrip("-,") else: - suffix = root + suffix = "*" + if isinstance(self.attributes, DiffusersModelAttributes) and self.attributes.model_type == "decoder": + suffix = "decoder" cleaned_string = re.sub(r"[.-]+", "_", cleaned_string.lower()).strip("-_") self.series = cleaned_string if suffix != "*": @@ -146,7 +133,3 @@ def tag_scheduler(self, scheduler_name: str) -> tuple[str, str]: def tag_tokenizer(): pass - - -def tag_tokenizer(): - pass diff --git a/tests/test_gather_diffusers.py b/tests/test_gather_diffusers.py new file mode 100644 index 0000000..3738cbb --- /dev/null +++ b/tests/test_gather_diffusers.py @@ -0,0 +1,10 @@ +from mir.generate.diffusers.gather import GatherLoop + + +def test_gather(): + gather = GatherLoop() + print(gather) + + +if __name__ == "__main__": + test_gather() diff --git a/tests/test_gather_transformers.py b/tests/test_gather_transformers.py new file mode 100644 index 0000000..e6e28ef --- /dev/null +++ b/tests/test_gather_transformers.py @@ -0,0 +1,10 @@ +from mir.generate.transformers.gather import GatherLoop + + +def test_gather(): + gather = GatherLoop() + print(gather) + + +if __name__ == "__main__": + test_gather() diff --git a/tests/test_harvest_transformers.py b/tests/test_harvest_transformers.py deleted file mode 100644 index 1d86502..0000000 --- a/tests/test_harvest_transformers.py +++ /dev/null @@ -1,6 +0,0 @@ -from mir.generate.transformers.harvest import HarvestLoop - - -def test_harvest(): - harvest_classes = HarvestLoop() - harvest_classes() From 5fcf1ec1ae0840c237b9c3795236797ac7b7f4fb Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Thu, 22 Jan 2026 20:58:56 -0500 Subject: [PATCH 15/16] ~rearrange stuff --- mir/__init__.py | 7 - mir/__main__.py | 21 - mir/{generate/diffusers => }/doc_parse.py | 0 mir/gatherers/__init__.py | 5 + .../gather.py => gatherers/diffusers.py} | 6 +- .../mlx/harvest.py => gatherers/mlx.py} | 0 .../torch/dtypes.py => gatherers/torch.py} | 0 .../gather.py => gatherers/transformers.py} | 15 +- mir/generate/__init__.py | 0 mir/generate/__main__.py | 394 - mir/generate/_tasks.py | 104 - mir/generate/diffusers/__init__.py | 7 - mir/generate/mlx/__init__.py | 0 mir/generate/test.json | 4549 -------- mir/generate/torch/__init__.py | 0 mir/generate/transformers/__init__.py | 14 - mir/{generate/from_module.py => lookups.py} | 29 +- mir/model.py | 4 +- mir/nesting.py | 8 +- mir/package.py | 4 +- mir/tag.py | 70 +- tests/subclasses_test.py | 16 + tests/test.json | 9814 +++++++++++++++++ 23 files changed, 9928 insertions(+), 5139 deletions(-) delete mode 100644 mir/__main__.py rename mir/{generate/diffusers => }/doc_parse.py (100%) create mode 100644 mir/gatherers/__init__.py rename mir/{generate/diffusers/gather.py => gatherers/diffusers.py} (88%) rename mir/{generate/mlx/harvest.py => gatherers/mlx.py} (100%) rename mir/{generate/torch/dtypes.py => gatherers/torch.py} (100%) rename mir/{generate/transformers/gather.py => gatherers/transformers.py} (62%) delete mode 100644 mir/generate/__init__.py delete mode 100644 mir/generate/__main__.py delete mode 100644 mir/generate/_tasks.py delete mode 100644 mir/generate/diffusers/__init__.py delete mode 100644 mir/generate/mlx/__init__.py delete mode 100644 mir/generate/test.json delete mode 100644 mir/generate/torch/__init__.py delete mode 100644 mir/generate/transformers/__init__.py rename mir/{generate/from_module.py => lookups.py} (66%) create mode 100644 tests/test.json diff --git a/mir/__init__.py b/mir/__init__.py index c43d89b..3b7e486 100644 --- a/mir/__init__.py +++ b/mir/__init__.py @@ -2,7 +2,6 @@ # import os -from importlib import import_module from logging import DEBUG, INFO, Logger from mir.json_io import read_json_file @@ -19,9 +18,3 @@ SEMANTIC = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["semantic"] SUFFIX = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["suffix"] IGNORE = read_json_file(os.path.join(ROOT_PATH, "spec", "regex.json"))["ignore"] - -# from mir.generate.transformers.harvest import HarvestClasses -# Mir = HarvestClasses().db.db -# from mir.generate.diffusers.harvest import HarvestClasses - -# Mir = HarvestClasses().db.db diff --git a/mir/__main__.py b/mir/__main__.py deleted file mode 100644 index 4e892d4..0000000 --- a/mir/__main__.py +++ /dev/null @@ -1,21 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable -from importlib import import_module - -tag = lambda path: path.rsplit(".", 1) # noqa -run = lambda parts: getattr(import_module(parts[0]), parts[1]) - - -def get_attribute_chain(root_object: Callable, attribute_path: str): - """Retrieve a nested attribute from *root_object* using a dot‑separated string.\n - :param root_object : The object from which the attribute chain will be resolved. - :param attribute_path : Dot‑separated attribute names, e.g. ``"ops.cnn.yolos"``. - :returns: The final attribute value reached by following the chain. - :raises: AttributeError If any part of the chain does not exist on the current object.""" - - current = root_object - for part in attribute_path.split("."): - current = getattr(current, part) - return current diff --git a/mir/generate/diffusers/doc_parse.py b/mir/doc_parse.py similarity index 100% rename from mir/generate/diffusers/doc_parse.py rename to mir/doc_parse.py diff --git a/mir/gatherers/__init__.py b/mir/gatherers/__init__.py new file mode 100644 index 0000000..3947adb --- /dev/null +++ b/mir/gatherers/__init__.py @@ -0,0 +1,5 @@ +# from mir.generate.transformers.harvest import HarvestClasses +# Mir = HarvestClasses().db.db +# from mir.generate.diffusers.harvest import HarvestClasses + +# Mir = HarvestClasses().db.db diff --git a/mir/generate/diffusers/gather.py b/mir/gatherers/diffusers.py similarity index 88% rename from mir/generate/diffusers/gather.py rename to mir/gatherers/diffusers.py index 43a68ca..0a7645b 100644 --- a/mir/generate/diffusers/gather.py +++ b/mir/gatherers/diffusers.py @@ -1,6 +1,10 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # +from diffusers.pipelines import _import_structure as IMPORT_STRUCTURE +from diffusers.pipelines.auto_pipeline import SUPPORTED_TASKS_MAPPINGS +from diffusers.pipelines.auto_pipeline import _get_task_class as GET_TASK_CLASS + from typing import get_type_hints @@ -19,7 +23,7 @@ def __init__(self) -> None: if module_path.rsplit(".", 1)[-1] not in EXCLUSIONS["exclusion_list"]: build_entries.extend([BuildEntry(model_type=model_type, model=model) for model_type, model in get_type_hints(pipeline.__init__).items()]) build_entries.append(BuildEntry(model_type="pipeline", model=pipeline)) - print([x.attributes for x in build_entries]) + self.model_db = {x.attributes.model_name: x.attributes.model_parameters for x in build_entries} # TODO: for data in prepared_data: def extract_subclass_data(self, package_name: str, base_class_name: str): diff --git a/mir/generate/mlx/harvest.py b/mir/gatherers/mlx.py similarity index 100% rename from mir/generate/mlx/harvest.py rename to mir/gatherers/mlx.py diff --git a/mir/generate/torch/dtypes.py b/mir/gatherers/torch.py similarity index 100% rename from mir/generate/torch/dtypes.py rename to mir/gatherers/torch.py diff --git a/mir/generate/transformers/gather.py b/mir/gatherers/transformers.py similarity index 62% rename from mir/generate/transformers/gather.py rename to mir/gatherers/transformers.py index 812d8f1..06c3768 100644 --- a/mir/generate/transformers/gather.py +++ b/mir/gatherers/transformers.py @@ -3,12 +3,21 @@ from typing import Callable +from transformers.models.auto.configuration_auto import CONFIG_MAPPING +from transformers.models.auto.modeling_auto import ( + MODEL_MAPPING, # config: model map + MODEL_MAPPING_NAMES, + AutoModel, +) +from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING + +AUTO_MAP = AutoModel._model_mapping +REVERSE_MAP = AUTO_MAP._reverse_config_mapping + class GatherLoop: def __init__(self) -> None: """Loops through transformers packages to harvest class data.""" - from mir.generate.transformers import AUTO_MAP - from mir.generate.transformers import TOKENIZER_MAPPING from mir.build_entry import BuildEntry from mir.maid import MIRDatabase @@ -21,4 +30,4 @@ def __init__(self) -> None: build_entries.append(BuildEntry("model", model)) if tokenizer := TOKENIZER_MAPPING.get(config, None): build_entries.append(BuildEntry("tokenizer", tokenizer)) - print([x.attributes for x in build_entries]) # type: ignore + self.model_db = {x.attributes.model_name: x.attributes.model_parameters for x in build_entries} diff --git a/mir/generate/__init__.py b/mir/generate/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/mir/generate/__main__.py b/mir/generate/__main__.py deleted file mode 100644 index 2255ae6..0000000 --- a/mir/generate/__main__.py +++ /dev/null @@ -1,394 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -import os -from mir.maid import MIRDatabase -from mir.generate.tasks import TaskAnalyzer -from typing import Callable - - -def run_task() -> None: - main() - - -def pipe(mir_db: MIRDatabase) -> MIRDatabase: - import argparse - import asyncio - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", - usage="mir-pipe", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - from mir.generate.automata import assimilate - - if not mir_db: - mir_db = MIRDatabase() - - tasker = TaskAnalyzer() - pipe_tuple = asyncio.run(tasker.detect_pipes(mir_db)) - assimilate(mir_db, [pipe for pipe in pipe_tuple]) - mir_db.write_to_disk() - return mir_db - - -# if __name__ == "__main__": -# pipe() - - -def main(): - # import ordered to prevent file lock - import mir.maid - from mir.maid import main as mir_main - - mir_main() - from mir.generate.tasks import main - - main() - from mir.generate.tasks import pipe - - pipe() - - import os - import shutil - - try: - os.remove("mir.json") - except FileNotFoundError: - pass - shutil.copy2(os.path.join(os.path.dirname(mir.maid.__file__), "mir.json"), os.path.join(os.getcwd(), "mir.json")) - - -if __name__ == "__main__": - main() - - -def main(mir_db: MIRDatabase | None = None) -> MIRDatabase: - """Parse arguments to feed to dict header reader""" - import argparse - import asyncio - from mir.generate.automata import assimilate - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", - usage="mir-tasks", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - if not mir_db: - mir_db = MIRDatabase() - - tasker = TaskAnalyzer() - task_tuple = asyncio.run(tasker.detect_tasks(mir_db)) - - assimilate(mir_db, [task for task in task_tuple]) - - mir_db.write_to_disk() - return mir_db - - -def main(mir_db: Callable | None = None, remake: bool = True) -> None: - """Build the database""" - from sys import modules as sys_modules - - if __name__ != "__main__" and "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="mir-maid", - epilog="""Does NOT include results of `mir-task` and `mir-pipe`. These commands should be run separately. Output: - 2025-08-03 14:22:47 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-03 14:22:47 INFO ('Wrote #### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Prevent erasing and remaking the MIR database file (default: False, always start from a completely empty MIR file)", - ) - - args = parser.parse_args() - remake = not args.remake_off - - from mir.generate.automata import ( - add_mir_audio, - add_mir_diffusion, - add_mir_dtype, - add_mir_llm, - add_mir_lora, - add_mir_schedulers, - add_mir_vae, - hf_pkg_to_mir, - mir_update, - ) - from mir.json_io import write_json_file - - if remake: - os.remove(MIR_PATH_NAMED) - folder_path_named = os.path.dirname(MIR_PATH_NAMED) - mode = "x" - else: - mode = "w" - write_json_file(folder_path_named, file_name="mir.json", data={"expected": "data"}, mode=mode) - mir_db = MIRDatabase() - mir_db.database.pop("expected", {}) - hf_pkg_to_mir(mir_db) - add_mir_dtype(mir_db) - add_mir_schedulers(mir_db) - add_mir_lora(mir_db) - add_mir_audio(mir_db) - add_mir_diffusion(mir_db) - add_mir_llm(mir_db) - add_mir_vae(mir_db) - mir_db.write_to_disk() - mir_db = MIRDatabase() - mir_db = MIRDatabase() - mir_update(mir_db) - mir_db.write_to_disk() - - -if __name__ == "__main__": - remake: bool = True - tasks = True - pipes = True - - from sys import modules as sys_modules - - if "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="python -m nnll.mir.maid", - epilog="""Includes `mir-task` and `mir-pipe` by default. Output: - 2025-08-15 19:41:18 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-15 19:38:48 INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Don't erase and remake the MIR database (default: False)", - ) - parser.add_argument( - "-t", - "--tasks_off", - action="store_true", - default=False, - help="Don't append task information to the MIR database (default: False)", - ) - parser.add_argument( - "-p", - "--pipes_off", - action="store_true", - default=False, - help="Don't append pipeline information to the MIR database (default: False)", - ) - - args = parser.parse_args() - remake = not args.remake_off - tasks = not args.tasks_off - pipes = not args.pipes_off - - main(remake=remake) - - from mir.generate.tasks import pipe, run_task - - mir_db = run_task() - pipe(mir_db) - - -def main(mir_db: MIRDatabase = None): - """Parse arguments to feed to dict header reader""" - import argparse - import asyncio - from mir.automata import assimilate - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Scrape the task classes from currently installed libraries and attach them to an existing MIR database.\nOffline function.", - usage="mir-tasks", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - if not mir_db: - mir_db = MIRDatabase() - - auto_pkg = TaskAnalyzer() - task_tuple = asyncio.run(auto_pkg.detect_tasks(mir_db)) - - assimilate(mir_db, [task for task in task_tuple]) - - mir_db.write_to_disk() - return mir_db - - -def run_task(): - main() - - -def pipe(mir_db: MIRDatabase = None): - import argparse - import asyncio - from sys import modules as sys_modules - - if "pytest" not in sys_modules: - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Infer pipe components from Diffusers library and attach them to an existing MIR database.\nOffline function.", - usage="mir-pipe", - epilog="Can be run automatically with `python -m nnll.mir.maid` Should only be used after `mir-maid`.\n\nOutput:\n INFO ('Wrote #### lines to MIR database file.',)", - ) - parser.parse_args() - - from mir.automata import assimilate - - if not mir_db: - mir_db = MIRDatabase() - - auto_pkg = TaskAnalyzer() - pipe_tuple = asyncio.run(auto_pkg.detect_pipes(mir_db)) - assimilate(mir_db, [pipe for pipe in pipe_tuple]) - mir_db.write_to_disk() - return mir_db - - -if __name__ == "__main__": - pipe() - - -def main(mir_db: Callable | None = None, remake: bool = True) -> None: - """Build the database""" - from sys import modules as sys_modules - - if __name__ != "__main__" and "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="mir-maid", - epilog="""Does NOT include results of `mir-task` and `mir-pipe`. These commands should be run separately. Output: - 2025-08-03 14:22:47 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-03 14:22:47 INFO ('Wrote #### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Prevent erasing and remaking the MIR database file (default: False, always start from a completely empty MIR file)", - ) - - args = parser.parse_args() - remake = not args.remake_off - - from mir.automata import ( - add_mir_audio, - add_mir_diffusion, - add_mir_dtype, - add_mir_llm, - add_mir_lora, - add_mir_schedulers, - add_mir_vae, - hf_pkg_to_mir, - mir_update, - ) - from mir.config.json_io import write_json_file - - if remake: - os.remove(MIR_PATH_NAMED) - folder_path_named = os.path.dirname(MIR_PATH_NAMED) - mode = "x" - else: - mode = "w" - write_json_file(folder_path_named, file_name="mir.json", data={"expected": "data"}, mode=mode) - mir_db = MIRDatabase() - mir_db.database.pop("expected", {}) - hf_pkg_to_mir(mir_db) - add_mir_dtype(mir_db) - add_mir_schedulers(mir_db) - add_mir_lora(mir_db) - add_mir_audio(mir_db) - add_mir_diffusion(mir_db) - add_mir_llm(mir_db) - add_mir_vae(mir_db) - mir_db.write_to_disk() - mir_db = MIRDatabase() - mir_db = MIRDatabase() - mir_update(mir_db) - mir_db.write_to_disk() - - -if __name__ == "__main__": - remake: bool = True - tasks = True - pipes = True - - from sys import modules as sys_modules - - if "pytest" not in sys_modules: # - import argparse - - parser = argparse.ArgumentParser( - formatter_class=argparse.RawTextHelpFormatter, - description="Build a custom MIR model database from the currently installed system environment.\nOffline function.", - usage="python -m nnll.mir.maid", - epilog="""Includes `mir-task` and `mir-pipe` by default. Output: - 2025-08-15 19:41:18 INFO ('Wrote 0 lines to MIR database file.',) - 2025-08-15 19:38:48 INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',) - INFO ('Wrote ### lines to MIR database file.',)""", - ) - parser.add_argument( - "-r", - "--remake_off", - action="store_true", - default=False, - help="Don't erase and remake the MIR database (default: False)", - ) - parser.add_argument( - "-t", - "--tasks_off", - action="store_true", - default=False, - help="Don't append task information to the MIR database (default: False)", - ) - parser.add_argument( - "-p", - "--pipes_off", - action="store_true", - default=False, - help="Don't append pipeline information to the MIR database (default: False)", - ) - - args = parser.parse_args() - remake = not args.remake_off - tasks = not args.tasks_off - pipes = not args.pipes_off - - main(remake=remake) - update_mir() - from mir.inspect.tasks import pipe, run_task - - mir_db = run_task() - pipe(mir_db) diff --git a/mir/generate/_tasks.py b/mir/generate/_tasks.py deleted file mode 100644 index 2745598..0000000 --- a/mir/generate/_tasks.py +++ /dev/null @@ -1,104 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from typing import Any, Callable, List -from mir.generate.diffusers.raw_data import ModelAttributes -from mir import DBUQ -from mir.tag import MIRTag - -flatten_map: List[Any] = lambda nested, unpack: [element for iterative in getattr(nested, unpack)() for element in iterative] -flatten_map.__annotations__ = {"nested": List[str], "unpack": str} - - -class TaskAnalyzer: - prepared_data: ModelAttributes - mir_tag: MIRTag - tasks: dict[str, str] | None = None - - def __init__(self, prepared_data: ModelAttributes, mir_tag: MIRTag) -> None: - self.prepared_data = prepared_data - self.mir_tag = mir_tag - self.skip_series = [ - "info.lora", - "info.vae", - "ops.precision", - "ops.scheduler", - "info.encoder.tokenizer", - "info.controlnet", - ] - self.skip_classes = [".gligen", "imagenet64"] - self.skip_auto = ["AutoTokenizer", "AutoModel", "AutoencoderTiny", "AutoencoderKL", "AutoPipelineForImage2Image"] - self.skip_types = ["int", "bool", "float", "Optional", "NoneType", "List", "UNet2DConditionModel"] - self.mflux_tasks = ["Image", "Redux", "Kontext", "Depth", "Fill", "ConceptAttention", "ControlNet", "CavTon", "IC-Edit"] - - async def __post_init__(self) -> None: - """Detects and traces Pipes MIR data\n - :param mir_db:: An instance of MIRDatabase containing the database of information. - :type mir_db: MIRDatabase - :param field_name: The name of the field in compatibility data to process for task detection, defaults to "pkg". - :type field_name: str, optional - :return:A dictionary mapping series names to their respective compatibility and traced tasks. - :rtype: dict""" - - data_tuple = [] - detected_pipe = await self.hyperlink_to_mir(self.prepared_data.model_params, self.mir_tag.series) - if hasattr(self.mir_tag, "comp") and self.mir_tag.comp: - self.tasks(*self.mir_tag.series, {self.mir_tag.comp: detected_pipe}) - else: - self.tasks({self.mir_tag.series: self.prepared_data.model_path}) - - self.tasks = data_tuple - - async def hyperlink_to_mir(self, pipe_args: dict, series: str): - """Maps pipeline components to MIR tags/IDs based on class names and roles.\n - :param pipe_args: Dictionary of pipeline roles to their corresponding classes - :return: Dictionary mapping pipeline roles to associated MIR tags/IDs""" - - mir_tag: None | list[str] = None - detected_links: dict[str, dict] = {"pipe_names": dict()} - for pipe_role, pipe_class in pipe_args.items(): - if pipe_role in ["tokenizer", "tokenizer_2", "tokenizer_3", "tokenizer_4", "prior_tokenizer"]: - detected_links["pipe_names"].setdefault(pipe_role, ["info.encoder.tokenizer", series.rsplit(".", 1)[-1]]) - continue - if not any(segment for segment in self.skip_types if pipe_class.__name__ == segment): - mir_tag = None - detected_links["pipe_names"][pipe_role] = [] - DBUQ(f"pipe_class.__name__ {pipe_class.__name__} {pipe_class}") - if pipe_class.__name__ in ["Union"]: - for union_class in pipe_class.__args__: - mir_tag = None - class_name = union_class.__name__ - if not any(segment for segment in self.skip_types if class_name == segment): - mir_tag, class_name = await self.tag_class(pipe_class=union_class, pipe_role=pipe_role, series=series) - # mir_tag = mir_db.find_tag(field="tasks", target=class_name) - # dbuq(f"{mir_tag} {class_name}") - detected_links["pipe_names"][pipe_role].append(mir_tag if mir_tag else class_name) - else: - mir_tag, class_name = await self.tag_class(pipe_class=pipe_class, pipe_role=pipe_role, series=series) - detected_links["pipe_names"][pipe_role] = mir_tag if mir_tag else [class_name] - mir_tag = None - class_name = None - return detected_links - - async def tag_class(self, pipe_class: Callable, pipe_role: str, series: str) -> tuple[str | None]: - """Maps a class to MIR tags/IDs based on its name and role.\n - :param pipe_class: Class to be mapped - :param pipe_role: Role of the class in the pipeline - :param series: Series identifier for the component - :return: Tuple containing MIR tag and class name""" - from mir.generate.diffusers.schedulers import tag_scheduler - - mir_tag = None - class_name = pipe_class.__name__ - if pipe_role in ["scheduler", "image_noising_scheduler", "prior_scheduler"]: - sub_field = pipe_class.__module__.split(".")[0] - scheduler_series, scheduler_comp = tag_scheduler(class_name) - mir_tag = [f"ops.scheduler.{scheduler_series}", scheduler_comp] - DBUQ(f"scheduler {mir_tag} {class_name} {sub_field} ") - elif pipe_role == "vae": - sub_field = pipe_class.__module__.split(".")[0] - mir_comp = series.rsplit(".", 1)[-1] - DBUQ(mir_comp) - mir_tag = "info.vae" - return mir_tag, class_name diff --git a/mir/generate/diffusers/__init__.py b/mir/generate/diffusers/__init__.py deleted file mode 100644 index c19bcec..0000000 --- a/mir/generate/diffusers/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - -from typing import Callable -from dataclasses import dataclass, field -from diffusers.pipelines import _import_structure as IMPORT_STRUCTURE -from diffusers.pipelines.auto_pipeline import SUPPORTED_TASKS_MAPPINGS, _get_task_class as GET_TASK_CLASS diff --git a/mir/generate/mlx/__init__.py b/mir/generate/mlx/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/mir/generate/test.json b/mir/generate/test.json deleted file mode 100644 index 2e8091a..0000000 --- a/mir/generate/test.json +++ /dev/null @@ -1,4549 +0,0 @@ -model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'hidden_sizes': 'hidden_sizes=[ - 256, - 512, - 1024, - 2048 - ]', 'depths': 'depths=[ - 3, - 4, - 6, - 3 - ]', 'layer_type': "layer_type='preactivation'", 'hidden_act': "hidden_act='relu'", 'global_padding': 'global_padding=None', 'num_groups': 'num_groups=32', 'drop_path_rate': 'drop_path_rate=0.0', 'embedding_dynamic_padding': 'embedding_dynamic_padding=False', 'output_stride': 'output_stride=32', 'width_factor': 'width_factor=1', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, -model_name='BitModel', library='transformers', import_path='transformers.models.bit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 128256', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int - ] = 6912', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 30', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 5', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int - ] = 128001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[str - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='BitNetModel', library='transformers', import_path='transformers.models.bitnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=8008', 'max_position_embeddings': 'max_position_embeddings=128', 'encoder_layers': 'encoder_layers=2', 'encoder_ffn_dim': 'encoder_ffn_dim=10240', 'encoder_attention_heads': 'encoder_attention_heads=32', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=10240', 'decoder_attention_heads': 'decoder_attention_heads=32', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=2560', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=1', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'encoder_no_repeat_ngram_size': 'encoder_no_repeat_ngram_size=3', 'forced_eos_token_id': 'forced_eos_token_id=2' -}, model_name='BlenderbotModel', library='transformers', import_path='transformers.models.blenderbot'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=True', 'vocab': 'vocab=None', 'merges': 'merges=None' -}, model_name='BlenderbotTokenizer', library='transformers', import_path='transformers.models.blenderbot'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=512', 'encoder_layers': 'encoder_layers=8', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=8', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=512', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=1', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' -}, model_name='BlenderbotSmallModel', library='transformers', import_path='transformers.models.blenderbot_small'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'bos_token': "bos_token='__start__'", 'eos_token': "eos_token='__end__'", 'unk_token': "unk_token='__unk__'", 'pad_token': "pad_token='__null__'" -}, model_name='BlenderbotSmallTokenizer', library='transformers', import_path='transformers.models.blenderbot_small'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'image_text_hidden_size': 'image_text_hidden_size=256', 'label_smoothing': 'label_smoothing=0.0' -}, model_name='BlipModel', library='transformers', import_path='transformers.models.blip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'image_text_hidden_size': 'image_text_hidden_size=256', 'image_token_index': 'image_token_index=None' -}, model_name='Blip2Model', library='transformers', import_path='transformers.models.blip_2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'cross_attention_frequency': 'cross_attention_frequency=2', 'encoder_hidden_size': 'encoder_hidden_size=1408', 'use_qformer_text_input': 'use_qformer_text_input=False' -}, model_name='Blip2QFormerModel', library='transformers', import_path='transformers.models.blip_2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250880', 'hidden_size': 'hidden_size=64', 'n_layer': 'n_layer=2', 'n_head': 'n_head=8', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'apply_residual_connection_post_layernorm': 'apply_residual_connection_post_layernorm=False', 'hidden_dropout': 'hidden_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'pretraining_tp': 'pretraining_tp=1', 'slow_but_exact': 'slow_but_exact=False' -}, model_name='BloomModel', library='transformers', import_path='transformers.models.bloom'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 260', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'patch_in_forward': 'patch_in_forward: Optional[bool - ] = True', 'patch_size': 'patch_size: Optional[int - ] = 4', 'patching_mode': "patching_mode: Optional[str] = 'entropy'", 'patching_threshold': 'patching_threshold: Optional[float - ] = 1.335442066192627', 'patching_batch_size': 'patching_batch_size: Optional[int - ] = 1', 'max_patch_length': 'max_patch_length: Optional[int - ] = None', 'cross_attn_k': 'cross_attn_k: Optional[int - ] = 2', 'encoder_hash_byte_group_size': 'encoder_hash_byte_group_size: Optional[int - ] = None', 'encoder_hash_byte_group_vocab': 'encoder_hash_byte_group_vocab: Optional[int - ] = 500002', 'encoder_hash_byte_group_nb_functions': 'encoder_hash_byte_group_nb_functions: Optional[int - ] = 1', 'patcher_config': 'patcher_config: Optional[dict - ] = None', 'encoder_config': 'encoder_config: Optional[dict - ] = None', 'decoder_config': 'decoder_config: Optional[dict - ] = None', 'global_config': 'global_config: Optional[dict - ] = None', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='BltModel', library='transformers', import_path='transformers.models.blt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'share_cross_modal_transformer_layers': 'share_cross_modal_transformer_layers=True', 'hidden_act': "hidden_act='gelu'", 'hidden_size': 'hidden_size=768', 'initializer_factor': 'initializer_factor=1', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'share_link_tower_layers': 'share_link_tower_layers=False', 'link_tower_type': "link_tower_type='add'", 'num_attention_heads': 'num_attention_heads=12', 'num_hidden_layers': 'num_hidden_layers=6', 'tie_word_embeddings': 'tie_word_embeddings=False', 'init_layernorm_from_vision_encoder': 'init_layernorm_from_vision_encoder=False', 'text_config': 'text_config=None', 'vision_config': 'vision_config=None' -}, model_name='BridgeTowerModel', library='transformers', import_path='transformers.models.bridgetower'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'dim_bbox': 'dim_bbox=8', 'bbox_scale': 'bbox_scale=100.0', 'n_relations': 'n_relations=1', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1' -}, model_name='BrosModel', library='transformers', import_path='transformers.models.bros'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='CamembertModel', library='transformers', import_path='transformers.models.camembert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': 'additional_special_tokens=None', 'add_prefix_space': 'add_prefix_space=True', 'vocab_file': 'vocab_file=None', 'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None' -}, model_name='CamembertTokenizer', library='transformers', import_path='transformers.models.camembert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=16384', 'type_vocab_size': 'type_vocab_size=16', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=57344', 'eos_token_id': 'eos_token_id=57345', 'downsampling_rate': 'downsampling_rate=4', 'upsampling_kernel_size': 'upsampling_kernel_size=4', 'num_hash_functions': 'num_hash_functions=8', 'num_hash_buckets': 'num_hash_buckets=16384', 'local_transformer_stride': 'local_transformer_stride=128' -}, model_name='CanineModel', library='transformers', import_path='transformers.models.canine'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'bos_token': "bos_token='\\ue000'", 'eos_token': "eos_token='\\ue001'", 'sep_token': "sep_token='\\ue001'", 'cls_token': "cls_token='\\ue000'", 'pad_token': "pad_token='\\x00'", 'mask_token': "mask_token='\\ue003'", 'add_prefix_space': 'add_prefix_space=False', 'model_max_length': 'model_max_length=2048' -}, model_name='CanineTokenizer', library='transformers', import_path='transformers.models.canine'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 65536', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'hidden_act': "hidden_act: Optional[int] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[int - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'model_parallel_size': 'model_parallel_size: Optional[int - ] = 1', 'swin_norm': 'swin_norm: Optional[bool - ] = False', 'vq_config': 'vq_config: Optional[dict - ] = None', 'vocabulary_map': 'vocabulary_map: Optional[dict - ] = None', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False' -}, model_name='ChameleonModel', library='transformers', import_path='transformers.models.chameleon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='ChineseCLIPModel', library='transformers', import_path='transformers.models.chinese_clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' -}, model_name='ChineseCLIPVisionModel', library='transformers', import_path='transformers.models.chinese_clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_config': 'audio_config=None', 'logit_scale_init_value': 'logit_scale_init_value=14.285714285714285', 'projection_dim': 'projection_dim=512', 'projection_hidden_act': "projection_hidden_act='relu'", 'initializer_factor': 'initializer_factor=1.0' -}, model_name='ClapModel', library='transformers', import_path='transformers.models.clap'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='CLIPModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=49408', 'hidden_size': 'hidden_size=512', 'intermediate_size': 'intermediate_size=2048', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=8', 'max_position_embeddings': 'max_position_embeddings=77', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=49406', 'eos_token_id': 'eos_token_id=49407' -}, model_name='CLIPTextModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'projection_dim': 'projection_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='quick_gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' -}, model_name='CLIPVisionModel', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'extract_layers': 'extract_layers=[ - 3, - 6, - 9 - ]', 'reduce_dim': 'reduce_dim=64', 'decoder_num_attention_heads': 'decoder_num_attention_heads=4', 'decoder_attention_dropout': 'decoder_attention_dropout=0.0', 'decoder_hidden_act': "decoder_hidden_act='quick_gelu'", 'decoder_intermediate_size': 'decoder_intermediate_size=2048', 'conditional_layer': 'conditional_layer=0', 'use_complex_transposed_convolution': 'use_complex_transposed_convolution=False' -}, model_name='CLIPSegModel', library='transformers', import_path='transformers.models.clipseg'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'speech_config': 'speech_config=None', 'decoder_config': 'decoder_config=None', 'projection_dim': 'projection_dim=768', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'initializer_factor': 'initializer_factor=1.0' -}, model_name='ClvpModelForConditionalGeneration', library='transformers', import_path='transformers.models.clvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'errors': "errors='replace'", 'unk_token': "unk_token='[UNK]'", 'bos_token': "bos_token='<|endoftext|>'", 'eos_token': "eos_token='[STOP]'", 'pad_token': "pad_token='[STOP]'", 'add_prefix_space': 'add_prefix_space=False' -}, model_name='ClvpTokenizer', library='transformers', import_path='transformers.models.clvp'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='LlamaModel', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50400', 'n_positions': 'n_positions=2048', 'n_ctx': 'n_ctx=2048', 'n_embd': 'n_embd=4096', 'n_layer': 'n_layer=28', 'n_head': 'n_head=16', 'rotary_dim': 'rotary_dim=64', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.0', 'embd_pdrop': 'embd_pdrop=0.0', 'attn_pdrop': 'attn_pdrop=0.0', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='CodeGenModel', library='transformers', import_path='transformers.models.codegen'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int - ] = 22528', 'logit_scale': 'logit_scale: Optional[float - ] = 0.0625', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 5', 'eos_token_id': 'eos_token_id: Optional[int - ] = 255001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'use_qk_norm': 'use_qk_norm: Optional[bool - ] = False' -}, model_name='CohereModel', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = '<|END_OF_TURN_TOKEN|>'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'sep_token': "sep_token: str = ''", 'mask_token': "mask_token: str = ''", 'use_default_system_prompt': 'use_default_system_prompt: bool = False', 'add_prefix_space': 'add_prefix_space: bool = False' -}, model_name='CohereTokenizer', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int - ] = 22528', 'logit_scale': 'logit_scale: Optional[float - ] = 0.0625', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 5', 'eos_token_id': 'eos_token_id: Optional[int - ] = 255001', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Cohere2Model', library='transformers', import_path='transformers.models.cohere2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = '<|END_OF_TURN_TOKEN|>'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'sep_token': "sep_token: str = ''", 'mask_token': "mask_token: str = ''", 'use_default_system_prompt': 'use_default_system_prompt: bool = False', 'add_prefix_space': 'add_prefix_space: bool = False' -}, model_name='CohereTokenizer', library='transformers', import_path='transformers.models.cohere'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'downsample_factor': 'downsample_factor=2', 'image_token_id': 'image_token_id=255036', 'alignment_intermediate_size': 'alignment_intermediate_size=36864' -}, model_name='Cohere2VisionModel', library='transformers', import_path='transformers.models.cohere2_vision'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=300', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=2', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'cls_loss_coefficient': 'cls_loss_coefficient=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'focal_alpha': 'focal_alpha=0.25' -}, model_name='ConditionalDetrModel', library='transformers', import_path='transformers.models.conditional_detr'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'embedding_size': 'embedding_size=768', 'head_ratio': 'head_ratio=2', 'conv_kernel_size': 'conv_kernel_size=9', 'num_groups': 'num_groups=1', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='ConvBertModel', library='transformers', import_path='transformers.models.convbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=4', 'num_stages': 'num_stages=4', 'hidden_sizes': 'hidden_sizes=None', 'depths': 'depths=None', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'layer_scale_init_value': 'layer_scale_init_value=1e-06', 'drop_path_rate': 'drop_path_rate=0.0', 'image_size': 'image_size=224', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='ConvNextModel', library='transformers', import_path='transformers.models.convnext'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=4', 'num_stages': 'num_stages=4', 'hidden_sizes': 'hidden_sizes=None', 'depths': 'depths=None', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'drop_path_rate': 'drop_path_rate=0.0', 'image_size': 'image_size=224', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='ConvNextV2Model', library='transformers', import_path='transformers.models.convnextv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 30720', 'hidden_size': 'hidden_size: int = 4096', 'num_attention_heads': 'num_attention_heads: int = 32', 'dim_head': 'dim_head: int = 128', 'dim_ff': 'dim_ff: int = 10240', 'num_hidden_layers': 'num_hidden_layers: int = 48', 'dropout_p': 'dropout_p: int = 0.0', 'position_bias_num_buckets': 'position_bias_num_buckets: int = 512', 'position_bias_max_distance': 'position_bias_max_distance: int = 2048', 'eps': 'eps: int = 1e-06', 'init_std': 'init_std: float = 1.0', 'prompt_types': 'prompt_types: int = 32', 'prompt_length': 'prompt_length: int = 32', 'segment_types': 'segment_types: int = 32' -}, model_name='CpmAntModel', library='transformers', import_path='transformers.models.cpmant'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bod_token': "bod_token=''", 'eod_token': "eod_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'line_token': "line_token=''", 'space_token': "space_token=''", 'padding_side': "padding_side='left'" -}, model_name='CpmAntTokenizer', library='transformers', import_path='transformers.models.cpmant'), ModelAttributes(model=, model_type='model', model_parameters={'num_codebooks': 'num_codebooks: Optional[int - ] = 32', 'vocab_size': 'vocab_size: Optional[int - ] = 2051', 'text_vocab_size': 'text_vocab_size: Optional[int - ] = 128256', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 128002', 'codebook_pad_token_id': 'codebook_pad_token_id: Optional[int - ] = 2050', 'codebook_eos_token_id': 'codebook_eos_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int - ] = None', 'audio_token_id': 'audio_token_id: Optional[int - ] = 128002', 'audio_eos_token_id': 'audio_eos_token_id: Optional[int - ] = 128003', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'head_dim': 'head_dim: Optional[int - ] = None', 'tie_codebooks_embeddings': 'tie_codebooks_embeddings: Optional[bool - ] = True', 'depth_decoder_config': 'depth_decoder_config: Optional[dict - ] = None', 'codec_config': 'codec_config: Optional[dict - ] = None' -}, model_name='CsmForConditionalGeneration', library='transformers', import_path='transformers.models.csm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=246534', 'n_positions': 'n_positions=256', 'n_embd': 'n_embd=1280', 'dff': 'dff=8192', 'n_layer': 'n_layer=48', 'n_head': 'n_head=16', 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_range': 'initializer_range=0.02' -}, model_name='CTRLModel', library='transformers', import_path='transformers.models.ctrl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'unk_token': "unk_token=''" -}, model_name='CTRLTokenizer', library='transformers', import_path='transformers.models.ctrl'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_sizes': 'patch_sizes=[ - 7, - 3, - 3 - ]', 'patch_stride': 'patch_stride=[ - 4, - 2, - 2 - ]', 'patch_padding': 'patch_padding=[ - 2, - 1, - 1 - ]', 'embed_dim': 'embed_dim=[ - 64, - 192, - 384 - ]', 'num_heads': 'num_heads=[ - 1, - 3, - 6 - ]', 'depth': 'depth=[ - 1, - 2, - 10 - ]', 'mlp_ratio': 'mlp_ratio=[ - 4.0, - 4.0, - 4.0 - ]', 'attention_drop_rate': 'attention_drop_rate=[ - 0.0, - 0.0, - 0.0 - ]', 'drop_rate': 'drop_rate=[ - 0.0, - 0.0, - 0.0 - ]', 'drop_path_rate': 'drop_path_rate=[ - 0.0, - 0.0, - 0.1 - ]', 'qkv_bias': 'qkv_bias=[True, True, True - ]', 'cls_token': 'cls_token=[False, False, True - ]', 'qkv_projection_method': "qkv_projection_method=['dw_bn', 'dw_bn', 'dw_bn']", 'kernel_qkv': 'kernel_qkv=[ - 3, - 3, - 3 - ]', 'padding_kv': 'padding_kv=[ - 1, - 1, - 1 - ]', 'stride_kv': 'stride_kv=[ - 2, - 2, - 2 - ]', 'padding_q': 'padding_q=[ - 1, - 1, - 1 - ]', 'stride_q': 'stride_q=[ - 1, - 1, - 1 - ]', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12' -}, model_name='CvtModel', library='transformers', import_path='transformers.models.cvt'), ModelAttributes(model=, model_type='model', model_parameters={'n_head': ['' - ] -}, model_name='CwmModel', library='transformers', import_path='transformers.models.cwm'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ - 512, - 1024, - 2048 - ]', 'feat_strides': 'feat_strides=[ - 8, - 16, - 32 - ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ - 2 - ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ - 256, - 256, - 256 - ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'weight_loss_fgl': 'weight_loss_fgl=0.15', 'weight_loss_ddf': 'weight_loss_ddf=1.5', 'eos_coefficient': 'eos_coefficient=0.0001', 'eval_idx': 'eval_idx=-1', 'layer_scale': 'layer_scale=1', 'max_num_bins': 'max_num_bins=32', 'reg_scale': 'reg_scale=4.0', 'depth_mult': 'depth_mult=1.0', 'top_prob_values': 'top_prob_values=4', 'lqe_hidden_dim': 'lqe_hidden_dim=64', 'lqe_layers': 'lqe_layers=2', 'decoder_offset_scale': 'decoder_offset_scale=0.5', 'decoder_method': "decoder_method='default'", 'up': 'up=0.5' -}, model_name='DFineModel', library='transformers', import_path='transformers.models.d_fine'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'num_queries': 'num_queries=300', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='prelu'", 'hidden_size': 'hidden_size=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'dilation': 'dilation=False', 'class_cost': 'class_cost=2', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'cls_loss_coefficient': 'cls_loss_coefficient=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'focal_alpha': 'focal_alpha=0.25', 'temperature_height': 'temperature_height=20', 'temperature_width': 'temperature_width=20', 'query_dim': 'query_dim=4', 'random_refpoints_xy': 'random_refpoints_xy=False', 'keep_query_pos': 'keep_query_pos=False', 'num_patterns': 'num_patterns=0', 'normalize_before': 'normalize_before=False', 'sine_position_embedding_scale': 'sine_position_embedding_scale=None', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None' -}, model_name='DabDetrModel', library='transformers', import_path='transformers.models.dab_detr'), ModelAttributes(model=, model_type='model', model_parameters={'encoder_hidden_size': 'encoder_hidden_size=64', 'downsampling_ratios': 'downsampling_ratios=[ - 2, - 4, - 8, - 8 - ]', 'decoder_hidden_size': 'decoder_hidden_size=1536', 'n_codebooks': 'n_codebooks=9', 'codebook_size': 'codebook_size=1024', 'codebook_dim': 'codebook_dim=8', 'quantizer_dropout': 'quantizer_dropout=0', 'commitment_loss_weight': 'commitment_loss_weight=0.25', 'codebook_loss_weight': 'codebook_loss_weight=1.0', 'sampling_rate': 'sampling_rate=16000' -}, model_name='DacModel', library='transformers', import_path='transformers.models.dac'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'conv_pos_kernel_size': 'conv_pos_kernel_size=19', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=5', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None' -}, model_name='Data2VecAudioModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' -}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='Data2VecTextModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'use_mask_token': 'use_mask_token=False', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=False', 'use_relative_position_bias': 'use_relative_position_bias=False', 'use_shared_relative_position_bias': 'use_shared_relative_position_bias=False', 'layer_scale_init_value': 'layer_scale_init_value=0.1', 'drop_path_rate': 'drop_path_rate=0.1', 'use_mean_pooling': 'use_mean_pooling=True', 'out_indices': 'out_indices=[ - 3, - 5, - 7, - 11 - ]', 'pool_scales': 'pool_scales=[ - 1, - 2, - 3, - 6 - ]', 'use_auxiliary_head': 'use_auxiliary_head=True', 'auxiliary_loss_weight': 'auxiliary_loss_weight=0.4', 'auxiliary_channels': 'auxiliary_channels=256', 'auxiliary_num_convs': 'auxiliary_num_convs=1', 'auxiliary_concat_input': 'auxiliary_concat_input=False', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' -}, model_name='Data2VecVisionModel', library='transformers', import_path='transformers.models.data2vec'), ModelAttributes(model=, model_type='model', model_parameters={'d_model': 'd_model: Optional[int - ] = 2048', 'n_heads': 'n_heads: Optional[int - ] = 16', 'n_layers': 'n_layers: Optional[int - ] = 24', 'max_seq_len': 'max_seq_len: Optional[int - ] = 2048', 'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'resid_pdrop': 'resid_pdrop: Optional[float - ] = 0.0', 'emb_pdrop': 'emb_pdrop: Optional[float - ] = 0.0', 'attn_config': 'attn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxAttentionConfig - ] = None', 'ffn_config': 'ffn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxFFNConfig - ] = None', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='DbrxModel', library='transformers', import_path='transformers.models.dbrx'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'relative_attention': 'relative_attention=False', 'max_relative_positions': 'max_relative_positions=-1', 'pad_token_id': 'pad_token_id=0', 'position_biased_input': 'position_biased_input=True', 'pos_att_type': 'pos_att_type=None', 'pooler_dropout': 'pooler_dropout=0', 'pooler_hidden_act': "pooler_hidden_act='gelu'", 'legacy': 'legacy=True' -}, model_name='DebertaModel', library='transformers', import_path='transformers.models.deberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors='replace'", 'bos_token': "bos_token='[CLS]'", 'eos_token': "eos_token='[SEP]'", 'sep_token': "sep_token='[SEP]'", 'cls_token': "cls_token='[CLS]'", 'unk_token': "unk_token='[UNK]'", 'pad_token': "pad_token='[PAD]'", 'mask_token': "mask_token='[MASK]'", 'add_prefix_space': 'add_prefix_space=False' -}, model_name='DebertaTokenizer', library='transformers', import_path='transformers.models.deberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128100', 'hidden_size': 'hidden_size=1536', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=24', 'intermediate_size': 'intermediate_size=6144', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'relative_attention': 'relative_attention=False', 'max_relative_positions': 'max_relative_positions=-1', 'pad_token_id': 'pad_token_id=0', 'position_biased_input': 'position_biased_input=True', 'pos_att_type': 'pos_att_type=None', 'pooler_dropout': 'pooler_dropout=0', 'pooler_hidden_act': "pooler_hidden_act='gelu'", 'legacy': 'legacy=True' -}, model_name='DebertaV2Model', library='transformers', import_path='transformers.models.deberta_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'do_lower_case': 'do_lower_case=False', 'split_by_punct': 'split_by_punct=False', 'bos_token': "bos_token='[CLS]'", 'eos_token': "eos_token='[SEP]'", 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'add_prefix_space': 'add_prefix_space=True', 'unk_id': 'unk_id=1' -}, model_name='DebertaV2Tokenizer', library='transformers', import_path='transformers.models.deberta_v2'), ModelAttributes(model=, model_type='model', model_parameters={'state_dim': 'state_dim=17', 'act_dim': 'act_dim=4', 'hidden_size': 'hidden_size=128', 'max_ep_len': 'max_ep_len=4096', 'action_tanh': 'action_tanh=True', 'vocab_size': 'vocab_size=1', 'n_positions': 'n_positions=1024', 'n_layer': 'n_layer=3', 'n_head': 'n_head=1', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='relu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' -}, model_name='DecisionTransformerModel', library='transformers', import_path='transformers.models.decision_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int - ] = 0', 'kv_lora_rank': 'kv_lora_rank: Optional[int - ] = 512', 'q_lora_rank': 'q_lora_rank: Optional[int - ] = 1536', 'n_group': 'n_group: Optional[int - ] = None', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = 64', 'n_shared_experts': 'n_shared_experts: Optional[int - ] = 2', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int - ] = 128', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int - ] = 64', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 1.0', 'topk_group': 'topk_group: Optional[int - ] = None', 'topk_method': "topk_method: Optional[str] = 'greedy'", 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False', 'v_head_dim': 'v_head_dim: Optional[int - ] = 128', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = None', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1407' -}, model_name='DeepseekV2Model', library='transformers', import_path='transformers.models.deepseek_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 129280', 'hidden_size': 'hidden_size: Optional[int - ] = 7168', 'intermediate_size': 'intermediate_size: Optional[int - ] = 18432', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 61', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 128', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 128', 'n_shared_experts': 'n_shared_experts: Optional[int - ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = 256', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 2.5', 'kv_lora_rank': 'kv_lora_rank: Optional[int - ] = 512', 'q_lora_rank': 'q_lora_rank: Optional[int - ] = 1536', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int - ] = 64', 'v_head_dim': 'v_head_dim: Optional[int - ] = 128', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int - ] = 128', 'n_group': 'n_group: Optional[int - ] = 8', 'topk_group': 'topk_group: Optional[int - ] = 4', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 8', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int - ] = 3', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = True', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'rope_interleave': 'rope_interleave: Optional[bool - ] = True', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='DeepseekV3Model', library='transformers', import_path='transformers.models.deepseek_v3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig - ] = None', 'vision_config': 'vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig - ] = None', 'image_token_id': 'image_token_id: int = 100015' -}, model_name='DeepseekVLModel', library='transformers', import_path='transformers.models.deepseek_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig - ] = None', 'vision_config': 'vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig - ] = None', 'high_res_vision_config': 'high_res_vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig - ] = None', 'image_token_id': 'image_token_id: int = 100015' -}, model_name='DeepseekVLHybridModel', library='transformers', import_path='transformers.models.deepseek_vl_hybrid'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=300', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'return_intermediate': 'return_intermediate=True', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=False', 'two_stage_num_proposals': 'two_stage_num_proposals=300', 'with_box_refine': 'with_box_refine=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False' -}, model_name='DeformableDetrModel', library='transformers', import_path='transformers.models.deformable_detr'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'encoder_stride': 'encoder_stride=16', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" -}, model_name='DeiTModel', library='transformers', import_path='transformers.models.deit'), ModelAttributes(model=, model_type='model', model_parameters={'fusion_hidden_size': 'fusion_hidden_size=256', 'patch_size': 'patch_size=384', 'initializer_range': 'initializer_range=0.02', 'intermediate_hook_ids': 'intermediate_hook_ids=[ - 11, - 5 - ]', 'intermediate_feature_dims': 'intermediate_feature_dims=[ - 256, - 256 - ]', 'scaled_images_ratios': 'scaled_images_ratios=[ - 0.25, - 0.5, - 1 - ]', 'scaled_images_overlap_ratios': 'scaled_images_overlap_ratios=[ - 0.0, - 0.5, - 0.25 - ]', 'scaled_images_feature_dims': 'scaled_images_feature_dims=[ - 1024, - 1024, - 512 - ]', 'merge_padding_value': 'merge_padding_value=3', 'use_batch_norm_in_fusion_residual': 'use_batch_norm_in_fusion_residual=False', 'use_bias_in_fusion_residual': 'use_bias_in_fusion_residual=True', 'use_fov_model': 'use_fov_model=False', 'num_fov_head_layers': 'num_fov_head_layers=2', 'image_model_config': 'image_model_config=None', 'patch_model_config': 'patch_model_config=None', 'fov_model_config': 'fov_model_config=None' -}, model_name='DepthProModel', library='transformers', import_path='transformers.models.depth_pro'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=100', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' -}, model_name='DetrModel', library='transformers', import_path='transformers.models.detr'), ModelAttributes(model=, model_type='model', model_parameters={'encoder_config': 'encoder_config: Optional[transformers.models.dia.configuration_dia.DiaEncoderConfig - ] = None', 'decoder_config': 'decoder_config: Optional[transformers.models.dia.configuration_dia.DiaDecoderConfig - ] = None', 'norm_eps': 'norm_eps: float = 1e-05', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'pad_token_id': 'pad_token_id: int = 1025', 'eos_token_id': 'eos_token_id: int = 1024', 'bos_token_id': 'bos_token_id: int = 1026', 'delay_pattern': 'delay_pattern: Optional[list[int - ] - ] = None', 'initializer_range': 'initializer_range: float = 0.02' -}, model_name='DiaModel', library='transformers', import_path='transformers.models.dia'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'pad_token': "pad_token: Optional[str] = ''", 'unk_token': "unk_token: Optional[str] = ''", 'max_length': 'max_length: Optional[int - ] = 1024', 'offset': 'offset: int = 0' -}, model_name='DiaTokenizer', library='transformers', import_path='transformers.models.dia'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'lambda_std_dev': 'lambda_std_dev: Optional[float - ] = 0.1', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='DiffLlamaModel', library='transformers', import_path='transformers.models.diffllama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=64', 'depths': 'depths=[ - 3, - 4, - 6, - 5 - ]', 'num_heads': 'num_heads=[ - 2, - 4, - 8, - 16 - ]', 'kernel_size': 'kernel_size=7', 'dilations': 'dilations=[ - [ - 1, - 8, - 1 - ], - [ - 1, - 4, - 1, - 4 - ], - [ - 1, - 2, - 1, - 2, - 1, - 2 - ], - [ - 1, - 1, - 1, - 1, - 1 - ] - ]', 'mlp_ratio': 'mlp_ratio=3.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'layer_scale_init_value': 'layer_scale_init_value=0.0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='DinatModel', library='transformers', import_path='transformers.models.dinat'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=14', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'layerscale_value': 'layerscale_value=1.0', 'drop_path_rate': 'drop_path_rate=0.0', 'use_swiglu_ffn': 'use_swiglu_ffn=False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True', 'use_mask_token': 'use_mask_token=True' -}, model_name='Dinov2Model', library='transformers', import_path='transformers.models.dinov2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'layerscale_value': 'layerscale_value=1.0', 'drop_path_rate': 'drop_path_rate=0.0', 'use_swiglu_ffn': 'use_swiglu_ffn=False', 'num_register_tokens': 'num_register_tokens=4', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True' -}, model_name='Dinov2WithRegistersModel', library='transformers', import_path='transformers.models.dinov2_with_registers'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels: int = 3', 'hidden_sizes': 'hidden_sizes: Optional[list[int - ] - ] = None', 'depths': 'depths: Optional[list[int - ] - ] = None', 'hidden_act': "hidden_act: str = 'gelu'", 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'layer_scale_init_value': 'layer_scale_init_value: float = 1e-06', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'image_size': 'image_size: int = 224', 'out_features': 'out_features: Optional[list[str - ] - ] = None', 'out_indices': 'out_indices: Optional[list[int - ] - ] = None' -}, model_name='DINOv3ConvNextModel', library='transformers', import_path='transformers.models.dinov3_convnext'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size: int = 16', 'hidden_size': 'hidden_size: int = 384', 'intermediate_size': 'intermediate_size: int = 1536', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 6', 'hidden_act': "hidden_act: str = 'gelu'", 'attention_dropout': 'attention_dropout: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-05', 'rope_theta': 'rope_theta: float = 100.0', 'image_size': 'image_size: int = 224', 'num_channels': 'num_channels: int = 3', 'query_bias': 'query_bias: bool = True', 'key_bias': 'key_bias: bool = False', 'value_bias': 'value_bias: bool = True', 'proj_bias': 'proj_bias: bool = True', 'mlp_bias': 'mlp_bias: bool = True', 'layerscale_value': 'layerscale_value: float = 1.0', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'use_gated_mlp': 'use_gated_mlp: bool = False', 'num_register_tokens': 'num_register_tokens: int = 0', 'pos_embed_shift': 'pos_embed_shift: Optional[float - ] = None', 'pos_embed_jitter': 'pos_embed_jitter: Optional[float - ] = None', 'pos_embed_rescale': 'pos_embed_rescale: Optional[float - ] = 2.0', 'out_features': 'out_features: Optional[list[str - ] - ] = None', 'out_indices': 'out_indices: Optional[list[int - ] - ] = None', 'apply_layernorm': 'apply_layernorm: bool = True', 'reshape_hidden_states': 'reshape_hidden_states: bool = True' -}, model_name='DINOv3ViTModel', library='transformers', import_path='transformers.models.dinov3_vit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'max_position_embeddings': 'max_position_embeddings=512', 'sinusoidal_pos_embds': 'sinusoidal_pos_embds=False', 'n_layers': 'n_layers=6', 'n_heads': 'n_heads=12', 'dim': 'dim=768', 'hidden_dim': 'hidden_dim=3072', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation': "activation='gelu'", 'initializer_range': 'initializer_range=0.02', 'qa_dropout': 'qa_dropout=0.1', 'seq_classif_dropout': 'seq_classif_dropout=0.2', 'pad_token_id': 'pad_token_id=0' -}, model_name='DistilBertModel', library='transformers', import_path='transformers.models.distilbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32768', 'hidden_size': 'hidden_size: Optional[int - ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int - ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'keep_window_size': 'keep_window_size: Optional[int - ] = 2048', 'is_moe': 'is_moe: Optional[bool - ] = False', 'num_experts': 'num_experts: Optional[int - ] = 16384', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 64', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001' -}, model_name='DogeModel', library='transformers', import_path='transformers.models.doge'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'num_heads': 'num_heads=[ - 3, - 6, - 12, - 24 - ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' -}, model_name='DonutSwinModel', library='transformers', import_path='transformers.models.donut'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 152064', 'hidden_size': 'hidden_size: Optional[int - ] = 4608', 'intermediate_size': 'intermediate_size: Optional[int - ] = 10944', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1408', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 62', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'n_shared_experts': 'n_shared_experts: Optional[int - ] = None', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = None', 'n_group': 'n_group: Optional[int - ] = 1', 'topk_group': 'topk_group: Optional[int - ] = 1', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = None', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int - ] = 0', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 1.0', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 62', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Dots1Model', library='transformers', import_path='transformers.models.dots1'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'projection_dim': 'projection_dim: int = 0' -}, model_name='DPRQuestionEncoder', library='transformers', import_path='transformers.models.dpr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='DPRQuestionEncoderTokenizerFast', library='transformers', import_path='transformers.models.dpr'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=384', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'is_hybrid': 'is_hybrid=False', 'qkv_bias': 'qkv_bias=True', 'backbone_out_indices': 'backbone_out_indices=[ - 2, - 5, - 8, - 11 - ]', 'readout_type': "readout_type='project'", 'reassemble_factors': 'reassemble_factors=[ - 4, - 2, - 1, - 0.5 - ]', 'neck_hidden_sizes': 'neck_hidden_sizes=[ - 96, - 192, - 384, - 768 - ]', 'fusion_hidden_size': 'fusion_hidden_size=256', 'head_in_index': 'head_in_index=-1', 'use_batch_norm_in_fusion_residual': 'use_batch_norm_in_fusion_residual=False', 'use_bias_in_fusion_residual': 'use_bias_in_fusion_residual=None', 'add_projection': 'add_projection=False', 'use_auxiliary_head': 'use_auxiliary_head=True', 'auxiliary_loss_weight': 'auxiliary_loss_weight=0.4', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255', 'semantic_classifier_dropout': 'semantic_classifier_dropout=0.1', 'backbone_featmap_shape': 'backbone_featmap_shape=[ - 1, - 1024, - 24, - 24 - ]', 'neck_ignore_stages': 'neck_ignore_stages=[ - 0, - 1 - ]', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" -}, model_name='DPTModel', library='transformers', import_path='transformers.models.dpt'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='EdgeTamModel', library='transformers', import_path='transformers.models.edgetam'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1024', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=-1', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=2', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_mlp_hidden_size': 'memory_attention_mlp_hidden_size=2048', 'memory_attention_mlp_hidden_act': "memory_attention_mlp_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_k_sizes': 'memory_attention_rope_k_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'perceiver_resampler_num_latents': 'perceiver_resampler_num_latents=256', 'perceiver_resampler_num_latents_2d': 'perceiver_resampler_num_latents_2d=256', 'perceiver_resampler_hidden_size': 'perceiver_resampler_hidden_size=64', 'perceiver_resampler_mlp_intermediate_size': 'perceiver_resampler_mlp_intermediate_size=256', 'perceiver_resampler_num_attention_heads': 'perceiver_resampler_num_attention_heads=1', 'perceiver_resampler_attention_head_dim': 'perceiver_resampler_attention_head_dim=64', 'perceiver_resampler_num_layers': 'perceiver_resampler_num_layers=2', 'perceiver_resampler_hidden_dropout': 'perceiver_resampler_hidden_dropout=0.0', 'perceiver_resampler_attention_dropout': 'perceiver_resampler_attention_dropout=0.0', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" -}, model_name='EdgeTamVideoModel', library='transformers', import_path='transformers.models.edgetam_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone_channel_list': 'backbone_channel_list=None', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'fpn_kernel_size': 'fpn_kernel_size=1', 'fpn_stride': 'fpn_stride=1', 'fpn_padding': 'fpn_padding=0', 'fpn_top_down_levels': 'fpn_top_down_levels=None', 'num_feature_levels': 'num_feature_levels=3', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' -}, model_name='EdgeTamVisionModel', library='transformers', import_path='transformers.models.edgetam'), ModelAttributes(model=, model_type='model', model_parameters={'stage_num_blocks': 'stage_num_blocks: Optional[list[int - ] - ] = None', 'out_features': 'out_features: Optional[list[int - ] - ] = None', 'stage_stride': 'stage_stride: Optional[list[int - ] - ] = None', 'hidden_size': 'hidden_size: int = 256', 'activation_function': "activation_function: str = 'relu'", 'q_aggregation_kernel_size': 'q_aggregation_kernel_size: int = 4', 'kv_aggregation_kernel_size': 'kv_aggregation_kernel_size: int = 4', 'q_aggregation_stride': 'q_aggregation_stride: int = 4', 'kv_aggregation_stride': 'kv_aggregation_stride: int = 4', 'num_attention_layers': 'num_attention_layers: int = 4', 'num_attention_heads': 'num_attention_heads: int = 8', 'attention_dropout': 'attention_dropout: float = 0.0', 'attention_bias': 'attention_bias: bool = False', 'mlp_activation_function': "mlp_activation_function: str = 'leaky_relu'", 'coarse_matching_skip_softmax': 'coarse_matching_skip_softmax: bool = False', 'coarse_matching_threshold': 'coarse_matching_threshold: float = 0.2', 'coarse_matching_temperature': 'coarse_matching_temperature: float = 0.1', 'coarse_matching_border_removal': 'coarse_matching_border_removal: int = 2', 'fine_kernel_size': 'fine_kernel_size: int = 8', 'batch_norm_eps': 'batch_norm_eps: float = 1e-05', 'rope_parameters': 'rope_parameters: Optional[dict - ] = None', 'fine_matching_slice_dim': 'fine_matching_slice_dim: int = 8', 'fine_matching_regress_temperature': 'fine_matching_regress_temperature: float = 10.0', 'initializer_range': 'initializer_range: float = 0.02' -}, model_name='EfficientLoFTRModel', library='transformers', import_path='transformers.models.efficientloftr'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels: int = 3', 'image_size': 'image_size: int = 600', 'width_coefficient': 'width_coefficient: float = 2.0', 'depth_coefficient': 'depth_coefficient: float = 3.1', 'depth_divisor': 'depth_divisor: int = 8', 'kernel_sizes': 'kernel_sizes: list[int - ] = [ - 3, - 3, - 5, - 3, - 5, - 5, - 3 - ]', 'in_channels': 'in_channels: list[int - ] = [ - 32, - 16, - 24, - 40, - 80, - 112, - 192 - ]', 'out_channels': 'out_channels: list[int - ] = [ - 16, - 24, - 40, - 80, - 112, - 192, - 320 - ]', 'depthwise_padding': 'depthwise_padding: list[int - ] = []', 'strides': 'strides: list[int - ] = [ - 1, - 2, - 2, - 2, - 1, - 2, - 1 - ]', 'num_block_repeats': 'num_block_repeats: list[int - ] = [ - 1, - 2, - 2, - 3, - 3, - 4, - 1 - ]', 'expand_ratios': 'expand_ratios: list[int - ] = [ - 1, - 6, - 6, - 6, - 6, - 6, - 6 - ]', 'squeeze_expansion_ratio': 'squeeze_expansion_ratio: float = 0.25', 'hidden_act': "hidden_act: str = 'swish'", 'hidden_dim': 'hidden_dim: int = 2560', 'pooling_type': "pooling_type: str = 'mean'", 'initializer_range': 'initializer_range: float = 0.02', 'batch_norm_eps': 'batch_norm_eps: float = 0.001', 'batch_norm_momentum': 'batch_norm_momentum: float = 0.99', 'dropout_rate': 'dropout_rate: float = 0.5', 'drop_connect_rate': 'drop_connect_rate: float = 0.2' -}, model_name='EfficientNetModel', library='transformers', import_path='transformers.models.efficientnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'embedding_size': 'embedding_size=128', 'hidden_size': 'hidden_size=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=4', 'intermediate_size': 'intermediate_size=1024', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': "summary_activation='gelu'", 'summary_last_dropout': 'summary_last_dropout=0.1', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='ElectraModel', library='transformers', import_path='transformers.models.electra'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vq_config': 'vq_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3VQVAEConfig - ] = None', 'text_config': 'text_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3TextConfig - ] = None', 'vocabulary_map': 'vocabulary_map: Optional[dict[int, int - ] - ] = None' -}, model_name='Emu3Model', library='transformers', import_path='transformers.models.emu3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'target_bandwidths': 'target_bandwidths=[ - 1.5, - 3.0, - 6.0, - 12.0, - 24.0 - ]', 'sampling_rate': 'sampling_rate=24000', 'audio_channels': 'audio_channels=1', 'normalize': 'normalize=False', 'chunk_length_s': 'chunk_length_s=None', 'overlap': 'overlap=None', 'hidden_size': 'hidden_size=128', 'num_filters': 'num_filters=32', 'num_residual_layers': 'num_residual_layers=1', 'upsampling_ratios': 'upsampling_ratios=[ - 8, - 5, - 4, - 2 - ]', 'norm_type': "norm_type='weight_norm'", 'kernel_size': 'kernel_size=7', 'last_kernel_size': 'last_kernel_size=7', 'residual_kernel_size': 'residual_kernel_size=3', 'dilation_growth_rate': 'dilation_growth_rate=2', 'use_causal_conv': 'use_causal_conv=True', 'pad_mode': "pad_mode='reflect'", 'compress': 'compress=2', 'num_lstm_layers': 'num_lstm_layers=2', 'trim_right_ratio': 'trim_right_ratio=1.0', 'codebook_size': 'codebook_size=1024', 'codebook_dim': 'codebook_dim=None', 'use_conv_shortcut': 'use_conv_shortcut=True' -}, model_name='EncodecModel', library='transformers', import_path='transformers.models.encodec'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'task_type_vocab_size': 'task_type_vocab_size=3', 'use_task_id': 'use_task_id=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='ErnieModel', library='transformers', import_path='transformers.models.ernie'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 103424', 'hidden_size': 'hidden_size: Optional[int - ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int - ] = 3072', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 18', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_bias': 'use_bias: Optional[bool - ] = False', 'head_dim': 'head_dim: Optional[int - ] = 128' -}, model_name='Ernie4_5Model', library='transformers', import_path='transformers.models.ernie4_5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 103424', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int - ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_bias': 'use_bias: Optional[int - ] = False', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1536', 'moe_k': 'moe_k: Optional[int - ] = 6', 'moe_num_experts': 'moe_num_experts: Optional[int - ] = 64', 'moe_num_shared_experts': 'moe_num_shared_experts: Optional[int - ] = 2', 'moe_layer_start_index': 'moe_layer_start_index: Optional[int - ] = 1', 'moe_layer_end_index': 'moe_layer_end_index: Optional[int - ] = -1', 'moe_layer_interval': 'moe_layer_interval: Optional[int - ] = 1', 'moe_norm_min': 'moe_norm_min: Optional[int - ] = 1e-12', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001' -}, model_name='Ernie4_5_MoeModel', library='transformers', import_path='transformers.models.ernie4_5_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_start_token_id': 'image_start_token_id=101304', 'image_end_token_id': 'image_end_token_id=101305', 'image_token_id': 'image_token_id=100295', 'video_start_token_id': 'video_start_token_id=101306', 'video_end_token_id': 'video_end_token_id=101307', 'video_token_id': 'video_token_id=103367' -}, model_name='Ernie4_5_VL_MoeModel', library='transformers', import_path='transformers.models.ernie4_5_vl_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'mask_token_id': 'mask_token_id=None', 'pad_token_id': 'pad_token_id=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1026', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'position_embedding_type': "position_embedding_type='absolute'", 'emb_layer_norm_before': 'emb_layer_norm_before=None', 'token_dropout': 'token_dropout=False', 'is_folding_model': 'is_folding_model=False', 'esmfold_config': 'esmfold_config=None', 'vocab_list': 'vocab_list=None' -}, model_name='EsmModel', library='transformers', import_path='transformers.models.esm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'unk_token': "unk_token=''", 'cls_token': "cls_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'eos_token': "eos_token=''" -}, model_name='EsmTokenizer', library='transformers', import_path='transformers.models.esm'), ModelAttributes(model=, model_type='model', model_parameters={'protein_encoder_config': 'protein_encoder_config: Optional[dict - ] = None', 'vocab_size': 'vocab_size: Optional[int - ] = 128256', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'aligner_ffn_mult': 'aligner_ffn_mult: Optional[int - ] = 4', 'aligner_enable_bias': 'aligner_enable_bias: Optional[bool - ] = True', 'aligner_attention_probs_dropout_prob': 'aligner_attention_probs_dropout_prob: Optional[float - ] = 0.1', 'aligner_num_add_layers': 'aligner_num_add_layers: Optional[int - ] = 8', 'resampler_depth': 'resampler_depth: Optional[int - ] = 6', 'resampler_dim_head': 'resampler_dim_head: Optional[int - ] = 64', 'resampler_heads': 'resampler_heads: Optional[int - ] = 8', 'resampler_num_latents': 'resampler_num_latents: Optional[int - ] = 64', 'resampler_ff_mult': 'resampler_ff_mult: Optional[int - ] = 4', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int - ] = 128009', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False' -}, model_name='EvollaModel', library='transformers', import_path='transformers.models.evolla'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 102400', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'sliding_window_pattern': 'sliding_window_pattern: Optional[int - ] = 4', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Exaone4Model', library='transformers', import_path='transformers.models.exaone4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 65024', 'hidden_size': 'hidden_size: Optional[int - ] = 4544', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 71', 'num_ln_in_parallel_attn': 'num_ln_in_parallel_attn: Optional[int - ] = None', 'layer_norm_epsilon': 'layer_norm_epsilon: Optional[int - ] = 1e-05', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_kv_heads': 'num_kv_heads: Optional[int - ] = None', 'alibi': 'alibi: Optional[bool - ] = False', 'new_decoder_architecture': 'new_decoder_architecture: Optional[bool - ] = False', 'multi_query': 'multi_query: Optional[bool - ] = True', 'parallel_attn': 'parallel_attn: Optional[bool - ] = True', 'bias': 'bias: Optional[bool - ] = False', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 11', 'eos_token_id': 'eos_token_id: Optional[int - ] = 11', 'ffn_hidden_size': 'ffn_hidden_size: Optional[int - ] = None', 'activation': "activation: Optional[str] = 'gelu'" -}, model_name='FalconModel', library='transformers', import_path='transformers.models.falcon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 128000', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'num_logits_to_keep': 'num_logits_to_keep: Optional[int - ] = 1', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mamba_d_ssm': 'mamba_d_ssm: Optional[int - ] = 1024', 'mamba_n_heads': 'mamba_n_heads: Optional[int - ] = 128', 'mamba_d_head': "mamba_d_head: Optional[str] = 'auto'", 'mamba_n_groups': 'mamba_n_groups: Optional[int - ] = 1', 'mamba_d_state': 'mamba_d_state: Optional[int - ] = 256', 'mamba_d_conv': 'mamba_d_conv: Optional[int - ] = 4', 'mamba_expand': 'mamba_expand: Optional[int - ] = 2', 'mamba_chunk_size': 'mamba_chunk_size: Optional[int - ] = 256', 'mamba_conv_bias': 'mamba_conv_bias: Optional[bool - ] = True', 'mamba_proj_bias': 'mamba_proj_bias: Optional[bool - ] = False', 'mamba_norm_before_gate': 'mamba_norm_before_gate: Optional[bool - ] = True', 'mamba_rms_norm': 'mamba_rms_norm: Optional[bool - ] = False', 'projectors_bias': 'projectors_bias: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'lm_head_multiplier': 'lm_head_multiplier: Optional[float - ] = 1.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float - ] = 1.0', 'mlp_multipliers': 'mlp_multipliers: Optional[int - ] = None', 'key_multiplier': 'key_multiplier: Optional[int - ] = None', 'attention_out_multiplier': 'attention_out_multiplier: Optional[int - ] = None', 'attention_in_multiplier': 'attention_in_multiplier: Optional[int - ] = None', 'ssm_multipliers': 'ssm_multipliers: Optional[int - ] = None', 'ssm_in_multiplier': 'ssm_in_multiplier: Optional[int - ] = None', 'ssm_out_multiplier': 'ssm_out_multiplier: Optional[int - ] = None' -}, model_name='FalconH1Model', library='transformers', import_path='transformers.models.falcon_h1'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50280', 'hidden_size': 'hidden_size=768', 'state_size': 'state_size=16', 'num_hidden_layers': 'num_hidden_layers=32', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_scale': 'time_step_scale=1.0', 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_init_scheme': "time_step_init_scheme='random'", 'time_step_floor': 'time_step_floor=0.0001', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'use_falcon_mambapy': 'use_falcon_mambapy=False', 'mixer_rms_eps': 'mixer_rms_eps=1e-06' -}, model_name='FalconMambaModel', library='transformers', import_path='transformers.models.falcon_mamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151646', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='full'", 'vision_feature_layer': 'vision_feature_layer=-1', 'multimodal_projector_bias': 'multimodal_projector_bias=True' -}, model_name='FastVlmModel', library='transformers', import_path='transformers.models.fast_vlm'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=384', 'vocab_size': 'vocab_size=78', 'num_mel_bins': 'num_mel_bins=80', 'encoder_num_attention_heads': 'encoder_num_attention_heads=2', 'encoder_layers': 'encoder_layers=4', 'encoder_linear_units': 'encoder_linear_units=1536', 'decoder_layers': 'decoder_layers=4', 'decoder_num_attention_heads': 'decoder_num_attention_heads=2', 'decoder_linear_units': 'decoder_linear_units=1536', 'speech_decoder_postnet_layers': 'speech_decoder_postnet_layers=5', 'speech_decoder_postnet_units': 'speech_decoder_postnet_units=256', 'speech_decoder_postnet_kernel': 'speech_decoder_postnet_kernel=5', 'positionwise_conv_kernel_size': 'positionwise_conv_kernel_size=3', 'encoder_normalize_before': 'encoder_normalize_before=False', 'decoder_normalize_before': 'decoder_normalize_before=False', 'encoder_concat_after': 'encoder_concat_after=False', 'decoder_concat_after': 'decoder_concat_after=False', 'reduction_factor': 'reduction_factor=1', 'speaking_speed': 'speaking_speed=1.0', 'use_macaron_style_in_conformer': 'use_macaron_style_in_conformer=True', 'use_cnn_in_conformer': 'use_cnn_in_conformer=True', 'encoder_kernel_size': 'encoder_kernel_size=7', 'decoder_kernel_size': 'decoder_kernel_size=31', 'duration_predictor_layers': 'duration_predictor_layers=2', 'duration_predictor_channels': 'duration_predictor_channels=256', 'duration_predictor_kernel_size': 'duration_predictor_kernel_size=3', 'energy_predictor_layers': 'energy_predictor_layers=2', 'energy_predictor_channels': 'energy_predictor_channels=256', 'energy_predictor_kernel_size': 'energy_predictor_kernel_size=3', 'energy_predictor_dropout': 'energy_predictor_dropout=0.5', 'energy_embed_kernel_size': 'energy_embed_kernel_size=1', 'energy_embed_dropout': 'energy_embed_dropout=0.0', 'stop_gradient_from_energy_predictor': 'stop_gradient_from_energy_predictor=False', 'pitch_predictor_layers': 'pitch_predictor_layers=5', 'pitch_predictor_channels': 'pitch_predictor_channels=256', 'pitch_predictor_kernel_size': 'pitch_predictor_kernel_size=5', 'pitch_predictor_dropout': 'pitch_predictor_dropout=0.5', 'pitch_embed_kernel_size': 'pitch_embed_kernel_size=1', 'pitch_embed_dropout': 'pitch_embed_dropout=0.0', 'stop_gradient_from_pitch_predictor': 'stop_gradient_from_pitch_predictor=True', 'encoder_dropout_rate': 'encoder_dropout_rate=0.2', 'encoder_positional_dropout_rate': 'encoder_positional_dropout_rate=0.2', 'encoder_attention_dropout_rate': 'encoder_attention_dropout_rate=0.2', 'decoder_dropout_rate': 'decoder_dropout_rate=0.2', 'decoder_positional_dropout_rate': 'decoder_positional_dropout_rate=0.2', 'decoder_attention_dropout_rate': 'decoder_attention_dropout_rate=0.2', 'duration_predictor_dropout_rate': 'duration_predictor_dropout_rate=0.2', 'speech_decoder_postnet_dropout': 'speech_decoder_postnet_dropout=0.5', 'max_source_positions': 'max_source_positions=5000', 'use_masking': 'use_masking=True', 'use_weighted_masking': 'use_weighted_masking=False', 'num_speakers': 'num_speakers=None', 'num_languages': 'num_languages=None', 'speaker_embed_dim': 'speaker_embed_dim=None', 'is_encoder_decoder': 'is_encoder_decoder=True', 'convolution_bias': 'convolution_bias=True' -}, model_name='FastSpeech2ConformerModel', library='transformers', import_path='transformers.models.fastspeech2_conformer'), ModelAttributes(model=, model_type='model', model_parameters={'model_config': 'model_config: Optional[dict - ] = None', 'vocoder_config': 'vocoder_config: Optional[dict - ] = None' -}, model_name='FastSpeech2ConformerWithHifiGan', library='transformers', import_path='transformers.models.fastspeech2_conformer'), ModelAttributes(model=, model_type='model', model_parameters={'pre_norm': 'pre_norm=False', 'layerdrop': 'layerdrop=0.0', 'vocab_size': 'vocab_size=30145', 'emb_dim': 'emb_dim=2048', 'n_layers': 'n_layers=12', 'n_heads': 'n_heads=16', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'gelu_activation': 'gelu_activation=True', 'sinusoidal_embeddings': 'sinusoidal_embeddings=False', 'causal': 'causal=False', 'asm': 'asm=False', 'n_langs': 'n_langs=1', 'use_lang_emb': 'use_lang_emb=True', 'max_position_embeddings': 'max_position_embeddings=512', 'embed_init_std': 'embed_init_std=0.02209708691207961', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'init_std': 'init_std=0.02', 'bos_index': 'bos_index=0', 'eos_index': 'eos_index=1', 'pad_index': 'pad_index=2', 'unk_index': 'unk_index=3', 'mask_index': 'mask_index=5', 'is_encoder': 'is_encoder=True', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'mask_token_id': 'mask_token_id=0', 'lang_id': 'lang_id=0', 'pad_token_id': 'pad_token_id=2', 'bos_token_id': 'bos_token_id=0' -}, model_name='FlaubertModel', library='transformers', import_path='transformers.models.flaubert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'do_lowercase': 'do_lowercase=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", 'lang2id': 'lang2id=None', 'id2lang': 'id2lang=None' -}, model_name='FlaubertTokenizer', library='transformers', import_path='transformers.models.flaubert'), ModelAttributes(model=, model_type='model', model_parameters={'image_config': 'image_config: Optional[dict[str, Any - ] - ] = None', 'text_config': 'text_config: Optional[dict[str, Any - ] - ] = None', 'multimodal_config': 'multimodal_config: Optional[dict[str, Any - ] - ] = None', 'image_codebook_config': 'image_codebook_config: Optional[dict[str, Any - ] - ] = None', 'hidden_size': 'hidden_size: int = 768', 'layer_norm_eps': 'layer_norm_eps: float = 1e-12', 'projection_dim': 'projection_dim: int = 768', 'init_codebook': 'init_codebook: bool = True', 'logit_scale_init_value': 'logit_scale_init_value: float = 2.6592', 'initializer_range': 'initializer_range: float = 0.02', 'ce_ignore_index': 'ce_ignore_index: int = -100', 'mim_weight': 'mim_weight: float = 1.0', 'mlm_weight': 'mlm_weight: float = 1.0', 'global_contrastive_weight': 'global_contrastive_weight: float = 1.0', 'itm_weight': 'itm_weight: float = 1.0', 'mmm_image_weight': 'mmm_image_weight: float = 1.0', 'mmm_text_weight': 'mmm_text_weight: float = 1.0', 'global_backprop_contrastive': 'global_backprop_contrastive: bool = True', 'skip_unmasked_multimodal_encoder': 'skip_unmasked_multimodal_encoder: bool = True', 'return_loss': 'return_loss: bool = True' -}, model_name='FlavaModel', library='transformers', import_path='transformers.models.flava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 100352', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 100277', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'eos_token_id': 'eos_token_id: Optional[int - ] = 100257', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 5', 'num_experts': 'num_experts: Optional[int - ] = 7', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.01', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False' -}, model_name='FlexOlmoModel', library='transformers', import_path='transformers.models.flex_olmo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=51289', 'is_encoder_decoder': 'is_encoder_decoder=True' -}, model_name='Florence2Model', library='transformers', import_path='transformers.models.florence2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_new'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=4', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_tpu_fourier_optimizations': 'use_tpu_fourier_optimizations=False', 'tpu_short_seq_length': 'tpu_short_seq_length=512', 'pad_token_id': 'pad_token_id=3', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' -}, model_name='FNetModel', library='transformers', import_path='transformers.models.fnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='FNetTokenizer', library='transformers', import_path='transformers.models.fnet'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'use_conv_embed': 'use_conv_embed=False', 'hidden_sizes': 'hidden_sizes=[ - 192, - 384, - 768, - 768 - ]', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'focal_levels': 'focal_levels=[ - 2, - 2, - 2, - 2 - ]', 'focal_windows': 'focal_windows=[ - 3, - 3, - 3, - 3 - ]', 'hidden_act': "hidden_act='gelu'", 'mlp_ratio': 'mlp_ratio=4.0', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'use_layerscale': 'use_layerscale=False', 'layerscale_value': 'layerscale_value=0.0001', 'use_post_layernorm': 'use_post_layernorm=False', 'use_post_layernorm_in_modulation': 'use_post_layernorm_in_modulation=False', 'normalize_modulator': 'normalize_modulator=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='FocalNetModel', library='transformers', import_path='transformers.models.focalnet'), ModelAttributes(model=, model_type='model', model_parameters={'langs': "langs=['en', 'de']", 'src_vocab_size': 'src_vocab_size=42024', 'tgt_vocab_size': 'tgt_vocab_size=42024', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'max_length': 'max_length=200', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_layers': 'encoder_layers=12', 'encoder_attention_heads': 'encoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_layers': 'decoder_layers=12', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'attention_dropout': 'attention_dropout=0.0', 'dropout': 'dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'is_encoder_decoder': 'is_encoder_decoder=True', 'scale_embedding': 'scale_embedding=True', 'tie_word_embeddings': 'tie_word_embeddings=False', 'num_beams': 'num_beams=5', 'length_penalty': 'length_penalty=1.0', 'early_stopping': 'early_stopping=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2', 'common_kwargs': '**common_kwargs' -}, model_name='FSMTModel', library='transformers', import_path='transformers.models.fsmt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'langs': 'langs=None', 'src_vocab_file': 'src_vocab_file=None', 'tgt_vocab_file': 'tgt_vocab_file=None', 'merges_file': 'merges_file=None', 'do_lower_case': 'do_lower_case=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''" -}, model_name='FSMTTokenizer', library='transformers', import_path='transformers.models.fsmt'), ModelAttributes(model=, model_type='model', model_parameters=None, model_name='FunnelModel', library='transformers', import_path='transformers.models.funnel'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = ''", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = ''", 'mask_token': "mask_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'clean_text': 'clean_text: bool = True', 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None', 'wordpieces_prefix': "wordpieces_prefix: str = '##'" -}, model_name='FunnelTokenizer', library='transformers', import_path='transformers.models.funnel'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 262144', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 16384', 'image_size': 'image_size: Optional[int - ] = 300', 'patch_size': 'patch_size: Optional[int - ] = 30', 'num_channels': 'num_channels: Optional[int - ] = 3', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool - ] = True', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'image_token_id': 'image_token_id: Optional[int - ] = 71011', 'text_config': 'text_config: Optional[dict - ] = None' -}, model_name='FuyuModel', library='transformers', import_path='transformers.models.fuyu'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int - ] = 24576', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 16', 'head_dim': 'head_dim: Optional[int - ] = 256', 'hidden_act': "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool - ] = None' -}, model_name='GemmaModel', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int - ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'head_dim': 'head_dim: Optional[int - ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int - ] = 256', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float - ] = 30.0', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float - ] = 50.0', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool - ] = None' -}, model_name='Gemma2Model', library='transformers', import_path='transformers.models.gemma2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Union[transformers.models.gemma3.configuration_gemma3.Gemma3TextConfig, dict[str, Any - ], NoneType - ] = None', 'vision_config': 'vision_config: Union[transformers.models.siglip.configuration_siglip.SiglipVisionConfig, dict[str, Any - ], NoneType - ] = None', 'mm_tokens_per_image': 'mm_tokens_per_image: int = 256', 'boi_token_index': 'boi_token_index: int = 255999', 'eoi_token_index': 'eoi_token_index: int = 256000', 'image_token_index': 'image_token_index: int = 262144', 'initializer_range': 'initializer_range: float = 0.02' -}, model_name='Gemma3Model', library='transformers', import_path='transformers.models.gemma3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 262208', 'hidden_size': 'hidden_size: Optional[int - ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int - ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'head_dim': 'head_dim: Optional[int - ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int - ] = 256', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float - ] = None', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float - ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_bidirectional_attention': 'use_bidirectional_attention: Optional[bool - ] = False' -}, model_name='Gemma3TextModel', library='transformers', import_path='transformers.models.gemma3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nTextConfig, dict[str, Any - ], NoneType - ] = None', 'vision_config': 'vision_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nVisionConfig, dict[str, Any - ], NoneType - ] = None', 'audio_config': 'audio_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nAudioConfig, dict[str, Any - ], NoneType - ] = None', 'audio_soft_tokens_per_image': 'audio_soft_tokens_per_image: int = 188', 'vision_soft_tokens_per_image': 'vision_soft_tokens_per_image: int = 256', 'boi_token_id': 'boi_token_id: int = 255999', 'eoi_token_id': 'eoi_token_id: int = 262144', 'image_token_id': 'image_token_id: int = 262145', 'boa_token_id': 'boa_token_id: int = 256000', 'eoa_token_id': 'eoa_token_id: int = 262272', 'audio_token_id': 'audio_token_id: int = 262273', 'initializer_range': 'initializer_range: float = 0.02' -}, model_name='Gemma3nModel', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 128', 'vocab_offset': 'vocab_offset: int = 262272', 'input_feat_size': 'input_feat_size: int = 128', 'hidden_size': 'hidden_size: int = 1536', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'gradient_clipping': 'gradient_clipping: float = 10000000000.0', 'conf_attention_chunk_size': 'conf_attention_chunk_size: int = 12', 'conf_attention_context_left': 'conf_attention_context_left: int = 13', 'conf_attention_context_right': 'conf_attention_context_right: int = 0', 'conf_attention_logit_cap': 'conf_attention_logit_cap: float = 50.0', 'conf_num_attention_heads': 'conf_num_attention_heads: int = 8', 'conf_num_hidden_layers': 'conf_num_hidden_layers: int = 12', 'conf_conv_kernel_size': 'conf_conv_kernel_size: int = 5', 'conf_reduction_factor': 'conf_reduction_factor: int = 4', 'conf_residual_weight': 'conf_residual_weight: float = 0.5', 'sscp_conv_channel_size': 'sscp_conv_channel_size: tuple[int, int - ] = (128, - 32)', 'sscp_conv_group_norm_eps': 'sscp_conv_group_norm_eps: float = 0.001', 'sscp_conv_kernel_size': 'sscp_conv_kernel_size: tuple[tuple[int, int - ], tuple[int, int - ] - ] = ((3, - 3), (3, - 3))', 'sscp_conv_stride_size': 'sscp_conv_stride_size: tuple[tuple[int, int - ], tuple[int, int - ] - ] = ((2, - 2), (2, - 2))' -}, model_name='Gemma3nAudioEncoder', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 262400', 'vocab_size_per_layer_input': 'vocab_size_per_layer_input: int = 262144', 'hidden_size': 'hidden_size: int = 2048', 'hidden_size_per_layer_input': 'hidden_size_per_layer_input: int = 256', 'intermediate_size': 'intermediate_size: Union[int, collections.abc.Sequence[int - ] - ] = 16384', 'num_hidden_layers': 'num_hidden_layers: int = 35', 'num_attention_heads': 'num_attention_heads: int = 8', 'num_key_value_heads': 'num_key_value_heads: int = 2', 'head_dim': 'head_dim: int = 256', 'hidden_activation': "hidden_activation: str = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: int = 32768', 'initializer_range': 'initializer_range: float = 0.02', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'pad_token_id': 'pad_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 2', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: bool = False', 'attention_dropout': 'attention_dropout: float = 0.0', 'sliding_window': 'sliding_window: int = 512', 'layer_types': 'layer_types: Optional[collections.abc.Sequence[str - ] - ] = None', 'final_logit_softcapping': 'final_logit_softcapping: float = 30.0', 'altup_active_idx': 'altup_active_idx: int = 0', 'altup_coef_clip': 'altup_coef_clip: float = 120.0', 'altup_correct_scale': 'altup_correct_scale: bool = True', 'altup_num_inputs': 'altup_num_inputs: int = 4', 'num_kv_shared_layers': 'num_kv_shared_layers: int = 15', 'laurel_rank': 'laurel_rank: int = 64', 'activation_sparsity_pattern': 'activation_sparsity_pattern: Union[float, collections.abc.Sequence[float - ], NoneType - ] = None' -}, model_name='Gemma3nTextModel', library='transformers', import_path='transformers.models.gemma3n'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'_resnet_': ['' - ] -}, model_name='TimmWrapperModel', library='transformers', import_path='transformers.models.timm_wrapper'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=6', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'tie_word_embeddings': 'tie_word_embeddings=False', 'bos_token_id': 'bos_token_id=101', 'eos_token_id': 'eos_token_id=102', 'num_image_with_embedding': 'num_image_with_embedding=None' -}, model_name='GitModel', library='transformers', import_path='transformers.models.git'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151552', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1.5625e-07', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'pad_token_id': 'pad_token_id: Optional[int - ] = 151329', 'eos_token_id': 'eos_token_id: Optional[list[int - ] - ] = [ - 151329, - 151336, - 151338 - ]', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = True' -}, model_name='GlmModel', library='transformers', import_path='transformers.models.glm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151552', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1.5625e-07', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'pad_token_id': 'pad_token_id: Optional[int - ] = 151329', 'eos_token_id': 'eos_token_id: Optional[list[int - ] - ] = [ - 151329, - 151336, - 151338 - ]', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = True' -}, model_name='Glm4Model', library='transformers', import_path='transformers.models.glm4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151343', 'video_token_id': 'video_token_id=151344', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151361', 'video_end_token_id': 'video_end_token_id=151362' -}, model_name='Glm46VModel', library='transformers', import_path='transformers.models.glm46v'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151552', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 10944', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 46', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 96', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 8', 'n_shared_experts': 'n_shared_experts: Optional[int - ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = 128', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 1.0', 'n_group': 'n_group: Optional[int - ] = 1', 'topk_group': 'topk_group: Optional[int - ] = 1', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int - ] = 1', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = True', 'use_qk_norm': 'use_qk_norm: Optional[bool - ] = False' -}, model_name='Glm4MoeModel', library='transformers', import_path='transformers.models.glm4_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151343', 'video_token_id': 'video_token_id=151344', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151341', 'video_end_token_id': 'video_end_token_id=151342' -}, model_name='Glm4vModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151363', 'video_token_id': 'video_token_id=151364', 'image_start_token_id': 'image_start_token_id=151339', 'image_end_token_id': 'image_end_token_id=151340', 'video_start_token_id': 'video_start_token_id=151341', 'video_end_token_id': 'video_end_token_id=151342' -}, model_name='Glm4vMoeModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151424', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 10944', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 46', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 96', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 65536', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = True', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 8', 'n_shared_experts': 'n_shared_experts: Optional[int - ] = 1', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = 128', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 1.0', 'n_group': 'n_group: Optional[int - ] = 1', 'topk_group': 'topk_group: Optional[int - ] = 1', 'first_k_dense_replace': 'first_k_dense_replace: Optional[int - ] = 1', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = True', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.0001' -}, model_name='Glm4vMoeTextModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='model', model_parameters={'depth': 'depth=24', 'hidden_size': 'hidden_size=1536', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'attention_dropout': 'attention_dropout=0.0', 'num_heads': 'num_heads=12', 'in_channels': 'in_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'spatial_merge_size': 'spatial_merge_size=2', 'temporal_patch_size': 'temporal_patch_size=2', 'out_hidden_size': 'out_hidden_size=4096', 'intermediate_size': 'intermediate_size=13696', 'initializer_range': 'initializer_range=0.02' -}, model_name='Glm4vMoeVisionModel', library='transformers', import_path='transformers.models.glm4v_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151552', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 13696', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 40', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='Glm4vTextModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='model', model_parameters={'depth': 'depth=24', 'hidden_size': 'hidden_size=1536', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'attention_dropout': 'attention_dropout=0.0', 'num_heads': 'num_heads=12', 'in_channels': 'in_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'spatial_merge_size': 'spatial_merge_size=2', 'temporal_patch_size': 'temporal_patch_size=2', 'out_hidden_size': 'out_hidden_size=4096', 'intermediate_size': 'intermediate_size=13696', 'initializer_range': 'initializer_range=0.02' -}, model_name='Glm4vVisionModel', library='transformers', import_path='transformers.models.glm4v'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config=None', 'text_config': 'text_config=None', 'audio_token_id': 'audio_token_id=59260', 'projector_hidden_act': "projector_hidden_act='gelu'" -}, model_name='GlmAsrForConditionalGeneration', library='transformers', import_path='transformers.models.glmasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1280', 'intermediate_size': 'intermediate_size=5120', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=20', 'num_key_value_heads': 'num_key_value_heads=None', 'hidden_act': "hidden_act='gelu'", 'max_position_embeddings': 'max_position_embeddings=1500', 'initializer_range': 'initializer_range=0.02', 'rope_parameters': 'rope_parameters=None', 'attention_dropout': 'attention_dropout=0.0', 'num_mel_bins': 'num_mel_bins=128' -}, model_name='GlmAsrEncoder', library='transformers', import_path='transformers.models.glmasr'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'num_encoder_blocks': 'num_encoder_blocks=4', 'depths': 'depths=[ - 2, - 2, - 2, - 2 - ]', 'sr_ratios': 'sr_ratios=[ - 8, - 4, - 2, - 1 - ]', 'hidden_sizes': 'hidden_sizes=[ - 32, - 64, - 160, - 256 - ]', 'patch_sizes': 'patch_sizes=[ - 7, - 3, - 3, - 3 - ]', 'strides': 'strides=[ - 4, - 2, - 2, - 2 - ]', 'num_attention_heads': 'num_attention_heads=[ - 1, - 2, - 5, - 8 - ]', 'mlp_ratios': 'mlp_ratios=[ - 4, - 4, - 4, - 4 - ]', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'drop_path_rate': 'drop_path_rate=0.1', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=64', 'max_depth': 'max_depth=10', 'head_in_index': 'head_in_index=-1' -}, model_name='GLPNModel', library='transformers', import_path='transformers.models.glpn'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config: Optional[dict - ] = None', 'text_config': 'text_config: Optional[dict - ] = None', 'image_token_index': 'image_token_index: Optional[int - ] = 151859', 'image_seq_length': 'image_seq_length: Optional[int - ] = 576', 'pad_token_id': 'pad_token_id: Optional[int - ] = -1' -}, model_name='GotOcr2Model', library='transformers', import_path='transformers.models.got_ocr2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' -}, model_name='GPT2Model', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' -}, model_name='GPT2Model', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_pytorch_tanh'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'attention_softmax_in_fp32': 'attention_softmax_in_fp32=True', 'scale_attention_softmax_in_fp32': 'scale_attention_softmax_in_fp32=True', 'multi_query': 'multi_query=True' -}, model_name='GPTBigCodeModel', library='transformers', import_path='transformers.models.gpt_bigcode'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50257', 'max_position_embeddings': 'max_position_embeddings=2048', 'hidden_size': 'hidden_size=2048', 'num_layers': 'num_layers=24', 'attention_types': "attention_types=[[['global', 'local'], 12]]", 'num_heads': 'num_heads=16', 'intermediate_size': 'intermediate_size=None', 'window_size': 'window_size=256', 'activation_function': "activation_function='gelu_new'", 'resid_dropout': 'resid_dropout=0.0', 'embed_dropout': 'embed_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'classifier_dropout': 'classifier_dropout=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256' -}, model_name='GPTNeoModel', library='transformers', import_path='transformers.models.gpt_neo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50432', 'hidden_size': 'hidden_size: Optional[int - ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 44', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'intermediate_size': 'intermediate_size: Optional[int - ] = 24576', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'classifier_dropout': 'classifier_dropout: Optional[float - ] = 0.1', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'use_parallel_residual': 'use_parallel_residual: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = True' -}, model_name='GPTNeoXModel', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'intermediate_multiple_size': 'intermediate_multiple_size: Optional[int - ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int - ] = 31996', 'eos_token_id': 'eos_token_id: Optional[int - ] = 31999', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.1', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0' -}, model_name='GPTNeoXJapaneseModel', library='transformers', import_path='transformers.models.gpt_neox_japanese'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'emoji_file': 'emoji_file', 'unk_token': "unk_token='<|endoftext|>'", 'pad_token': "pad_token='<|endoftext|>'", 'bos_token': "bos_token='<|startoftext|>'", 'eos_token': "eos_token='<|endoftext|>'", 'do_clean_text': 'do_clean_text=False' -}, model_name='GPTNeoXJapaneseTokenizer', library='transformers', import_path='transformers.models.gpt_neox_japanese'), ModelAttributes(model=, model_type='model', model_parameters={'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 36', 'num_local_experts': 'num_local_experts: Optional[int - ] = 128', 'vocab_size': 'vocab_size: Optional[int - ] = 201088', 'hidden_size': 'hidden_size: Optional[int - ] = 2880', 'intermediate_size': 'intermediate_size: Optional[int - ] = 2880', 'head_dim': 'head_dim: Optional[int - ] = 64', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'sliding_window': 'sliding_window: Optional[int - ] = 128', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'rope_parameters': "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = {'rope_type': 'yarn', 'factor': 32.0, 'beta_fast': 32.0, 'beta_slow': 1.0, 'truncate': False, 'original_max_position_embeddings': 4096}", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 4', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.9', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='GptOssModel', library='transformers', import_path='transformers.models.gpt_oss'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50400', 'n_positions': 'n_positions=2048', 'n_embd': 'n_embd=4096', 'n_layer': 'n_layer=28', 'n_head': 'n_head=16', 'rotary_dim': 'rotary_dim=64', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='gelu_new'", 'resid_pdrop': 'resid_pdrop=0.0', 'embd_pdrop': 'embd_pdrop=0.0', 'attn_pdrop': 'attn_pdrop=0.0', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='GPTJModel', library='transformers', import_path='transformers.models.gptj'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'embedding_multiplier': 'embedding_multiplier: Optional[float - ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float - ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float - ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float - ] = 1.0' -}, model_name='GraniteModel', library='transformers', import_path='transformers.models.granite'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float - ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float - ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float - ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float - ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001' -}, model_name='GraniteMoeModel', library='transformers', import_path='transformers.models.granitemoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float - ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float - ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float - ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float - ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'shared_intermediate_size': 'shared_intermediate_size: Optional[int - ] = 1024', 'position_embedding_type': 'position_embedding_type: Optional[str - ] = None', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'mamba_n_heads': 'mamba_n_heads: Optional[int - ] = 128', 'mamba_n_groups': 'mamba_n_groups: Optional[int - ] = 1', 'mamba_d_state': 'mamba_d_state: Optional[int - ] = 256', 'mamba_d_head': "mamba_d_head: Optional[str] = 'auto'", 'mamba_d_conv': 'mamba_d_conv: Optional[int - ] = 4', 'mamba_expand': 'mamba_expand: Optional[int - ] = 2', 'mamba_chunk_size': 'mamba_chunk_size: Optional[int - ] = 256', 'mamba_conv_bias': 'mamba_conv_bias: Optional[bool - ] = True', 'mamba_proj_bias': 'mamba_proj_bias: Optional[bool - ] = False' -}, model_name='GraniteMoeHybridModel', library='transformers', import_path='transformers.models.granitemoehybrid'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'embedding_multiplier': 'embedding_multiplier: Optional[float - ] = 1.0', 'logits_scaling': 'logits_scaling: Optional[float - ] = 1.0', 'residual_multiplier': 'residual_multiplier: Optional[float - ] = 1.0', 'attention_multiplier': 'attention_multiplier: Optional[float - ] = 1.0', 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'shared_intermediate_size': 'shared_intermediate_size: Optional[int - ] = 0' -}, model_name='GraniteMoeSharedModel', library='transformers', import_path='transformers.models.granitemoeshared'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'text_config': 'text_config=None', 'num_queries': 'num_queries=900', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=True', 'class_cost': 'class_cost=1.0', 'bbox_cost': 'bbox_cost=5.0', 'giou_cost': 'giou_cost=2.0', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5.0', 'giou_loss_coefficient': 'giou_loss_coefficient=2.0', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False', 'max_text_len': 'max_text_len=256', 'text_enhancer_dropout': 'text_enhancer_dropout=0.0', 'fusion_droppath': 'fusion_droppath=0.1', 'fusion_dropout': 'fusion_dropout=0.0', 'embedding_init_target': 'embedding_init_target=True', 'query_dim': 'query_dim=4', 'decoder_bbox_embed_share': 'decoder_bbox_embed_share=True', 'two_stage_bbox_embed_share': 'two_stage_bbox_embed_share=False', 'positional_embedding_temperature': 'positional_embedding_temperature=20', 'init_std': 'init_std=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' -}, model_name='GroundingDinoModel', library='transformers', import_path='transformers.models.grounding_dino'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=256', 'projection_intermediate_dim': 'projection_intermediate_dim=4096', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='GroupViTModel', library='transformers', import_path='transformers.models.groupvit'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 48000', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int - ] = 7040', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 20', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 20', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-08', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'pad_token_id': 'pad_token_id: Optional[int - ] = 3', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False' -}, model_name='HeliumModel', library='transformers', import_path='transformers.models.helium'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'depths': 'depths=[ - 3, - 4, - 6, - 3 - ]', 'hidden_sizes': 'hidden_sizes=[ - 256, - 512, - 1024, - 2048 - ]', 'hidden_act': "hidden_act='relu'", 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'stem_channels': 'stem_channels=[ - 3, - 32, - 48 - ]', 'stage_in_channels': 'stage_in_channels=[ - 48, - 128, - 512, - 1024 - ]', 'stage_mid_channels': 'stage_mid_channels=[ - 48, - 96, - 192, - 384 - ]', 'stage_out_channels': 'stage_out_channels=[ - 128, - 512, - 1024, - 2048 - ]', 'stage_num_blocks': 'stage_num_blocks=[ - 1, - 1, - 3, - 1 - ]', 'stage_downsample': 'stage_downsample=[False, True, True, True - ]', 'stage_light_block': 'stage_light_block=[False, False, True, True - ]', 'stage_kernel_size': 'stage_kernel_size=[ - 3, - 3, - 5, - 5 - ]', 'stage_numb_of_layers': 'stage_numb_of_layers=[ - 6, - 6, - 6, - 6 - ]', 'use_learnable_affine_block': 'use_learnable_affine_block=False', 'initializer_range': 'initializer_range=0.02' -}, model_name='HGNetV2Backbone', library='transformers', import_path='transformers.models.hgnet_v2'), ModelAttributes(model=, model_type='model', model_parameters={'embed_dim': 'embed_dim=96', 'image_size': 'image_size=[ - 224, - 224 - ]', 'patch_size': 'patch_size=[ - 7, - 7 - ]', 'patch_stride': 'patch_stride=[ - 4, - 4 - ]', 'patch_padding': 'patch_padding=[ - 3, - 3 - ]', 'mlp_ratio': 'mlp_ratio=4.0', 'depths': 'depths=[ - 2, - 3, - 16, - 3 - ]', 'num_heads': 'num_heads=[ - 1, - 2, - 4, - 8 - ]', 'embed_dim_multiplier': 'embed_dim_multiplier=2.0', 'num_query_pool': 'num_query_pool=3', 'query_stride': 'query_stride=[ - 2, - 2 - ]', 'masked_unit_size': 'masked_unit_size=[ - 8, - 8 - ]', 'masked_unit_attention': 'masked_unit_attention=[True, True, False, False - ]', 'drop_path_rate': 'drop_path_rate=0.0', 'num_channels': 'num_channels=3', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_init': 'layer_norm_init=1.0', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=None', 'decoder_depth': 'decoder_depth=None', 'decoder_num_heads': 'decoder_num_heads=None', 'normalize_pixel_loss': 'normalize_pixel_loss=True', 'mask_ratio': 'mask_ratio=0.6', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='HieraModel', library='transformers', import_path='transformers.models.hiera'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_layer_norm': 'feat_proj_layer_norm=True', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'conv_pos_batch_norm': 'conv_pos_batch_norm=False', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' -}, model_name='HubertModel', library='transformers', import_path='transformers.models.hubert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' -}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 290943', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'eod_token_id': 'eod_token_id: Optional[int - ] = 3', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='HunYuanDenseV1Model', library='transformers', import_path='transformers.models.hunyuan_v1_dense'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 290943', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'eod_token_id': 'eod_token_id: Optional[int - ] = 3', 'sep_token_id': 'sep_token_id: Optional[int - ] = 4', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts': 'num_experts: Union[int, list - ] = 1', 'moe_topk': 'moe_topk: Union[int, list - ] = 1', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='HunYuanMoEV1Model', library='transformers', import_path='transformers.models.hunyuan_v1_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'quant_mode': 'quant_mode=False', 'force_dequant': "force_dequant='none'" -}, model_name='IBertModel', library='transformers', import_path='transformers.models.ibert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'additional_vocab_size': 'additional_vocab_size=0', 'hidden_size': 'hidden_size=4096', 'intermediate_size': 'intermediate_size=11008', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=32', 'dropout': 'dropout=0.0', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.02', 'alpha_initializer': "alpha_initializer='zeros'", 'alphas_initializer_range': 'alphas_initializer_range=0.0', 'alpha_type': "alpha_type='float'", 'rms_norm_eps': 'rms_norm_eps=1e-06', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'tie_word_embeddings': 'tie_word_embeddings=False', 'cross_layer_interval': 'cross_layer_interval=1', 'qk_layer_norms': 'qk_layer_norms=False', 'freeze_text_layers': 'freeze_text_layers=True', 'freeze_text_module_exceptions': 'freeze_text_module_exceptions=[]', 'freeze_lm_head': 'freeze_lm_head=False', 'freeze_vision_layers': 'freeze_vision_layers=True', 'freeze_vision_module_exceptions': 'freeze_vision_module_exceptions=[]', 'use_resampler': 'use_resampler=False', 'vision_config': 'vision_config=None', 'perceiver_config': 'perceiver_config=None' -}, model_name='IdeficsModel', library='transformers', import_path='transformers.models.idefics'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=32001', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'perceiver_config': 'perceiver_config=None', 'text_config': 'text_config=None' -}, model_name='Idefics2Model', library='transformers', import_path='transformers.models.idefics2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=128257', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'scale_factor': 'scale_factor=2', 'pad_token_id': 'pad_token_id=128002' -}, model_name='Idefics3Model', library='transformers', import_path='transformers.models.idefics3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1152', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' -}, model_name='Idefics3VisionTransformer', library='transformers', import_path='transformers.models.idefics3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" -}, model_name='IJepaModel', library='transformers', import_path='transformers.models.ijepa'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=513', 'n_positions': 'n_positions=1024', 'n_embd': 'n_embd=512', 'n_layer': 'n_layer=24', 'n_head': 'n_head=8', 'n_inner': 'n_inner=None', 'activation_function': "activation_function='quick_gelu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'scale_attn_weights': 'scale_attn_weights=True', 'tie_word_embeddings': 'tie_word_embeddings=False', 'scale_attn_by_inverse_layer_idx': 'scale_attn_by_inverse_layer_idx=False', 'reorder_and_upcast_attn': 'reorder_and_upcast_attn=False' -}, model_name='ImageGPTModel', library='transformers', import_path='transformers.models.imagegpt'), ModelAttributes(model=, model_type='model', model_parameters={'prediction_length': 'prediction_length: Optional[int - ] = None', 'context_length': 'context_length: Optional[int - ] = None', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'nll'", 'input_size': 'input_size: int = 1', 'lags_sequence': 'lags_sequence: Optional[list[int - ] - ] = None', 'scaling': "scaling: Union[str, bool, NoneType] = 'mean'", 'num_dynamic_real_features': 'num_dynamic_real_features: int = 0', 'num_static_real_features': 'num_static_real_features: int = 0', 'num_static_categorical_features': 'num_static_categorical_features: int = 0', 'num_time_features': 'num_time_features: int = 0', 'cardinality': 'cardinality: Optional[list[int - ] - ] = None', 'embedding_dimension': 'embedding_dimension: Optional[list[int - ] - ] = None', 'd_model': 'd_model: int = 64', 'encoder_ffn_dim': 'encoder_ffn_dim: int = 32', 'decoder_ffn_dim': 'decoder_ffn_dim: int = 32', 'encoder_attention_heads': 'encoder_attention_heads: int = 2', 'decoder_attention_heads': 'decoder_attention_heads: int = 2', 'encoder_layers': 'encoder_layers: int = 2', 'decoder_layers': 'decoder_layers: int = 2', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'dropout': 'dropout: float = 0.05', 'encoder_layerdrop': 'encoder_layerdrop: float = 0.1', 'decoder_layerdrop': 'decoder_layerdrop: float = 0.1', 'attention_dropout': 'attention_dropout: float = 0.1', 'activation_dropout': 'activation_dropout: float = 0.1', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'init_std': 'init_std: float = 0.02', 'attention_type': "attention_type: str = 'prob'", 'sampling_factor': 'sampling_factor: int = 5', 'distil': 'distil: bool = True' -}, model_name='InformerModel', library='transformers', import_path='transformers.models.informer'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'image_token_index': 'image_token_index=None' -}, model_name='InstructBlipModel', library='transformers', import_path='transformers.models.instructblip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'qformer_config': 'qformer_config=None', 'text_config': 'text_config=None', 'num_query_tokens': 'num_query_tokens=32', 'video_token_index': 'video_token_index=None' -}, model_name='InstructBlipVideoModel', library='transformers', import_path='transformers.models.instructblipvideo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151667', 'image_seq_length': 'image_seq_length=256', 'downsample_ratio': 'downsample_ratio=0.5', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_layer': 'vision_feature_layer=-1', 'vision_feature_select_strategy': "vision_feature_select_strategy='default'" -}, model_name='InternVLModel', library='transformers', import_path='transformers.models.internvl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'attention_bias': 'attention_bias=False', 'use_qk_norm': 'use_qk_norm=False', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_dropout': 'attention_dropout=0.0', 'projection_dropout': 'projection_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'norm_type': "norm_type='layer_norm'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=[ - 448, - 448 - ]', 'patch_size': 'patch_size=[ - 14, - 14 - ]', 'num_channels': 'num_channels=3', 'use_mask_token': 'use_mask_token=False', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=True', 'layer_scale_init_value': 'layer_scale_init_value=0.1', 'use_mean_pooling': 'use_mean_pooling=True' -}, model_name='InternVLVisionModel', library='transformers', import_path='transformers.models.internvl'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 150272', 'hidden_size': 'hidden_size: Optional[int - ] = 3328', 'intermediate_size': 'intermediate_size: Optional[int - ] = 26624', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 26', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 150024', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'attention_bias': 'attention_bias: Optional[bool - ] = True', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = True', 'head_dim': 'head_dim: Optional[int - ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='Jais2Model', library='transformers', import_path='transformers.models.jais2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=65536', 'tie_word_embeddings': 'tie_word_embeddings=False', 'hidden_size': 'hidden_size=4096', 'intermediate_size': 'intermediate_size=14336', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=32', 'num_key_value_heads': 'num_key_value_heads=8', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-06', 'output_router_logits': 'output_router_logits=False', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'max_position_embeddings': 'max_position_embeddings=262144', 'attention_dropout': 'attention_dropout=0.0', 'num_experts_per_tok': 'num_experts_per_tok=2', 'num_experts': 'num_experts=16', 'expert_layer_period': 'expert_layer_period=2', 'expert_layer_offset': 'expert_layer_offset=1', 'attn_layer_period': 'attn_layer_period=8', 'attn_layer_offset': 'attn_layer_offset=4', 'use_mamba_kernels': 'use_mamba_kernels=True', 'mamba_d_state': 'mamba_d_state=16', 'mamba_d_conv': 'mamba_d_conv=4', 'mamba_expand': 'mamba_expand=2', 'mamba_dt_rank': "mamba_dt_rank='auto'", 'mamba_conv_bias': 'mamba_conv_bias=True', 'mamba_proj_bias': 'mamba_proj_bias=False' -}, model_name='JambaModel', library='transformers', import_path='transformers.models.jamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'vq_config': 'vq_config=None', 'image_token_id': 'image_token_id=100581' -}, model_name='JanusModel', library='transformers', import_path='transformers.models.janus'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 12', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 16', 'kv_channels': 'kv_channels: Optional[int - ] = 128', 'intermediate_size': 'intermediate_size: Optional[int - ] = 5632', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'activation_function': "activation_function: Optional[str] = 'silu'", 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'aux_loss_coef': 'aux_loss_coef: Optional[float - ] = 0.01', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'initializer_range': 'initializer_range: Optional[float - ] = 0.01', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='JetMoeModel', library='transformers', import_path='transformers.models.jetmoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'latent_query_num': 'latent_query_num=64' -}, model_name='Kosmos2Model', library='transformers', import_path='transformers.models.kosmos2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'latent_query_num': 'latent_query_num=2048' -}, model_name='Kosmos2_5Model', library='transformers', import_path='transformers.models.kosmos2_5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'codebook_vocab_size': 'codebook_vocab_size: Optional[int - ] = 2049', 'vocab_size': 'vocab_size: Optional[int - ] = 4001', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 48', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 750', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'head_dim': 'head_dim: Optional[int - ] = None', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'sliding_window': 'sliding_window: Optional[int - ] = 375', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'ffn_dim': 'ffn_dim: Optional[int - ] = 11264', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-08', 'num_codebooks': 'num_codebooks: Optional[int - ] = 32', 'audio_bos_token_id': 'audio_bos_token_id: Optional[int - ] = 2048', 'audio_pad_token_id': 'audio_pad_token_id: Optional[int - ] = 69569', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'pad_token_id': 'pad_token_id: Optional[int - ] = 3', 'bos_token_id': 'bos_token_id: Optional[int - ] = 48000', 'codec_config': 'codec_config: Optional[dict - ] = None' -}, model_name='KyutaiSpeechToTextModel', library='transformers', import_path='transformers.models.kyutai_speech_to_text'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=512', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=True', 'encoder_config': 'encoder_config: Union[dict, transformers.models.lasr.configuration_lasr.LasrEncoderConfig - ] = None', 'pad_token_id': 'pad_token_id=0' -}, model_name='LasrForCTC', library='transformers', import_path='transformers.models.lasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='ParakeetTokenizerFast', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=512', 'num_hidden_layers': 'num_hidden_layers=17', 'num_attention_heads': 'num_attention_heads=8', 'intermediate_size': 'intermediate_size=2048', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=False', 'convolution_bias': 'convolution_bias=False', 'conv_kernel_size': 'conv_kernel_size=32', 'subsampling_conv_channels': 'subsampling_conv_channels=256', 'subsampling_conv_kernel_size': 'subsampling_conv_kernel_size=5', 'subsampling_conv_stride': 'subsampling_conv_stride=2', 'num_mel_bins': 'num_mel_bins=128', 'dropout': 'dropout=0.1', 'dropout_positions': 'dropout_positions=0.0', 'layerdrop': 'layerdrop=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'max_position_embeddings': 'max_position_embeddings=10000', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'feed_forward_residual_weights': 'feed_forward_residual_weights=[ - 1.5, - 0.5 - ]', 'conv_residual_weights': 'conv_residual_weights=[ - 2.0, - 1.0 - ]', 'batch_norm_momentum': 'batch_norm_momentum=0.01', 'rope_parameters': 'rope_parameters=None' -}, model_name='LasrEncoder', library='transformers', import_path='transformers.models.lasr'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='ParakeetTokenizerFast', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024' -}, model_name='LayoutLMModel', library='transformers', import_path='transformers.models.layoutlm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'max_rel_pos': 'max_rel_pos=128', 'rel_pos_bins': 'rel_pos_bins=32', 'fast_qkv': 'fast_qkv=True', 'max_rel_2d_pos': 'max_rel_2d_pos=256', 'rel_2d_pos_bins': 'rel_2d_pos_bins=64', 'convert_sync_batchnorm': 'convert_sync_batchnorm=True', 'image_feature_pool_shape': 'image_feature_pool_shape=[ - 7, - 7, - 256 - ]', 'coordinate_size': 'coordinate_size=128', 'shape_size': 'shape_size=128', 'has_relative_attention_bias': 'has_relative_attention_bias=True', 'has_spatial_attention_bias': 'has_spatial_attention_bias=True', 'has_visual_segment_embedding': 'has_visual_segment_embedding=False', 'detectron2_config_args': 'detectron2_config_args=None' -}, model_name='LayoutLMv2Model', library='transformers', import_path='transformers.models.layoutlmv2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case=True', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'cls_token_box': 'cls_token_box=[ - 0, - 0, - 0, - 0 - ]', 'sep_token_box': 'sep_token_box=[ - 1000, - 1000, - 1000, - 1000 - ]', 'pad_token_box': 'pad_token_box=[ - 0, - 0, - 0, - 0 - ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' -}, model_name='LayoutLMv2Tokenizer', library='transformers', import_path='transformers.models.layoutlmv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'coordinate_size': 'coordinate_size=128', 'shape_size': 'shape_size=128', 'has_relative_attention_bias': 'has_relative_attention_bias=True', 'rel_pos_bins': 'rel_pos_bins=32', 'max_rel_pos': 'max_rel_pos=128', 'rel_2d_pos_bins': 'rel_2d_pos_bins=64', 'max_rel_2d_pos': 'max_rel_2d_pos=256', 'has_spatial_attention_bias': 'has_spatial_attention_bias=True', 'text_embed': 'text_embed=True', 'visual_embed': 'visual_embed=True', 'input_size': 'input_size=224', 'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='LayoutLMv3Model', library='transformers', import_path='transformers.models.layoutlmv3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'errors': "errors='replace'", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=True', 'cls_token_box': 'cls_token_box=[ - 0, - 0, - 0, - 0 - ]', 'sep_token_box': 'sep_token_box=[ - 0, - 0, - 0, - 0 - ]', 'pad_token_box': 'pad_token_box=[ - 0, - 0, - 0, - 0 - ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None' -}, model_name='LayoutLMv3Tokenizer', library='transformers', import_path='transformers.models.layoutlmv3'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_encoder_position_embeddings': 'max_encoder_position_embeddings=16384', 'max_decoder_position_embeddings': 'max_decoder_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'classifier_dropout': 'classifier_dropout=0.0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'attention_window': 'attention_window: Union[list[int - ], int - ] = 512' -}, model_name='LEDModel', library='transformers', import_path='transformers.models.led'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_channels': 'num_channels=3', 'kernel_size': 'kernel_size=3', 'stride': 'stride=2', 'padding': 'padding=1', 'patch_size': 'patch_size=16', 'hidden_sizes': 'hidden_sizes=[ - 128, - 256, - 384 - ]', 'num_attention_heads': 'num_attention_heads=[ - 4, - 8, - 12 - ]', 'depths': 'depths=[ - 4, - 4, - 4 - ]', 'key_dim': 'key_dim=[ - 16, - 16, - 16 - ]', 'drop_path_rate': 'drop_path_rate=0', 'mlp_ratio': 'mlp_ratio=[ - 2, - 2, - 2 - ]', 'attention_ratio': 'attention_ratio=[ - 2, - 2, - 2 - ]', 'initializer_range': 'initializer_range=0.02' -}, model_name='LevitModel', library='transformers', import_path='transformers.models.levit'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 65536', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int - ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 128000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'norm_eps': 'norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'conv_bias': 'conv_bias: Optional[bool - ] = False', 'conv_L_cache': 'conv_L_cache: Optional[int - ] = 3', 'block_multiple_of': 'block_multiple_of: Optional[int - ] = 256', 'block_ffn_dim_multiplier': 'block_ffn_dim_multiplier: Optional[float - ] = 1.0', 'block_auto_adjust_ff_dim': 'block_auto_adjust_ff_dim: Optional[bool - ] = True', 'full_attn_idxs': 'full_attn_idxs: Optional[list[int - ] - ] = None', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Lfm2Model', library='transformers', import_path='transformers.models.lfm2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 65536', 'hidden_size': 'hidden_size: int = 2048', 'intermediate_size': 'intermediate_size: int = 7168', 'moe_intermediate_size': 'moe_intermediate_size: int = 1792', 'num_hidden_layers': 'num_hidden_layers: int = 32', 'pad_token_id': 'pad_token_id: int = 0', 'bos_token_id': 'bos_token_id: int = 1', 'eos_token_id': 'eos_token_id: int = 2', 'tie_word_embeddings': 'tie_word_embeddings: bool = True', 'rope_parameters': 'rope_parameters: transformers.modeling_rope_utils.RopeParameters = None', 'max_position_embeddings': 'max_position_embeddings: int = 128000', 'initializer_range': 'initializer_range: float = 0.02', 'norm_eps': 'norm_eps: float = 1e-05', 'num_attention_heads': 'num_attention_heads: int = 32', 'num_key_value_heads': 'num_key_value_heads: int = 8', 'conv_bias': 'conv_bias: bool = False', 'conv_L_cache': 'conv_L_cache: int = 3', 'num_dense_layers': 'num_dense_layers: int = 2', 'num_experts_per_tok': 'num_experts_per_tok: int = 4', 'num_experts': 'num_experts: int = 32', 'use_expert_bias': 'use_expert_bias: bool = True', 'routed_scaling_factor': 'routed_scaling_factor: float = 1.0', 'norm_topk_prob': 'norm_topk_prob: bool = True', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Lfm2MoeModel', library='transformers', import_path='transformers.models.lfm2_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=396', 'projector_hidden_act': "projector_hidden_act='gelu'", 'projector_hidden_size': 'projector_hidden_size=2560', 'projector_bias': 'projector_bias=True', 'projector_use_layernorm': 'projector_use_layernorm=True', 'downsample_factor': 'downsample_factor=2' -}, model_name='Lfm2VlModel', library='transformers', import_path='transformers.models.lfm2_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'keypoint_detector_config': 'keypoint_detector_config: transformers.models.superpoint.configuration_superpoint.SuperPointConfig = None', 'descriptor_dim': 'descriptor_dim: int = 256', 'num_hidden_layers': 'num_hidden_layers: int = 9', 'num_attention_heads': 'num_attention_heads: int = 4', 'num_key_value_heads': 'num_key_value_heads=None', 'depth_confidence': 'depth_confidence: float = 0.95', 'width_confidence': 'width_confidence: float = 0.99', 'filter_threshold': 'filter_threshold: float = 0.1', 'initializer_range': 'initializer_range: float = 0.02', 'hidden_act': "hidden_act: str = 'gelu'", 'attention_dropout': 'attention_dropout=0.0', 'attention_bias': 'attention_bias=True', 'trust_remote_code': 'trust_remote_code: bool = False' -}, model_name='LightGlueForKeypointMatching', library='transformers', import_path='transformers.models.lightglue'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None', 'channel_shrink_ratio': 'channel_shrink_ratio=4', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024' -}, model_name='LiltModel', library='transformers', import_path='transformers.models.lilt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='LlamaModel', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'boi_token_index': 'boi_token_index=200080', 'eoi_token_index': 'eoi_token_index=200081', 'image_token_index': 'image_token_index=200092', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='Llama4ForConditionalGeneration', library='transformers', import_path='transformers.models.llama4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=202048', 'hidden_size': 'hidden_size=5120', 'intermediate_size': 'intermediate_size=8192', 'intermediate_size_mlp': 'intermediate_size_mlp=16384', 'num_hidden_layers': 'num_hidden_layers=48', 'num_attention_heads': 'num_attention_heads=40', 'num_key_value_heads': 'num_key_value_heads=8', 'head_dim': 'head_dim=128', 'hidden_act': "hidden_act='silu'", 'max_position_embeddings': 'max_position_embeddings=131072', 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=None', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'tie_word_embeddings': 'tie_word_embeddings=False', 'attention_dropout': 'attention_dropout=0.0', 'num_experts_per_tok': 'num_experts_per_tok=1', 'num_local_experts': 'num_local_experts=16', 'moe_layers': 'moe_layers=None', 'interleave_moe_layer_step': 'interleave_moe_layer_step=1', 'use_qk_norm': 'use_qk_norm=True', 'output_router_logits': 'output_router_logits=False', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'router_jitter_noise': 'router_jitter_noise=0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'no_rope_layers': 'no_rope_layers=None', 'no_rope_layer_interval': 'no_rope_layer_interval=4', 'attention_chunk_size': 'attention_chunk_size=8192', 'layer_types': 'layer_types=None', 'attn_temperature_tuning': 'attn_temperature_tuning=True', 'floor_scale': 'floor_scale=8192', 'attn_scale': 'attn_scale=0.1' -}, model_name='Llama4TextModel', library='transformers', import_path='transformers.models.llama4'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_seq_length': 'image_seq_length=576', 'multimodal_projector_bias': 'multimodal_projector_bias=True' -}, model_name='LlavaModel', library='transformers', import_path='transformers.models.llava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'tie_word_embeddings': 'tie_word_embeddings=False', 'image_seq_length': 'image_seq_length=576', 'multimodal_projector_bias': 'multimodal_projector_bias=True' -}, model_name='LlavaNextModel', library='transformers', import_path='transformers.models.llava_next'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32001', 'projector_hidden_act': "projector_hidden_act='gelu'", 'multimodal_projector_bias': 'multimodal_projector_bias=True', 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'video_token_index': 'video_token_index=32000', 'spatial_pool_mode': "spatial_pool_mode='average'", 'spatial_pool_stride': 'spatial_pool_stride=2', 'image_seq_length': 'image_seq_length=576', 'video_seq_length': 'video_seq_length=288' -}, model_name='LlavaNextVideoModel', library='transformers', import_path='transformers.models.llava_next_video'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=151646', 'video_token_index': 'video_token_index=151647', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='full'", 'vision_feature_layer': 'vision_feature_layer=-1', 'vision_aspect_ratio': "vision_aspect_ratio='anyres_max_9'", 'image_grid_pinpoints': 'image_grid_pinpoints=None', 'multimodal_projector_bias': 'multimodal_projector_bias=True' -}, model_name='LlavaOnevisionModel', library='transformers', import_path='transformers.models.llava_onevision'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 131072', 'hidden_size': 'hidden_size: Optional[int - ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 56', 'num_layers': 'num_layers: Optional[int - ] = 28', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'ffn_hidden_size': 'ffn_hidden_size: Optional[int - ] = 12288', 'q_lora_rank': 'q_lora_rank: Optional[int - ] = 1536', 'kv_lora_rank': 'kv_lora_rank: Optional[int - ] = 512', 'qk_nope_head_dim': 'qk_nope_head_dim: Optional[int - ] = 128', 'qk_rope_head_dim': 'qk_rope_head_dim: Optional[int - ] = 64', 'head_dim': 'head_dim: Optional[int - ] = 64', 'v_head_dim': 'v_head_dim: Optional[int - ] = 128', 'qk_head_dim': 'qk_head_dim: Optional[int - ] = None', 'moe_topk': 'moe_topk: Optional[int - ] = 12', 'n_routed_experts': 'n_routed_experts: Optional[int - ] = 512', 'zero_expert_num': 'zero_expert_num: Optional[int - ] = 256', 'expert_ffn_hidden_size': 'expert_ffn_hidden_size: Optional[int - ] = 2048', 'routed_scaling_factor': 'routed_scaling_factor: Optional[float - ] = 6.0' -}, model_name='LongcatFlashModel', library='transformers', import_path='transformers.models.longcat_flash'), ModelAttributes(model=, model_type='model', model_parameters={'attention_window': 'attention_window: Union[list[int - ], int - ] = 512', 'sep_token_id': 'sep_token_id: int = 2', 'pad_token_id': 'pad_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 2', 'vocab_size': 'vocab_size: int = 30522', 'hidden_size': 'hidden_size: int = 768', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 12', 'intermediate_size': 'intermediate_size: int = 3072', 'hidden_act': "hidden_act: str = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.1', 'max_position_embeddings': 'max_position_embeddings: int = 512', 'type_vocab_size': 'type_vocab_size: int = 2', 'initializer_range': 'initializer_range: float = 0.02', 'layer_norm_eps': 'layer_norm_eps: float = 1e-12', 'onnx_export': 'onnx_export: bool = False' -}, model_name='LongformerModel', library='transformers', import_path='transformers.models.longformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'num_layers': 'num_layers=6', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=8', 'local_radius': 'local_radius=127', 'global_block_size': 'global_block_size=16', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_attention_type': "encoder_attention_type='local'", 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1' -}, model_name='LongT5Model', library='transformers', import_path='transformers.models.longt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50267', 'entity_vocab_size': 'entity_vocab_size=500000', 'hidden_size': 'hidden_size=768', 'entity_emb_size': 'entity_emb_size=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_entity_aware_attention': 'use_entity_aware_attention=True', 'classifier_dropout': 'classifier_dropout=None', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='LukeModel', library='transformers', import_path='transformers.models.luke'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'entity_vocab': 'entity_vocab: Union[str, dict, list, NoneType - ] = None', 'errors': "errors='replace'", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'add_prefix_space': 'add_prefix_space=False', 'task': 'task=None', 'max_entity_length': 'max_entity_length=32', 'max_mention_length': 'max_mention_length=30', 'entity_token_1': "entity_token_1=''", 'entity_token_2': "entity_token_2=''", 'entity_unk_token': "entity_unk_token='[UNK]'", 'entity_pad_token': "entity_pad_token='[PAD]'", 'entity_mask_token': "entity_mask_token='[MASK]'", 'entity_mask2_token': "entity_mask2_token='[MASK2]'" -}, model_name='LukeTokenizer', library='transformers', import_path='transformers.models.luke'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_attention_heads': 'num_attention_heads=12', 'num_qa_labels': 'num_qa_labels=9500', 'num_object_labels': 'num_object_labels=1600', 'num_attr_labels': 'num_attr_labels=400', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'l_layers': 'l_layers=9', 'x_layers': 'x_layers=5', 'r_layers': 'r_layers=5', 'visual_feat_dim': 'visual_feat_dim=2048', 'visual_pos_dim': 'visual_pos_dim=4', 'visual_loss_normalizer': 'visual_loss_normalizer=6.67', 'task_matched': 'task_matched=True', 'task_mask_lm': 'task_mask_lm=True', 'task_obj_predict': 'task_obj_predict=True', 'task_qa': 'task_qa=True', 'visual_obj_loss': 'visual_obj_loss=True', 'visual_attr_loss': 'visual_attr_loss=True', 'visual_feat_loss': 'visual_feat_loss=True' -}, model_name='LxmertModel', library='transformers', import_path='transformers.models.lxmert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128112', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='M2M100Model', library='transformers', import_path='transformers.models.m2m_100'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'spm_file': 'spm_file', 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'language_codes': "language_codes='m2m100'", 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None', 'num_madeup_words': 'num_madeup_words=8' -}, model_name='M2M100Tokenizer', library='transformers', import_path='transformers.models.m2m_100'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50280', 'hidden_size': 'hidden_size=768', 'state_size': 'state_size=16', 'num_hidden_layers': 'num_hidden_layers=32', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_scale': 'time_step_scale=1.0', 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_init_scheme': "time_step_init_scheme='random'", 'time_step_floor': 'time_step_floor=0.0001', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'use_mambapy': 'use_mambapy=False' -}, model_name='MambaModel', library='transformers', import_path='transformers.models.mamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'num_heads': 'num_heads=128', 'head_dim': 'head_dim=64', 'vocab_size': 'vocab_size=32768', 'hidden_size': 'hidden_size=4096', 'state_size': 'state_size=128', 'num_hidden_layers': 'num_hidden_layers=64', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'expand': 'expand=2', 'conv_kernel': 'conv_kernel=4', 'n_groups': 'n_groups=8', 'use_bias': 'use_bias=False', 'use_conv_bias': 'use_conv_bias=True', 'hidden_act': "hidden_act='silu'", 'initializer_range': 'initializer_range=0.1', 'residual_in_fp32': 'residual_in_fp32=True', 'time_step_rank': "time_step_rank='auto'", 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_floor': 'time_step_floor=0.0001', 'time_step_limit': 'time_step_limit=(0.0, inf)', 'rescale_prenorm_residual': 'rescale_prenorm_residual=False', 'rms_norm': 'rms_norm=True', 'chunk_size': 'chunk_size=256', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='Mamba2Model', library='transformers', import_path='transformers.models.mamba2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=58101', 'decoder_vocab_size': 'decoder_vocab_size=None', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=58100', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=58100', 'eos_token_id': 'eos_token_id=0', 'forced_eos_token_id': 'forced_eos_token_id=0', 'share_encoder_decoder_embeddings': 'share_encoder_decoder_embeddings=True' -}, model_name='MarianModel', library='transformers', import_path='transformers.models.marian'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'source_spm': 'source_spm', 'target_spm': 'target_spm', 'vocab': 'vocab', 'target_vocab_file': 'target_vocab_file=None', 'source_lang': 'source_lang=None', 'target_lang': 'target_lang=None', 'unk_token': "unk_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'model_max_length': 'model_max_length=512', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None', 'separate_vocabs': 'separate_vocabs=False' -}, model_name='MarianTokenizer', library='transformers', import_path='transformers.models.marian'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_xpath_tag_unit_embeddings': 'max_xpath_tag_unit_embeddings=256', 'max_xpath_subs_unit_embeddings': 'max_xpath_subs_unit_embeddings=1024', 'tag_pad_id': 'tag_pad_id=216', 'subs_pad_id': 'subs_pad_id=1001', 'xpath_unit_hidden_size': 'xpath_unit_hidden_size=32', 'max_depth': 'max_depth=50', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='MarkupLMModel', library='transformers', import_path='transformers.models.markuplm'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'feature_size': 'feature_size: int = 256', 'mask_feature_size': 'mask_feature_size: int = 256', 'hidden_dim': 'hidden_dim: int = 256', 'encoder_feedforward_dim': 'encoder_feedforward_dim: int = 1024', 'activation_function': "activation_function: str = 'relu'", 'encoder_layers': 'encoder_layers: int = 6', 'decoder_layers': 'decoder_layers: int = 10', 'num_attention_heads': 'num_attention_heads: int = 8', 'dropout': 'dropout: float = 0.0', 'dim_feedforward': 'dim_feedforward: int = 2048', 'pre_norm': 'pre_norm: bool = False', 'enforce_input_projection': 'enforce_input_projection: bool = False', 'common_stride': 'common_stride: int = 4', 'ignore_value': 'ignore_value: int = 255', 'num_queries': 'num_queries: int = 100', 'no_object_weight': 'no_object_weight: float = 0.1', 'class_weight': 'class_weight: float = 2.0', 'mask_weight': 'mask_weight: float = 5.0', 'dice_weight': 'dice_weight: float = 5.0', 'train_num_points': 'train_num_points: int = 12544', 'oversample_ratio': 'oversample_ratio: float = 3.0', 'importance_sample_ratio': 'importance_sample_ratio: float = 0.75', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = True', 'feature_strides': 'feature_strides: list[int - ] = [ - 4, - 8, - 16, - 32 - ]', 'output_auxiliary_logits': 'output_auxiliary_logits: Optional[bool - ] = None', 'backbone': 'backbone: Optional[str - ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict - ] = None' -}, model_name='Mask2FormerModel', library='transformers', import_path='transformers.models.mask2former'), ModelAttributes(model=, model_type='model', model_parameters={'fpn_feature_size': 'fpn_feature_size: int = 256', 'mask_feature_size': 'mask_feature_size: int = 256', 'no_object_weight': 'no_object_weight: float = 0.1', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = False', 'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'decoder_config': 'decoder_config: Optional[dict - ] = None', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'dice_weight': 'dice_weight: float = 1.0', 'cross_entropy_weight': 'cross_entropy_weight: float = 1.0', 'mask_weight': 'mask_weight: float = 20.0', 'output_auxiliary_logits': 'output_auxiliary_logits: Optional[bool - ] = None', 'backbone': 'backbone: Optional[str - ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict - ] = None' -}, model_name='MaskFormerModel', library='transformers', import_path='transformers.models.maskformer'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'num_heads': 'num_heads=[ - 3, - 6, - 12, - 24 - ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='MaskFormerSwinModel', library='transformers', import_path='transformers.models.maskformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' -}, model_name='MBartModel', library='transformers', import_path='transformers.models.mbart'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='MBartTokenizer', library='transformers', import_path='transformers.models.mbart'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=29056', 'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0' -}, model_name='MegatronBertModel', library='transformers', import_path='transformers.models.megatron_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='MetaClip2Model', library='transformers', import_path='transformers.models.metaclip_2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=[ - 32, - 128 - ]', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'max_token_length': 'max_token_length=27', 'num_character_labels': 'num_character_labels=38', 'num_bpe_labels': 'num_bpe_labels=50257', 'num_wordpiece_labels': 'num_wordpiece_labels=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'distilled': 'distilled=False', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'drop_rate': 'drop_rate=0.0', 'attn_drop_rate': 'attn_drop_rate=0.0', 'drop_path_rate': 'drop_path_rate=0.0', 'output_a3_attentions': 'output_a3_attentions=False', 'initializer_range': 'initializer_range=0.02' -}, model_name='MgpstrForSceneTextRecognition', library='transformers', import_path='transformers.models.mgp_str'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'unk_token': "unk_token='[GO]'", 'bos_token': "bos_token='[GO]'", 'eos_token': "eos_token='[s]'", 'pad_token': "pad_token='[GO]'" -}, model_name='MgpstrTokenizer', library='transformers', import_path='transformers.models.mgp_str'), ModelAttributes(model=, model_type='model', model_parameters={'sampling_rate': 'sampling_rate: Optional[int - ] = 24000', 'frame_rate': 'frame_rate: Optional[int - ] = None', 'audio_channels': 'audio_channels: Optional[int - ] = 1', 'hidden_size': 'hidden_size: Optional[int - ] = 512', 'num_filters': 'num_filters: Optional[int - ] = 64', 'num_residual_layers': 'num_residual_layers: Optional[int - ] = 1', 'upsampling_ratios': 'upsampling_ratios: Optional[list[int - ] - ] = None', 'kernel_size': 'kernel_size: Optional[int - ] = 7', 'last_kernel_size': 'last_kernel_size: Optional[int - ] = 3', 'residual_kernel_size': 'residual_kernel_size: Optional[int - ] = 3', 'dilation_growth_rate': 'dilation_growth_rate: Optional[int - ] = 2', 'use_causal_conv': 'use_causal_conv: Optional[bool - ] = True', 'pad_mode': "pad_mode: Optional[str] = 'constant'", 'compress': 'compress: Optional[int - ] = 2', 'trim_right_ratio': 'trim_right_ratio: Optional[float - ] = 1.0', 'codebook_size': 'codebook_size: Optional[int - ] = 2048', 'codebook_dim': 'codebook_dim: Optional[int - ] = 256', 'num_quantizers': 'num_quantizers: Optional[int - ] = 32', 'use_conv_shortcut': 'use_conv_shortcut: Optional[bool - ] = False', 'vector_quantization_hidden_dimension': 'vector_quantization_hidden_dimension: Optional[int - ] = 256', 'num_semantic_quantizers': 'num_semantic_quantizers: Optional[int - ] = 1', 'upsample_groups': 'upsample_groups: Optional[int - ] = 512', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 8', 'intermediate_size': 'intermediate_size: Optional[int - ] = 2048', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'norm_eps': 'norm_eps: Optional[int - ] = 1e-05', 'use_streaming': 'use_streaming: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = 250', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'layer_scale_initial_scale': 'layer_scale_initial_scale: Optional[float - ] = 0.01', 'attention_bias': 'attention_bias: Optional[bool - ] = False' -}, model_name='MimiModel', library='transformers', import_path='transformers.models.mimi'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'block_size': 'block_size: Optional[int - ] = 256', 'full_attn_alpha_factor': 'full_attn_alpha_factor: Optional[int - ] = 1', 'full_attn_beta_factor': 'full_attn_beta_factor: Optional[int - ] = 1', 'linear_attn_alpha_factor': 'linear_attn_alpha_factor: Optional[int - ] = 1', 'linear_attn_beta_factor': 'linear_attn_beta_factor: Optional[int - ] = 1', 'mlp_alpha_factor': 'mlp_alpha_factor: Optional[int - ] = 1', 'mlp_beta_factor': 'mlp_beta_factor: Optional[int - ] = 1' -}, model_name='MiniMaxModel', library='transformers', import_path='transformers.models.minimax'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='MinistralModel', library='transformers', import_path='transformers.models.ministral'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 131072', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 34', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 262144', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 11', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='Ministral3Model', library='transformers', import_path='transformers.models.ministral3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='MistralModel', library='transformers', import_path='transformers.models.mistral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=10', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_layer': 'vision_feature_layer=-1', 'multimodal_projector_bias': 'multimodal_projector_bias=False', 'spatial_merge_size': 'spatial_merge_size=2' -}, model_name='Mistral3Model', library='transformers', import_path='transformers.models.mistral3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 14336', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'head_dim': 'head_dim: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'num_local_experts': 'num_local_experts: Optional[int - ] = 8', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='MixtralModel', library='transformers', import_path='transformers.models.mixtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1664', 'intermediate_size': 'intermediate_size=8192', 'num_hidden_layers': 'num_hidden_layers=48', 'num_attention_heads': 'num_attention_heads=16', 'num_key_value_groups': 'num_key_value_groups=1', 'num_channels': 'num_channels=3', 'image_size': 'image_size=336', 'patch_size': 'patch_size=14', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-05', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02', 'initializer_factor': 'initializer_factor=1.0' -}, model_name='MLCDVisionModel', library='transformers', import_path='transformers.models.mlcd'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=128256' -}, model_name='MllamaModel', library='transformers', import_path='transformers.models.mllama'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'text_config': 'text_config=None', 'num_queries': 'num_queries=900', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'num_feature_levels': 'num_feature_levels=4', 'encoder_n_points': 'encoder_n_points=4', 'decoder_n_points': 'decoder_n_points=4', 'two_stage': 'two_stage=True', 'class_cost': 'class_cost=1.0', 'bbox_cost': 'bbox_cost=5.0', 'giou_cost': 'giou_cost=2.0', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5.0', 'giou_loss_coefficient': 'giou_loss_coefficient=2.0', 'focal_alpha': 'focal_alpha=0.25', 'disable_custom_kernels': 'disable_custom_kernels=False', 'max_text_len': 'max_text_len=256', 'text_enhancer_dropout': 'text_enhancer_dropout=0.0', 'fusion_droppath': 'fusion_droppath=0.1', 'fusion_dropout': 'fusion_dropout=0.0', 'embedding_init_target': 'embedding_init_target=True', 'query_dim': 'query_dim=4', 'positional_embedding_temperature': 'positional_embedding_temperature=20', 'init_std': 'init_std=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05' -}, model_name='MMGroundingDinoModel', library='transformers', import_path='transformers.models.mm_grounding_dino'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=512', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=4', 'intermediate_size': 'intermediate_size=512', 'hidden_act': "hidden_act='relu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'embedding_size': 'embedding_size=128', 'trigram_input': 'trigram_input=True', 'use_bottleneck': 'use_bottleneck=True', 'intra_bottleneck_size': 'intra_bottleneck_size=128', 'use_bottleneck_attention': 'use_bottleneck_attention=False', 'key_query_shared_bottleneck': 'key_query_shared_bottleneck=True', 'num_feedforward_networks': 'num_feedforward_networks=4', 'normalization_type': "normalization_type='no_norm'", 'classifier_activation': 'classifier_activation=True', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='MobileBertModel', library='transformers', import_path='transformers.models.mobilebert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'depth_multiplier': 'depth_multiplier=1.0', 'min_depth': 'min_depth=8', 'hidden_act': "hidden_act='relu6'", 'tf_padding': 'tf_padding=True', 'classifier_dropout_prob': 'classifier_dropout_prob=0.999', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=0.001' -}, model_name='MobileNetV1Model', library='transformers', import_path='transformers.models.mobilenet_v1'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'depth_multiplier': 'depth_multiplier=1.0', 'depth_divisible_by': 'depth_divisible_by=8', 'min_depth': 'min_depth=8', 'expand_ratio': 'expand_ratio=6.0', 'output_stride': 'output_stride=32', 'first_layer_is_expansion': 'first_layer_is_expansion=True', 'finegrained_output': 'finegrained_output=True', 'hidden_act': "hidden_act='relu6'", 'tf_padding': 'tf_padding=True', 'classifier_dropout_prob': 'classifier_dropout_prob=0.8', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=0.001', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' -}, model_name='MobileNetV2Model', library='transformers', import_path='transformers.models.mobilenet_v2'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=256', 'patch_size': 'patch_size=2', 'hidden_sizes': 'hidden_sizes=[ - 144, - 192, - 240 - ]', 'neck_hidden_sizes': 'neck_hidden_sizes=[ - 16, - 32, - 64, - 96, - 128, - 160, - 640 - ]', 'num_attention_heads': 'num_attention_heads=4', 'mlp_ratio': 'mlp_ratio=2.0', 'expand_ratio': 'expand_ratio=4.0', 'hidden_act': "hidden_act='silu'", 'conv_kernel_size': 'conv_kernel_size=3', 'output_stride': 'output_stride=32', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'qkv_bias': 'qkv_bias=True', 'aspp_out_channels': 'aspp_out_channels=256', 'atrous_rates': 'atrous_rates=[ - 6, - 12, - 18 - ]', 'aspp_dropout_prob': 'aspp_dropout_prob=0.1', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' -}, model_name='MobileViTModel', library='transformers', import_path='transformers.models.mobilevit'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'image_size': 'image_size=256', 'patch_size': 'patch_size=2', 'expand_ratio': 'expand_ratio=2.0', 'hidden_act': "hidden_act='swish'", 'conv_kernel_size': 'conv_kernel_size=3', 'output_stride': 'output_stride=32', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'aspp_out_channels': 'aspp_out_channels=512', 'atrous_rates': 'atrous_rates=[ - 6, - 12, - 18 - ]', 'aspp_dropout_prob': 'aspp_dropout_prob=0.1', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255', 'n_attn_blocks': 'n_attn_blocks=[ - 2, - 4, - 3 - ]', 'base_attn_unit_dims': 'base_attn_unit_dims=[ - 128, - 192, - 256 - ]', 'width_multiplier': 'width_multiplier=1.0', 'ffn_multiplier': 'ffn_multiplier=2', 'attn_dropout': 'attn_dropout=0.0', 'ffn_dropout': 'ffn_dropout=0.0' -}, model_name='MobileViTV2Model', library='transformers', import_path='transformers.models.mobilevitv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50368', 'hidden_size': 'hidden_size: Optional[int - ] = 768', 'intermediate_size': 'intermediate_size: Optional[int - ] = 1152', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 22', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 12', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'initializer_cutoff_factor': 'initializer_cutoff_factor: Optional[float - ] = 2.0', 'norm_eps': 'norm_eps: Optional[int - ] = 1e-05', 'norm_bias': 'norm_bias: Optional[bool - ] = False', 'pad_token_id': 'pad_token_id: Optional[int - ] = 50283', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50282', 'bos_token_id': 'bos_token_id: Optional[int - ] = 50281', 'cls_token_id': 'cls_token_id: Optional[int - ] = 50281', 'sep_token_id': 'sep_token_id: Optional[int - ] = 50282', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'local_attention': 'local_attention: Optional[int - ] = 128', 'embedding_dropout': 'embedding_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'mlp_dropout': 'mlp_dropout: Optional[float - ] = 0.0', 'decoder_bias': 'decoder_bias: Optional[bool - ] = True', 'classifier_pooling': "classifier_pooling: Literal['cls', 'mean'] = 'cls'", 'classifier_dropout': 'classifier_dropout: Optional[float - ] = 0.0', 'classifier_bias': 'classifier_bias: Optional[bool - ] = False', 'classifier_activation': "classifier_activation: Optional[str] = 'gelu'", 'deterministic_flash_attn': 'deterministic_flash_attn: Optional[bool - ] = False', 'sparse_prediction': 'sparse_prediction: Optional[bool - ] = False', 'sparse_pred_ignore_index': 'sparse_pred_ignore_index: Optional[int - ] = -100', 'reference_compile': 'reference_compile: Optional[bool - ] = None', 'repad_logits_with_grad': 'repad_logits_with_grad: Optional[bool - ] = False' -}, model_name='ModernBertModel', library='transformers', import_path='transformers.models.modernbert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50368', 'hidden_size': 'hidden_size: Optional[int - ] = 768', 'intermediate_size': 'intermediate_size: Optional[int - ] = 1152', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 22', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 12', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'initializer_cutoff_factor': 'initializer_cutoff_factor: Optional[float - ] = 2.0', 'norm_eps': 'norm_eps: Optional[int - ] = 1e-05', 'norm_bias': 'norm_bias: Optional[bool - ] = False', 'pad_token_id': 'pad_token_id: Optional[int - ] = 50283', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50282', 'bos_token_id': 'bos_token_id: Optional[int - ] = 50281', 'cls_token_id': 'cls_token_id: Optional[int - ] = 50281', 'sep_token_id': 'sep_token_id: Optional[int - ] = 50282', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'embedding_dropout': 'embedding_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'mlp_dropout': 'mlp_dropout: Optional[float - ] = 0.0', 'decoder_bias': 'decoder_bias: Optional[bool - ] = True', 'classifier_dropout': 'classifier_dropout: Optional[float - ] = 0.0', 'classifier_bias': 'classifier_bias: Optional[bool - ] = False', 'classifier_activation': "classifier_activation: Optional[str] = 'gelu'", 'local_attention': 'local_attention: Optional[int - ] = 128', 'global_attn_every_n_layers': 'global_attn_every_n_layers: Optional[int - ] = 3', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None' -}, model_name='ModernBertDecoderModel', library='transformers', import_path='transformers.models.modernbert_decoder'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32768', 'hidden_size': 'hidden_size: Optional[int - ] = 288', 'intermediate_size': 'intermediate_size: Optional[int - ] = 1152', 'encoder_num_hidden_layers': 'encoder_num_hidden_layers: Optional[int - ] = 6', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers: Optional[int - ] = 6', 'encoder_num_attention_heads': 'encoder_num_attention_heads: Optional[int - ] = 8', 'decoder_num_attention_heads': 'decoder_num_attention_heads: Optional[int - ] = 8', 'encoder_num_key_value_heads': 'encoder_num_key_value_heads: Optional[int - ] = None', 'decoder_num_key_value_heads': 'decoder_num_key_value_heads: Optional[int - ] = None', 'pad_head_dim_to_multiple_of': 'pad_head_dim_to_multiple_of: Optional[int - ] = None', 'encoder_hidden_act': "encoder_hidden_act: Optional[str] = 'gelu'", 'decoder_hidden_act': "decoder_hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 512', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'decoder_start_token_id': 'decoder_start_token_id: Optional[int - ] = 1', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool - ] = True', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2' -}, model_name='MoonshineModel', library='transformers', import_path='transformers.models.moonshine'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'audio_vocab_size': 'audio_vocab_size: Optional[int - ] = None', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 3000', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'head_dim': 'head_dim: Optional[int - ] = None', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'sliding_window': 'sliding_window: Optional[int - ] = 3000', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'ffn_dim': 'ffn_dim: Optional[int - ] = 22528', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-08', 'num_codebooks': 'num_codebooks: Optional[int - ] = 8', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False' -}, model_name='MoshiModel', library='transformers', import_path='transformers.models.moshi'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30527', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='MPNetModel', library='transformers', import_path='transformers.models.mpnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case=True', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token='[UNK]'", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' -}, model_name='MPNetTokenizer', library='transformers', import_path='transformers.models.mpnet'), ModelAttributes(model=, model_type='model', model_parameters={'d_model': 'd_model: int = 2048', 'n_heads': 'n_heads: int = 16', 'n_layers': 'n_layers: int = 24', 'expansion_ratio': 'expansion_ratio: int = 4', 'max_seq_len': 'max_seq_len: int = 2048', 'vocab_size': 'vocab_size: int = 50368', 'resid_pdrop': 'resid_pdrop: float = 0.0', 'layer_norm_epsilon': 'layer_norm_epsilon: float = 1e-05', 'emb_pdrop': 'emb_pdrop: float = 0.0', 'learned_pos_emb': 'learned_pos_emb: bool = True', 'attn_config': 'attn_config: transformers.models.mpt.configuration_mpt.MptAttentionConfig = None', 'init_device': "init_device: str = 'cpu'", 'logit_scale': 'logit_scale: Union[float, str, NoneType - ] = None', 'no_bias': 'no_bias: bool = True', 'verbose': 'verbose: int = 0', 'embedding_fraction': 'embedding_fraction: float = 1.0', 'norm_type': "norm_type: str = 'low_precision_layernorm'", 'initializer_range': 'initializer_range=0.02' -}, model_name='MptModel', library='transformers', import_path='transformers.models.mpt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'block_per_row': 'block_per_row=4', 'approx_mode': "approx_mode='full'", 'initial_prior_first_n_blocks': 'initial_prior_first_n_blocks=0', 'initial_prior_diagonal_n_blocks': 'initial_prior_diagonal_n_blocks=0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='MraModel', library='transformers', import_path='transformers.models.mra'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250112', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=1024', 'num_layers': 'num_layers=8', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=6', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='gated-gelu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'tokenizer_class': "tokenizer_class='T5Tokenizer'", 'tie_word_embeddings': 'tie_word_embeddings=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'decoder_start_token_id': 'decoder_start_token_id=0', 'classifier_dropout': 'classifier_dropout=0.0' -}, model_name='MT5Model', library='transformers', import_path='transformers.models.mt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'text_encoder': 'text_encoder', 'audio_encoder': 'audio_encoder', 'decoder': 'decoder' -}, model_name='MusicgenModel', library='transformers', import_path='transformers.models.musicgen'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'text_encoder': 'text_encoder', 'audio_encoder': 'audio_encoder', 'decoder': 'decoder', 'num_chroma': 'num_chroma=12', 'chroma_length': 'chroma_length=235' -}, model_name='MusicgenMelodyModel', library='transformers', import_path='transformers.models.musicgen_melody'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50267', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'is_encoder_decoder': 'is_encoder_decoder=True', 'decoder_start_token_id': 'decoder_start_token_id=2', 'use_prompt': 'use_prompt=False', 'prompt_length': 'prompt_length=100', 'prompt_mid_dim': 'prompt_mid_dim=800' -}, model_name='MvpModel', library='transformers', import_path='transformers.models.mvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 50304', 'hidden_size': 'hidden_size: int = 768', 'intermediate_size': 'intermediate_size: int | None = 8192', 'num_hidden_layers': 'num_hidden_layers: int = 12', 'num_attention_heads': 'num_attention_heads: int = 6', 'num_key_value_heads': 'num_key_value_heads: int | None = None', 'max_position_embeddings': 'max_position_embeddings: int = 2048', 'hidden_act': "hidden_act: str = 'relu2'", 'attention_dropout': 'attention_dropout: float = 0.0', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'initializer_range': 'initializer_range: float = 0.02', 'rope_parameters': 'rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None', 'final_logit_softcapping': 'final_logit_softcapping: float | None = 15.0', 'attention_bias': 'attention_bias: bool = False', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 1', 'pad_token_id': 'pad_token_id: int = 1', 'tie_word_embeddings': 'tie_word_embeddings: bool = False' -}, model_name='NanoChatModel', library='transformers', import_path='transformers.models.nanochat'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 6144', 'intermediate_size': 'intermediate_size: Optional[int - ] = 24576', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 48', 'head_dim': 'head_dim: Optional[int - ] = None', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.0134', 'norm_eps': 'norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'eos_token_id': 'eos_token_id: Optional[int - ] = 3', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False' -}, model_name='NemotronModel', library='transformers', import_path='transformers.models.nemotron'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=128112', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'router_bias': 'router_bias=False', 'router_dtype': "router_dtype='float32'", 'router_ignore_padding_tokens': 'router_ignore_padding_tokens=False', 'num_experts': 'num_experts=128', 'expert_capacity': 'expert_capacity=64', 'encoder_sparse_step': 'encoder_sparse_step=4', 'decoder_sparse_step': 'decoder_sparse_step=4', 'router_z_loss_coef': 'router_z_loss_coef=0.001', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'second_expert_policy': "second_expert_policy='all'", 'normalize_router_prob_before_dropping': 'normalize_router_prob_before_dropping=False', 'batch_prioritized_routing': 'batch_prioritized_routing=False', 'moe_eval_capacity_token_fraction': 'moe_eval_capacity_token_fraction=1.0', 'moe_token_dropout': 'moe_token_dropout=0.2', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'output_router_logits': 'output_router_logits=False' -}, model_name='NllbMoeModel', library='transformers', import_path='transformers.models.nllb_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'additional_special_tokens': 'additional_special_tokens=None', 'legacy_behaviour': 'legacy_behaviour=False' -}, model_name='NllbTokenizer', library='transformers', import_path='transformers.models.nllb'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30000', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_new'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=510', 'type_vocab_size': 'type_vocab_size=2', 'segment_means_seq_len': 'segment_means_seq_len=64', 'num_landmarks': 'num_landmarks=64', 'conv_kernel_size': 'conv_kernel_size=65', 'inv_coeff_init_option': 'inv_coeff_init_option=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='NystromformerModel', library='transformers', import_path='transformers.models.nystromformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='AlbertTokenizer', library='transformers', import_path='transformers.models.albert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50304', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'clip_qkv': 'clip_qkv: Optional[bool - ] = None' -}, model_name='OlmoModel', library='transformers', import_path='transformers.models.olmo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50304', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05' -}, model_name='Olmo2Model', library='transformers', import_path='transformers.models.olmo2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50304', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'pad_token_id': 'pad_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Olmo3Model', library='transformers', import_path='transformers.models.olmo3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50304', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 2048', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 16', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = None', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50279', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'clip_qkv': 'clip_qkv: Optional[bool - ] = None', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 8', 'num_experts': 'num_experts: Optional[int - ] = 64', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.01', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False' -}, model_name='OlmoeModel', library='transformers', import_path='transformers.models.olmoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'backbone_config': 'backbone_config=None', 'use_timm_backbone': 'use_timm_backbone=True', 'backbone': "backbone='swin_tiny_patch4_window7_224'", 'backbone_kwargs': 'backbone_kwargs=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'apply_layernorm_after_vision_backbone': 'apply_layernorm_after_vision_backbone=True', 'image_size': 'image_size=640', 'disable_custom_kernels': 'disable_custom_kernels=False', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'init_std': 'init_std=0.02', 'text_projection_in_dim': 'text_projection_in_dim=512', 'text_projection_out_dim': 'text_projection_out_dim=512', 'task_encoder_hidden_dim': 'task_encoder_hidden_dim=1024', 'class_embed_dim': 'class_embed_dim=512', 'class_distance_type': "class_distance_type='cosine'", 'num_queries': 'num_queries=900', 'csp_activation': "csp_activation='silu'", 'conv_norm_activation': "conv_norm_activation='gelu'", 'encoder_feedforward_activation': "encoder_feedforward_activation='relu'", 'encoder_feedforward_dropout': 'encoder_feedforward_dropout=0.0', 'encoder_dropout': 'encoder_dropout=0.0', 'hidden_expansion': 'hidden_expansion=1', 'vision_features_channels': 'vision_features_channels=[ - 256, - 256, - 256 - ]', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ - 192, - 384, - 768 - ]', 'encoder_projection_indices': 'encoder_projection_indices=[ - 2 - ]', 'encoder_attention_heads': 'encoder_attention_heads=8', 'encoder_dim_feedforward': 'encoder_dim_feedforward=2048', 'encoder_layers': 'encoder_layers=1', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'num_feature_levels': 'num_feature_levels=3', 'decoder_hidden_dim': 'decoder_hidden_dim=256', 'decoder_num_heads': 'decoder_num_heads=8', 'decoder_num_layers': 'decoder_num_layers=6', 'decoder_activation': "decoder_activation='relu'", 'decoder_dim_feedforward': 'decoder_dim_feedforward=2048', 'decoder_num_points': 'decoder_num_points=4', 'decoder_dropout': 'decoder_dropout=0.0', 'eval_size': 'eval_size=None', 'learn_initial_query': 'learn_initial_query=False', 'cache_size': 'cache_size=100', 'is_encoder_decoder': 'is_encoder_decoder=True' -}, model_name='OmDetTurboForObjectDetection', library='transformers', import_path='transformers.models.omdet_turbo'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'backbone': 'backbone: Optional[str - ] = None', 'use_pretrained_backbone': 'use_pretrained_backbone: bool = False', 'use_timm_backbone': 'use_timm_backbone: bool = False', 'backbone_kwargs': 'backbone_kwargs: Optional[dict - ] = None', 'ignore_value': 'ignore_value: int = 255', 'num_queries': 'num_queries: int = 150', 'no_object_weight': 'no_object_weight: int = 0.1', 'class_weight': 'class_weight: float = 2.0', 'mask_weight': 'mask_weight: float = 5.0', 'dice_weight': 'dice_weight: float = 5.0', 'contrastive_weight': 'contrastive_weight: float = 0.5', 'contrastive_temperature': 'contrastive_temperature: float = 0.07', 'train_num_points': 'train_num_points: int = 12544', 'oversample_ratio': 'oversample_ratio: float = 3.0', 'importance_sample_ratio': 'importance_sample_ratio: float = 0.75', 'init_std': 'init_std: float = 0.02', 'init_xavier_std': 'init_xavier_std: float = 1.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-05', 'is_training': 'is_training: bool = False', 'use_auxiliary_loss': 'use_auxiliary_loss: bool = True', 'output_auxiliary_logits': 'output_auxiliary_logits: bool = True', 'strides': 'strides: Optional[list - ] = [ - 4, - 8, - 16, - 32 - ]', 'task_seq_len': 'task_seq_len: int = 77', 'text_encoder_width': 'text_encoder_width: int = 256', 'text_encoder_context_length': 'text_encoder_context_length: int = 77', 'text_encoder_num_layers': 'text_encoder_num_layers: int = 6', 'text_encoder_vocab_size': 'text_encoder_vocab_size: int = 49408', 'text_encoder_proj_layers': 'text_encoder_proj_layers: int = 2', 'text_encoder_n_ctx': 'text_encoder_n_ctx: int = 16', 'conv_dim': 'conv_dim: int = 256', 'mask_dim': 'mask_dim: int = 256', 'hidden_dim': 'hidden_dim: int = 256', 'encoder_feedforward_dim': 'encoder_feedforward_dim: int = 1024', 'norm': "norm: str = 'GN'", 'encoder_layers': 'encoder_layers: int = 6', 'decoder_layers': 'decoder_layers: int = 10', 'use_task_norm': 'use_task_norm: bool = True', 'num_attention_heads': 'num_attention_heads: int = 8', 'dropout': 'dropout: float = 0.1', 'dim_feedforward': 'dim_feedforward: int = 2048', 'pre_norm': 'pre_norm: bool = False', 'enforce_input_proj': 'enforce_input_proj: bool = False', 'query_dec_layers': 'query_dec_layers: int = 2', 'common_stride': 'common_stride: int = 4' -}, model_name='OneFormerModel', library='transformers', import_path='transformers.models.oneformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=40478', 'n_positions': 'n_positions=512', 'n_embd': 'n_embd=768', 'n_layer': 'n_layer=12', 'n_head': 'n_head=12', 'afn': "afn='gelu'", 'resid_pdrop': 'resid_pdrop=0.1', 'embd_pdrop': 'embd_pdrop=0.1', 'attn_pdrop': 'attn_pdrop=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'initializer_range': 'initializer_range=0.02', 'summary_type': "summary_type='cls_index'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1' -}, model_name='OpenAIGPTModel', library='transformers', import_path='transformers.models.openai'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''" -}, model_name='OpenAIGPTTokenizer', library='transformers', import_path='transformers.models.openai'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50272', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'ffn_dim': 'ffn_dim=3072', 'max_position_embeddings': 'max_position_embeddings=2048', 'do_layer_norm_before': 'do_layer_norm_before=True', '_remove_final_layer_norm': '_remove_final_layer_norm=False', 'word_embed_proj_dim': 'word_embed_proj_dim=None', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'num_attention_heads': 'num_attention_heads=12', 'activation_function': "activation_function='relu'", 'layerdrop': 'layerdrop=0.0', 'init_std': 'init_std=0.02', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=2', 'enable_bias': 'enable_bias=True', 'layer_norm_elementwise_affine': 'layer_norm_elementwise_affine=True' -}, model_name='OPTModel', library='transformers', import_path='transformers.models.opt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_id': 'image_token_id=151665', 'visual_indicator_token_ids': 'visual_indicator_token_ids=[ - 151666, - 151667, - 151668, - 151669, - 151670 - ]', 'vocab_size': 'vocab_size=151643', 'hidden_size': 'hidden_size=1536' -}, model_name='Ovis2Model', library='transformers', import_path='transformers.models.ovis2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'return_dict': 'return_dict=True' -}, model_name='Owlv2Model', library='transformers', import_path='transformers.models.owlv2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592', 'return_dict': 'return_dict=True' -}, model_name='OwlViTModel', library='transformers', import_path='transformers.models.owlvit'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=256000', 'vocab_size': 'vocab_size=257152', 'projection_dim': 'projection_dim=2048', 'hidden_size': 'hidden_size=2048' -}, model_name='PaliGemmaModel', library='transformers', import_path='transformers.models.paligemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=1025', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=True', 'encoder_config': 'encoder_config: Union[dict, transformers.models.parakeet.configuration_parakeet.ParakeetEncoderConfig - ] = None', 'pad_token_id': 'pad_token_id=1024' -}, model_name='ParakeetForCTC', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=8', 'intermediate_size': 'intermediate_size=4096', 'hidden_act': "hidden_act='silu'", 'attention_bias': 'attention_bias=True', 'convolution_bias': 'convolution_bias=True', 'conv_kernel_size': 'conv_kernel_size=9', 'subsampling_factor': 'subsampling_factor=8', 'subsampling_conv_channels': 'subsampling_conv_channels=256', 'num_mel_bins': 'num_mel_bins=80', 'subsampling_conv_kernel_size': 'subsampling_conv_kernel_size=3', 'subsampling_conv_stride': 'subsampling_conv_stride=2', 'dropout': 'dropout=0.1', 'dropout_positions': 'dropout_positions=0.0', 'layerdrop': 'layerdrop=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'max_position_embeddings': 'max_position_embeddings=5000', 'scale_input': 'scale_input=True', 'initializer_range': 'initializer_range=0.02' -}, model_name='ParakeetEncoder', library='transformers', import_path='transformers.models.parakeet'), ModelAttributes(model=, model_type='model', model_parameters={'context_length': 'context_length: int = 32', 'patch_length': 'patch_length: int = 8', 'num_input_channels': 'num_input_channels: int = 1', 'patch_stride': 'patch_stride: int = 8', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'd_model': 'd_model: int = 8', 'expansion_factor': 'expansion_factor: int = 2', 'num_layers': 'num_layers: int = 3', 'dropout': 'dropout: float = 0.2', 'mode': "mode: str = 'common_channel'", 'gated_attn': 'gated_attn: bool = True', 'norm_mlp': "norm_mlp: str = 'LayerNorm'", 'self_attn': 'self_attn: bool = False', 'self_attn_heads': 'self_attn_heads: int = 1', 'use_positional_encoding': 'use_positional_encoding: bool = False', 'positional_encoding_type': "positional_encoding_type: str = 'sincos'", 'scaling': "scaling: Union[str, bool, NoneType] = 'std'", 'loss': "loss: str = 'mse'", 'init_std': 'init_std: float = 0.02', 'post_init': 'post_init: bool = False', 'norm_eps': 'norm_eps: float = 1e-05', 'mask_type': "mask_type: str = 'random'", 'random_mask_ratio': 'random_mask_ratio: float = 0.5', 'num_forecast_mask_patches': 'num_forecast_mask_patches: Union[int, list[int - ], NoneType - ] = [ - 2 - ]', 'mask_value': 'mask_value: int = 0', 'masked_loss': 'masked_loss: bool = True', 'channel_consistent_masking': 'channel_consistent_masking: bool = True', 'unmasked_channel_indices': 'unmasked_channel_indices: Optional[list[int - ] - ] = None', 'head_dropout': 'head_dropout: float = 0.2', 'distribution_output': "distribution_output: str = 'student_t'", 'prediction_length': 'prediction_length: int = 16', 'prediction_channel_indices': 'prediction_channel_indices: Optional[list - ] = None', 'num_targets': 'num_targets: int = 3', 'output_range': 'output_range: Optional[list - ] = None', 'head_aggregation': "head_aggregation: str = 'max_pool'" -}, model_name='PatchTSMixerModel', library='transformers', import_path='transformers.models.patchtsmixer'), ModelAttributes(model=, model_type='model', model_parameters={'num_input_channels': 'num_input_channels: int = 1', 'context_length': 'context_length: int = 32', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'mse'", 'patch_length': 'patch_length: int = 1', 'patch_stride': 'patch_stride: int = 1', 'num_hidden_layers': 'num_hidden_layers: int = 3', 'd_model': 'd_model: int = 128', 'num_attention_heads': 'num_attention_heads: int = 4', 'share_embedding': 'share_embedding: bool = True', 'channel_attention': 'channel_attention: bool = False', 'ffn_dim': 'ffn_dim: int = 512', 'norm_type': "norm_type: str = 'batchnorm'", 'norm_eps': 'norm_eps: float = 1e-05', 'attention_dropout': 'attention_dropout: float = 0.0', 'positional_dropout': 'positional_dropout: float = 0.0', 'path_dropout': 'path_dropout: float = 0.0', 'ff_dropout': 'ff_dropout: float = 0.0', 'bias': 'bias: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'pre_norm': 'pre_norm: bool = True', 'positional_encoding_type': "positional_encoding_type: str = 'sincos'", 'use_cls_token': 'use_cls_token: bool = False', 'init_std': 'init_std: float = 0.02', 'share_projection': 'share_projection: bool = True', 'scaling': "scaling: Union[str, bool, NoneType] = 'std'", 'do_mask_input': 'do_mask_input: Optional[bool - ] = None', 'mask_type': "mask_type: str = 'random'", 'random_mask_ratio': 'random_mask_ratio: float = 0.5', 'num_forecast_mask_patches': 'num_forecast_mask_patches: Union[int, list[int - ], NoneType - ] = [ - 2 - ]', 'channel_consistent_masking': 'channel_consistent_masking: Optional[bool - ] = False', 'unmasked_channel_indices': 'unmasked_channel_indices: Optional[list[int - ] - ] = None', 'mask_value': 'mask_value: int = 0', 'pooling_type': "pooling_type: str = 'mean'", 'head_dropout': 'head_dropout: float = 0.0', 'prediction_length': 'prediction_length: int = 24', 'num_targets': 'num_targets: int = 1', 'output_range': 'output_range: Optional[list - ] = None', 'num_parallel_samples': 'num_parallel_samples: int = 100' -}, model_name='PatchTSTModel', library='transformers', import_path='transformers.models.patchtst'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_config': 'audio_config=None' -}, model_name='PeAudioModel', library='transformers', import_path='transformers.models.pe_audio'), ModelAttributes(model=, model_type='model', model_parameters={'dac_config': 'dac_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'hidden_size': 'hidden_size: Optional[int - ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int - ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 10000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='PeAudioEncoder', library='transformers', import_path='transformers.models.pe_audio'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'audio_video_config': 'audio_video_config=None' -}, model_name='PeAudioVideoModel', library='transformers', import_path='transformers.models.pe_audio_video'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'video_config': 'video_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'hidden_size': 'hidden_size: Optional[int - ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int - ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 10000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='PeAudioVideoEncoder', library='transformers', import_path='transformers.models.pe_audio_video'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'video_config': 'video_config=None' -}, model_name='PeVideoModel', library='transformers', import_path='transformers.models.pe_video'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType - ] = None', 'hidden_size': 'hidden_size: Optional[int - ] = 1792', 'intermediate_size': 'intermediate_size: Optional[int - ] = 4800', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 6', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 14', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 10000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-05', 'rope_parameters': "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='PeVideoEncoder', library='transformers', import_path='transformers.models.pe_video'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=12', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=0', 'scale_embedding': 'scale_embedding=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'forced_eos_token_id': 'forced_eos_token_id=1' -}, model_name='PegasusModel', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'pad_token': "pad_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'mask_token': "mask_token=''", 'mask_token_sent': "mask_token_sent=''", 'additional_special_tokens': 'additional_special_tokens=None', 'offset': 'offset=103' -}, model_name='PegasusTokenizer', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=96103', 'max_position_embeddings': 'max_position_embeddings=16384', 'encoder_layers': 'encoder_layers=16', 'encoder_ffn_dim': 'encoder_ffn_dim=4096', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=16', 'decoder_ffn_dim': 'decoder_ffn_dim=4096', 'decoder_attention_heads': 'decoder_attention_heads=16', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=1024', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=0', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'forced_eos_token_id': 'forced_eos_token_id=1', 'num_global_tokens': 'num_global_tokens=32', 'block_size': 'block_size=512', 'stagger_local_blocks': 'stagger_local_blocks=True' -}, model_name='PegasusXModel', library='transformers', import_path='transformers.models.pegasus_x'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'pad_token': "pad_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'mask_token': "mask_token=''", 'mask_token_sent': "mask_token_sent=''", 'additional_special_tokens': 'additional_special_tokens=None', 'offset': 'offset=103' -}, model_name='PegasusTokenizer', library='transformers', import_path='transformers.models.pegasus'), ModelAttributes(model=, model_type='model', model_parameters={'num_latents': 'num_latents=256', 'd_latents': 'd_latents=1280', 'd_model': 'd_model=768', 'num_blocks': 'num_blocks=1', 'num_self_attends_per_block': 'num_self_attends_per_block=26', 'num_self_attention_heads': 'num_self_attention_heads=8', 'num_cross_attention_heads': 'num_cross_attention_heads=8', 'qk_channels': 'qk_channels=None', 'v_channels': 'v_channels=None', 'cross_attention_shape_for_attention': "cross_attention_shape_for_attention='kv'", 'self_attention_widening_factor': 'self_attention_widening_factor=1', 'cross_attention_widening_factor': 'cross_attention_widening_factor=1', 'hidden_act': "hidden_act='gelu'", 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_query_residual': 'use_query_residual=True', 'vocab_size': 'vocab_size=262', 'max_position_embeddings': 'max_position_embeddings=2048', 'image_size': 'image_size=56', 'train_size': 'train_size=[ - 368, - 496 - ]', 'num_frames': 'num_frames=16', 'audio_samples_per_frame': 'audio_samples_per_frame=1920', 'samples_per_patch': 'samples_per_patch=16', 'output_shape': 'output_shape=[ - 1, - 16, - 224, - 224 - ]', 'output_num_channels': 'output_num_channels=512', '_label_trainable_num_channels': '_label_trainable_num_channels=1024' -}, model_name='PerceiverModel', library='transformers', import_path='transformers.models.perceiver'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'pad_token': "pad_token='[PAD]'", 'bos_token': "bos_token='[BOS]'", 'eos_token': "eos_token='[EOS]'", 'mask_token': "mask_token='[MASK]'", 'cls_token': "cls_token='[CLS]'", 'sep_token': "sep_token='[SEP]'", 'model_max_length': 'model_max_length=2048' -}, model_name='PerceiverTokenizer', library='transformers', import_path='transformers.models.perceiver'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'vision_use_cls_token': 'vision_use_cls_token=True', 'projector_pooling_ratio': 'projector_pooling_ratio=1', 'image_token_id': 'image_token_id=128002', 'video_token_id': 'video_token_id=128003' -}, model_name='PerceptionLMModel', library='transformers', import_path='transformers.models.perception_lm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 262144', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 16384', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'hidden_act': "hidden_act: Optional[str] = 'relu2'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 16384', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool - ] = True', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2' -}, model_name='PersimmonModel', library='transformers', import_path='transformers.models.persimmon'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 51200', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'resid_pdrop': 'resid_pdrop: Optional[float - ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'gelu_new'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 2048', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'qk_layernorm': 'qk_layernorm: Optional[bool - ] = False', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2' -}, model_name='PhiModel', library='transformers', import_path='transformers.models.phi'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32064', 'hidden_size': 'hidden_size: Optional[int - ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int - ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'resid_pdrop': 'resid_pdrop: Optional[float - ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'original_max_position_embeddings': 'original_max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 32000', 'pad_token_id': 'pad_token_id: Optional[int - ] = 32000', 'sliding_window': 'sliding_window: Optional[int - ] = None' -}, model_name='Phi3Model', library='transformers', import_path='transformers.models.phi3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 200064', 'hidden_size': 'hidden_size: Optional[int - ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int - ] = 8192', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'resid_pdrop': 'resid_pdrop: Optional[float - ] = 0.0', 'embd_pdrop': 'embd_pdrop: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 199999', 'eos_token_id': 'eos_token_id: Optional[list[int - ] - ] = [ - 199999, - 200020 - ]', 'pad_token_id': 'pad_token_id: Optional[int - ] = 199999', 'original_max_position_embeddings': 'original_max_position_embeddings: Optional[int - ] = 4096', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'vision_config': 'vision_config: Optional[dict - ] = None', 'audio_config': 'audio_config: Optional[dict - ] = None' -}, model_name='Phi4MultimodalModel', library='transformers', import_path='transformers.models.phi4_multimodal'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32064', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 6400', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 131072', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'pad_token_id': 'pad_token_id: Optional[int - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[int - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 2', 'num_local_experts': 'num_local_experts: Optional[int - ] = 16', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'router_jitter_noise': 'router_jitter_noise: Optional[float - ] = 0.01', 'input_jitter_noise': 'input_jitter_noise: Optional[float - ] = 0.0', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'lm_head_bias': 'lm_head_bias: Optional[bool - ] = False' -}, model_name='PhimoeModel', library='transformers', import_path='transformers.models.phimoe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1280', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=16', 'mlp_ratio': 'mlp_ratio=4', 'n_cls_tokens': 'n_cls_tokens=8', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=256', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'drop_path_rate': 'drop_path_rate=0.0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None', 'apply_layernorm': 'apply_layernorm=True', 'reshape_hidden_states': 'reshape_hidden_states=True' -}, model_name='PixioModel', library='transformers', import_path='transformers.models.pixio'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size: Optional[int - ] = 1024', 'intermediate_size': 'intermediate_size: Optional[int - ] = 4096', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_channels': 'num_channels: Optional[int - ] = 3', 'image_size': 'image_size: Optional[int - ] = 1024', 'patch_size': 'patch_size: Optional[int - ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02' -}, model_name='PixtralVisionModel', library='transformers', import_path='transformers.models.pixtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50005', 'max_position_embeddings': 'max_position_embeddings=1024', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=3072', 'encoder_attention_heads': 'encoder_attention_heads=12', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=3072', 'decoder_attention_heads': 'decoder_attention_heads=12', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=768', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'classifier_dropout': 'classifier_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'forced_eos_token_id': 'forced_eos_token_id=2' -}, model_name='PLBartModel', library='transformers', import_path='transformers.models.plbart'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'mask_token': "mask_token=''", 'language_codes': "language_codes='base'", 'src_lang': 'src_lang=None', 'tgt_lang': 'tgt_lang=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None', 'additional_special_tokens': 'additional_special_tokens=None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=True' -}, model_name='PLBartTokenizer', library='transformers', import_path='transformers.models.plbart'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'stride': 'stride=16', 'pool_size': 'pool_size=3', 'mlp_ratio': 'mlp_ratio=4.0', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'hidden_sizes': 'hidden_sizes=[ - 64, - 128, - 320, - 512 - ]', 'patch_sizes': 'patch_sizes=[ - 7, - 3, - 3, - 3 - ]', 'strides': 'strides=[ - 4, - 2, - 2, - 2 - ]', 'padding': 'padding=[ - 2, - 1, - 1, - 1 - ]', 'num_encoder_blocks': 'num_encoder_blocks=4', 'drop_path_rate': 'drop_path_rate=0.0', 'hidden_act': "hidden_act='gelu'", 'use_layer_scale': 'use_layer_scale=True', 'layer_scale_init_value': 'layer_scale_init_value=1e-05', 'initializer_range': 'initializer_range=0.02' -}, model_name='PoolFormerModel', library='transformers', import_path='transformers.models.poolformer'), ModelAttributes(model=, model_type='model', model_parameters={'activation_dropout': 'activation_dropout: Optional[float - ] = 0.1', 'activation_function': "activation_function: Union[str, collections.abc.Callable, NoneType] = 'gelu'", 'vocab_size': 'vocab_size: Optional[int - ] = 30522', 'hidden_size': 'hidden_size: Optional[int - ] = 1024', 'encoder_ffn_dim': 'encoder_ffn_dim: Optional[int - ] = 4096', 'num_encoder_layers': 'num_encoder_layers: Optional[int - ] = 12', 'num_encoder_attention_heads': 'num_encoder_attention_heads: Optional[int - ] = 16', 'decoder_ffn_dim': 'decoder_ffn_dim: Optional[int - ] = 4096', 'num_decoder_layers': 'num_decoder_layers: Optional[int - ] = 12', 'num_decoder_attention_heads': 'num_decoder_attention_heads: Optional[int - ] = 16', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.1', 'dropout': 'dropout: Optional[float - ] = 0.1', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 512', 'init_std': 'init_std: Optional[float - ] = 0.02', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool - ] = True', 'add_cross_attention': 'add_cross_attention: Optional[bool - ] = True', 'decoder_start_token_id': 'decoder_start_token_id: Optional[int - ] = 0', 'ngram': 'ngram: Optional[int - ] = 2', 'num_buckets': 'num_buckets: Optional[int - ] = 32', 'relative_max_distance': 'relative_max_distance: Optional[int - ] = 128', 'disable_ngram_loss': 'disable_ngram_loss: Optional[bool - ] = False', 'eps': 'eps: Optional[float - ] = 0.0', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2' -}, model_name='ProphetNetModel', library='transformers', import_path='transformers.models.prophetnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file: str', 'do_lower_case': 'do_lower_case: Optional[bool - ] = True', 'do_basic_tokenize': 'do_basic_tokenize: Optional[bool - ] = True', 'never_split': 'never_split: Optional[collections.abc.Iterable - ] = None', 'unk_token': "unk_token: Optional[str] = '[UNK]'", 'sep_token': "sep_token: Optional[str] = '[SEP]'", 'x_sep_token': "x_sep_token: Optional[str] = '[X_SEP]'", 'pad_token': "pad_token: Optional[str] = '[PAD]'", 'mask_token': "mask_token: Optional[str] = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: Optional[bool - ] = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces: bool = True' -}, model_name='ProphetNetTokenizer', library='transformers', import_path='transformers.models.prophetnet'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size: int = 224', 'num_channels': 'num_channels: int = 3', 'num_encoder_blocks': 'num_encoder_blocks: int = 4', 'depths': 'depths: list[int - ] = [ - 2, - 2, - 2, - 2 - ]', 'sequence_reduction_ratios': 'sequence_reduction_ratios: list[int - ] = [ - 8, - 4, - 2, - 1 - ]', 'hidden_sizes': 'hidden_sizes: list[int - ] = [ - 64, - 128, - 320, - 512 - ]', 'patch_sizes': 'patch_sizes: list[int - ] = [ - 4, - 2, - 2, - 2 - ]', 'strides': 'strides: list[int - ] = [ - 4, - 2, - 2, - 2 - ]', 'num_attention_heads': 'num_attention_heads: list[int - ] = [ - 1, - 2, - 5, - 8 - ]', 'mlp_ratios': 'mlp_ratios: list[int - ] = [ - 8, - 8, - 4, - 4 - ]', 'hidden_act': "hidden_act: collections.abc.Mapping[str, collections.abc.Callable] = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'qkv_bias': 'qkv_bias: bool = True', 'num_labels': 'num_labels: int = 1000' -}, model_name='PvtModel', library='transformers', import_path='transformers.models.pvt'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size: Union[int, tuple[int, int - ] - ] = 224', 'num_channels': 'num_channels: int = 3', 'num_encoder_blocks': 'num_encoder_blocks: int = 4', 'depths': 'depths: list[int - ] = [ - 2, - 2, - 2, - 2 - ]', 'sr_ratios': 'sr_ratios: list[int - ] = [ - 8, - 4, - 2, - 1 - ]', 'hidden_sizes': 'hidden_sizes: list[int - ] = [ - 32, - 64, - 160, - 256 - ]', 'patch_sizes': 'patch_sizes: list[int - ] = [ - 7, - 3, - 3, - 3 - ]', 'strides': 'strides: list[int - ] = [ - 4, - 2, - 2, - 2 - ]', 'num_attention_heads': 'num_attention_heads: list[int - ] = [ - 1, - 2, - 5, - 8 - ]', 'mlp_ratios': 'mlp_ratios: list[int - ] = [ - 8, - 8, - 4, - 4 - ]', 'hidden_act': "hidden_act: Union[str, collections.abc.Callable] = 'gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob: float = 0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'drop_path_rate': 'drop_path_rate: float = 0.0', 'layer_norm_eps': 'layer_norm_eps: float = 1e-06', 'qkv_bias': 'qkv_bias: bool = True', 'linear_attention': 'linear_attention: bool = False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='PvtV2Model', library='transformers', import_path='transformers.models.pvt_v2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 28', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='Qwen2Model', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653' -}, model_name='Qwen2_5_VLModel', library='transformers', import_path='transformers.models.qwen2_5_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 152064', 'hidden_size': 'hidden_size: Optional[int - ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int - ] = 29568', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 80', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 80', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 151643', 'eos_token_id': 'eos_token_id: Optional[int - ] = 151645', 'pad_token_id': 'pad_token_id: Optional[int - ] = None' -}, model_name='Qwen2_5_VLTextModel', library='transformers', import_path='transformers.models.qwen2_5_vl'), ModelAttributes(model=, model_type='model', model_parameters={'num_mel_bins': 'num_mel_bins=128', 'encoder_layers': 'encoder_layers=32', 'encoder_attention_heads': 'encoder_attention_heads=20', 'encoder_ffn_dim': 'encoder_ffn_dim=5120', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'd_model': 'd_model=1280', 'dropout': 'dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'activation_function': "activation_function='gelu'", 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=False', 'initializer_range': 'initializer_range=0.02', 'max_source_positions': 'max_source_positions=1500' -}, model_name='Qwen2AudioEncoder', library='transformers', import_path='transformers.models.qwen2_audio'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 28', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int - ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1408', 'shared_expert_intermediate_size': 'shared_expert_intermediate_size: Optional[int - ] = 5632', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 4', 'num_experts': 'num_experts: Optional[int - ] = 60', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[bool - ] = None', 'qkv_bias': 'qkv_bias: Optional[bool - ] = True', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Qwen2MoeModel', library='transformers', import_path='transformers.models.qwen2_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653' -}, model_name='Qwen2VLModel', library='transformers', import_path='transformers.models.qwen2_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 152064', 'hidden_size': 'hidden_size: Optional[int - ] = 8192', 'intermediate_size': 'intermediate_size: Optional[int - ] = 29568', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 80', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 64', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 80', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'bos_token_id': 'bos_token_id: Optional[int - ] = 151643', 'eos_token_id': 'eos_token_id: Optional[int - ] = 151645', 'pad_token_id': 'pad_token_id: Optional[int - ] = None' -}, model_name='Qwen2VLTextModel', library='transformers', import_path='transformers.models.qwen2_vl'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'max_window_layers': 'max_window_layers: Optional[int - ] = 28', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='Qwen3Model', library='transformers', import_path='transformers.models.qwen3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 6144', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int - ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 768', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 8', 'num_experts': 'num_experts: Optional[int - ] = 128', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = False', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[bool - ] = None' -}, model_name='Qwen3MoeModel', library='transformers', import_path='transformers.models.qwen3_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 48', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'head_dim': 'head_dim: Optional[int - ] = 256', 'linear_conv_kernel_dim': 'linear_conv_kernel_dim: Optional[int - ] = 4', 'linear_key_head_dim': 'linear_key_head_dim: Optional[int - ] = 128', 'linear_value_head_dim': 'linear_value_head_dim: Optional[int - ] = 128', 'linear_num_key_heads': 'linear_num_key_heads: Optional[int - ] = 16', 'linear_num_value_heads': 'linear_num_value_heads: Optional[int - ] = 32', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int - ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 512', 'shared_expert_intermediate_size': 'shared_expert_intermediate_size: Optional[int - ] = 512', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 10', 'num_experts': 'num_experts: Optional[int - ] = 512', 'norm_topk_prob': 'norm_topk_prob: Optional[bool - ] = True', 'output_router_logits': 'output_router_logits: Optional[bool - ] = False', 'router_aux_loss_coef': 'router_aux_loss_coef: Optional[float - ] = 0.001', 'mlp_only_layers': 'mlp_only_layers: Optional[list[int - ] - ] = []', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None' -}, model_name='Qwen3NextModel', library='transformers', import_path='transformers.models.qwen3_next'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='Qwen3VLModel', library='transformers', import_path='transformers.models.qwen3_vl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656', 'vision_start_token_id': 'vision_start_token_id=151652', 'vision_end_token_id': 'vision_end_token_id=151653', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='Qwen3VLMoeModel', library='transformers', import_path='transformers.models.qwen3_vl_moe'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'vocab_file': 'vocab_file=None', 'merges_file': 'merges_file=None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': 'bos_token=None', 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=None' -}, model_name='Qwen2Tokenizer', library='transformers', import_path='transformers.models.qwen2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 5632', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 24', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 16', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 128000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'decoder_sparse_step': 'decoder_sparse_step: Optional[int - ] = 1', 'moe_intermediate_size': 'moe_intermediate_size: Optional[int - ] = 1408', 'num_experts_per_tok': 'num_experts_per_tok: Optional[int - ] = 4', 'num_experts': 'num_experts: Optional[int - ] = 60', 'mlp_only_layers': 'mlp_only_layers: Optional[list[int - ] - ] = None', 'rope_parameters': 'rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters - ] = None', 'head_dim': 'head_dim: Optional[int - ] = None' -}, model_name='Qwen3VLMoeTextModel', library='transformers', import_path='transformers.models.qwen3_vl_moe'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 151936', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 22016', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'head_dim': 'head_dim: Optional[int - ] = 128', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 128000', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0' -}, model_name='Qwen3VLTextModel', library='transformers', import_path='transformers.models.qwen3_vl'), ModelAttributes(model=, model_type='model', model_parameters={'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 26', 'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'intermediate_size': 'intermediate_size: Optional[int - ] = 7680', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 10', 'lru_width': 'lru_width: Optional[int - ] = None', 'attention_window_size': 'attention_window_size: Optional[int - ] = 2048', 'conv1d_width': 'conv1d_width: Optional[int - ] = 4', 'logits_soft_cap': 'logits_soft_cap: Optional[float - ] = 30.0', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'block_types': "block_types: Optional[list[str]] = ('recurrent', 'recurrent', 'attention')", 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'attention_bias': 'attention_bias: Optional[str - ] = False', 'w_init_variance_scale': 'w_init_variance_scale: Optional[float - ] = 0.01' -}, model_name='RecurrentGemmaModel', library='transformers', import_path='transformers.models.recurrent_gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'attention_head_size': 'attention_head_size=64', 'attn_layers': "attn_layers=['local', 'lsh', 'local', 'lsh', 'local', 'lsh']", 'axial_norm_std': 'axial_norm_std=1.0', 'axial_pos_embds': 'axial_pos_embds=True', 'axial_pos_shape': 'axial_pos_shape=[ - 64, - 64 - ]', 'axial_pos_embds_dim': 'axial_pos_embds_dim=[ - 64, - 192 - ]', 'chunk_size_lm_head': 'chunk_size_lm_head=0', 'eos_token_id': 'eos_token_id=2', 'feed_forward_size': 'feed_forward_size=512', 'hash_seed': 'hash_seed=None', 'hidden_act': "hidden_act='relu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.05', 'hidden_size': 'hidden_size=256', 'initializer_range': 'initializer_range=0.02', 'is_decoder': 'is_decoder=False', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'local_num_chunks_before': 'local_num_chunks_before=1', 'local_num_chunks_after': 'local_num_chunks_after=0', 'local_attention_probs_dropout_prob': 'local_attention_probs_dropout_prob=0.05', 'local_attn_chunk_length': 'local_attn_chunk_length=64', 'lsh_attn_chunk_length': 'lsh_attn_chunk_length=64', 'lsh_attention_probs_dropout_prob': 'lsh_attention_probs_dropout_prob=0.0', 'lsh_num_chunks_before': 'lsh_num_chunks_before=1', 'lsh_num_chunks_after': 'lsh_num_chunks_after=0', 'max_position_embeddings': 'max_position_embeddings=4096', 'num_attention_heads': 'num_attention_heads=12', 'num_buckets': 'num_buckets=None', 'num_hashes': 'num_hashes=1', 'pad_token_id': 'pad_token_id=0', 'vocab_size': 'vocab_size=320', 'tie_word_embeddings': 'tie_word_embeddings=False', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='ReformerModel', library='transformers', import_path='transformers.models.reformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'eos_token': "eos_token: str = ''", 'unk_token': "unk_token: str = ''", 'additional_special_tokens': 'additional_special_tokens: Optional[list - ] = None' -}, model_name='ReformerTokenizer', library='transformers', import_path='transformers.models.reformer'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=32', 'hidden_sizes': 'hidden_sizes=[ - 128, - 192, - 512, - 1088 - ]', 'depths': 'depths=[ - 2, - 6, - 12, - 2 - ]', 'groups_width': 'groups_width=64', 'layer_type': "layer_type='y'", 'hidden_act': "hidden_act='relu'" -}, model_name='RegNetModel', library='transformers', import_path='transformers.models.regnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250300', 'hidden_size': 'hidden_size=1152', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=18', 'input_embedding_size': 'input_embedding_size=256', 'output_embedding_size': 'output_embedding_size=1664', 'intermediate_size': 'intermediate_size=4608', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=312', 'eos_token_id': 'eos_token_id=313' -}, model_name='RemBertModel', library='transformers', import_path='transformers.models.rembert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'remove_space': 'remove_space: bool = True' -}, model_name='RemBertTokenizer', library='transformers', import_path='transformers.models.rembert'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'embedding_size': 'embedding_size=64', 'hidden_sizes': 'hidden_sizes=[ - 256, - 512, - 1024, - 2048 - ]', 'depths': 'depths=[ - 3, - 4, - 6, - 3 - ]', 'layer_type': "layer_type='bottleneck'", 'hidden_act': "hidden_act='relu'", 'downsample_in_first_stage': 'downsample_in_first_stage=False', 'downsample_in_bottleneck': 'downsample_in_bottleneck=False', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='ResNetModel', library='transformers', import_path='transformers.models.resnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='RobertaModel', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='RobertaPreLayerNormModel', library='transformers', import_path='transformers.models.roberta_prelayernorm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='RobertaTokenizer', library='transformers', import_path='transformers.models.roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'classifier_dropout': 'classifier_dropout=None', 'enable_pronunciation': 'enable_pronunciation=True', 'enable_shape': 'enable_shape=True', 'pronunciation_embed_dim': 'pronunciation_embed_dim=768', 'pronunciation_vocab_size': 'pronunciation_vocab_size=910', 'shape_embed_dim': 'shape_embed_dim=512', 'shape_vocab_size': 'shape_vocab_size=24858', 'concat_input': 'concat_input=True' -}, model_name='RoCBertModel', library='transformers', import_path='transformers.models.roc_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'word_shape_file': 'word_shape_file', 'word_pronunciation_file': 'word_pronunciation_file', 'do_lower_case': 'do_lower_case=True', 'do_basic_tokenize': 'do_basic_tokenize=True', 'never_split': 'never_split=None', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' -}, model_name='RoCBertTokenizer', library='transformers', import_path='transformers.models.roc_bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50000', 'embedding_size': 'embedding_size=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1536', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'rotary_value': 'rotary_value=False' -}, model_name='RoFormerModel', library='transformers', import_path='transformers.models.roformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Optional[dict[str, int - ] - ] = None', 'do_lower_case': 'do_lower_case=True', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None' -}, model_name='RoFormerTokenizer', library='transformers', import_path='transformers.models.roformer'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ - 512, - 1024, - 2048 - ]', 'feat_strides': 'feat_strides=[ - 8, - 16, - 32 - ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ - 2 - ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ - 256, - 256, - 256 - ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'disable_custom_kernels': 'disable_custom_kernels=True', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'eos_coefficient': 'eos_coefficient=0.0001' -}, model_name='RTDetrModel', library='transformers', import_path='transformers.models.rt_detr'), ModelAttributes(model=, model_type='model', model_parameters={'initializer_range': 'initializer_range=0.01', 'initializer_bias_prior_prob': 'initializer_bias_prior_prob=None', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'freeze_backbone_batch_norms': 'freeze_backbone_batch_norms=True', 'backbone_kwargs': 'backbone_kwargs=None', 'encoder_hidden_dim': 'encoder_hidden_dim=256', 'encoder_in_channels': 'encoder_in_channels=[ - 512, - 1024, - 2048 - ]', 'feat_strides': 'feat_strides=[ - 8, - 16, - 32 - ]', 'encoder_layers': 'encoder_layers=1', 'encoder_ffn_dim': 'encoder_ffn_dim=1024', 'encoder_attention_heads': 'encoder_attention_heads=8', 'dropout': 'dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'encode_proj_layers': 'encode_proj_layers=[ - 2 - ]', 'positional_encoding_temperature': 'positional_encoding_temperature=10000', 'encoder_activation_function': "encoder_activation_function='gelu'", 'activation_function': "activation_function='silu'", 'eval_size': 'eval_size=None', 'normalize_before': 'normalize_before=False', 'hidden_expansion': 'hidden_expansion=1.0', 'd_model': 'd_model=256', 'num_queries': 'num_queries=300', 'decoder_in_channels': 'decoder_in_channels=[ - 256, - 256, - 256 - ]', 'decoder_ffn_dim': 'decoder_ffn_dim=1024', 'num_feature_levels': 'num_feature_levels=3', 'decoder_n_points': 'decoder_n_points=4', 'decoder_layers': 'decoder_layers=6', 'decoder_attention_heads': 'decoder_attention_heads=8', 'decoder_activation_function': "decoder_activation_function='relu'", 'attention_dropout': 'attention_dropout=0.0', 'num_denoising': 'num_denoising=100', 'label_noise_ratio': 'label_noise_ratio=0.5', 'box_noise_scale': 'box_noise_scale=1.0', 'learn_initial_query': 'learn_initial_query=False', 'anchor_image_size': 'anchor_image_size=None', 'with_box_refine': 'with_box_refine=True', 'is_encoder_decoder': 'is_encoder_decoder=True', 'matcher_alpha': 'matcher_alpha=0.25', 'matcher_gamma': 'matcher_gamma=2.0', 'matcher_class_cost': 'matcher_class_cost=2.0', 'matcher_bbox_cost': 'matcher_bbox_cost=5.0', 'matcher_giou_cost': 'matcher_giou_cost=2.0', 'use_focal_loss': 'use_focal_loss=True', 'auxiliary_loss': 'auxiliary_loss=True', 'focal_loss_alpha': 'focal_loss_alpha=0.75', 'focal_loss_gamma': 'focal_loss_gamma=2.0', 'weight_loss_vfl': 'weight_loss_vfl=1.0', 'weight_loss_bbox': 'weight_loss_bbox=5.0', 'weight_loss_giou': 'weight_loss_giou=2.0', 'eos_coefficient': 'eos_coefficient=0.0001', 'decoder_n_levels': 'decoder_n_levels=3', 'decoder_offset_scale': 'decoder_offset_scale=0.5', 'decoder_method': "decoder_method='default'" -}, model_name='RTDetrV2Model', library='transformers', import_path='transformers.models.rt_detr_v2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50277', 'context_length': 'context_length=1024', 'hidden_size': 'hidden_size=4096', 'num_hidden_layers': 'num_hidden_layers=32', 'attention_hidden_size': 'attention_hidden_size=None', 'intermediate_size': 'intermediate_size=None', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-05', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=0', 'rescale_every': 'rescale_every=6', 'tie_word_embeddings': 'tie_word_embeddings=False' -}, model_name='RwkvModel', library='transformers', import_path='transformers.models.rwkv'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='SamModel', library='transformers', import_path='transformers.models.sam'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam2Model', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=96', 'num_attention_heads': 'num_attention_heads=1', 'num_channels': 'num_channels=3', 'image_size': 'image_size=None', 'patch_kernel_size': 'patch_kernel_size=None', 'patch_stride': 'patch_stride=None', 'patch_padding': 'patch_padding=None', 'query_stride': 'query_stride=None', 'window_positional_embedding_background_size': 'window_positional_embedding_background_size=None', 'num_query_pool_stages': 'num_query_pool_stages=3', 'blocks_per_stage': 'blocks_per_stage=None', 'embed_dim_per_stage': 'embed_dim_per_stage=None', 'num_attention_heads_per_stage': 'num_attention_heads_per_stage=None', 'window_size_per_stage': 'window_size_per_stage=None', 'global_attention_blocks': 'global_attention_blocks=None', 'mlp_ratio': 'mlp_ratio=4.0', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam2HieraDetModel', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1024', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=-1', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=4', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_feed_forward_hidden_size': 'memory_attention_feed_forward_hidden_size=2048', 'memory_attention_feed_forward_hidden_act': "memory_attention_feed_forward_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" -}, model_name='Sam2VideoModel', library='transformers', import_path='transformers.models.sam2_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone_channel_list': 'backbone_channel_list=None', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'fpn_kernel_size': 'fpn_kernel_size=1', 'fpn_stride': 'fpn_stride=1', 'fpn_padding': 'fpn_padding=0', 'fpn_top_down_levels': 'fpn_top_down_levels=None', 'num_feature_levels': 'num_feature_levels=3', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam2VisionModel', library='transformers', import_path='transformers.models.sam2'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'geometry_encoder_config': 'geometry_encoder_config=None', 'detr_encoder_config': 'detr_encoder_config=None', 'detr_decoder_config': 'detr_decoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam3Model', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam3TrackerModel', library='transformers', import_path='transformers.models.sam3_tracker'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02', 'num_maskmem': 'num_maskmem=7', 'image_size': 'image_size=1008', 'sigmoid_scale_for_mem_enc': 'sigmoid_scale_for_mem_enc=20.0', 'sigmoid_bias_for_mem_enc': 'sigmoid_bias_for_mem_enc=-10.0', 'enable_occlusion_spatial_embedding': 'enable_occlusion_spatial_embedding=True', 'multimask_output_in_sam': 'multimask_output_in_sam=True', 'multimask_min_pt_num': 'multimask_min_pt_num=0', 'multimask_max_pt_num': 'multimask_max_pt_num=1', 'multimask_output_for_tracking': 'multimask_output_for_tracking=True', 'max_object_pointers_in_encoder': 'max_object_pointers_in_encoder=16', 'max_cond_frame_num': 'max_cond_frame_num=4', 'enable_temporal_pos_encoding_for_object_pointers': 'enable_temporal_pos_encoding_for_object_pointers=True', 'memory_attention_hidden_size': 'memory_attention_hidden_size=256', 'memory_attention_num_layers': 'memory_attention_num_layers=4', 'memory_attention_num_attention_heads': 'memory_attention_num_attention_heads=1', 'memory_attention_downsample_rate': 'memory_attention_downsample_rate=1', 'memory_attention_feed_forward_hidden_size': 'memory_attention_feed_forward_hidden_size=2048', 'memory_attention_feed_forward_hidden_act': "memory_attention_feed_forward_hidden_act='relu'", 'memory_attention_dropout': 'memory_attention_dropout=0.1', 'memory_attention_rope_theta': 'memory_attention_rope_theta=10000', 'memory_attention_rope_feat_sizes': 'memory_attention_rope_feat_sizes=None', 'memory_attention_rope_dropout': 'memory_attention_rope_dropout=0.1', 'memory_encoder_hidden_size': 'memory_encoder_hidden_size=256', 'memory_encoder_output_channels': 'memory_encoder_output_channels=64', 'mask_downsampler_embed_dim': 'mask_downsampler_embed_dim=256', 'mask_downsampler_kernel_size': 'mask_downsampler_kernel_size=3', 'mask_downsampler_stride': 'mask_downsampler_stride=2', 'mask_downsampler_padding': 'mask_downsampler_padding=1', 'mask_downsampler_total_stride': 'mask_downsampler_total_stride=16', 'mask_downsampler_hidden_act': "mask_downsampler_hidden_act='gelu'", 'memory_fuser_num_layers': 'memory_fuser_num_layers=2', 'memory_fuser_embed_dim': 'memory_fuser_embed_dim=256', 'memory_fuser_intermediate_dim': 'memory_fuser_intermediate_dim=1024', 'memory_fuser_kernel_size': 'memory_fuser_kernel_size=7', 'memory_fuser_padding': 'memory_fuser_padding=3', 'memory_fuser_layer_scale_init_value': 'memory_fuser_layer_scale_init_value=1e-06', 'memory_fuser_hidden_act': "memory_fuser_hidden_act='gelu'" -}, model_name='Sam3TrackerVideoModel', library='transformers', import_path='transformers.models.sam3_tracker_video'), ModelAttributes(model=, model_type='model', model_parameters={'detector_config': 'detector_config=None', 'tracker_config': 'tracker_config=None', 'initializer_range': 'initializer_range=0.02', 'low_res_mask_size': 'low_res_mask_size=288', 'score_threshold_detection': 'score_threshold_detection=0.5', 'det_nms_thresh': 'det_nms_thresh=0.1', 'assoc_iou_thresh': 'assoc_iou_thresh=0.1', 'trk_assoc_iou_thresh': 'trk_assoc_iou_thresh=0.5', 'new_det_thresh': 'new_det_thresh=0.7', 'recondition_on_trk_masks': 'recondition_on_trk_masks=True', 'hotstart_delay': 'hotstart_delay=15', 'hotstart_unmatch_thresh': 'hotstart_unmatch_thresh=8', 'hotstart_dup_thresh': 'hotstart_dup_thresh=8', 'suppress_unmatched_only_within_hotstart': 'suppress_unmatched_only_within_hotstart=True', 'init_trk_keep_alive': 'init_trk_keep_alive=30', 'max_trk_keep_alive': 'max_trk_keep_alive=30', 'min_trk_keep_alive': 'min_trk_keep_alive=-1', 'suppress_overlapping_based_on_recent_occlusion_threshold': 'suppress_overlapping_based_on_recent_occlusion_threshold=0.7', 'decrease_trk_keep_alive_for_empty_masklets': 'decrease_trk_keep_alive_for_empty_masklets=False', 'fill_hole_area': 'fill_hole_area=16', 'max_num_objects': 'max_num_objects=10000', 'recondition_every_nth_frame': 'recondition_every_nth_frame=16', 'high_conf_thresh': 'high_conf_thresh=0.8', 'high_iou_thresh': 'high_iou_thresh=0.8' -}, model_name='Sam3VideoModel', library='transformers', import_path='transformers.models.sam3_video'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'fpn_hidden_size': 'fpn_hidden_size=256', 'backbone_feature_sizes': 'backbone_feature_sizes=None', 'scale_factors': 'scale_factors=None', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam3VisionModel', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'intermediate_size': 'intermediate_size=4736', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1008', 'patch_size': 'patch_size=14', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'rope_theta': 'rope_theta=10000.0', 'window_size': 'window_size=24', 'global_attn_indexes': 'global_attn_indexes=None', 'layer_scale_init_value': 'layer_scale_init_value=None', 'pretrain_image_size': 'pretrain_image_size=336', 'hidden_dropout': 'hidden_dropout=0.0', 'initializer_range': 'initializer_range=0.02' -}, model_name='Sam3ViTModel', library='transformers', import_path='transformers.models.sam3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'prompt_encoder_config': 'prompt_encoder_config=None', 'mask_decoder_config': 'mask_decoder_config=None', 'initializer_range': 'initializer_range=0.02' -}, model_name='SamHQModel', library='transformers', import_path='transformers.models.sam_hq'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'output_channels': 'output_channels=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1024', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=1e-10', 'qkv_bias': 'qkv_bias=True', 'mlp_ratio': 'mlp_ratio=4.0', 'use_abs_pos': 'use_abs_pos=True', 'use_rel_pos': 'use_rel_pos=True', 'window_size': 'window_size=14', 'global_attn_indexes': 'global_attn_indexes=[ - 2, - 5, - 8, - 11 - ]', 'num_pos_feats': 'num_pos_feats=128', 'mlp_dim': 'mlp_dim=None' -}, model_name='SamHQVisionModel', library='transformers', import_path='transformers.models.sam_hq'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'output_channels': 'output_channels=256', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=1024', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=1e-10', 'qkv_bias': 'qkv_bias=True', 'mlp_ratio': 'mlp_ratio=4.0', 'use_abs_pos': 'use_abs_pos=True', 'use_rel_pos': 'use_rel_pos=True', 'window_size': 'window_size=14', 'global_attn_indexes': 'global_attn_indexes=[ - 2, - 5, - 8, - 11 - ]', 'num_pos_feats': 'num_pos_feats=128', 'mlp_dim': 'mlp_dim=None' -}, model_name='SamVisionModel', library='transformers', import_path='transformers.models.sam'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256102', 't2u_vocab_size': 't2u_vocab_size=10082', 'hidden_size': 'hidden_size=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'max_position_embeddings': 'max_position_embeddings=1024', 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'activation_function': "activation_function='relu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'encoder_layers': 'encoder_layers=24', 'encoder_ffn_dim': 'encoder_ffn_dim=8192', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=8192', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_start_token_id': 'decoder_start_token_id=3', 'max_new_tokens': 'max_new_tokens=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=3', 'speech_encoder_layers': 'speech_encoder_layers=24', 'speech_encoder_attention_heads': 'speech_encoder_attention_heads=16', 'speech_encoder_intermediate_size': 'speech_encoder_intermediate_size=4096', 'speech_encoder_hidden_act': "speech_encoder_hidden_act='swish'", 'speech_encoder_dropout': 'speech_encoder_dropout=0.0', 'add_adapter': 'add_adapter=True', 'speech_encoder_layerdrop': 'speech_encoder_layerdrop=0.1', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'adaptor_kernel_size': 'adaptor_kernel_size=8', 'adaptor_stride': 'adaptor_stride=8', 'adaptor_dropout': 'adaptor_dropout=0.1', 'num_adapter_layers': 'num_adapter_layers=1', 'position_embeddings_type': "position_embeddings_type='relative'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=4096', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 't2u_bos_token_id': 't2u_bos_token_id=0', 't2u_pad_token_id': 't2u_pad_token_id=1', 't2u_eos_token_id': 't2u_eos_token_id=2', 't2u_decoder_start_token_id': 't2u_decoder_start_token_id=2', 't2u_max_new_tokens': 't2u_max_new_tokens=1024', 't2u_encoder_layers': 't2u_encoder_layers=6', 't2u_encoder_ffn_dim': 't2u_encoder_ffn_dim=8192', 't2u_encoder_attention_heads': 't2u_encoder_attention_heads=16', 't2u_decoder_layers': 't2u_decoder_layers=6', 't2u_decoder_ffn_dim': 't2u_decoder_ffn_dim=8192', 't2u_decoder_attention_heads': 't2u_decoder_attention_heads=16', 't2u_max_position_embeddings': 't2u_max_position_embeddings=2048', 'sampling_rate': 'sampling_rate=16000', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ - 5, - 4, - 4, - 2, - 2 - ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ - 11, - 8, - 8, - 4, - 4 - ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ - 3, - 7, - 11 - ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ] - ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'unit_hifi_gan_vocab_size': 'unit_hifi_gan_vocab_size=10000', 'unit_embed_dim': 'unit_embed_dim=1280', 'lang_embed_dim': 'lang_embed_dim=256', 'spkr_embed_dim': 'spkr_embed_dim=256', 'vocoder_num_langs': 'vocoder_num_langs=36', 'vocoder_num_spkrs': 'vocoder_num_spkrs=200', 'variance_predictor_kernel_size': 'variance_predictor_kernel_size=3', 'var_pred_dropout': 'var_pred_dropout=0.5', 'vocoder_offset': 'vocoder_offset=4' -}, model_name='SeamlessM4TModel', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'src_lang': "src_lang='eng'", 'tgt_lang': "tgt_lang='fra'", 'additional_special_tokens': 'additional_special_tokens=None', 'keep_accents': 'keep_accents=None', 'vocab_file': 'vocab_file=None' -}, model_name='SeamlessM4TTokenizer', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256102', 't2u_vocab_size': 't2u_vocab_size=10082', 'char_vocab_size': 'char_vocab_size=10943', 'hidden_size': 'hidden_size=1024', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'max_position_embeddings': 'max_position_embeddings=4096', 'is_encoder_decoder': 'is_encoder_decoder=True', 'encoder_layerdrop': 'encoder_layerdrop=0.05', 'decoder_layerdrop': 'decoder_layerdrop=0.05', 'activation_function': "activation_function='relu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'scale_embedding': 'scale_embedding=True', 'encoder_layers': 'encoder_layers=24', 'encoder_ffn_dim': 'encoder_ffn_dim=8192', 'encoder_attention_heads': 'encoder_attention_heads=16', 'decoder_layers': 'decoder_layers=24', 'decoder_ffn_dim': 'decoder_ffn_dim=8192', 'decoder_attention_heads': 'decoder_attention_heads=16', 'decoder_start_token_id': 'decoder_start_token_id=3', 'max_new_tokens': 'max_new_tokens=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=2', 'eos_token_id': 'eos_token_id=3', 'speech_encoder_layers': 'speech_encoder_layers=24', 'speech_encoder_attention_heads': 'speech_encoder_attention_heads=16', 'speech_encoder_intermediate_size': 'speech_encoder_intermediate_size=4096', 'speech_encoder_hidden_act': "speech_encoder_hidden_act='swish'", 'speech_encoder_dropout': 'speech_encoder_dropout=0.0', 'add_adapter': 'add_adapter=True', 'speech_encoder_layerdrop': 'speech_encoder_layerdrop=0.1', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'adaptor_kernel_size': 'adaptor_kernel_size=8', 'adaptor_stride': 'adaptor_stride=8', 'adaptor_dropout': 'adaptor_dropout=0.1', 'num_adapter_layers': 'num_adapter_layers=1', 'position_embeddings_type': "position_embeddings_type='relative_key'", 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'left_max_position_embeddings': 'left_max_position_embeddings=64', 'right_max_position_embeddings': 'right_max_position_embeddings=8', 'speech_encoder_chunk_size': 'speech_encoder_chunk_size=20000', 'speech_encoder_left_chunk_num': 'speech_encoder_left_chunk_num=128', 't2u_bos_token_id': 't2u_bos_token_id=0', 't2u_pad_token_id': 't2u_pad_token_id=1', 't2u_eos_token_id': 't2u_eos_token_id=2', 't2u_encoder_layers': 't2u_encoder_layers=6', 't2u_encoder_ffn_dim': 't2u_encoder_ffn_dim=8192', 't2u_encoder_attention_heads': 't2u_encoder_attention_heads=16', 't2u_decoder_layers': 't2u_decoder_layers=6', 't2u_decoder_ffn_dim': 't2u_decoder_ffn_dim=8192', 't2u_decoder_attention_heads': 't2u_decoder_attention_heads=16', 't2u_max_position_embeddings': 't2u_max_position_embeddings=4096', 't2u_variance_predictor_embed_dim': 't2u_variance_predictor_embed_dim=1024', 't2u_variance_predictor_hidden_dim': 't2u_variance_predictor_hidden_dim=256', 't2u_variance_predictor_kernel_size': 't2u_variance_predictor_kernel_size=3', 't2u_variance_pred_dropout': 't2u_variance_pred_dropout=0.5', 'sampling_rate': 'sampling_rate=16000', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ - 5, - 4, - 4, - 2, - 2 - ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ - 11, - 8, - 8, - 4, - 4 - ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ - 3, - 7, - 11 - ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ] - ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'unit_hifi_gan_vocab_size': 'unit_hifi_gan_vocab_size=10000', 'unit_embed_dim': 'unit_embed_dim=1280', 'lang_embed_dim': 'lang_embed_dim=256', 'spkr_embed_dim': 'spkr_embed_dim=256', 'vocoder_num_langs': 'vocoder_num_langs=36', 'vocoder_num_spkrs': 'vocoder_num_spkrs=200', 'variance_predictor_kernel_size': 'variance_predictor_kernel_size=3', 'var_pred_dropout': 'var_pred_dropout=0.5', 'vocoder_offset': 'vocoder_offset=4' -}, model_name='SeamlessM4Tv2Model', library='transformers', import_path='transformers.models.seamless_m4t_v2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'cls_token': "cls_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'src_lang': "src_lang='eng'", 'tgt_lang': "tgt_lang='fra'", 'additional_special_tokens': 'additional_special_tokens=None', 'keep_accents': 'keep_accents=None', 'vocab_file': 'vocab_file=None' -}, model_name='SeamlessM4TTokenizer', library='transformers', import_path='transformers.models.seamless_m4t'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 155136', 'hidden_size': 'hidden_size: Optional[int - ] = 4096', 'intermediate_size': 'intermediate_size: Optional[int - ] = 27648', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 64', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 80', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 8', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 524288', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[float - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'pretraining_tp': 'pretraining_tp: Optional[int - ] = 1', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = True', 'attention_out_bias': 'attention_out_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.1', 'residual_dropout': 'residual_dropout: Optional[float - ] = 0.1', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False', 'head_dim': 'head_dim: Optional[int - ] = 128' -}, model_name='SeedOssModel', library='transformers', import_path='transformers.models.seed_oss'), ModelAttributes(model=, model_type='model', model_parameters={'num_channels': 'num_channels=3', 'num_encoder_blocks': 'num_encoder_blocks=4', 'depths': 'depths=[ - 2, - 2, - 2, - 2 - ]', 'sr_ratios': 'sr_ratios=[ - 8, - 4, - 2, - 1 - ]', 'hidden_sizes': 'hidden_sizes=[ - 32, - 64, - 160, - 256 - ]', 'patch_sizes': 'patch_sizes=[ - 7, - 3, - 3, - 3 - ]', 'strides': 'strides=[ - 4, - 2, - 2, - 2 - ]', 'num_attention_heads': 'num_attention_heads=[ - 1, - 2, - 5, - 8 - ]', 'mlp_ratios': 'mlp_ratios=[ - 4, - 4, - 4, - 4 - ]', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'classifier_dropout_prob': 'classifier_dropout_prob=0.1', 'initializer_range': 'initializer_range=0.02', 'drop_path_rate': 'drop_path_rate=0.1', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'decoder_hidden_size': 'decoder_hidden_size=256', 'semantic_loss_ignore_index': 'semantic_loss_ignore_index=255' -}, model_name='SegformerModel', library='transformers', import_path='transformers.models.segformer'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=[ - 896, - 448 - ]', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'mlp_dim': 'mlp_dim=None', 'drop_path_rate': 'drop_path_rate=0.1', 'pretrain_image_size': 'pretrain_image_size=224', 'decoder_hidden_size': 'decoder_hidden_size=64', 'use_relative_position_embeddings': 'use_relative_position_embeddings=True', 'merge_index': 'merge_index=2', 'intermediate_hidden_state_indices': 'intermediate_hidden_state_indices=[ - 5, - 11, - 17, - 23 - ]', 'beta': 'beta=0.01' -}, model_name='SegGptModel', library='transformers', import_path='transformers.models.seggpt'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'squeeze_factor': 'squeeze_factor=2', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(64, - 128, - 128, - 128, - 128, - 256, - 256, - 256, - 256, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1)', 'conv_kernel': 'conv_kernel=(10, - 3, - 1, - 3, - 1, - 3, - 1, - 3, - 1, - 2, - 1, - 2, - 1)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' -}, model_name='SEWModel', library='transformers', import_path='transformers.models.sew'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'squeeze_factor': 'squeeze_factor=2', 'max_position_embeddings': 'max_position_embeddings=512', 'position_buckets': 'position_buckets=256', 'share_att_key': 'share_att_key=True', 'relative_attention': 'relative_attention=True', 'pos_att_type': "pos_att_type=('p2c', 'c2p')", 'norm_rel_ebd': "norm_rel_ebd='layer_norm'", 'hidden_act': "hidden_act='gelu_python'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-07', 'feature_layer_norm_eps': 'feature_layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(64, - 128, - 128, - 128, - 128, - 256, - 256, - 256, - 256, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1, - 2, - 1)', 'conv_kernel': 'conv_kernel=(10, - 3, - 1, - 3, - 1, - 3, - 1, - 3, - 1, - 2, - 1, - 2, - 1)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' -}, model_name='SEWDModel', library='transformers', import_path='transformers.models.sew_d'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None' -}, model_name='SiglipModel', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'additional_special_tokens': 'additional_special_tokens=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None', 'model_max_length': 'model_max_length=64', 'do_lower_case': 'do_lower_case=True' -}, model_name='SiglipTokenizer', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None' -}, model_name='Siglip2Model', library='transformers', import_path='transformers.models.siglip2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'num_patches': 'num_patches=256', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0' -}, model_name='Siglip2VisionModel', library='transformers', import_path='transformers.models.siglip2'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0' -}, model_name='SiglipVisionModel', library='transformers', import_path='transformers.models.siglip'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 128256', 'hidden_size': 'hidden_size: Optional[int - ] = 2048', 'intermediate_size': 'intermediate_size: Optional[int - ] = 11008', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 36', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 16', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 32768', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 128004', 'bos_token_id': 'bos_token_id: Optional[int - ] = 128000', 'eos_token_id': 'eos_token_id: Optional[int - ] = 128001', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_sliding_window': 'use_sliding_window: Optional[bool - ] = False', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'no_rope_layers': 'no_rope_layers: Optional[int - ] = None', 'no_rope_layer_interval': 'no_rope_layer_interval: Optional[int - ] = 4', 'layer_types': 'layer_types: Optional[int - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'mlp_bias': 'mlp_bias: Optional[bool - ] = False' -}, model_name='SmolLM3Model', library='transformers', import_path='transformers.models.smollm3'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'args': '*args' -}, model_name='TokenizersBackend', library='transformers', import_path='transformers'), ModelAttributes(model=, model_type='model', model_parameters={'image_token_id': 'image_token_id=128257', 'tie_word_embeddings': 'tie_word_embeddings=False', 'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'scale_factor': 'scale_factor=2', 'pad_token_id': 'pad_token_id=128002' -}, model_name='SmolVLMModel', library='transformers', import_path='transformers.models.smolvlm'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=1152', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=16', 'num_channels': 'num_channels=3', 'image_size': 'image_size=224', 'patch_size': 'patch_size=32', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' -}, model_name='SmolVLMVisionTransformer', library='transformers', import_path='transformers.models.smolvlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=10000', 'encoder_layers': 'encoder_layers=12', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=4', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=4', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'decoder_start_token_id': 'decoder_start_token_id=2', 'scale_embedding': 'scale_embedding=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'max_source_positions': 'max_source_positions=6000', 'max_target_positions': 'max_target_positions=1024', 'num_conv_layers': 'num_conv_layers=2', 'conv_kernel_sizes': 'conv_kernel_sizes=(5, - 5)', 'conv_channels': 'conv_channels=1024', 'input_feat_per_channel': 'input_feat_per_channel=80', 'input_channels': 'input_channels=1' -}, model_name='Speech2TextModel', library='transformers', import_path='transformers.models.speech_to_text'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'spm_file': 'spm_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'do_upper_case': 'do_upper_case=False', 'do_lower_case': 'do_lower_case=False', 'tgt_lang': 'tgt_lang=None', 'lang_codes': 'lang_codes=None', 'additional_special_tokens': 'additional_special_tokens=None', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None' -}, model_name='Speech2TextTokenizer', library='transformers', import_path='transformers.models.speech_to_text'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=81', 'hidden_size': 'hidden_size=768', 'encoder_layers': 'encoder_layers=12', 'encoder_attention_heads': 'encoder_attention_heads=12', 'encoder_ffn_dim': 'encoder_ffn_dim=3072', 'encoder_layerdrop': 'encoder_layerdrop=0.1', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=3072', 'decoder_attention_heads': 'decoder_attention_heads=12', 'decoder_layerdrop': 'decoder_layerdrop=0.1', 'hidden_act': "hidden_act='gelu'", 'positional_dropout': 'positional_dropout=0.1', 'hidden_dropout': 'hidden_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'scale_embedding': 'scale_embedding=False', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'decoder_start_token_id': 'decoder_start_token_id=2', 'num_mel_bins': 'num_mel_bins=80', 'speech_decoder_prenet_layers': 'speech_decoder_prenet_layers=2', 'speech_decoder_prenet_units': 'speech_decoder_prenet_units=256', 'speech_decoder_prenet_dropout': 'speech_decoder_prenet_dropout=0.5', 'speaker_embedding_dim': 'speaker_embedding_dim=512', 'speech_decoder_postnet_layers': 'speech_decoder_postnet_layers=5', 'speech_decoder_postnet_units': 'speech_decoder_postnet_units=256', 'speech_decoder_postnet_kernel': 'speech_decoder_postnet_kernel=5', 'speech_decoder_postnet_dropout': 'speech_decoder_postnet_dropout=0.5', 'reduction_factor': 'reduction_factor=2', 'max_speech_positions': 'max_speech_positions=4000', 'max_text_positions': 'max_text_positions=450', 'encoder_max_relative_position': 'encoder_max_relative_position=160', 'use_guided_attention_loss': 'use_guided_attention_loss=True', 'guided_attention_loss_num_heads': 'guided_attention_loss_num_heads=2', 'guided_attention_loss_sigma': 'guided_attention_loss_sigma=0.4', 'guided_attention_loss_scale': 'guided_attention_loss_scale=10.0', 'is_encoder_decoder': 'is_encoder_decoder=True' -}, model_name='SpeechT5Model', library='transformers', import_path='transformers.models.speecht5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'normalize': 'normalize=False', 'sp_model_kwargs': 'sp_model_kwargs: Optional[dict[str, Any - ] - ] = None' -}, model_name='SpeechT5Tokenizer', library='transformers', import_path='transformers.models.speecht5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'question_token_id': 'question_token_id=104' -}, model_name='SplinterModel', library='transformers', import_path='transformers.models.splinter'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'question_token': "question_token: str = '[QUESTION]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='SplinterTokenizer', library='transformers', import_path='transformers.models.splinter'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'embedding_size': 'embedding_size=768', 'q_groups': 'q_groups=4', 'k_groups': 'k_groups=4', 'v_groups': 'v_groups=4', 'post_attention_groups': 'post_attention_groups=1', 'intermediate_groups': 'intermediate_groups=4', 'output_groups': 'output_groups=4' -}, model_name='SqueezeBertModel', library='transformers', import_path='transformers.models.squeezebert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 50304', 'intermediate_size': 'intermediate_size: Optional[int - ] = 6912', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 32', 'hidden_act': "hidden_act: Optional[str] = 'silu'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'layer_norm_eps': 'layer_norm_eps: Optional[float - ] = 1e-05', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'use_qkv_bias': 'use_qkv_bias: Optional[bool - ] = False', 'qk_layernorm': 'qk_layernorm: Optional[bool - ] = False', 'use_parallel_residual': 'use_parallel_residual: Optional[bool - ] = False', 'hidden_dropout': 'hidden_dropout: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 0' -}, model_name='StableLmModel', library='transformers', import_path='transformers.models.stablelm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 49152', 'hidden_size': 'hidden_size: Optional[int - ] = 3072', 'intermediate_size': 'intermediate_size: Optional[int - ] = 12288', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 30', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 24', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 2', 'hidden_act': "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'initializer_range': 'initializer_range: Optional[float - ] = 0.018042', 'norm_epsilon': 'norm_epsilon: Optional[int - ] = 1e-05', 'bos_token_id': 'bos_token_id: Optional[int - ] = 50256', 'eos_token_id': 'eos_token_id: Optional[int - ] = 50256', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'sliding_window': 'sliding_window: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'residual_dropout': 'residual_dropout: Optional[float - ] = 0.0', 'embedding_dropout': 'embedding_dropout: Optional[float - ] = 0.0', 'use_bias': 'use_bias: Optional[bool - ] = True' -}, model_name='Starcoder2Model', library='transformers', import_path='transformers.models.starcoder2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'bos_token': "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'eos_token': "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", 'pad_token': 'pad_token: Union[tokenizers.AddedToken, str, NoneType - ] = None', 'add_prefix_space': 'add_prefix_space=False' -}, model_name='GPT2Tokenizer', library='transformers', import_path='transformers.models.gpt2'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_channels': 'num_channels=3', 'depths': 'depths=[ - 3, - 3, - 6, - 4 - ]', 'embed_dims': 'embed_dims=[ - 48, - 56, - 112, - 220 - ]', 'mlp_ratio': 'mlp_ratio=4', 'downsamples': 'downsamples=[True, True, True, True - ]', 'hidden_act': "hidden_act='gelu'", 'down_patch_size': 'down_patch_size=3', 'down_stride': 'down_stride=2', 'down_pad': 'down_pad=1', 'drop_path_rate': 'drop_path_rate=0.0', 'drop_mlp_rate': 'drop_mlp_rate=0.0', 'drop_conv_encoder_rate': 'drop_conv_encoder_rate=0.0', 'use_layer_scale': 'use_layer_scale=True', 'layer_scale_init_value': 'layer_scale_init_value=1e-05', 'batch_norm_eps': 'batch_norm_eps=1e-05' -}, model_name='SwiftFormerModel', library='transformers', import_path='transformers.models.swiftformer'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'num_heads': 'num_heads=[ - 3, - 6, - 12, - 24 - ]', 'window_size': 'window_size=7', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='SwinModel', library='transformers', import_path='transformers.models.swin'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=64', 'patch_size': 'patch_size=1', 'num_channels': 'num_channels=3', 'num_channels_out': 'num_channels_out=None', 'embed_dim': 'embed_dim=180', 'depths': 'depths=[ - 6, - 6, - 6, - 6, - 6, - 6 - ]', 'num_heads': 'num_heads=[ - 6, - 6, - 6, - 6, - 6, - 6 - ]', 'window_size': 'window_size=8', 'mlp_ratio': 'mlp_ratio=2.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'upscale': 'upscale=2', 'img_range': 'img_range=1.0', 'resi_connection': "resi_connection='1conv'", 'upsampler': "upsampler='pixelshuffle'" -}, model_name='Swin2SRModel', library='transformers', import_path='transformers.models.swin2sr'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=4', 'num_channels': 'num_channels=3', 'embed_dim': 'embed_dim=96', 'depths': 'depths=[ - 2, - 2, - 6, - 2 - ]', 'num_heads': 'num_heads=[ - 3, - 6, - 12, - 24 - ]', 'window_size': 'window_size=7', 'pretrained_window_sizes': 'pretrained_window_sizes=[ - 0, - 0, - 0, - 0 - ]', 'mlp_ratio': 'mlp_ratio=4.0', 'qkv_bias': 'qkv_bias=True', 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'drop_path_rate': 'drop_path_rate=0.1', 'hidden_act': "hidden_act='gelu'", 'use_absolute_embeddings': 'use_absolute_embeddings=False', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'encoder_stride': 'encoder_stride=32', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='Swinv2Model', library='transformers', import_path='transformers.models.swinv2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=768', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'expert_capacity': 'expert_capacity=64', 'num_layers': 'num_layers=12', 'num_sparse_encoder_layers': 'num_sparse_encoder_layers=3', 'num_decoder_layers': 'num_decoder_layers=12', 'num_sparse_decoder_layers': 'num_sparse_decoder_layers=3', 'num_heads': 'num_heads=12', 'num_experts': 'num_experts=8', 'router_bias': 'router_bias=False', 'router_jitter_noise': 'router_jitter_noise=0.01', 'router_dtype': "router_dtype='float32'", 'router_ignore_padding_tokens': 'router_ignore_padding_tokens=False', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'router_z_loss_coef': 'router_z_loss_coef=0.001', 'router_aux_loss_coef': 'router_aux_loss_coef=0.001', 'initializer_factor': 'initializer_factor=1.0', 'dense_act_fn': "dense_act_fn='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'add_router_probs': 'add_router_probs=False', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1' -}, model_name='SwitchTransformersModel', library='transformers', import_path='transformers.models.switch_transformers'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32128', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=2048', 'num_layers': 'num_layers=6', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=8', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'classifier_dropout': 'classifier_dropout=0.0' -}, model_name='T5Model', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'encoder': 'encoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any - ], NoneType - ] = None', 'decoder': 'decoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any - ], NoneType - ] = None', 'is_encoder_decoder': 'is_encoder_decoder: Optional[bool - ] = True', 'dropout_rate': 'dropout_rate: Optional[float - ] = 0.0', 'classifier_dropout_rate': 'classifier_dropout_rate: Optional[float - ] = 0.0', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'vocab_size': 'vocab_size: Optional[int - ] = 256000' -}, model_name='T5GemmaModel', library='transformers', import_path='transformers.models.t5gemma'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = ''", 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='GemmaTokenizer', library='transformers', import_path='transformers.models.gemma'), ModelAttributes(model=, model_type='model', model_parameters={'encoder': 'encoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2EncoderConfig, dict[str, Any - ], NoneType - ] = None', 'decoder': 'decoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2DecoderConfig, dict[str, Any - ], NoneType - ] = None', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'dropout_rate': 'dropout_rate: float = 0.0', 'attention_dropout': 'attention_dropout: float = 0.0', 'classifier_dropout_rate': 'classifier_dropout_rate: float = 0.0', 'initializer_range': 'initializer_range: float = 0.02', 'image_token_index': 'image_token_index: int = 256001' -}, model_name='T5Gemma2Model', library='transformers', import_path='transformers.models.t5gemma2'), ModelAttributes(model=, model_type='model', model_parameters={'use_timm_backbone': 'use_timm_backbone=True', 'backbone_config': 'backbone_config=None', 'num_channels': 'num_channels=3', 'num_queries': 'num_queries=100', 'encoder_layers': 'encoder_layers=6', 'encoder_ffn_dim': 'encoder_ffn_dim=2048', 'encoder_attention_heads': 'encoder_attention_heads=8', 'decoder_layers': 'decoder_layers=6', 'decoder_ffn_dim': 'decoder_ffn_dim=2048', 'decoder_attention_heads': 'decoder_attention_heads=8', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='relu'", 'd_model': 'd_model=256', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'init_xavier_std': 'init_xavier_std=1.0', 'auxiliary_loss': 'auxiliary_loss=False', 'position_embedding_type': "position_embedding_type='sine'", 'backbone': "backbone='resnet50'", 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'backbone_kwargs': 'backbone_kwargs=None', 'dilation': 'dilation=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'mask_loss_coefficient': 'mask_loss_coefficient=1', 'dice_loss_coefficient': 'dice_loss_coefficient=1', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' -}, model_name='TableTransformerModel', library='transformers', import_path='transformers.models.table_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=1024', 'type_vocab_sizes': 'type_vocab_sizes=[ - 3, - 256, - 256, - 2, - 256, - 256, - 10 - ]', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=0', 'positive_label_weight': 'positive_label_weight=10.0', 'num_aggregation_labels': 'num_aggregation_labels=0', 'aggregation_loss_weight': 'aggregation_loss_weight=1.0', 'use_answer_as_supervision': 'use_answer_as_supervision=None', 'answer_loss_importance': 'answer_loss_importance=1.0', 'use_normalized_answer_loss': 'use_normalized_answer_loss=False', 'huber_loss_delta': 'huber_loss_delta=None', 'temperature': 'temperature=1.0', 'aggregation_temperature': 'aggregation_temperature=1.0', 'use_gumbel_for_cells': 'use_gumbel_for_cells=False', 'use_gumbel_for_aggregation': 'use_gumbel_for_aggregation=False', 'average_approximation_function': "average_approximation_function='ratio'", 'cell_selection_preference': 'cell_selection_preference=None', 'answer_loss_cutoff': 'answer_loss_cutoff=None', 'max_num_rows': 'max_num_rows=64', 'max_num_columns': 'max_num_columns=32', 'average_logits_per_cell': 'average_logits_per_cell=False', 'select_one_column': 'select_one_column=True', 'allow_empty_column_selection': 'allow_empty_column_selection=False', 'init_cell_selection_weights_to_zero': 'init_cell_selection_weights_to_zero=False', 'reset_position_index_per_cell': 'reset_position_index_per_cell=True', 'disable_per_token_loss': 'disable_per_token_loss=False', 'aggregation_labels': 'aggregation_labels=None', 'no_aggregation_label_index': 'no_aggregation_label_index=None' -}, model_name='TapasModel', library='transformers', import_path='transformers.models.tapas'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'do_lower_case': 'do_lower_case=True', 'do_basic_tokenize': 'do_basic_tokenize=True', 'never_split': 'never_split=None', 'unk_token': "unk_token='[UNK]'", 'sep_token': "sep_token='[SEP]'", 'pad_token': "pad_token='[PAD]'", 'cls_token': "cls_token='[CLS]'", 'mask_token': "mask_token='[MASK]'", 'empty_token': "empty_token='[EMPTY]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars=True', 'strip_accents': 'strip_accents=None', 'cell_trim_length': 'cell_trim_length: int = -1', 'max_column_id': 'max_column_id: Optional[int - ] = None', 'max_row_id': 'max_row_id: Optional[int - ] = None', 'strip_column_names': 'strip_column_names: bool = False', 'update_answer_coordinates': 'update_answer_coordinates: bool = False', 'min_question_length': 'min_question_length=None', 'max_question_length': 'max_question_length=None', 'model_max_length': 'model_max_length: int = 512', 'additional_special_tokens': 'additional_special_tokens: Optional[list[str - ] - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=True' -}, model_name='TapasTokenizer', library='transformers', import_path='transformers.models.tapas'), ModelAttributes(model=, model_type='model', model_parameters={'stem_kernel_size': 'stem_kernel_size=3', 'stem_stride': 'stem_stride=2', 'stem_num_channels': 'stem_num_channels=3', 'stem_out_channels': 'stem_out_channels=64', 'stem_act_func': "stem_act_func='relu'", 'image_size': 'image_size=[ - 640, - 640 - ]', 'conv_layer_kernel_sizes': 'conv_layer_kernel_sizes=None', 'conv_layer_strides': 'conv_layer_strides=None', 'hidden_sizes': 'hidden_sizes=[ - 64, - 64, - 128, - 256, - 512 - ]', 'batch_norm_eps': 'batch_norm_eps=1e-05', 'initializer_range': 'initializer_range=0.02', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='TextNetModel', library='transformers', import_path='transformers.models.textnet'), ModelAttributes(model=, model_type='model', model_parameters={'prediction_length': 'prediction_length: Optional[int - ] = None', 'context_length': 'context_length: Optional[int - ] = None', 'distribution_output': "distribution_output: str = 'student_t'", 'loss': "loss: str = 'nll'", 'input_size': 'input_size: int = 1', 'lags_sequence': 'lags_sequence: list[int - ] = [ - 1, - 2, - 3, - 4, - 5, - 6, - 7 - ]', 'scaling': "scaling: Union[str, bool, NoneType] = 'mean'", 'num_dynamic_real_features': 'num_dynamic_real_features: int = 0', 'num_static_categorical_features': 'num_static_categorical_features: int = 0', 'num_static_real_features': 'num_static_real_features: int = 0', 'num_time_features': 'num_time_features: int = 0', 'cardinality': 'cardinality: Optional[list[int - ] - ] = None', 'embedding_dimension': 'embedding_dimension: Optional[list[int - ] - ] = None', 'encoder_ffn_dim': 'encoder_ffn_dim: int = 32', 'decoder_ffn_dim': 'decoder_ffn_dim: int = 32', 'encoder_attention_heads': 'encoder_attention_heads: int = 2', 'decoder_attention_heads': 'decoder_attention_heads: int = 2', 'encoder_layers': 'encoder_layers: int = 2', 'decoder_layers': 'decoder_layers: int = 2', 'is_encoder_decoder': 'is_encoder_decoder: bool = True', 'activation_function': "activation_function: str = 'gelu'", 'd_model': 'd_model: int = 64', 'dropout': 'dropout: float = 0.1', 'encoder_layerdrop': 'encoder_layerdrop: float = 0.1', 'decoder_layerdrop': 'decoder_layerdrop: float = 0.1', 'attention_dropout': 'attention_dropout: float = 0.1', 'activation_dropout': 'activation_dropout: float = 0.1', 'num_parallel_samples': 'num_parallel_samples: int = 100', 'init_std': 'init_std: float = 0.02' -}, model_name='TimeSeriesTransformerModel', library='transformers', import_path='transformers.models.time_series_transformer'), ModelAttributes(model=, model_type='model', model_parameters={'patch_length': 'patch_length: int = 32', 'context_length': 'context_length: int = 512', 'horizon_length': 'horizon_length: int = 128', 'freq_size': 'freq_size: int = 3', 'num_hidden_layers': 'num_hidden_layers: int = 50', 'hidden_size': 'hidden_size: int = 1280', 'intermediate_size': 'intermediate_size: int = 1280', 'head_dim': 'head_dim: int = 80', 'num_attention_heads': 'num_attention_heads: int = 16', 'tolerance': 'tolerance: float = 1e-06', 'rms_norm_eps': 'rms_norm_eps: float = 1e-06', 'quantiles': 'quantiles: list[float - ] = [ - 0.1, - 0.2, - 0.3, - 0.4, - 0.5, - 0.6, - 0.7, - 0.8, - 0.9 - ]', 'pad_val': 'pad_val: float = 1123581321.0', 'attention_dropout': 'attention_dropout: float = 0.0', 'use_positional_embedding': 'use_positional_embedding: bool = False', 'initializer_range': 'initializer_range: float = 0.02', 'min_timescale': 'min_timescale: int = 1', 'max_timescale': 'max_timescale: int = 10000' -}, model_name='TimesFmModel', library='transformers', import_path='transformers.models.timesfm'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'num_frames': 'num_frames=8', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True', 'attention_type': "attention_type='divided_space_time'", 'drop_path_rate': 'drop_path_rate=0' -}, model_name='TimesformerModel', library='transformers', import_path='transformers.models.timesformer'), ModelAttributes(model=, model_type='model', model_parameters={'backbone': 'backbone=None', 'num_channels': 'num_channels=3', 'features_only': 'features_only=True', 'use_pretrained_backbone': 'use_pretrained_backbone=True', 'out_indices': 'out_indices=None', 'freeze_batch_norm_2d': 'freeze_batch_norm_2d=False' -}, model_name='TimmBackbone', library='transformers', import_path='transformers.models.timm_backbone'), ModelAttributes(model=, model_type='model', model_parameters={'_resnet_': ['' - ] -}, model_name='TimmWrapperModel', library='transformers', import_path='transformers.models.timm_wrapper'), ModelAttributes(model=, model_type='model', model_parameters={'backbone_config': 'backbone_config=None', 'backbone': 'backbone=None', 'use_pretrained_backbone': 'use_pretrained_backbone=False', 'use_timm_backbone': 'use_timm_backbone=False', 'backbone_kwargs': 'backbone_kwargs=None', 'distance_loss_weight': 'distance_loss_weight=1.0', 'duration_loss_weight': 'duration_loss_weight=0.1', 'visual_prompter_type': "visual_prompter_type='framepad'", 'visual_prompter_apply': "visual_prompter_apply='replace'", 'visual_prompt_size': 'visual_prompt_size=96', 'max_img_size': 'max_img_size=448', 'num_frames': 'num_frames=48', 'vocab_size': 'vocab_size=30522', 'type_vocab_size': 'type_vocab_size=2', 'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'max_position_embeddings': 'max_position_embeddings=512', 'max_grid_col_position_embeddings': 'max_grid_col_position_embeddings=100', 'max_grid_row_position_embeddings': 'max_grid_row_position_embeddings=100', 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'hidden_act': "hidden_act='gelu'", 'layer_norm_eps': 'layer_norm_eps=1e-12', 'initializer_range': 'initializer_range=0.02', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1' -}, model_name='TvpModel', library='transformers', import_path='transformers.models.tvp'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=33201', 'd_model': 'd_model=1024', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=4096', 'num_layers': 'num_layers=24', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=16', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'relative_bias_args': "relative_bias_args=[{'type': '1d'}, {'type': 'horizontal'}, {'type': 'vertical'}]", 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='relu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'max_2d_position_embeddings': 'max_2d_position_embeddings=1024', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3' -}, model_name='UdopModel', library='transformers', import_path='transformers.models.udop'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'sep_token': "sep_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'sep_token_box': 'sep_token_box=[ - 1000, - 1000, - 1000, - 1000 - ]', 'pad_token_box': 'pad_token_box=[ - 0, - 0, - 0, - 0 - ]', 'pad_token_label': 'pad_token_label=-100', 'only_label_first_subword': 'only_label_first_subword=True', 'extra_special_tokens': 'extra_special_tokens=None' -}, model_name='UdopTokenizer', library='transformers', import_path='transformers.models.udop'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250112', 'd_model': 'd_model=512', 'd_kv': 'd_kv=64', 'd_ff': 'd_ff=1024', 'num_layers': 'num_layers=8', 'num_decoder_layers': 'num_decoder_layers=None', 'num_heads': 'num_heads=6', 'relative_attention_num_buckets': 'relative_attention_num_buckets=32', 'relative_attention_max_distance': 'relative_attention_max_distance=128', 'dropout_rate': 'dropout_rate=0.1', 'layer_norm_epsilon': 'layer_norm_epsilon=1e-06', 'initializer_factor': 'initializer_factor=1.0', 'feed_forward_proj': "feed_forward_proj='gated-gelu'", 'is_encoder_decoder': 'is_encoder_decoder=True', 'tokenizer_class': "tokenizer_class='T5Tokenizer'", 'pad_token_id': 'pad_token_id=0', 'eos_token_id': 'eos_token_id=1', 'decoder_start_token_id': 'decoder_start_token_id=0', 'classifier_dropout': 'classifier_dropout=0.0' -}, model_name='UMT5Model', library='transformers', import_path='transformers.models.umt5'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'extra_ids': 'extra_ids=100', 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='T5Tokenizer', library='transformers', import_path='transformers.models.t5'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'num_ctc_classes': 'num_ctc_classes=80', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'replace_prob': 'replace_prob=0.5' -}, model_name='UniSpeechModel', library='transformers', import_path='transformers.models.unispeech'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'num_clusters': 'num_clusters=504' -}, model_name='UniSpeechSatModel', library='transformers', import_path='transformers.models.unispeech_sat'), ModelAttributes(model=, model_type='model', model_parameters={'model_in_channels': 'model_in_channels=64', 'model_hidden_channels': 'model_hidden_channels=32', 'num_mel_bins': 'num_mel_bins=100', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ - 3, - 3, - 3 - ]', 'resblock_stride_sizes': 'resblock_stride_sizes=[ - 8, - 8, - 4 - ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ - [ - 1, - 3, - 9, - 27 - ], - [ - 1, - 3, - 9, - 27 - ], - [ - 1, - 3, - 9, - 27 - ] - ]', 'kernel_predictor_num_blocks': 'kernel_predictor_num_blocks=3', 'kernel_predictor_hidden_channels': 'kernel_predictor_hidden_channels=64', 'kernel_predictor_conv_size': 'kernel_predictor_conv_size=3', 'kernel_predictor_dropout': 'kernel_predictor_dropout=0.0', 'initializer_range': 'initializer_range=0.01', 'leaky_relu_slope': 'leaky_relu_slope=0.2' -}, model_name='UnivNetModel', library='transformers', import_path='transformers.models.univnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 256000', 'hidden_size': 'hidden_size: Optional[int - ] = 2304', 'intermediate_size': 'intermediate_size: Optional[int - ] = 9216', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 26', 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 8', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = 4', 'head_dim': 'head_dim: Optional[int - ] = 256', 'hidden_activation': "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 8192', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-06', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'eos_token_id': 'eos_token_id: Optional[int - ] = 1', 'bos_token_id': 'bos_token_id: Optional[int - ] = 2', 'tie_word_embeddings': 'tie_word_embeddings: Optional[bool - ] = True', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'attention_bias': 'attention_bias: Optional[bool - ] = False', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'query_pre_attn_scalar': 'query_pre_attn_scalar: Optional[int - ] = 256', 'sliding_window': 'sliding_window: Optional[int - ] = 4096', 'layer_types': 'layer_types: Optional[list[str - ] - ] = None', 'final_logit_softcapping': 'final_logit_softcapping: Optional[float - ] = 30.0', 'attn_logit_softcapping': 'attn_logit_softcapping: Optional[float - ] = 50.0' -}, model_name='VaultGemmaModel', library='transformers', import_path='transformers.models.vaultgemma'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'image_token_id': 'image_token_id=151655', 'video_token_id': 'video_token_id=151656' -}, model_name='VideoLlama3Model', library='transformers', import_path='transformers.models.video_llama_3'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'intermediate_size': 'intermediate_size=3072', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'num_channels': 'num_channels=3', 'patch_size': 'patch_size=16', 'hidden_act': "hidden_act='gelu_pytorch_tanh'", 'layer_norm_eps': 'layer_norm_eps=1e-06', 'attention_dropout': 'attention_dropout=0.0', 'initializer_range': 'initializer_range=0.02' -}, model_name='VideoLlama3VisionModel', library='transformers', import_path='transformers.models.video_llama_3'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'video_token_index': 'video_token_index=32001', 'projector_hidden_act': "projector_hidden_act='gelu'", 'vision_feature_select_strategy': "vision_feature_select_strategy='default'", 'vision_feature_layer': 'vision_feature_layer=-2', 'image_seq_length': 'image_seq_length=256', 'video_seq_length': 'video_seq_length=2056', 'multimodal_projector_bias': 'multimodal_projector_bias=True' -}, model_name='VideoLlavaModel', library='transformers', import_path='transformers.models.video_llava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'num_frames': 'num_frames=16', 'tubelet_size': 'tubelet_size=2', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'qkv_bias': 'qkv_bias=True', 'use_mean_pooling': 'use_mean_pooling=True', 'decoder_num_attention_heads': 'decoder_num_attention_heads=6', 'decoder_hidden_size': 'decoder_hidden_size=384', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers=4', 'decoder_intermediate_size': 'decoder_intermediate_size=1536', 'norm_pix_loss': 'norm_pix_loss=True' -}, model_name='VideoMAEModel', library='transformers', import_path='transformers.models.videomae'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'type_vocab_size': 'type_vocab_size=2', 'modality_type_vocab_size': 'modality_type_vocab_size=2', 'max_position_embeddings': 'max_position_embeddings=40', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=384', 'patch_size': 'patch_size=32', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'max_image_length': 'max_image_length=-1', 'tie_word_embeddings': 'tie_word_embeddings=True', 'num_images': 'num_images=-1' -}, model_name='ViltModel', library='transformers', import_path='transformers.models.vilt'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'vision_config': 'vision_config=None', 'text_config': 'text_config=None', 'image_token_index': 'image_token_index=32000', 'projector_hidden_act': "projector_hidden_act='gelu'", 'projector_layernorm_eps': 'projector_layernorm_eps=1e-05', 'vision_feature_layers': 'vision_feature_layers=[ - -2, - -5, - -8, - -11, - 6 - ]', 'image_seq_length': 'image_seq_length=576' -}, model_name='VipLlavaModel', library='transformers', import_path='transformers.models.vipllava'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'projection_dim': 'projection_dim=512', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='VisionTextDualEncoderModel', library='transformers', import_path='transformers.models.vision_text_dual_encoder'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'visual_embedding_dim': 'visual_embedding_dim=512', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'bypass_transformer': 'bypass_transformer=False', 'special_visual_initialize': 'special_visual_initialize=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='VisualBertModel', library='transformers', import_path='transformers.models.visual_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = False', 'unk_token': "unk_token: str = '[UNK]'", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = '[PAD]'", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'tokenize_chinese_chars': 'tokenize_chinese_chars: bool = True', 'strip_accents': 'strip_accents: Optional[bool - ] = None' -}, model_name='BertTokenizer', library='transformers', import_path='transformers.models.bert'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'encoder_stride': 'encoder_stride=16', 'pooler_output_size': 'pooler_output_size=None', 'pooler_act': "pooler_act='tanh'" -}, model_name='ViTModel', library='transformers', import_path='transformers.models.vit'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'decoder_num_attention_heads': 'decoder_num_attention_heads=16', 'decoder_hidden_size': 'decoder_hidden_size=512', 'decoder_num_hidden_layers': 'decoder_num_hidden_layers=8', 'decoder_intermediate_size': 'decoder_intermediate_size=2048', 'mask_ratio': 'mask_ratio=0.75', 'norm_pix_loss': 'norm_pix_loss=False' -}, model_name='ViTMAEModel', library='transformers', import_path='transformers.models.vit_mae'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True' -}, model_name='ViTMSNModel', library='transformers', import_path='transformers.models.vit_msn'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'mlp_ratio': 'mlp_ratio=4', 'hidden_act': "hidden_act='gelu'", 'dropout_prob': 'dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'image_size': 'image_size=224', 'pretrain_image_size': 'pretrain_image_size=224', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'drop_path_rate': 'drop_path_rate=0.0', 'window_block_indices': 'window_block_indices=[]', 'residual_block_indices': 'residual_block_indices=[]', 'use_absolute_position_embeddings': 'use_absolute_position_embeddings=True', 'use_relative_position_embeddings': 'use_relative_position_embeddings=False', 'window_size': 'window_size=0', 'out_features': 'out_features=None', 'out_indices': 'out_indices=None' -}, model_name='VitDetModel', library='transformers', import_path='transformers.models.vitdet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=38', 'hidden_size': 'hidden_size=192', 'num_hidden_layers': 'num_hidden_layers=6', 'num_attention_heads': 'num_attention_heads=2', 'window_size': 'window_size=4', 'use_bias': 'use_bias=True', 'ffn_dim': 'ffn_dim=768', 'layerdrop': 'layerdrop=0.1', 'ffn_kernel_size': 'ffn_kernel_size=3', 'flow_size': 'flow_size=192', 'spectrogram_bins': 'spectrogram_bins=513', 'hidden_act': "hidden_act='relu'", 'hidden_dropout': 'hidden_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'use_stochastic_duration_prediction': 'use_stochastic_duration_prediction=True', 'num_speakers': 'num_speakers=1', 'speaker_embedding_size': 'speaker_embedding_size=0', 'upsample_initial_channel': 'upsample_initial_channel=512', 'upsample_rates': 'upsample_rates=[ - 8, - 8, - 2, - 2 - ]', 'upsample_kernel_sizes': 'upsample_kernel_sizes=[ - 16, - 16, - 4, - 4 - ]', 'resblock_kernel_sizes': 'resblock_kernel_sizes=[ - 3, - 7, - 11 - ]', 'resblock_dilation_sizes': 'resblock_dilation_sizes=[ - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ], - [ - 1, - 3, - 5 - ] - ]', 'leaky_relu_slope': 'leaky_relu_slope=0.1', 'depth_separable_channels': 'depth_separable_channels=2', 'depth_separable_num_layers': 'depth_separable_num_layers=3', 'duration_predictor_flow_bins': 'duration_predictor_flow_bins=10', 'duration_predictor_tail_bound': 'duration_predictor_tail_bound=5.0', 'duration_predictor_kernel_size': 'duration_predictor_kernel_size=3', 'duration_predictor_dropout': 'duration_predictor_dropout=0.5', 'duration_predictor_num_flows': 'duration_predictor_num_flows=4', 'duration_predictor_filter_channels': 'duration_predictor_filter_channels=256', 'prior_encoder_num_flows': 'prior_encoder_num_flows=4', 'prior_encoder_num_wavenet_layers': 'prior_encoder_num_wavenet_layers=4', 'posterior_encoder_num_wavenet_layers': 'posterior_encoder_num_wavenet_layers=16', 'wavenet_kernel_size': 'wavenet_kernel_size=5', 'wavenet_dilation_rate': 'wavenet_dilation_rate=1', 'wavenet_dropout': 'wavenet_dropout=0.0', 'speaking_rate': 'speaking_rate=1.0', 'noise_scale': 'noise_scale=0.667', 'noise_scale_duration': 'noise_scale_duration=0.8', 'sampling_rate': 'sampling_rate=16000' -}, model_name='VitsModel', library='transformers', import_path='transformers.models.vits'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'pad_token': "pad_token=''", 'unk_token': "unk_token=''", 'language': 'language=None', 'add_blank': 'add_blank=True', 'normalize': 'normalize=True', 'phonemize': 'phonemize=True', 'is_uroman': 'is_uroman=False' -}, model_name='VitsTokenizer', library='transformers', import_path='transformers.models.vits'), ModelAttributes(model=, model_type='model', model_parameters={'image_size': 'image_size=224', 'num_frames': 'num_frames=32', 'tubelet_size': 'tubelet_size=[ - 2, - 16, - 16 - ]', 'num_channels': 'num_channels=3', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu_fast'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True' -}, model_name='VivitModel', library='transformers', import_path='transformers.models.vivit'), ModelAttributes(model=, model_type='model', model_parameters={'patch_size': 'patch_size=16', 'crop_size': 'crop_size=256', 'frames_per_clip': 'frames_per_clip=64', 'tubelet_size': 'tubelet_size=2', 'hidden_size': 'hidden_size=1024', 'in_chans': 'in_chans=3', 'num_attention_heads': 'num_attention_heads=16', 'num_hidden_layers': 'num_hidden_layers=24', 'drop_path_rate': 'drop_path_rate=0.0', 'mlp_ratio': 'mlp_ratio=4.0', 'layer_norm_eps': 'layer_norm_eps=1e-06', 'qkv_bias': 'qkv_bias=True', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'hidden_act': "hidden_act='gelu'", 'initializer_range': 'initializer_range=0.02', 'attention_dropout': 'attention_dropout=0.0', 'num_pooler_layers': 'num_pooler_layers=3', 'pred_hidden_size': 'pred_hidden_size=384', 'pred_num_attention_heads': 'pred_num_attention_heads=12', 'pred_num_hidden_layers': 'pred_num_hidden_layers=12', 'pred_num_mask_tokens': 'pred_num_mask_tokens=10', 'pred_zero_init_mask_tokens': 'pred_zero_init_mask_tokens=True', 'pred_mlp_ratio': 'pred_mlp_ratio=4.0' -}, model_name='VJEPA2Model', library='transformers', import_path='transformers.models.vjepa2'), ModelAttributes(model=, model_type='model', model_parameters={'audio_config': 'audio_config=None', 'text_config': 'text_config=None', 'audio_token_id': 'audio_token_id=None', 'projector_hidden_act': "projector_hidden_act='gelu'" -}, model_name='VoxtralForConditionalGeneration', library='transformers', import_path='transformers.models.voxtral'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=51866', 'hidden_size': 'hidden_size=1280', 'intermediate_size': 'intermediate_size=5120', 'num_hidden_layers': 'num_hidden_layers=32', 'num_attention_heads': 'num_attention_heads=20', 'scale_embedding': 'scale_embedding=False', 'activation_function': "activation_function='gelu'", 'num_mel_bins': 'num_mel_bins=128', 'max_source_positions': 'max_source_positions=1500', 'initializer_range': 'initializer_range=0.02', 'attention_dropout': 'attention_dropout=0.0' -}, model_name='VoxtralEncoder', library='transformers', import_path='transformers.models.voxtral'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None', 'adapter_attn_dim': 'adapter_attn_dim=None' -}, model_name='Wav2Vec2Model', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' -}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'hidden_size': 'hidden_size=1024', 'num_hidden_layers': 'num_hidden_layers=24', 'num_attention_heads': 'num_attention_heads=16', 'intermediate_size': 'intermediate_size=4096', 'feature_projection_input_dim': 'feature_projection_input_dim=160', 'hidden_act': "hidden_act='swish'", 'hidden_dropout': 'hidden_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=768', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=1', 'adapter_act': "adapter_act='relu'", 'use_intermediate_ffn_before_adapter': 'use_intermediate_ffn_before_adapter=False', 'output_hidden_size': 'output_hidden_size=None', 'position_embeddings_type': "position_embeddings_type='relative_key'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=5000', 'left_max_position_embeddings': 'left_max_position_embeddings=64', 'right_max_position_embeddings': 'right_max_position_embeddings=8', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'conformer_conv_dropout': 'conformer_conv_dropout=0.1' -}, model_name='Wav2Vec2BertModel', library='transformers', import_path='transformers.models.wav2vec2_bert'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' -}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=None', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'feat_quantizer_dropout': 'feat_quantizer_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='sum'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None', 'position_embeddings_type': "position_embeddings_type='relative'", 'rotary_embedding_base': 'rotary_embedding_base=10000', 'max_source_positions': 'max_source_positions=5000', 'conv_depthwise_kernel_size': 'conv_depthwise_kernel_size=31', 'conformer_conv_dropout': 'conformer_conv_dropout=0.1' -}, model_name='Wav2Vec2ConformerModel', library='transformers', import_path='transformers.models.wav2vec2_conformer'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'pad_token': "pad_token=''", 'word_delimiter_token': "word_delimiter_token='|'", 'replace_word_delimiter_char': "replace_word_delimiter_char=' '", 'do_lower_case': 'do_lower_case=False', 'target_lang': 'target_lang=None' -}, model_name='Wav2Vec2CTCTokenizer', library='transformers', import_path='transformers.models.wav2vec2'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout': 'hidden_dropout=0.1', 'activation_dropout': 'activation_dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'feat_proj_dropout': 'feat_proj_dropout=0.0', 'final_dropout': 'final_dropout=0.1', 'layerdrop': 'layerdrop=0.1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'feat_extract_norm': "feat_extract_norm='group'", 'feat_extract_activation': "feat_extract_activation='gelu'", 'conv_dim': 'conv_dim=(512, - 512, - 512, - 512, - 512, - 512, - 512)', 'conv_stride': 'conv_stride=(5, - 2, - 2, - 2, - 2, - 2, - 2)', 'conv_kernel': 'conv_kernel=(10, - 3, - 3, - 3, - 3, - 2, - 2)', 'conv_bias': 'conv_bias=False', 'num_conv_pos_embeddings': 'num_conv_pos_embeddings=128', 'num_conv_pos_embedding_groups': 'num_conv_pos_embedding_groups=16', 'num_buckets': 'num_buckets=320', 'max_bucket_distance': 'max_bucket_distance=800', 'do_stable_layer_norm': 'do_stable_layer_norm=False', 'apply_spec_augment': 'apply_spec_augment=True', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'num_codevectors_per_group': 'num_codevectors_per_group=320', 'num_codevector_groups': 'num_codevector_groups=2', 'contrastive_logits_temperature': 'contrastive_logits_temperature=0.1', 'num_negatives': 'num_negatives=100', 'codevector_dim': 'codevector_dim=256', 'proj_codevector_dim': 'proj_codevector_dim=256', 'diversity_loss_weight': 'diversity_loss_weight=0.1', 'ctc_loss_reduction': "ctc_loss_reduction='mean'", 'ctc_zero_infinity': 'ctc_zero_infinity=False', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'tdnn_dim': 'tdnn_dim=(512, - 512, - 512, - 512, - 1500)', 'tdnn_kernel': 'tdnn_kernel=(5, - 3, - 3, - 1, - 1)', 'tdnn_dilation': 'tdnn_dilation=(1, - 2, - 3, - 1, - 1)', 'xvector_output_dim': 'xvector_output_dim=512', 'num_ctc_classes': 'num_ctc_classes=80', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'add_adapter': 'add_adapter=False', 'adapter_kernel_size': 'adapter_kernel_size=3', 'adapter_stride': 'adapter_stride=2', 'num_adapter_layers': 'num_adapter_layers=3', 'output_hidden_size': 'output_hidden_size=None' -}, model_name='WavLMModel', library='transformers', import_path='transformers.models.wavlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=51865', 'num_mel_bins': 'num_mel_bins=80', 'encoder_layers': 'encoder_layers=4', 'encoder_attention_heads': 'encoder_attention_heads=6', 'decoder_layers': 'decoder_layers=4', 'decoder_attention_heads': 'decoder_attention_heads=6', 'decoder_ffn_dim': 'decoder_ffn_dim=1536', 'encoder_ffn_dim': 'encoder_ffn_dim=1536', 'encoder_layerdrop': 'encoder_layerdrop=0.0', 'decoder_layerdrop': 'decoder_layerdrop=0.0', 'decoder_start_token_id': 'decoder_start_token_id=50257', 'is_encoder_decoder': 'is_encoder_decoder=True', 'activation_function': "activation_function='gelu'", 'd_model': 'd_model=384', 'dropout': 'dropout=0.0', 'attention_dropout': 'attention_dropout=0.0', 'activation_dropout': 'activation_dropout=0.0', 'init_std': 'init_std=0.02', 'scale_embedding': 'scale_embedding=False', 'max_source_positions': 'max_source_positions=1500', 'max_target_positions': 'max_target_positions=448', 'pad_token_id': 'pad_token_id=50256', 'bos_token_id': 'bos_token_id=50256', 'eos_token_id': 'eos_token_id=50256', 'suppress_tokens': 'suppress_tokens=None', 'begin_suppress_tokens': 'begin_suppress_tokens=[ - 220, - 50256 - ]', 'use_weighted_layer_sum': 'use_weighted_layer_sum=False', 'classifier_proj_size': 'classifier_proj_size=256', 'apply_spec_augment': 'apply_spec_augment=False', 'mask_time_prob': 'mask_time_prob=0.05', 'mask_time_length': 'mask_time_length=10', 'mask_time_min_masks': 'mask_time_min_masks=2', 'mask_feature_prob': 'mask_feature_prob=0.0', 'mask_feature_length': 'mask_feature_length=10', 'mask_feature_min_masks': 'mask_feature_min_masks=0', 'median_filter_width': 'median_filter_width=7' -}, model_name='WhisperModel', library='transformers', import_path='transformers.models.whisper'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges=None', 'normalizer_file': 'normalizer_file=None', 'unk_token': "unk_token='<|endoftext|>'", 'bos_token': "bos_token='<|endoftext|>'", 'eos_token': "eos_token='<|endoftext|>'", 'add_prefix_space': 'add_prefix_space=False', 'language': 'language=None', 'task': 'task=None', 'predict_timestamps': 'predict_timestamps=False' -}, model_name='WhisperTokenizer', library='transformers', import_path='transformers.models.whisper'), ModelAttributes(model=, model_type='model', model_parameters={'text_config': 'text_config=None', 'vision_config': 'vision_config=None', 'projection_dim': 'projection_dim=512', 'prompt_layers': 'prompt_layers=2', 'prompt_alpha': 'prompt_alpha=0.1', 'prompt_hidden_act': "prompt_hidden_act='quick_gelu'", 'prompt_num_attention_heads': 'prompt_num_attention_heads=8', 'prompt_attention_dropout': 'prompt_attention_dropout=0.0', 'prompt_projection_dropout': 'prompt_projection_dropout=0.0', 'logit_scale_init_value': 'logit_scale_init_value=2.6592' -}, model_name='XCLIPModel', library='transformers', import_path='transformers.models.x_clip'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|startoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|endoftext|>'" -}, model_name='CLIPTokenizer', library='transformers', import_path='transformers.models.clip'), ModelAttributes(model=, model_type='model', model_parameters={'target_bandwidths': 'target_bandwidths: Optional[list[float - ] - ] = None', 'sample_rate': 'sample_rate: int = 16000', 'kernel_size': 'kernel_size: int = 3', 'channel_ratios': 'channel_ratios: list[float - ] = [ - 1, - 1 - ]', 'strides': 'strides: list[int - ] = [ - 1, - 1 - ]', 'block_dilations': 'block_dilations: list[int - ] = [ - 1, - 1 - ]', 'unit_kernel_size': 'unit_kernel_size: int = 3', 'codebook_size': 'codebook_size: int = 1024', 'codebook_dim': 'codebook_dim: Optional[int - ] = None', 'initializer_range': 'initializer_range: float = 0.02', 'acoustic_model_config': 'acoustic_model_config: Union[dict, transformers.models.dac.configuration_dac.DacConfig, NoneType - ] = None', 'semantic_model_config': 'semantic_model_config: Union[dict, transformers.models.hubert.configuration_hubert.HubertConfig, NoneType - ] = None' -}, model_name='XcodecModel', library='transformers', import_path='transformers.models.xcodec'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=256008', 'max_position_embeddings': 'max_position_embeddings=2048', 'd_model': 'd_model=1024', 'ffn_dim': 'ffn_dim=4096', 'num_layers': 'num_layers=24', 'attention_heads': 'attention_heads=16', 'activation_function': "activation_function='gelu'", 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'activation_dropout': 'activation_dropout=0.0', 'layerdrop': 'layerdrop=0.0', 'init_std': 'init_std=0.02', 'scale_embedding': 'scale_embedding=True', 'decoder_start_token_id': 'decoder_start_token_id=2', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='XGLMModel', library='transformers', import_path='transformers.models.xglm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'add_prefix_space': 'add_prefix_space: bool = True' -}, model_name='XGLMTokenizer', library='transformers', import_path='transformers.models.xglm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30145', 'emb_dim': 'emb_dim=2048', 'n_layers': 'n_layers=12', 'n_heads': 'n_heads=16', 'dropout': 'dropout=0.1', 'attention_dropout': 'attention_dropout=0.1', 'gelu_activation': 'gelu_activation=True', 'sinusoidal_embeddings': 'sinusoidal_embeddings=False', 'causal': 'causal=False', 'asm': 'asm=False', 'n_langs': 'n_langs=1', 'use_lang_emb': 'use_lang_emb=True', 'max_position_embeddings': 'max_position_embeddings=512', 'embed_init_std': 'embed_init_std=0.02209708691207961', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'init_std': 'init_std=0.02', 'bos_index': 'bos_index=0', 'eos_index': 'eos_index=1', 'pad_index': 'pad_index=2', 'unk_index': 'unk_index=3', 'mask_index': 'mask_index=5', 'is_encoder': 'is_encoder=True', 'summary_type': "summary_type='first'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': 'summary_activation=None', 'summary_proj_to_labels': 'summary_proj_to_labels=True', 'summary_first_dropout': 'summary_first_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'mask_token_id': 'mask_token_id=0', 'lang_id': 'lang_id=0', 'pad_token_id': 'pad_token_id=2', 'bos_token_id': 'bos_token_id=0' -}, model_name='XLMModel', library='transformers', import_path='transformers.models.xlm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab_file': 'vocab_file', 'merges_file': 'merges_file', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", 'lang2id': 'lang2id=None', 'id2lang': 'id2lang=None', 'do_lowercase_and_remove_accent': 'do_lowercase_and_remove_accent=True' -}, model_name='XLMTokenizer', library='transformers', import_path='transformers.models.xlm'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='XLMRobertaModel', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=250880', 'hidden_size': 'hidden_size=2560', 'num_hidden_layers': 'num_hidden_layers=36', 'num_attention_heads': 'num_attention_heads=32', 'intermediate_size': 'intermediate_size=10240', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=514', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-05', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None' -}, model_name='XLMRobertaXLModel', library='transformers', import_path='transformers.models.xlm_roberta_xl'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'd_model': 'd_model=1024', 'n_layer': 'n_layer=24', 'n_head': 'n_head=16', 'd_inner': 'd_inner=4096', 'ff_activation': "ff_activation='gelu'", 'attn_type': "attn_type='bi'", 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'dropout': 'dropout=0.1', 'mem_len': 'mem_len=512', 'reuse_len': 'reuse_len=None', 'use_mems_eval': 'use_mems_eval=True', 'use_mems_train': 'use_mems_train=False', 'bi_data': 'bi_data=False', 'clamp_len': 'clamp_len=-1', 'same_length': 'same_length=False', 'summary_type': "summary_type='last'", 'summary_use_proj': 'summary_use_proj=True', 'summary_activation': "summary_activation='tanh'", 'summary_last_dropout': 'summary_last_dropout=0.1', 'start_n_top': 'start_n_top=5', 'end_n_top': 'end_n_top=5', 'pad_token_id': 'pad_token_id=5', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2' -}, model_name='XLNetModel', library='transformers', import_path='transformers.models.xlnet'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'unk_id': 'unk_id: int = 0', 'do_lower_case': 'do_lower_case=False', 'remove_space': 'remove_space=True', 'keep_accents': 'keep_accents=False', 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'unk_token': "unk_token=''", 'sep_token': "sep_token=''", 'pad_token': "pad_token=''", 'cls_token': "cls_token=''", 'mask_token': "mask_token=''", 'additional_special_tokens': 'additional_special_tokens=None' -}, model_name='XLNetTokenizer', library='transformers', import_path='transformers.models.xlnet'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: int = 50304', 'hidden_size': 'hidden_size: int = 4096', 'embedding_dim': 'embedding_dim: Optional[int - ] = None', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 32', 'num_blocks': 'num_blocks: Optional[int - ] = None', 'num_heads': 'num_heads: int = 8', 'use_bias': 'use_bias: bool = False', 'norm_reduction_force_float32': 'norm_reduction_force_float32: bool = True', 'tie_word_embeddings': 'tie_word_embeddings: bool = False', 'add_out_norm': 'add_out_norm: bool = True', 'norm_eps': 'norm_eps: float = 1e-06', 'qk_dim_factor': 'qk_dim_factor: float = 0.5', 'v_dim_factor': 'v_dim_factor: float = 1.0', 'chunkwise_kernel': "chunkwise_kernel: Literal['chunkwise--native_autograd', 'parallel--native_autograd'] = 'chunkwise--native_autograd'", 'sequence_kernel': "sequence_kernel: Literal['native_sequence__native'] = 'native_sequence__native'", 'step_kernel': "step_kernel: Literal['native'] = 'native'", 'mode': "mode: Literal['train', 'train_with_padding', 'inference'] = 'inference'", 'chunk_size': 'chunk_size: int = 64', 'return_last_states': 'return_last_states: bool = True', 'autocast_kernel_dtype': "autocast_kernel_dtype: Literal['float32', 'bfloat16', 'float16'] = 'bfloat16'", 'eps': 'eps: float = 1e-06', 'inference_state_dtype': "inference_state_dtype: Literal['float32', 'bfloat16', 'float16'] = 'float32'", 'ffn_proj_factor': 'ffn_proj_factor: float = 2.667', 'ffn_round_up_to_multiple_of': 'ffn_round_up_to_multiple_of: int = 64', 'gate_soft_cap': 'gate_soft_cap: float = 15.0', 'output_logit_soft_cap': 'output_logit_soft_cap: float = 30.0', 'weight_mode': "weight_mode: Literal['single', 'fused'] = 'single'", 'pad_token_id': 'pad_token_id: int = 1', 'bos_token_id': 'bos_token_id: int = 0', 'eos_token_id': 'eos_token_id: int = 2', 'max_inference_chunksize': 'max_inference_chunksize: int = 16384' -}, model_name='xLSTMModel', library='transformers', import_path='transformers.models.xlstm'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict[str, int - ], NoneType - ] = None', 'merges': 'merges: Union[str, list[str - ], NoneType - ] = None', 'errors': "errors: str = 'replace'", 'unk_token': "unk_token: str = '<|endoftext|>'", 'bos_token': "bos_token: str = '<|endoftext|>'", 'eos_token': "eos_token: str = '<|endoftext|>'", 'pad_token': "pad_token: str = '<|padding|>'", 'add_prefix_space': 'add_prefix_space: bool = False', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='GPTNeoXTokenizer', library='transformers', import_path='transformers.models.gpt_neox'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=30522', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=512', 'type_vocab_size': 'type_vocab_size=2', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2', 'classifier_dropout': 'classifier_dropout=None', 'pre_norm': 'pre_norm=False', 'adapter_reduction_factor': 'adapter_reduction_factor=2', 'adapter_layer_norm': 'adapter_layer_norm=False', 'adapter_reuse_layer_norm': 'adapter_reuse_layer_norm=True', 'ln_before_adapter': 'ln_before_adapter=True', 'languages': "languages=('en_XX',)", 'default_language': 'default_language=None' -}, model_name='XmodModel', library='transformers', import_path='transformers.models.xmod'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'add_prefix_space': 'add_prefix_space: bool = True', 'bos_token': "bos_token: str = ''", 'eos_token': "eos_token: str = ''", 'sep_token': "sep_token: str = ''", 'cls_token': "cls_token: str = ''", 'unk_token': "unk_token: str = ''", 'pad_token': "pad_token: str = ''", 'mask_token': "mask_token: str = ''" -}, model_name='XLMRobertaTokenizer', library='transformers', import_path='transformers.models.xlm_roberta'), ModelAttributes(model=, model_type='model', model_parameters={'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.0', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.0', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'image_size': 'image_size=[ - 512, - 864 - ]', 'patch_size': 'patch_size=16', 'num_channels': 'num_channels=3', 'qkv_bias': 'qkv_bias=True', 'num_detection_tokens': 'num_detection_tokens=100', 'use_mid_position_embeddings': 'use_mid_position_embeddings=True', 'auxiliary_loss': 'auxiliary_loss=False', 'class_cost': 'class_cost=1', 'bbox_cost': 'bbox_cost=5', 'giou_cost': 'giou_cost=2', 'bbox_loss_coefficient': 'bbox_loss_coefficient=5', 'giou_loss_coefficient': 'giou_loss_coefficient=2', 'eos_coefficient': 'eos_coefficient=0.1' -}, model_name='YolosModel', library='transformers', import_path='transformers.models.yolos'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=50265', 'hidden_size': 'hidden_size=768', 'num_hidden_layers': 'num_hidden_layers=12', 'num_attention_heads': 'num_attention_heads=12', 'intermediate_size': 'intermediate_size=3072', 'hidden_act': "hidden_act='gelu'", 'hidden_dropout_prob': 'hidden_dropout_prob=0.1', 'attention_probs_dropout_prob': 'attention_probs_dropout_prob=0.1', 'max_position_embeddings': 'max_position_embeddings=4096', 'type_vocab_size': 'type_vocab_size=1', 'initializer_range': 'initializer_range=0.02', 'layer_norm_eps': 'layer_norm_eps=1e-12', 'use_expectation': 'use_expectation=True', 'hash_code_len': 'hash_code_len=9', 'num_hash': 'num_hash=64', 'conv_window': 'conv_window=None', 'use_fast_hash': 'use_fast_hash=True', 'lsh_backward': 'lsh_backward=True', 'pad_token_id': 'pad_token_id=1', 'bos_token_id': 'bos_token_id=0', 'eos_token_id': 'eos_token_id=2' -}, model_name='YosoModel', library='transformers', import_path='transformers.models.yoso'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, list[tuple[str, float - ] - ], NoneType - ] = None', 'do_lower_case': 'do_lower_case: bool = True', 'keep_accents': 'keep_accents: bool = False', 'bos_token': "bos_token: str = '[CLS]'", 'eos_token': "eos_token: str = '[SEP]'", 'unk_token': "unk_token: str = ''", 'sep_token': "sep_token: str = '[SEP]'", 'pad_token': "pad_token: str = ''", 'cls_token': "cls_token: str = '[CLS]'", 'mask_token': "mask_token: str = '[MASK]'", 'add_prefix_space': 'add_prefix_space: bool = True', 'trim_offsets': 'trim_offsets: bool = True' -}, model_name='AlbertTokenizer', library='transformers', import_path='transformers.models.albert'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size=32000', 'tie_word_embeddings': 'tie_word_embeddings=True', 'hidden_size': 'hidden_size=3712', 'attention_hidden_size': 'attention_hidden_size=None', 'intermediate_size': 'intermediate_size=14848', 'num_hidden_layers': 'num_hidden_layers=76', 'num_attention_heads': 'num_attention_heads=16', 'attention_head_dim': 'attention_head_dim=None', 'num_key_value_heads': 'num_key_value_heads=16', 'n_mamba_heads': 'n_mamba_heads=2', 'hidden_act': "hidden_act='gelu'", 'hidden_mamba_act': "hidden_mamba_act='silu'", 'initializer_range': 'initializer_range=0.02', 'rms_norm_eps': 'rms_norm_eps=1e-05', 'num_logits_to_keep': 'num_logits_to_keep=1', 'pad_token_id': 'pad_token_id=0', 'bos_token_id': 'bos_token_id=1', 'eos_token_id': 'eos_token_id=2', 'max_position_embeddings': 'max_position_embeddings=4096', 'attention_dropout': 'attention_dropout=0.0', 'attn_layer_period': 'attn_layer_period=6', 'attn_layer_offset': 'attn_layer_offset=4', 'use_mamba_kernels': 'use_mamba_kernels=True', 'mamba_d_state': 'mamba_d_state=16', 'mamba_d_conv': 'mamba_d_conv=4', 'mamba_expand': 'mamba_expand=2', 'mamba_dt_rank': "mamba_dt_rank='auto'", 'time_step_min': 'time_step_min=0.001', 'time_step_max': 'time_step_max=0.1', 'time_step_floor': 'time_step_floor=0.0001', 'mamba_conv_bias': 'mamba_conv_bias=True', 'mamba_proj_bias': 'mamba_proj_bias=False' -}, model_name='ZambaModel', library='transformers', import_path='transformers.models.zamba'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama'), ModelAttributes(model=, model_type='model', model_parameters={'vocab_size': 'vocab_size: Optional[int - ] = 32000', 'max_position_embeddings': 'max_position_embeddings: Optional[int - ] = 4096', 'hidden_size': 'hidden_size: Optional[int - ] = 2560', 'num_hidden_layers': 'num_hidden_layers: Optional[int - ] = 54', 'layers_block_type': 'layers_block_type: Optional[list[str - ] - ] = None', 'mamba_d_state': 'mamba_d_state: Optional[int - ] = 64', 'mamba_d_conv': 'mamba_d_conv: Optional[int - ] = 4', 'mamba_expand': 'mamba_expand: Optional[int - ] = 2', 'mamba_ngroups': 'mamba_ngroups: Optional[int - ] = 1', 'time_step_min': 'time_step_min: Optional[float - ] = 0.001', 'time_step_max': 'time_step_max: Optional[float - ] = 0.1', 'time_step_floor': 'time_step_floor: Optional[int - ] = 0.0001', 'time_step_limit': 'time_step_limit: Optional[int - ] = None', 'n_mamba_heads': 'n_mamba_heads: Optional[int - ] = 8', 'use_conv_bias': 'use_conv_bias: Optional[bool - ] = True', 'chunk_size': 'chunk_size: Optional[int - ] = 256', 'use_mem_eff_path': 'use_mem_eff_path: Optional[bool - ] = False', 'add_bias_linear': 'add_bias_linear: Optional[bool - ] = False', 'intermediate_size': 'intermediate_size: Optional[int - ] = None', 'hidden_act': "hidden_act: Optional[str] = 'gelu'", 'num_attention_heads': 'num_attention_heads: Optional[int - ] = 32', 'num_key_value_heads': 'num_key_value_heads: Optional[int - ] = None', 'attention_dropout': 'attention_dropout: Optional[float - ] = 0.0', 'num_mem_blocks': 'num_mem_blocks: Optional[int - ] = 1', 'use_shared_attention_adapter': 'use_shared_attention_adapter: Optional[bool - ] = False', 'adapter_rank': 'adapter_rank: Optional[int - ] = 128', 'use_mem_rope': 'use_mem_rope: Optional[bool - ] = False', 'rope_parameters': 'rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters - ], NoneType - ] = None', 'initializer_range': 'initializer_range: Optional[float - ] = 0.02', 'rms_norm_eps': 'rms_norm_eps: Optional[int - ] = 1e-05', 'num_logits_to_keep': 'num_logits_to_keep: Optional[int - ] = 1', 'pad_token_id': 'pad_token_id: Optional[int - ] = 0', 'bos_token_id': 'bos_token_id: Optional[int - ] = 1', 'eos_token_id': 'eos_token_id: Optional[int - ] = 2', 'use_long_context': 'use_long_context: Optional[bool - ] = False' -}, model_name='Zamba2Model', library='transformers', import_path='transformers.models.zamba2'), ModelAttributes(model=, model_type='tokenizer', model_parameters={'vocab': 'vocab: Union[str, dict, list, NoneType - ] = None', 'merges': 'merges: Union[str, list, NoneType - ] = None', 'clean_up_tokenization_spaces': 'clean_up_tokenization_spaces=False', 'unk_token': "unk_token=''", 'bos_token': "bos_token=''", 'eos_token': "eos_token=''", 'use_default_system_prompt': 'use_default_system_prompt=False', 'legacy': 'legacy=False', 'add_prefix_space': 'add_prefix_space=None' -}, model_name='LlamaTokenizer', library='transformers', import_path='transformers.models.llama') -] \ No newline at end of file diff --git a/mir/generate/torch/__init__.py b/mir/generate/torch/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/mir/generate/transformers/__init__.py b/mir/generate/transformers/__init__.py deleted file mode 100644 index 7cd0886..0000000 --- a/mir/generate/transformers/__init__.py +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 -# - - -from transformers.models.auto.configuration_auto import CONFIG_MAPPING -from transformers.models.auto.modeling_auto import ( - MODEL_MAPPING, # config: model map - MODEL_MAPPING_NAMES, - AutoModel, -) -from transformers.models.auto.tokenization_auto import TOKENIZER_MAPPING - -AUTO_MAP = AutoModel._model_mapping -REVERSE_MAP = AUTO_MAP._reverse_config_mapping diff --git a/mir/generate/from_module.py b/mir/lookups.py similarity index 66% rename from mir/generate/from_module.py rename to mir/lookups.py index 586c46d..9e9df60 100644 --- a/mir/generate/from_module.py +++ b/mir/lookups.py @@ -4,10 +4,37 @@ # 模块发现和解构 import inspect - from importlib import import_module +from types import ModuleType from typing import Callable +tag = lambda path: path.rsplit(".", 1) # noqa +run = lambda parts: getattr(import_module(parts[0]), parts[1]) + + +def get_attribute_chain(root_object: Callable | ModuleType, attribute_path: str) -> Callable | ModuleType: + """Retrieve a nested attribute from *root_object* using a dot-separated string.\n + :param root_object : The object from which the attribute chain will be resolved. + :param attribute_path : Dot-separated attribute names, e.g. ``"ops.cnn.yolos"``. + :returns: The final attribute value reached by following the chain. + :raises: AttributeError If any part of the chain does not exist on the current object.""" + current = root_object + for part in attribute_path.split("."): + current = getattr(current, part) + return current + + +def get_import_chain(class_path: str) -> Callable | ModuleType: + """Retrieve a class object from dot-separated string reference.\n + :param class_path : The object from which the attribute chain will be resolved. + :returns: The final imported object reached by following the chain. + :raises: AttributeError If any part of the chain does not exist on the current object.""" + library_name = class_path.split(".")[0] + attribute_path = class_path.replace(library_name + ".", "") + library = import_module(library_name) + path_chain = get_attribute_chain(library, attribute_path) + return path_chain + def migrations(repo_path: str) -> str: """Replaces old organization names in repository paths with new ones.\n diff --git a/mir/model.py b/mir/model.py index ac8da16..8f51052 100644 --- a/mir/model.py +++ b/mir/model.py @@ -33,13 +33,13 @@ def __post_init__(self) -> None: if not hasattr(self, "config") and any(x in self.model_type for x in ["tokenizer", "prior_tokenizer"]): self.config = self.model elif not hasattr(self, "config") and self.library == "transformers" and "model" in self.model_type: - from mir.generate.transformers import AUTO_MAP + from mir.gatherers.transformers import AUTO_MAP config: dict = {model: config for config, model in AUTO_MAP.items() if model == self.model} self.config = config.get(self.model, None) # type:ignore if getattr(self, "config", None) and self.library == "transformers": from mir.data import PARAMETERS - from mir.generate.from_module import show_init_fields_for + from mir.lookups import show_init_fields_for config_name = self.config.__name__ config_parameters = PARAMETERS.get(config_name, show_init_fields_for(self.config)) diff --git a/mir/nesting.py b/mir/nesting.py index c038d97..803327e 100644 --- a/mir/nesting.py +++ b/mir/nesting.py @@ -2,8 +2,7 @@ # from typing import Any -from dataclasses import dataclass, field -from mir.model import ModelAttributes +from dataclasses import field from mir.tag import MIRTag from mir.package import MIRPackage @@ -20,13 +19,12 @@ class MIRNesting: framework: dict[str, str] = field(init=False) tokenizer: str | None = field(default_factory=str) - def __init__(self, mir_tag: MIRTag, prepared_data: ModelAttributes | ModelAttributes) -> None: + def __init__(self, mir_tag: MIRTag, mir_package: MIRPackage) -> None: """\nInitialize the framework with MIR tag and prepared data.\n :param mir_tag : The MIR tag instance. :param prepared_data : The prepared data for processing.""" self.mir_tag = mir_tag - - self.prepared_data = prepared_data + self.mir_package = mir_package self.loops = [] self.framework_data = {} diff --git a/mir/package.py b/mir/package.py index 20f0750..6da370c 100644 --- a/mir/package.py +++ b/mir/package.py @@ -62,7 +62,7 @@ def repo_from_config(self) -> None: continue def repo_from_doc_string(self, doc_string: str) -> None: - from mir.generate.diffusers.doc_parse import DocStringParser + from mir.doc_parse import DocStringParser doc_parser = DocStringParser( doc_string=doc_string, @@ -80,7 +80,7 @@ def tasks_from_internal_name(self) -> None: :param class_name: To find task pipes from a Diffusers class pipe, defaults to None :param code_name: To find task pipes from a Transformers class pipe, defaults to None :return: A list of alternate class pipelines derived from the specified class""" - from mir.generate.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS + from mir.gatherers.diffusers import SUPPORTED_TASKS_MAPPINGS, GET_TASK_CLASS alt_tasks = set({}) self.internal_name = self.attributes.import_path.rsplit(".", 2)[-1] diff --git a/mir/tag.py b/mir/tag.py index c6c5408..a2edddc 100644 --- a/mir/tag.py +++ b/mir/tag.py @@ -26,8 +26,17 @@ class MIRTag: def __post_init__(self) -> None: """Initializes MIRTag instance, setting up database connection and generating package and MIR tag information.""" - self.generate_arch() - self.generate_series_and_comp() + + if "scheduler" in self.attributes.model_type: + self.tag_scheduler() + elif "tokenizer" in self.attributes.model_type: + self.arch = "encoder" + self.generate_series_and_comp() + self.comp = self.series + self.series = "tokenizer" + else: + self.generate_arch() + self.generate_series_and_comp() if hasattr(self, "comp"): self.flat = f"{self.arch}.{self.series}.{self.comp}" else: @@ -41,7 +50,7 @@ def generate_arch(self) -> None: assert arch is not None, f"Unrecognized model type, no tag matched {self.attributes.model_name} with {self.attributes}" self.arch = arch - def generate_series_and_comp(self, base_model_label="*") -> None: + def generate_series_and_comp(self) -> None: """Generates the MIR tag components from a repository title.\n :param repo_title: The title of the repository from which to derive the MIR tag. :param decoder: Boolean flag indicating if the model is a decoder. @@ -76,21 +85,24 @@ def generate_series_and_comp(self, base_model_label="*") -> None: cleaned_string = re.sub(suffix.lower(), "-", cleaned_string).rstrip("-,") else: suffix = "*" - if isinstance(self.attributes, DiffusersModelAttributes) and self.attributes.model_type == "decoder": + if self.attributes.model_type == "decoder": suffix = "decoder" cleaned_string = re.sub(r"[.-]+", "_", cleaned_string.lower()).strip("-_") self.series = cleaned_string if suffix != "*": self.comp = suffix - def tag_architecture(self, library: str, **kwargs) -> str | None: + def tag_architecture(self) -> str | None: """Set type of MIR prefix depending on model type\n :param library: Library source of the original data :raises ValueError: Model type not detected :return: MIR prefix based on model configuration""" from mir.data import NN_FILTER + library = self.attributes.library + flags = NN_FILTER["arch"][library] # pylint:disable=unsubscriptable-object + if library == "diffusers": for module_type, module_obj in kwargs.items(): module_name = module_obj.__module__ @@ -104,31 +116,31 @@ def tag_architecture(self, library: str, **kwargs) -> str | None: return mir_prefix return None + def tag_scheduler(self) -> tuple[str, str]: + """Create a mir label from a scheduler operation\n + :param class_name: Known period-separated prefix and model type + :return: The assembled mir tag with compatibility pre-separated""" + import re -def tag_scheduler(self, scheduler_name: str) -> tuple[str, str]: - """Create a mir label from a scheduler operation\n - :param class_name: Known period-separated prefix and model type - :return: The assembled mir tag with compatibility pre-separated""" - import re - - series_name = None - comp_name = None - patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] - for scheduler in patterns: - compiled = re.compile(scheduler) - match = re.search(compiled, scheduler_name) - if match: - comp_name = match.group() - comp_name = comp_name.lower() - break - for pattern in patterns: - series_name = re.sub(pattern, "", scheduler_name) - if not series_name: - series_name = scheduler_name - series_name.lower() - assert series_name is not None, "Expected series tag but got None" - assert comp_name is not None, "Expected compatibility tag but got None" - return series_name, comp_name + scheduler_name = self.attributes.model_name + series_name = None + comp_name = None + patterns = [r"Schedulers", r"Multistep", r"Solver", r"Discrete", r"Scheduler"] + for scheduler in patterns: + compiled = re.compile(scheduler) + match = re.search(compiled, scheduler_name) + if match: + comp_name = match.group() + comp_name = comp_name.lower() + break + for pattern in patterns: + series_name = re.sub(pattern, "", scheduler_name) + if not series_name: + series_name = scheduler_name + series_name.lower() + assert series_name is not None, "Expected series tag but got None" + assert comp_name is not None, "Expected compatibility tag but got None" + return series_name, comp_name def tag_tokenizer(): diff --git a/tests/subclasses_test.py b/tests/subclasses_test.py index e69de29..131601c 100644 --- a/tests/subclasses_test.py +++ b/tests/subclasses_test.py @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from mir.gatherers.transformers import GatherLoop +from mir.json_io import write_json_file + + +transformers_packages = GatherLoop() + +from mir.gatherers.diffusers import GatherLoop + +diffusers_packages = GatherLoop() + +packages = {"transformers": transformers_packages.model_db, "diffusers": diffusers_packages.model_db} + +write_json_file(folder_path_named="tests", file_name="test.json", data=packages) diff --git a/tests/test.json b/tests/test.json new file mode 100644 index 0000000..1732d30 --- /dev/null +++ b/tests/test.json @@ -0,0 +1,9814 @@ +{ + "transformers": { + "AfmoeModel": { + "vocab_size": "vocab_size: Optional[int] = 200192", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 6144", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_dense_layers": "num_dense_layers: Optional[int] = 1", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 16384", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_theta": "rope_theta: Optional[float] = 10000.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "num_experts": "num_experts: Optional[int] = 64", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 6", + "num_shared_experts": "num_shared_experts: Optional[int] = 2", + "route_scale": "route_scale: Optional[float] = 1.0", + "global_attn_every_n_layers": "global_attn_every_n_layers: Optional[int] = 4", + "sliding_window": "sliding_window: Optional[int] = 1024", + "layer_types": "layer_types: Optional[list] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mup_enabled": "mup_enabled: Optional[bool] = False" + }, + "Aimv2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "CLIPTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "unk_token": "unk_token: str = '<|endoftext|>'", + "bos_token": "bos_token: str = '<|startoftext|>'", + "eos_token": "eos_token: str = '<|endoftext|>'", + "pad_token": "pad_token: str = '<|endoftext|>'" + }, + "Aimv2VisionModel": { + "hidden_size": "hidden_size: int = 1024", + "intermediate_size": "intermediate_size: int = 2816", + "num_hidden_layers": "num_hidden_layers: int = 24", + "num_attention_heads": "num_attention_heads: int = 8", + "num_channels": "num_channels: int = 3", + "image_size": "image_size: int = 224", + "patch_size": "patch_size: int = 14", + "rms_norm_eps": "rms_norm_eps: float = 1e-05", + "attention_dropout": "attention_dropout: float = 0.0", + "qkv_bias": "qkv_bias: bool = False", + "mlp_bias": "mlp_bias: bool = False", + "hidden_act": "hidden_act: str = 'silu'", + "initializer_range": "initializer_range: float = 0.02", + "use_head": "use_head: bool = True", + "is_native": "is_native: bool = False" + }, + "AlbertModel": { + "vocab_size": "vocab_size=30000", + "embedding_size": "embedding_size=128", + "hidden_size": "hidden_size=4096", + "num_hidden_layers": "num_hidden_layers=12", + "num_hidden_groups": "num_hidden_groups=1", + "num_attention_heads": "num_attention_heads=64", + "intermediate_size": "intermediate_size=16384", + "inner_group_num": "inner_group_num=1", + "hidden_act": "hidden_act='gelu_new'", + "hidden_dropout_prob": "hidden_dropout_prob=0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=3" + }, + "AlbertTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "do_lower_case": "do_lower_case: bool = True", + "keep_accents": "keep_accents: bool = False", + "bos_token": "bos_token: str = '[CLS]'", + "eos_token": "eos_token: str = '[SEP]'", + "unk_token": "unk_token: str = ''", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = ''", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "add_prefix_space": "add_prefix_space: bool = True", + "trim_offsets": "trim_offsets: bool = True" + }, + "AlignModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=640", + "temperature_init_value": "temperature_init_value=1.0", + "initializer_range": "initializer_range=0.02" + }, + "BertTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case: bool = False", + "unk_token": "unk_token: str = '[UNK]'", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = '[PAD]'", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars: bool = True", + "strip_accents": "strip_accents: Optional[bool] = None" + }, + "AltCLIPModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=768", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "ApertusModel": { + "vocab_size": "vocab_size: Optional[int] = 131072", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'xielu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 65536", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 3", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = {'rope_type': 'llama3', 'rope_theta': 12000000.0, 'factor': 8.0, 'original_max_position_embeddings': 8192, 'low_freq_factor': 1.0, 'high_freq_factor': 4.0}", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "ArceeModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 18432", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 128000", + "eos_token_id": "eos_token_id: Optional[int] = 128001", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "head_dim": "head_dim: Optional[int] = None" + }, + "LlamaTokenizer": { + "vocab": "vocab: Union[str, dict, list, NoneType] = None", + "merges": "merges: Union[str, list, NoneType] = None", + "clean_up_tokenization_spaces": "clean_up_tokenization_spaces=False", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "use_default_system_prompt": "use_default_system_prompt=False", + "legacy": "legacy=False", + "add_prefix_space": "add_prefix_space=None" + }, + "AriaModel": { + "vision_config": "vision_config=None", + "vision_feature_layer": "vision_feature_layer: int = -1", + "text_config": "text_config: transformers.models.aria.configuration_aria.AriaTextConfig = None", + "projector_patch_to_query_dict": "projector_patch_to_query_dict: Optional[dict] = None", + "image_token_index": "image_token_index: int = 9", + "initializer_range": "initializer_range: float = 0.02" + }, + "AriaTextModel": { + "vision_config": [ + "" + ], + "text_config": [ + "" + ] + }, + "ASTModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "patch_size": "patch_size=16", + "qkv_bias": "qkv_bias=True", + "frequency_stride": "frequency_stride=10", + "time_stride": "time_stride=10", + "max_length": "max_length=1024", + "num_mel_bins": "num_mel_bins=128" + }, + "AudioFlamingo3ForConditionalGeneration": { + "audio_config": "audio_config=None", + "text_config": "text_config=None", + "audio_token_id": "audio_token_id=151669", + "projector_hidden_act": "projector_hidden_act='gelu'", + "projector_bias": "projector_bias=True" + }, + "Qwen2Tokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "vocab_file": "vocab_file=None", + "merges_file": "merges_file=None", + "unk_token": "unk_token: str = '<|endoftext|>'", + "bos_token": "bos_token=None", + "eos_token": "eos_token: str = '<|endoftext|>'", + "pad_token": "pad_token: str = '<|endoftext|>'", + "add_prefix_space": "add_prefix_space=None" + }, + "AudioFlamingo3Encoder": { + "num_mel_bins": "num_mel_bins=128", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=20", + "intermediate_size": "intermediate_size=5120", + "layerdrop": "layerdrop=0.0", + "activation_function": "activation_function='gelu'", + "hidden_size": "hidden_size=1280", + "dropout": "dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "scale_embedding": "scale_embedding=False", + "max_source_positions": "max_source_positions=1500" + }, + "AutoformerModel": { + "prediction_length": "prediction_length: Optional[int] = None", + "context_length": "context_length: Optional[int] = None", + "distribution_output": "distribution_output: str = 'student_t'", + "loss": "loss: str = 'nll'", + "input_size": "input_size: int = 1", + "lags_sequence": "lags_sequence: list[int] = [1, 2, 3, 4, 5, 6, 7]", + "scaling": "scaling: bool = True", + "num_time_features": "num_time_features: int = 0", + "num_dynamic_real_features": "num_dynamic_real_features: int = 0", + "num_static_categorical_features": "num_static_categorical_features: int = 0", + "num_static_real_features": "num_static_real_features: int = 0", + "cardinality": "cardinality: Optional[list[int]] = None", + "embedding_dimension": "embedding_dimension: Optional[list[int]] = None", + "d_model": "d_model: int = 64", + "encoder_attention_heads": "encoder_attention_heads: int = 2", + "decoder_attention_heads": "decoder_attention_heads: int = 2", + "encoder_layers": "encoder_layers: int = 2", + "decoder_layers": "decoder_layers: int = 2", + "encoder_ffn_dim": "encoder_ffn_dim: int = 32", + "decoder_ffn_dim": "decoder_ffn_dim: int = 32", + "activation_function": "activation_function: str = 'gelu'", + "dropout": "dropout: float = 0.1", + "encoder_layerdrop": "encoder_layerdrop: float = 0.1", + "decoder_layerdrop": "decoder_layerdrop: float = 0.1", + "attention_dropout": "attention_dropout: float = 0.1", + "activation_dropout": "activation_dropout: float = 0.1", + "num_parallel_samples": "num_parallel_samples: int = 100", + "init_std": "init_std: float = 0.02", + "is_encoder_decoder": "is_encoder_decoder=True", + "label_length": "label_length: int = 10", + "moving_average": "moving_average: int = 25", + "autocorrelation_factor": "autocorrelation_factor: int = 3" + }, + "AyaVisionModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "vision_feature_select_strategy": "vision_feature_select_strategy='full'", + "vision_feature_layer": "vision_feature_layer=-1", + "downsample_factor": "downsample_factor=2", + "adapter_layer_norm_eps": "adapter_layer_norm_eps=1e-06", + "image_token_index": "image_token_index=255036" + }, + "CohereTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors: str = 'replace'", + "unk_token": "unk_token: str = ''", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = '<|END_OF_TURN_TOKEN|>'", + "pad_token": "pad_token: str = ''", + "cls_token": "cls_token: str = ''", + "sep_token": "sep_token: str = ''", + "mask_token": "mask_token: str = ''", + "use_default_system_prompt": "use_default_system_prompt: bool = False", + "add_prefix_space": "add_prefix_space: bool = False" + }, + "BambaModel": { + "vocab_size": "vocab_size: Optional[int] = 128000", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "num_logits_to_keep": "num_logits_to_keep: Optional[int] = 1", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 262144", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "attn_layer_indices": "attn_layer_indices: Optional[list[int]] = None", + "mamba_n_heads": "mamba_n_heads: Optional[int] = 128", + "mamba_d_head": "mamba_d_head: Optional[str] = 'auto'", + "mamba_n_groups": "mamba_n_groups: Optional[int] = 1", + "mamba_d_state": "mamba_d_state: Optional[int] = 256", + "mamba_d_conv": "mamba_d_conv: Optional[int] = 4", + "mamba_expand": "mamba_expand: Optional[int] = 2", + "mamba_chunk_size": "mamba_chunk_size: Optional[int] = 256", + "mamba_conv_bias": "mamba_conv_bias: Optional[bool] = True", + "mamba_proj_bias": "mamba_proj_bias: Optional[bool] = False", + "z_loss_coefficient": "z_loss_coefficient: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = None" + }, + "BarkModel": { + "n_head": [ + "" + ] + }, + "BartModel": { + "vocab_size": "vocab_size=50265", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "classifier_dropout": "classifier_dropout=0.0", + "scale_embedding": "scale_embedding=False", + "num_labels": "num_labels=3", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "is_encoder_decoder": "is_encoder_decoder=True", + "decoder_start_token_id": "decoder_start_token_id=2" + }, + "RobertaTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors: str = 'replace'", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "sep_token": "sep_token: str = ''", + "cls_token": "cls_token: str = ''", + "unk_token": "unk_token: str = ''", + "pad_token": "pad_token: str = ''", + "mask_token": "mask_token: str = ''", + "add_prefix_space": "add_prefix_space: bool = False", + "trim_offsets": "trim_offsets: bool = True" + }, + "BeitModel": { + "vocab_size": "vocab_size=8192", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "use_mask_token": "use_mask_token=False", + "use_absolute_position_embeddings": "use_absolute_position_embeddings=False", + "use_relative_position_bias": "use_relative_position_bias=False", + "use_shared_relative_position_bias": "use_shared_relative_position_bias=False", + "layer_scale_init_value": "layer_scale_init_value=0.1", + "drop_path_rate": "drop_path_rate=0.1", + "use_mean_pooling": "use_mean_pooling=True", + "pool_scales": "pool_scales=[1, 2, 3, 6]", + "use_auxiliary_head": "use_auxiliary_head=True", + "auxiliary_loss_weight": "auxiliary_loss_weight=0.4", + "auxiliary_channels": "auxiliary_channels=256", + "auxiliary_num_convs": "auxiliary_num_convs=1", + "auxiliary_concat_input": "auxiliary_concat_input=False", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255", + "out_features": "out_features=None", + "out_indices": "out_indices=None", + "add_fpn": "add_fpn=False", + "reshape_hidden_states": "reshape_hidden_states=True" + }, + "BertModel": { + "act_dropout": [ + "" + ] + }, + "BertGenerationEncoder": { + "vocab_size": "vocab_size=50358", + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "intermediate_size": "intermediate_size=4096", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=1" + }, + "BertGenerationTokenizer": { + "vocab_file": "vocab_file", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "sep_token": "sep_token='<::::>'", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None" + }, + "BigBirdModel": { + "vocab_size": "vocab_size=50358", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu_new'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=4096", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "sep_token_id": "sep_token_id=66", + "attention_type": "attention_type='block_sparse'", + "use_bias": "use_bias=True", + "rescale_embeddings": "rescale_embeddings=False", + "block_size": "block_size=64", + "num_random_blocks": "num_random_blocks=3", + "classifier_dropout": "classifier_dropout=None" + }, + "BigBirdTokenizer": { + "vocab": "vocab: Union[str, dict, list, NoneType] = None", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "pad_token": "pad_token=''", + "sep_token": "sep_token='[SEP]'", + "mask_token": "mask_token='[MASK]'", + "cls_token": "cls_token='[CLS]'", + "add_prefix_space": "add_prefix_space=True" + }, + "BigBirdPegasusModel": { + "vocab_size": "vocab_size=96103", + "max_position_embeddings": "max_position_embeddings=4096", + "encoder_layers": "encoder_layers=16", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=16", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu_new'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "classifier_dropout": "classifier_dropout=0.0", + "scale_embedding": "scale_embedding=True", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=1", + "attention_type": "attention_type='block_sparse'", + "block_size": "block_size=64", + "num_random_blocks": "num_random_blocks=3", + "use_bias": "use_bias=False" + }, + "PegasusTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "pad_token": "pad_token=''", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "mask_token": "mask_token=''", + "mask_token_sent": "mask_token_sent=''", + "additional_special_tokens": "additional_special_tokens=None", + "offset": "offset=103" + }, + "BioGptModel": { + "vocab_size": "vocab_size=42384", + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "intermediate_size": "intermediate_size=4096", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=1024", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "scale_embedding": "scale_embedding=True", + "layerdrop": "layerdrop=0.0", + "activation_dropout": "activation_dropout=0.0", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "BioGptTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''" + }, + "BitModel": { + "num_channels": "num_channels=3", + "embedding_size": "embedding_size=64", + "hidden_sizes": "hidden_sizes=[256, 512, 1024, 2048]", + "depths": "depths=[3, 4, 6, 3]", + "layer_type": "layer_type='preactivation'", + "hidden_act": "hidden_act='relu'", + "global_padding": "global_padding=None", + "num_groups": "num_groups=32", + "drop_path_rate": "drop_path_rate=0.0", + "embedding_dynamic_padding": "embedding_dynamic_padding=False", + "output_stride": "output_stride=32", + "width_factor": "width_factor=1", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "BitNetModel": { + "vocab_size": "vocab_size: Optional[int] = 128256", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 6912", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 30", + "num_attention_heads": "num_attention_heads: Optional[int] = 20", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 5", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 128000", + "eos_token_id": "eos_token_id: Optional[int] = 128001", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[str] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "TokenizersBackend": { + "args": "*args" + }, + "BlenderbotModel": { + "vocab_size": "vocab_size=8008", + "max_position_embeddings": "max_position_embeddings=128", + "encoder_layers": "encoder_layers=2", + "encoder_ffn_dim": "encoder_ffn_dim=10240", + "encoder_attention_heads": "encoder_attention_heads=32", + "decoder_layers": "decoder_layers=24", + "decoder_ffn_dim": "decoder_ffn_dim=10240", + "decoder_attention_heads": "decoder_attention_heads=32", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=2560", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=1", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "encoder_no_repeat_ngram_size": "encoder_no_repeat_ngram_size=3", + "forced_eos_token_id": "forced_eos_token_id=2" + }, + "BlenderbotTokenizer": { + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "add_prefix_space": "add_prefix_space=True", + "vocab": "vocab=None", + "merges": "merges=None" + }, + "BlenderbotSmallModel": { + "vocab_size": "vocab_size=50265", + "max_position_embeddings": "max_position_embeddings=512", + "encoder_layers": "encoder_layers=8", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=8", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=512", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=1", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "forced_eos_token_id": "forced_eos_token_id=2" + }, + "BlenderbotSmallTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "bos_token": "bos_token='__start__'", + "eos_token": "eos_token='__end__'", + "unk_token": "unk_token='__unk__'", + "pad_token": "pad_token='__null__'" + }, + "BlipModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592", + "image_text_hidden_size": "image_text_hidden_size=256", + "label_smoothing": "label_smoothing=0.0" + }, + "Blip2Model": { + "vision_config": "vision_config=None", + "qformer_config": "qformer_config=None", + "text_config": "text_config=None", + "num_query_tokens": "num_query_tokens=32", + "image_text_hidden_size": "image_text_hidden_size=256", + "image_token_index": "image_token_index=None" + }, + "GPT2Tokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors: str = 'replace'", + "unk_token": "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "bos_token": "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "eos_token": "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "pad_token": "pad_token: Union[tokenizers.AddedToken, str, NoneType] = None", + "add_prefix_space": "add_prefix_space=False" + }, + "Blip2QFormerModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "cross_attention_frequency": "cross_attention_frequency=2", + "encoder_hidden_size": "encoder_hidden_size=1408", + "use_qformer_text_input": "use_qformer_text_input=False" + }, + "BloomModel": { + "vocab_size": "vocab_size=250880", + "hidden_size": "hidden_size=64", + "n_layer": "n_layer=2", + "n_head": "n_head=8", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "apply_residual_connection_post_layernorm": "apply_residual_connection_post_layernorm=False", + "hidden_dropout": "hidden_dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "pretraining_tp": "pretraining_tp=1", + "slow_but_exact": "slow_but_exact=False" + }, + "BltModel": { + "vocab_size": "vocab_size: Optional[int] = 260", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "patch_in_forward": "patch_in_forward: Optional[bool] = True", + "patch_size": "patch_size: Optional[int] = 4", + "patching_mode": "patching_mode: Optional[str] = 'entropy'", + "patching_threshold": "patching_threshold: Optional[float] = 1.335442066192627", + "patching_batch_size": "patching_batch_size: Optional[int] = 1", + "max_patch_length": "max_patch_length: Optional[int] = None", + "cross_attn_k": "cross_attn_k: Optional[int] = 2", + "encoder_hash_byte_group_size": "encoder_hash_byte_group_size: Optional[int] = None", + "encoder_hash_byte_group_vocab": "encoder_hash_byte_group_vocab: Optional[int] = 500002", + "encoder_hash_byte_group_nb_functions": "encoder_hash_byte_group_nb_functions: Optional[int] = 1", + "patcher_config": "patcher_config: Optional[dict] = None", + "encoder_config": "encoder_config: Optional[dict] = None", + "decoder_config": "decoder_config: Optional[dict] = None", + "global_config": "global_config: Optional[dict] = None", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "BridgeTowerModel": { + "share_cross_modal_transformer_layers": "share_cross_modal_transformer_layers=True", + "hidden_act": "hidden_act='gelu'", + "hidden_size": "hidden_size=768", + "initializer_factor": "initializer_factor=1", + "layer_norm_eps": "layer_norm_eps=1e-05", + "share_link_tower_layers": "share_link_tower_layers=False", + "link_tower_type": "link_tower_type='add'", + "num_attention_heads": "num_attention_heads=12", + "num_hidden_layers": "num_hidden_layers=6", + "tie_word_embeddings": "tie_word_embeddings=False", + "init_layernorm_from_vision_encoder": "init_layernorm_from_vision_encoder=False", + "text_config": "text_config=None", + "vision_config": "vision_config=None" + }, + "BrosModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "dim_bbox": "dim_bbox=8", + "bbox_scale": "bbox_scale=100.0", + "n_relations": "n_relations=1", + "classifier_dropout_prob": "classifier_dropout_prob=0.1" + }, + "CamembertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "CamembertTokenizer": { + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "additional_special_tokens": "additional_special_tokens=None", + "add_prefix_space": "add_prefix_space=True", + "vocab_file": "vocab_file=None", + "vocab": "vocab: Union[str, dict, list, NoneType] = None" + }, + "CanineModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=16384", + "type_vocab_size": "type_vocab_size=16", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=57344", + "eos_token_id": "eos_token_id=57345", + "downsampling_rate": "downsampling_rate=4", + "upsampling_kernel_size": "upsampling_kernel_size=4", + "num_hash_functions": "num_hash_functions=8", + "num_hash_buckets": "num_hash_buckets=16384", + "local_transformer_stride": "local_transformer_stride=128" + }, + "CanineTokenizer": { + "bos_token": "bos_token='\\ue000'", + "eos_token": "eos_token='\\ue001'", + "sep_token": "sep_token='\\ue001'", + "cls_token": "cls_token='\\ue000'", + "pad_token": "pad_token='\\x00'", + "mask_token": "mask_token='\\ue003'", + "add_prefix_space": "add_prefix_space=False", + "model_max_length": "model_max_length=2048" + }, + "ChameleonModel": { + "vocab_size": "vocab_size: Optional[int] = 65536", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "hidden_act": "hidden_act: Optional[int] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[int] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "model_parallel_size": "model_parallel_size: Optional[int] = 1", + "swin_norm": "swin_norm: Optional[bool] = False", + "vq_config": "vq_config: Optional[dict] = None", + "vocabulary_map": "vocabulary_map: Optional[dict] = None", + "mlp_bias": "mlp_bias: Optional[bool] = False" + }, + "ChineseCLIPModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "ChineseCLIPVisionModel": { + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "projection_dim": "projection_dim=512", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "patch_size": "patch_size=32", + "hidden_act": "hidden_act='quick_gelu'", + "layer_norm_eps": "layer_norm_eps=1e-05", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "initializer_factor": "initializer_factor=1.0" + }, + "ClapModel": { + "text_config": "text_config=None", + "audio_config": "audio_config=None", + "logit_scale_init_value": "logit_scale_init_value=14.285714285714285", + "projection_dim": "projection_dim=512", + "projection_hidden_act": "projection_hidden_act='relu'", + "initializer_factor": "initializer_factor=1.0" + }, + "CLIPModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "CLIPTextModel": { + "vocab_size": "vocab_size=49408", + "hidden_size": "hidden_size=512", + "intermediate_size": "intermediate_size=2048", + "projection_dim": "projection_dim=512", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=8", + "max_position_embeddings": "max_position_embeddings=77", + "hidden_act": "hidden_act='quick_gelu'", + "layer_norm_eps": "layer_norm_eps=1e-05", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "initializer_factor": "initializer_factor=1.0", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=49406", + "eos_token_id": "eos_token_id=49407" + }, + "CLIPVisionModel": { + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "projection_dim": "projection_dim=512", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "patch_size": "patch_size=32", + "hidden_act": "hidden_act='quick_gelu'", + "layer_norm_eps": "layer_norm_eps=1e-05", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "initializer_factor": "initializer_factor=1.0" + }, + "CLIPSegModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592", + "extract_layers": "extract_layers=[3, 6, 9]", + "reduce_dim": "reduce_dim=64", + "decoder_num_attention_heads": "decoder_num_attention_heads=4", + "decoder_attention_dropout": "decoder_attention_dropout=0.0", + "decoder_hidden_act": "decoder_hidden_act='quick_gelu'", + "decoder_intermediate_size": "decoder_intermediate_size=2048", + "conditional_layer": "conditional_layer=0", + "use_complex_transposed_convolution": "use_complex_transposed_convolution=False" + }, + "ClvpModelForConditionalGeneration": { + "text_config": "text_config=None", + "speech_config": "speech_config=None", + "decoder_config": "decoder_config=None", + "projection_dim": "projection_dim=768", + "logit_scale_init_value": "logit_scale_init_value=2.6592", + "initializer_factor": "initializer_factor=1.0" + }, + "ClvpTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "errors": "errors='replace'", + "unk_token": "unk_token='[UNK]'", + "bos_token": "bos_token='<|endoftext|>'", + "eos_token": "eos_token='[STOP]'", + "pad_token": "pad_token='[STOP]'", + "add_prefix_space": "add_prefix_space=False" + }, + "LlamaModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "pretraining_tp": "pretraining_tp: Optional[int] = 1", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "head_dim": "head_dim: Optional[int] = None" + }, + "CodeGenModel": { + "vocab_size": "vocab_size=50400", + "n_positions": "n_positions=2048", + "n_ctx": "n_ctx=2048", + "n_embd": "n_embd=4096", + "n_layer": "n_layer=28", + "n_head": "n_head=16", + "rotary_dim": "rotary_dim=64", + "n_inner": "n_inner=None", + "activation_function": "activation_function='gelu_new'", + "resid_pdrop": "resid_pdrop=0.0", + "embd_pdrop": "embd_pdrop=0.0", + "attn_pdrop": "attn_pdrop=0.0", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "CohereModel": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 8192", + "intermediate_size": "intermediate_size: Optional[int] = 22528", + "logit_scale": "logit_scale: Optional[float] = 0.0625", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 40", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 5", + "eos_token_id": "eos_token_id: Optional[int] = 255001", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "use_qk_norm": "use_qk_norm: Optional[bool] = False" + }, + "Cohere2Model": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 8192", + "intermediate_size": "intermediate_size: Optional[int] = 22528", + "logit_scale": "logit_scale: Optional[float] = 0.0625", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 40", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 5", + "eos_token_id": "eos_token_id: Optional[int] = 255001", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "sliding_window": "sliding_window: Optional[int] = 4096", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Cohere2VisionModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "downsample_factor": "downsample_factor=2", + "image_token_id": "image_token_id=255036", + "alignment_intermediate_size": "alignment_intermediate_size=36864" + }, + "ConditionalDetrModel": { + "use_timm_backbone": "use_timm_backbone=True", + "backbone_config": "backbone_config=None", + "num_channels": "num_channels=3", + "num_queries": "num_queries=300", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "init_xavier_std": "init_xavier_std=1.0", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "backbone": "backbone='resnet50'", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "backbone_kwargs": "backbone_kwargs=None", + "dilation": "dilation=False", + "class_cost": "class_cost=2", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "mask_loss_coefficient": "mask_loss_coefficient=1", + "dice_loss_coefficient": "dice_loss_coefficient=1", + "cls_loss_coefficient": "cls_loss_coefficient=2", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "focal_alpha": "focal_alpha=0.25" + }, + "ConvBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "embedding_size": "embedding_size=768", + "head_ratio": "head_ratio=2", + "conv_kernel_size": "conv_kernel_size=9", + "num_groups": "num_groups=1", + "classifier_dropout": "classifier_dropout=None" + }, + "ConvNextModel": { + "num_channels": "num_channels=3", + "patch_size": "patch_size=4", + "num_stages": "num_stages=4", + "hidden_sizes": "hidden_sizes=None", + "depths": "depths=None", + "hidden_act": "hidden_act='gelu'", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "layer_scale_init_value": "layer_scale_init_value=1e-06", + "drop_path_rate": "drop_path_rate=0.0", + "image_size": "image_size=224", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "ConvNextV2Model": { + "num_channels": "num_channels=3", + "patch_size": "patch_size=4", + "num_stages": "num_stages=4", + "hidden_sizes": "hidden_sizes=None", + "depths": "depths=None", + "hidden_act": "hidden_act='gelu'", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "drop_path_rate": "drop_path_rate=0.0", + "image_size": "image_size=224", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "CpmAntModel": { + "vocab_size": "vocab_size: int = 30720", + "hidden_size": "hidden_size: int = 4096", + "num_attention_heads": "num_attention_heads: int = 32", + "dim_head": "dim_head: int = 128", + "dim_ff": "dim_ff: int = 10240", + "num_hidden_layers": "num_hidden_layers: int = 48", + "dropout_p": "dropout_p: int = 0.0", + "position_bias_num_buckets": "position_bias_num_buckets: int = 512", + "position_bias_max_distance": "position_bias_max_distance: int = 2048", + "eps": "eps: int = 1e-06", + "init_std": "init_std: float = 1.0", + "prompt_types": "prompt_types: int = 32", + "prompt_length": "prompt_length: int = 32", + "segment_types": "segment_types: int = 32" + }, + "CpmAntTokenizer": { + "vocab_file": "vocab_file", + "bod_token": "bod_token=''", + "eod_token": "eod_token=''", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "pad_token": "pad_token=''", + "unk_token": "unk_token=''", + "line_token": "line_token=''", + "space_token": "space_token=''", + "padding_side": "padding_side='left'" + }, + "CsmForConditionalGeneration": { + "num_codebooks": "num_codebooks: Optional[int] = 32", + "vocab_size": "vocab_size: Optional[int] = 2051", + "text_vocab_size": "text_vocab_size: Optional[int] = 128256", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 8192", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 16", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 128002", + "codebook_pad_token_id": "codebook_pad_token_id: Optional[int] = 2050", + "codebook_eos_token_id": "codebook_eos_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 128000", + "eos_token_id": "eos_token_id: Optional[int] = None", + "audio_token_id": "audio_token_id: Optional[int] = 128002", + "audio_eos_token_id": "audio_eos_token_id: Optional[int] = 128003", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "head_dim": "head_dim: Optional[int] = None", + "tie_codebooks_embeddings": "tie_codebooks_embeddings: Optional[bool] = True", + "depth_decoder_config": "depth_decoder_config: Optional[dict] = None", + "codec_config": "codec_config: Optional[dict] = None" + }, + "CTRLModel": { + "vocab_size": "vocab_size=246534", + "n_positions": "n_positions=256", + "n_embd": "n_embd=1280", + "dff": "dff=8192", + "n_layer": "n_layer=48", + "n_head": "n_head=16", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_range": "initializer_range=0.02" + }, + "CTRLTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "unk_token": "unk_token=''" + }, + "CvtModel": { + "num_channels": "num_channels=3", + "patch_sizes": "patch_sizes=[7, 3, 3]", + "patch_stride": "patch_stride=[4, 2, 2]", + "patch_padding": "patch_padding=[2, 1, 1]", + "embed_dim": "embed_dim=[64, 192, 384]", + "num_heads": "num_heads=[1, 3, 6]", + "depth": "depth=[1, 2, 10]", + "mlp_ratio": "mlp_ratio=[4.0, 4.0, 4.0]", + "attention_drop_rate": "attention_drop_rate=[0.0, 0.0, 0.0]", + "drop_rate": "drop_rate=[0.0, 0.0, 0.0]", + "drop_path_rate": "drop_path_rate=[0.0, 0.0, 0.1]", + "qkv_bias": "qkv_bias=[True, True, True]", + "cls_token": "cls_token=[False, False, True]", + "qkv_projection_method": "qkv_projection_method=['dw_bn', 'dw_bn', 'dw_bn']", + "kernel_qkv": "kernel_qkv=[3, 3, 3]", + "padding_kv": "padding_kv=[1, 1, 1]", + "stride_kv": "stride_kv=[2, 2, 2]", + "padding_q": "padding_q=[1, 1, 1]", + "stride_q": "stride_q=[1, 1, 1]", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12" + }, + "CwmModel": { + "n_head": [ + "" + ] + }, + "DFineModel": { + "initializer_range": "initializer_range=0.01", + "initializer_bias_prior_prob": "initializer_bias_prior_prob=None", + "layer_norm_eps": "layer_norm_eps=1e-05", + "batch_norm_eps": "batch_norm_eps=1e-05", + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "freeze_backbone_batch_norms": "freeze_backbone_batch_norms=True", + "backbone_kwargs": "backbone_kwargs=None", + "encoder_hidden_dim": "encoder_hidden_dim=256", + "encoder_in_channels": "encoder_in_channels=[512, 1024, 2048]", + "feat_strides": "feat_strides=[8, 16, 32]", + "encoder_layers": "encoder_layers=1", + "encoder_ffn_dim": "encoder_ffn_dim=1024", + "encoder_attention_heads": "encoder_attention_heads=8", + "dropout": "dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "encode_proj_layers": "encode_proj_layers=[2]", + "positional_encoding_temperature": "positional_encoding_temperature=10000", + "encoder_activation_function": "encoder_activation_function='gelu'", + "activation_function": "activation_function='silu'", + "eval_size": "eval_size=None", + "normalize_before": "normalize_before=False", + "hidden_expansion": "hidden_expansion=1.0", + "d_model": "d_model=256", + "num_queries": "num_queries=300", + "decoder_in_channels": "decoder_in_channels=[256, 256, 256]", + "decoder_ffn_dim": "decoder_ffn_dim=1024", + "num_feature_levels": "num_feature_levels=3", + "decoder_n_points": "decoder_n_points=4", + "decoder_layers": "decoder_layers=6", + "decoder_attention_heads": "decoder_attention_heads=8", + "decoder_activation_function": "decoder_activation_function='relu'", + "attention_dropout": "attention_dropout=0.0", + "num_denoising": "num_denoising=100", + "label_noise_ratio": "label_noise_ratio=0.5", + "box_noise_scale": "box_noise_scale=1.0", + "learn_initial_query": "learn_initial_query=False", + "anchor_image_size": "anchor_image_size=None", + "with_box_refine": "with_box_refine=True", + "is_encoder_decoder": "is_encoder_decoder=True", + "matcher_alpha": "matcher_alpha=0.25", + "matcher_gamma": "matcher_gamma=2.0", + "matcher_class_cost": "matcher_class_cost=2.0", + "matcher_bbox_cost": "matcher_bbox_cost=5.0", + "matcher_giou_cost": "matcher_giou_cost=2.0", + "use_focal_loss": "use_focal_loss=True", + "auxiliary_loss": "auxiliary_loss=True", + "focal_loss_alpha": "focal_loss_alpha=0.75", + "focal_loss_gamma": "focal_loss_gamma=2.0", + "weight_loss_vfl": "weight_loss_vfl=1.0", + "weight_loss_bbox": "weight_loss_bbox=5.0", + "weight_loss_giou": "weight_loss_giou=2.0", + "weight_loss_fgl": "weight_loss_fgl=0.15", + "weight_loss_ddf": "weight_loss_ddf=1.5", + "eos_coefficient": "eos_coefficient=0.0001", + "eval_idx": "eval_idx=-1", + "layer_scale": "layer_scale=1", + "max_num_bins": "max_num_bins=32", + "reg_scale": "reg_scale=4.0", + "depth_mult": "depth_mult=1.0", + "top_prob_values": "top_prob_values=4", + "lqe_hidden_dim": "lqe_hidden_dim=64", + "lqe_layers": "lqe_layers=2", + "decoder_offset_scale": "decoder_offset_scale=0.5", + "decoder_method": "decoder_method='default'", + "up": "up=0.5" + }, + "DabDetrModel": { + "use_timm_backbone": "use_timm_backbone=True", + "backbone_config": "backbone_config=None", + "backbone": "backbone='resnet50'", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "backbone_kwargs": "backbone_kwargs=None", + "num_queries": "num_queries=300", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='prelu'", + "hidden_size": "hidden_size=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "init_xavier_std": "init_xavier_std=1.0", + "auxiliary_loss": "auxiliary_loss=False", + "dilation": "dilation=False", + "class_cost": "class_cost=2", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "cls_loss_coefficient": "cls_loss_coefficient=2", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "focal_alpha": "focal_alpha=0.25", + "temperature_height": "temperature_height=20", + "temperature_width": "temperature_width=20", + "query_dim": "query_dim=4", + "random_refpoints_xy": "random_refpoints_xy=False", + "keep_query_pos": "keep_query_pos=False", + "num_patterns": "num_patterns=0", + "normalize_before": "normalize_before=False", + "sine_position_embedding_scale": "sine_position_embedding_scale=None", + "initializer_bias_prior_prob": "initializer_bias_prior_prob=None" + }, + "DacModel": { + "encoder_hidden_size": "encoder_hidden_size=64", + "downsampling_ratios": "downsampling_ratios=[2, 4, 8, 8]", + "decoder_hidden_size": "decoder_hidden_size=1536", + "n_codebooks": "n_codebooks=9", + "codebook_size": "codebook_size=1024", + "codebook_dim": "codebook_dim=8", + "quantizer_dropout": "quantizer_dropout=0", + "commitment_loss_weight": "commitment_loss_weight=0.25", + "codebook_loss_weight": "codebook_loss_weight=1.0", + "sampling_rate": "sampling_rate=16000" + }, + "Data2VecAudioModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "conv_pos_kernel_size": "conv_pos_kernel_size=19", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=5", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "ctc_loss_reduction": "ctc_loss_reduction='sum'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "add_adapter": "add_adapter=False", + "adapter_kernel_size": "adapter_kernel_size=3", + "adapter_stride": "adapter_stride=2", + "num_adapter_layers": "num_adapter_layers=3", + "output_hidden_size": "output_hidden_size=None" + }, + "Wav2Vec2CTCTokenizer": { + "vocab_file": "vocab_file", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "word_delimiter_token": "word_delimiter_token='|'", + "replace_word_delimiter_char": "replace_word_delimiter_char=' '", + "do_lower_case": "do_lower_case=False", + "target_lang": "target_lang=None" + }, + "Data2VecTextModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "Data2VecVisionModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "use_mask_token": "use_mask_token=False", + "use_absolute_position_embeddings": "use_absolute_position_embeddings=False", + "use_relative_position_bias": "use_relative_position_bias=False", + "use_shared_relative_position_bias": "use_shared_relative_position_bias=False", + "layer_scale_init_value": "layer_scale_init_value=0.1", + "drop_path_rate": "drop_path_rate=0.1", + "use_mean_pooling": "use_mean_pooling=True", + "out_indices": "out_indices=[3, 5, 7, 11]", + "pool_scales": "pool_scales=[1, 2, 3, 6]", + "use_auxiliary_head": "use_auxiliary_head=True", + "auxiliary_loss_weight": "auxiliary_loss_weight=0.4", + "auxiliary_channels": "auxiliary_channels=256", + "auxiliary_num_convs": "auxiliary_num_convs=1", + "auxiliary_concat_input": "auxiliary_concat_input=False", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255" + }, + "DbrxModel": { + "d_model": "d_model: Optional[int] = 2048", + "n_heads": "n_heads: Optional[int] = 16", + "n_layers": "n_layers: Optional[int] = 24", + "max_seq_len": "max_seq_len: Optional[int] = 2048", + "vocab_size": "vocab_size: Optional[int] = 32000", + "resid_pdrop": "resid_pdrop: Optional[float] = 0.0", + "emb_pdrop": "emb_pdrop: Optional[float] = 0.0", + "attn_config": "attn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxAttentionConfig] = None", + "ffn_config": "ffn_config: Optional[transformers.models.dbrx.configuration_dbrx.DbrxFFNConfig] = None", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "DebertaModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-07", + "relative_attention": "relative_attention=False", + "max_relative_positions": "max_relative_positions=-1", + "pad_token_id": "pad_token_id=0", + "position_biased_input": "position_biased_input=True", + "pos_att_type": "pos_att_type=None", + "pooler_dropout": "pooler_dropout=0", + "pooler_hidden_act": "pooler_hidden_act='gelu'", + "legacy": "legacy=True" + }, + "DebertaTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors='replace'", + "bos_token": "bos_token='[CLS]'", + "eos_token": "eos_token='[SEP]'", + "sep_token": "sep_token='[SEP]'", + "cls_token": "cls_token='[CLS]'", + "unk_token": "unk_token='[UNK]'", + "pad_token": "pad_token='[PAD]'", + "mask_token": "mask_token='[MASK]'", + "add_prefix_space": "add_prefix_space=False" + }, + "DebertaV2Model": { + "vocab_size": "vocab_size=128100", + "hidden_size": "hidden_size=1536", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=24", + "intermediate_size": "intermediate_size=6144", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-07", + "relative_attention": "relative_attention=False", + "max_relative_positions": "max_relative_positions=-1", + "pad_token_id": "pad_token_id=0", + "position_biased_input": "position_biased_input=True", + "pos_att_type": "pos_att_type=None", + "pooler_dropout": "pooler_dropout=0", + "pooler_hidden_act": "pooler_hidden_act='gelu'", + "legacy": "legacy=True" + }, + "DebertaV2Tokenizer": { + "vocab": "vocab: Union[str, dict, list, NoneType] = None", + "do_lower_case": "do_lower_case=False", + "split_by_punct": "split_by_punct=False", + "bos_token": "bos_token='[CLS]'", + "eos_token": "eos_token='[SEP]'", + "unk_token": "unk_token='[UNK]'", + "sep_token": "sep_token='[SEP]'", + "pad_token": "pad_token='[PAD]'", + "cls_token": "cls_token='[CLS]'", + "mask_token": "mask_token='[MASK]'", + "add_prefix_space": "add_prefix_space=True", + "unk_id": "unk_id=1" + }, + "DecisionTransformerModel": { + "state_dim": "state_dim=17", + "act_dim": "act_dim=4", + "hidden_size": "hidden_size=128", + "max_ep_len": "max_ep_len=4096", + "action_tanh": "action_tanh=True", + "vocab_size": "vocab_size=1", + "n_positions": "n_positions=1024", + "n_layer": "n_layer=3", + "n_head": "n_head=1", + "n_inner": "n_inner=None", + "activation_function": "activation_function='relu'", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "attn_pdrop": "attn_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "scale_attn_weights": "scale_attn_weights=True", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "scale_attn_by_inverse_layer_idx": "scale_attn_by_inverse_layer_idx=False", + "reorder_and_upcast_attn": "reorder_and_upcast_attn=False" + }, + "DeepseekV2Model": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "first_k_dense_replace": "first_k_dense_replace: Optional[int] = 0", + "kv_lora_rank": "kv_lora_rank: Optional[int] = 512", + "q_lora_rank": "q_lora_rank: Optional[int] = 1536", + "n_group": "n_group: Optional[int] = None", + "n_routed_experts": "n_routed_experts: Optional[int] = 64", + "n_shared_experts": "n_shared_experts: Optional[int] = 2", + "qk_nope_head_dim": "qk_nope_head_dim: Optional[int] = 128", + "qk_rope_head_dim": "qk_rope_head_dim: Optional[int] = 64", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 1.0", + "topk_group": "topk_group: Optional[int] = None", + "topk_method": "topk_method: Optional[str] = 'greedy'", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False", + "v_head_dim": "v_head_dim: Optional[int] = 128", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = None", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1407" + }, + "DeepseekV3Model": { + "vocab_size": "vocab_size: Optional[int] = 129280", + "hidden_size": "hidden_size: Optional[int] = 7168", + "intermediate_size": "intermediate_size: Optional[int] = 18432", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 2048", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 61", + "num_attention_heads": "num_attention_heads: Optional[int] = 128", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 128", + "n_shared_experts": "n_shared_experts: Optional[int] = 1", + "n_routed_experts": "n_routed_experts: Optional[int] = 256", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 2.5", + "kv_lora_rank": "kv_lora_rank: Optional[int] = 512", + "q_lora_rank": "q_lora_rank: Optional[int] = 1536", + "qk_rope_head_dim": "qk_rope_head_dim: Optional[int] = 64", + "v_head_dim": "v_head_dim: Optional[int] = 128", + "qk_nope_head_dim": "qk_nope_head_dim: Optional[int] = 128", + "n_group": "n_group: Optional[int] = 8", + "topk_group": "topk_group: Optional[int] = 4", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 8", + "first_k_dense_replace": "first_k_dense_replace: Optional[int] = 3", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = True", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "pretraining_tp": "pretraining_tp: Optional[int] = 1", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "rope_interleave": "rope_interleave: Optional[bool] = True", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "DeepseekVLModel": { + "text_config": "text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig] = None", + "vision_config": "vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig] = None", + "image_token_id": "image_token_id: int = 100015" + }, + "DeepseekVLHybridModel": { + "text_config": "text_config: Optional[transformers.models.auto.configuration_auto.AutoConfig] = None", + "vision_config": "vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig] = None", + "high_res_vision_config": "high_res_vision_config: Optional[transformers.models.auto.configuration_auto.AutoConfig] = None", + "image_token_id": "image_token_id: int = 100015" + }, + "DeformableDetrModel": { + "use_timm_backbone": "use_timm_backbone=True", + "backbone_config": "backbone_config=None", + "num_channels": "num_channels=3", + "num_queries": "num_queries=300", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=1024", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=1024", + "decoder_attention_heads": "decoder_attention_heads=8", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "init_xavier_std": "init_xavier_std=1.0", + "return_intermediate": "return_intermediate=True", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "backbone": "backbone='resnet50'", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "backbone_kwargs": "backbone_kwargs=None", + "dilation": "dilation=False", + "num_feature_levels": "num_feature_levels=4", + "encoder_n_points": "encoder_n_points=4", + "decoder_n_points": "decoder_n_points=4", + "two_stage": "two_stage=False", + "two_stage_num_proposals": "two_stage_num_proposals=300", + "with_box_refine": "with_box_refine=False", + "class_cost": "class_cost=1", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "mask_loss_coefficient": "mask_loss_coefficient=1", + "dice_loss_coefficient": "dice_loss_coefficient=1", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "eos_coefficient": "eos_coefficient=0.1", + "focal_alpha": "focal_alpha=0.25", + "disable_custom_kernels": "disable_custom_kernels=False" + }, + "DeiTModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "encoder_stride": "encoder_stride=16", + "pooler_output_size": "pooler_output_size=None", + "pooler_act": "pooler_act='tanh'" + }, + "DepthProModel": { + "fusion_hidden_size": "fusion_hidden_size=256", + "patch_size": "patch_size=384", + "initializer_range": "initializer_range=0.02", + "intermediate_hook_ids": "intermediate_hook_ids=[11, 5]", + "intermediate_feature_dims": "intermediate_feature_dims=[256, 256]", + "scaled_images_ratios": "scaled_images_ratios=[0.25, 0.5, 1]", + "scaled_images_overlap_ratios": "scaled_images_overlap_ratios=[0.0, 0.5, 0.25]", + "scaled_images_feature_dims": "scaled_images_feature_dims=[1024, 1024, 512]", + "merge_padding_value": "merge_padding_value=3", + "use_batch_norm_in_fusion_residual": "use_batch_norm_in_fusion_residual=False", + "use_bias_in_fusion_residual": "use_bias_in_fusion_residual=True", + "use_fov_model": "use_fov_model=False", + "num_fov_head_layers": "num_fov_head_layers=2", + "image_model_config": "image_model_config=None", + "patch_model_config": "patch_model_config=None", + "fov_model_config": "fov_model_config=None" + }, + "DetrModel": { + "use_timm_backbone": "use_timm_backbone=True", + "backbone_config": "backbone_config=None", + "num_channels": "num_channels=3", + "num_queries": "num_queries=100", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "init_xavier_std": "init_xavier_std=1.0", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "backbone": "backbone='resnet50'", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "backbone_kwargs": "backbone_kwargs=None", + "dilation": "dilation=False", + "class_cost": "class_cost=1", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "mask_loss_coefficient": "mask_loss_coefficient=1", + "dice_loss_coefficient": "dice_loss_coefficient=1", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "eos_coefficient": "eos_coefficient=0.1" + }, + "DiaModel": { + "encoder_config": "encoder_config: Optional[transformers.models.dia.configuration_dia.DiaEncoderConfig] = None", + "decoder_config": "decoder_config: Optional[transformers.models.dia.configuration_dia.DiaDecoderConfig] = None", + "norm_eps": "norm_eps: float = 1e-05", + "is_encoder_decoder": "is_encoder_decoder: bool = True", + "pad_token_id": "pad_token_id: int = 1025", + "eos_token_id": "eos_token_id: int = 1024", + "bos_token_id": "bos_token_id: int = 1026", + "delay_pattern": "delay_pattern: Optional[list[int]] = None", + "initializer_range": "initializer_range: float = 0.02" + }, + "DiaTokenizer": { + "pad_token": "pad_token: Optional[str] = ''", + "unk_token": "unk_token: Optional[str] = ''", + "max_length": "max_length: Optional[int] = 1024", + "offset": "offset: int = 0" + }, + "DiffLlamaModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 8192", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 16", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "lambda_std_dev": "lambda_std_dev: Optional[float] = 0.1", + "head_dim": "head_dim: Optional[int] = None" + }, + "DinatModel": { + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=64", + "depths": "depths=[3, 4, 6, 5]", + "num_heads": "num_heads=[2, 4, 8, 16]", + "kernel_size": "kernel_size=7", + "dilations": "dilations=[[1, 8, 1], [1, 4, 1, 4], [1, 2, 1, 2, 1, 2], [1, 1, 1, 1, 1]]", + "mlp_ratio": "mlp_ratio=3.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "layer_scale_init_value": "layer_scale_init_value=0.0", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "Dinov2Model": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "mlp_ratio": "mlp_ratio=4", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=224", + "patch_size": "patch_size=14", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "layerscale_value": "layerscale_value=1.0", + "drop_path_rate": "drop_path_rate=0.0", + "use_swiglu_ffn": "use_swiglu_ffn=False", + "out_features": "out_features=None", + "out_indices": "out_indices=None", + "apply_layernorm": "apply_layernorm=True", + "reshape_hidden_states": "reshape_hidden_states=True", + "use_mask_token": "use_mask_token=True" + }, + "Dinov2WithRegistersModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "mlp_ratio": "mlp_ratio=4", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "layerscale_value": "layerscale_value=1.0", + "drop_path_rate": "drop_path_rate=0.0", + "use_swiglu_ffn": "use_swiglu_ffn=False", + "num_register_tokens": "num_register_tokens=4", + "out_features": "out_features=None", + "out_indices": "out_indices=None", + "apply_layernorm": "apply_layernorm=True", + "reshape_hidden_states": "reshape_hidden_states=True" + }, + "DINOv3ConvNextModel": { + "num_channels": "num_channels: int = 3", + "hidden_sizes": "hidden_sizes: Optional[list[int]] = None", + "depths": "depths: Optional[list[int]] = None", + "hidden_act": "hidden_act: str = 'gelu'", + "initializer_range": "initializer_range: float = 0.02", + "layer_norm_eps": "layer_norm_eps: float = 1e-06", + "layer_scale_init_value": "layer_scale_init_value: float = 1e-06", + "drop_path_rate": "drop_path_rate: float = 0.0", + "image_size": "image_size: int = 224", + "out_features": "out_features: Optional[list[str]] = None", + "out_indices": "out_indices: Optional[list[int]] = None" + }, + "DINOv3ViTModel": { + "patch_size": "patch_size: int = 16", + "hidden_size": "hidden_size: int = 384", + "intermediate_size": "intermediate_size: int = 1536", + "num_hidden_layers": "num_hidden_layers: int = 12", + "num_attention_heads": "num_attention_heads: int = 6", + "hidden_act": "hidden_act: str = 'gelu'", + "attention_dropout": "attention_dropout: float = 0.0", + "initializer_range": "initializer_range: float = 0.02", + "layer_norm_eps": "layer_norm_eps: float = 1e-05", + "rope_theta": "rope_theta: float = 100.0", + "image_size": "image_size: int = 224", + "num_channels": "num_channels: int = 3", + "query_bias": "query_bias: bool = True", + "key_bias": "key_bias: bool = False", + "value_bias": "value_bias: bool = True", + "proj_bias": "proj_bias: bool = True", + "mlp_bias": "mlp_bias: bool = True", + "layerscale_value": "layerscale_value: float = 1.0", + "drop_path_rate": "drop_path_rate: float = 0.0", + "use_gated_mlp": "use_gated_mlp: bool = False", + "num_register_tokens": "num_register_tokens: int = 0", + "pos_embed_shift": "pos_embed_shift: Optional[float] = None", + "pos_embed_jitter": "pos_embed_jitter: Optional[float] = None", + "pos_embed_rescale": "pos_embed_rescale: Optional[float] = 2.0", + "out_features": "out_features: Optional[list[str]] = None", + "out_indices": "out_indices: Optional[list[int]] = None", + "apply_layernorm": "apply_layernorm: bool = True", + "reshape_hidden_states": "reshape_hidden_states: bool = True" + }, + "DistilBertModel": { + "vocab_size": "vocab_size=30522", + "max_position_embeddings": "max_position_embeddings=512", + "sinusoidal_pos_embds": "sinusoidal_pos_embds=False", + "n_layers": "n_layers=6", + "n_heads": "n_heads=12", + "dim": "dim=768", + "hidden_dim": "hidden_dim=3072", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation": "activation='gelu'", + "initializer_range": "initializer_range=0.02", + "qa_dropout": "qa_dropout=0.1", + "seq_classif_dropout": "seq_classif_dropout=0.2", + "pad_token_id": "pad_token_id=0" + }, + "DogeModel": { + "vocab_size": "vocab_size: Optional[int] = 32768", + "hidden_size": "hidden_size: Optional[int] = 1024", + "intermediate_size": "intermediate_size: Optional[int] = 2048", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "num_attention_heads": "num_attention_heads: Optional[int] = 8", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = None", + "keep_window_size": "keep_window_size: Optional[int] = 2048", + "is_moe": "is_moe: Optional[bool] = False", + "num_experts": "num_experts: Optional[int] = 16384", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 64", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001" + }, + "DonutSwinModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=96", + "depths": "depths=[2, 2, 6, 2]", + "num_heads": "num_heads=[3, 6, 12, 24]", + "window_size": "window_size=7", + "mlp_ratio": "mlp_ratio=4.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "use_absolute_embeddings": "use_absolute_embeddings=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05" + }, + "Dots1Model": { + "vocab_size": "vocab_size: Optional[int] = 152064", + "hidden_size": "hidden_size: Optional[int] = 4608", + "intermediate_size": "intermediate_size: Optional[int] = 10944", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 62", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "n_shared_experts": "n_shared_experts: Optional[int] = None", + "n_routed_experts": "n_routed_experts: Optional[int] = None", + "n_group": "n_group: Optional[int] = 1", + "topk_group": "topk_group: Optional[int] = 1", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = None", + "first_k_dense_replace": "first_k_dense_replace: Optional[int] = 0", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 1.0", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 62", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "DPRQuestionEncoder": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "projection_dim": "projection_dim: int = 0" + }, + "DPRQuestionEncoderTokenizerFast": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case: bool = False", + "unk_token": "unk_token: str = '[UNK]'", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = '[PAD]'", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars: bool = True", + "strip_accents": "strip_accents: Optional[bool] = None" + }, + "DPTModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=384", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "is_hybrid": "is_hybrid=False", + "qkv_bias": "qkv_bias=True", + "backbone_out_indices": "backbone_out_indices=[2, 5, 8, 11]", + "readout_type": "readout_type='project'", + "reassemble_factors": "reassemble_factors=[4, 2, 1, 0.5]", + "neck_hidden_sizes": "neck_hidden_sizes=[96, 192, 384, 768]", + "fusion_hidden_size": "fusion_hidden_size=256", + "head_in_index": "head_in_index=-1", + "use_batch_norm_in_fusion_residual": "use_batch_norm_in_fusion_residual=False", + "use_bias_in_fusion_residual": "use_bias_in_fusion_residual=None", + "add_projection": "add_projection=False", + "use_auxiliary_head": "use_auxiliary_head=True", + "auxiliary_loss_weight": "auxiliary_loss_weight=0.4", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255", + "semantic_classifier_dropout": "semantic_classifier_dropout=0.1", + "backbone_featmap_shape": "backbone_featmap_shape=[1, 1024, 24, 24]", + "neck_ignore_stages": "neck_ignore_stages=[0, 1]", + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "backbone_kwargs": "backbone_kwargs=None", + "pooler_output_size": "pooler_output_size=None", + "pooler_act": "pooler_act='tanh'" + }, + "EdgeTamModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "EdgeTamVideoModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02", + "num_maskmem": "num_maskmem=7", + "image_size": "image_size=1024", + "sigmoid_scale_for_mem_enc": "sigmoid_scale_for_mem_enc=20.0", + "sigmoid_bias_for_mem_enc": "sigmoid_bias_for_mem_enc=-10.0", + "enable_occlusion_spatial_embedding": "enable_occlusion_spatial_embedding=True", + "multimask_output_in_sam": "multimask_output_in_sam=True", + "multimask_min_pt_num": "multimask_min_pt_num=0", + "multimask_max_pt_num": "multimask_max_pt_num=1", + "multimask_output_for_tracking": "multimask_output_for_tracking=True", + "max_object_pointers_in_encoder": "max_object_pointers_in_encoder=16", + "max_cond_frame_num": "max_cond_frame_num=-1", + "enable_temporal_pos_encoding_for_object_pointers": "enable_temporal_pos_encoding_for_object_pointers=True", + "memory_attention_hidden_size": "memory_attention_hidden_size=256", + "memory_attention_num_layers": "memory_attention_num_layers=2", + "memory_attention_num_attention_heads": "memory_attention_num_attention_heads=1", + "memory_attention_downsample_rate": "memory_attention_downsample_rate=1", + "memory_attention_mlp_hidden_size": "memory_attention_mlp_hidden_size=2048", + "memory_attention_mlp_hidden_act": "memory_attention_mlp_hidden_act='relu'", + "memory_attention_dropout": "memory_attention_dropout=0.1", + "memory_attention_rope_theta": "memory_attention_rope_theta=10000", + "memory_attention_rope_feat_sizes": "memory_attention_rope_feat_sizes=None", + "memory_attention_rope_k_sizes": "memory_attention_rope_k_sizes=None", + "memory_attention_rope_dropout": "memory_attention_rope_dropout=0.1", + "perceiver_resampler_num_latents": "perceiver_resampler_num_latents=256", + "perceiver_resampler_num_latents_2d": "perceiver_resampler_num_latents_2d=256", + "perceiver_resampler_hidden_size": "perceiver_resampler_hidden_size=64", + "perceiver_resampler_mlp_intermediate_size": "perceiver_resampler_mlp_intermediate_size=256", + "perceiver_resampler_num_attention_heads": "perceiver_resampler_num_attention_heads=1", + "perceiver_resampler_attention_head_dim": "perceiver_resampler_attention_head_dim=64", + "perceiver_resampler_num_layers": "perceiver_resampler_num_layers=2", + "perceiver_resampler_hidden_dropout": "perceiver_resampler_hidden_dropout=0.0", + "perceiver_resampler_attention_dropout": "perceiver_resampler_attention_dropout=0.0", + "memory_encoder_hidden_size": "memory_encoder_hidden_size=256", + "memory_encoder_output_channels": "memory_encoder_output_channels=64", + "mask_downsampler_embed_dim": "mask_downsampler_embed_dim=256", + "memory_fuser_intermediate_dim": "memory_fuser_intermediate_dim=1024", + "mask_downsampler_kernel_size": "mask_downsampler_kernel_size=3", + "mask_downsampler_stride": "mask_downsampler_stride=2", + "mask_downsampler_padding": "mask_downsampler_padding=1", + "mask_downsampler_total_stride": "mask_downsampler_total_stride=16", + "mask_downsampler_hidden_act": "mask_downsampler_hidden_act='gelu'", + "memory_fuser_num_layers": "memory_fuser_num_layers=2", + "memory_fuser_embed_dim": "memory_fuser_embed_dim=256", + "memory_fuser_kernel_size": "memory_fuser_kernel_size=7", + "memory_fuser_padding": "memory_fuser_padding=3", + "memory_fuser_layer_scale_init_value": "memory_fuser_layer_scale_init_value=1e-06", + "memory_fuser_hidden_act": "memory_fuser_hidden_act='gelu'" + }, + "EdgeTamVisionModel": { + "backbone_config": "backbone_config=None", + "backbone_channel_list": "backbone_channel_list=None", + "backbone_feature_sizes": "backbone_feature_sizes=None", + "fpn_hidden_size": "fpn_hidden_size=256", + "fpn_kernel_size": "fpn_kernel_size=1", + "fpn_stride": "fpn_stride=1", + "fpn_padding": "fpn_padding=0", + "fpn_top_down_levels": "fpn_top_down_levels=None", + "num_feature_levels": "num_feature_levels=3", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "initializer_range": "initializer_range=0.02" + }, + "EfficientLoFTRModel": { + "stage_num_blocks": "stage_num_blocks: Optional[list[int]] = None", + "out_features": "out_features: Optional[list[int]] = None", + "stage_stride": "stage_stride: Optional[list[int]] = None", + "hidden_size": "hidden_size: int = 256", + "activation_function": "activation_function: str = 'relu'", + "q_aggregation_kernel_size": "q_aggregation_kernel_size: int = 4", + "kv_aggregation_kernel_size": "kv_aggregation_kernel_size: int = 4", + "q_aggregation_stride": "q_aggregation_stride: int = 4", + "kv_aggregation_stride": "kv_aggregation_stride: int = 4", + "num_attention_layers": "num_attention_layers: int = 4", + "num_attention_heads": "num_attention_heads: int = 8", + "attention_dropout": "attention_dropout: float = 0.0", + "attention_bias": "attention_bias: bool = False", + "mlp_activation_function": "mlp_activation_function: str = 'leaky_relu'", + "coarse_matching_skip_softmax": "coarse_matching_skip_softmax: bool = False", + "coarse_matching_threshold": "coarse_matching_threshold: float = 0.2", + "coarse_matching_temperature": "coarse_matching_temperature: float = 0.1", + "coarse_matching_border_removal": "coarse_matching_border_removal: int = 2", + "fine_kernel_size": "fine_kernel_size: int = 8", + "batch_norm_eps": "batch_norm_eps: float = 1e-05", + "rope_parameters": "rope_parameters: Optional[dict] = None", + "fine_matching_slice_dim": "fine_matching_slice_dim: int = 8", + "fine_matching_regress_temperature": "fine_matching_regress_temperature: float = 10.0", + "initializer_range": "initializer_range: float = 0.02" + }, + "EfficientNetModel": { + "num_channels": "num_channels: int = 3", + "image_size": "image_size: int = 600", + "width_coefficient": "width_coefficient: float = 2.0", + "depth_coefficient": "depth_coefficient: float = 3.1", + "depth_divisor": "depth_divisor: int = 8", + "kernel_sizes": "kernel_sizes: list[int] = [3, 3, 5, 3, 5, 5, 3]", + "in_channels": "in_channels: list[int] = [32, 16, 24, 40, 80, 112, 192]", + "out_channels": "out_channels: list[int] = [16, 24, 40, 80, 112, 192, 320]", + "depthwise_padding": "depthwise_padding: list[int] = []", + "strides": "strides: list[int] = [1, 2, 2, 2, 1, 2, 1]", + "num_block_repeats": "num_block_repeats: list[int] = [1, 2, 2, 3, 3, 4, 1]", + "expand_ratios": "expand_ratios: list[int] = [1, 6, 6, 6, 6, 6, 6]", + "squeeze_expansion_ratio": "squeeze_expansion_ratio: float = 0.25", + "hidden_act": "hidden_act: str = 'swish'", + "hidden_dim": "hidden_dim: int = 2560", + "pooling_type": "pooling_type: str = 'mean'", + "initializer_range": "initializer_range: float = 0.02", + "batch_norm_eps": "batch_norm_eps: float = 0.001", + "batch_norm_momentum": "batch_norm_momentum: float = 0.99", + "dropout_rate": "dropout_rate: float = 0.5", + "drop_connect_rate": "drop_connect_rate: float = 0.2" + }, + "ElectraModel": { + "vocab_size": "vocab_size=30522", + "embedding_size": "embedding_size=128", + "hidden_size": "hidden_size=256", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=4", + "intermediate_size": "intermediate_size=1024", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "summary_type": "summary_type='first'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation='gelu'", + "summary_last_dropout": "summary_last_dropout=0.1", + "pad_token_id": "pad_token_id=0", + "classifier_dropout": "classifier_dropout=None" + }, + "Emu3Model": { + "vq_config": "vq_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3VQVAEConfig] = None", + "text_config": "text_config: Union[dict, transformers.models.emu3.configuration_emu3.Emu3TextConfig] = None", + "vocabulary_map": "vocabulary_map: Optional[dict[int, int]] = None" + }, + "EncodecModel": { + "target_bandwidths": "target_bandwidths=[1.5, 3.0, 6.0, 12.0, 24.0]", + "sampling_rate": "sampling_rate=24000", + "audio_channels": "audio_channels=1", + "normalize": "normalize=False", + "chunk_length_s": "chunk_length_s=None", + "overlap": "overlap=None", + "hidden_size": "hidden_size=128", + "num_filters": "num_filters=32", + "num_residual_layers": "num_residual_layers=1", + "upsampling_ratios": "upsampling_ratios=[8, 5, 4, 2]", + "norm_type": "norm_type='weight_norm'", + "kernel_size": "kernel_size=7", + "last_kernel_size": "last_kernel_size=7", + "residual_kernel_size": "residual_kernel_size=3", + "dilation_growth_rate": "dilation_growth_rate=2", + "use_causal_conv": "use_causal_conv=True", + "pad_mode": "pad_mode='reflect'", + "compress": "compress=2", + "num_lstm_layers": "num_lstm_layers=2", + "trim_right_ratio": "trim_right_ratio=1.0", + "codebook_size": "codebook_size=1024", + "codebook_dim": "codebook_dim=None", + "use_conv_shortcut": "use_conv_shortcut=True" + }, + "ErnieModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "task_type_vocab_size": "task_type_vocab_size=3", + "use_task_id": "use_task_id=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "classifier_dropout": "classifier_dropout=None" + }, + "Ernie4_5Model": { + "vocab_size": "vocab_size: Optional[int] = 103424", + "hidden_size": "hidden_size: Optional[int] = 1024", + "intermediate_size": "intermediate_size: Optional[int] = 3072", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 18", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_bias": "use_bias: Optional[bool] = False", + "head_dim": "head_dim: Optional[int] = 128" + }, + "Ernie4_5_MoeModel": { + "vocab_size": "vocab_size: Optional[int] = 103424", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 12288", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 28", + "num_attention_heads": "num_attention_heads: Optional[int] = 20", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_bias": "use_bias: Optional[int] = False", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1536", + "moe_k": "moe_k: Optional[int] = 6", + "moe_num_experts": "moe_num_experts: Optional[int] = 64", + "moe_num_shared_experts": "moe_num_shared_experts: Optional[int] = 2", + "moe_layer_start_index": "moe_layer_start_index: Optional[int] = 1", + "moe_layer_end_index": "moe_layer_end_index: Optional[int] = -1", + "moe_layer_interval": "moe_layer_interval: Optional[int] = 1", + "moe_norm_min": "moe_norm_min: Optional[int] = 1e-12", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001" + }, + "Ernie4_5_VL_MoeModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_start_token_id": "image_start_token_id=101304", + "image_end_token_id": "image_end_token_id=101305", + "image_token_id": "image_token_id=100295", + "video_start_token_id": "video_start_token_id=101306", + "video_end_token_id": "video_end_token_id=101307", + "video_token_id": "video_token_id=103367" + }, + "EsmModel": { + "vocab_size": "vocab_size=None", + "mask_token_id": "mask_token_id=None", + "pad_token_id": "pad_token_id=None", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=1026", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "position_embedding_type": "position_embedding_type='absolute'", + "emb_layer_norm_before": "emb_layer_norm_before=None", + "token_dropout": "token_dropout=False", + "is_folding_model": "is_folding_model=False", + "esmfold_config": "esmfold_config=None", + "vocab_list": "vocab_list=None" + }, + "EsmTokenizer": { + "vocab_file": "vocab_file", + "unk_token": "unk_token=''", + "cls_token": "cls_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "eos_token": "eos_token=''" + }, + "EvollaModel": { + "protein_encoder_config": "protein_encoder_config: Optional[dict] = None", + "vocab_size": "vocab_size: Optional[int] = 128256", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "aligner_ffn_mult": "aligner_ffn_mult: Optional[int] = 4", + "aligner_enable_bias": "aligner_enable_bias: Optional[bool] = True", + "aligner_attention_probs_dropout_prob": "aligner_attention_probs_dropout_prob: Optional[float] = 0.1", + "aligner_num_add_layers": "aligner_num_add_layers: Optional[int] = 8", + "resampler_depth": "resampler_depth: Optional[int] = 6", + "resampler_dim_head": "resampler_dim_head: Optional[int] = 64", + "resampler_heads": "resampler_heads: Optional[int] = 8", + "resampler_num_latents": "resampler_num_latents: Optional[int] = 64", + "resampler_ff_mult": "resampler_ff_mult: Optional[int] = 4", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 128000", + "eos_token_id": "eos_token_id: Optional[int] = 128009", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False" + }, + "Exaone4Model": { + "vocab_size": "vocab_size: Optional[int] = 102400", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 16384", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "sliding_window": "sliding_window: Optional[int] = 4096", + "sliding_window_pattern": "sliding_window_pattern: Optional[int] = 4", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "FalconModel": { + "vocab_size": "vocab_size: Optional[int] = 65024", + "hidden_size": "hidden_size: Optional[int] = 4544", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 71", + "num_ln_in_parallel_attn": "num_ln_in_parallel_attn: Optional[int] = None", + "layer_norm_epsilon": "layer_norm_epsilon: Optional[int] = 1e-05", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_kv_heads": "num_kv_heads: Optional[int] = None", + "alibi": "alibi: Optional[bool] = False", + "new_decoder_architecture": "new_decoder_architecture: Optional[bool] = False", + "multi_query": "multi_query: Optional[bool] = True", + "parallel_attn": "parallel_attn: Optional[bool] = True", + "bias": "bias: Optional[bool] = False", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "bos_token_id": "bos_token_id: Optional[int] = 11", + "eos_token_id": "eos_token_id: Optional[int] = 11", + "ffn_hidden_size": "ffn_hidden_size: Optional[int] = None", + "activation": "activation: Optional[str] = 'gelu'" + }, + "FalconH1Model": { + "vocab_size": "vocab_size: Optional[int] = 128000", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "num_logits_to_keep": "num_logits_to_keep: Optional[int] = 1", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mamba_d_ssm": "mamba_d_ssm: Optional[int] = 1024", + "mamba_n_heads": "mamba_n_heads: Optional[int] = 128", + "mamba_d_head": "mamba_d_head: Optional[str] = 'auto'", + "mamba_n_groups": "mamba_n_groups: Optional[int] = 1", + "mamba_d_state": "mamba_d_state: Optional[int] = 256", + "mamba_d_conv": "mamba_d_conv: Optional[int] = 4", + "mamba_expand": "mamba_expand: Optional[int] = 2", + "mamba_chunk_size": "mamba_chunk_size: Optional[int] = 256", + "mamba_conv_bias": "mamba_conv_bias: Optional[bool] = True", + "mamba_proj_bias": "mamba_proj_bias: Optional[bool] = False", + "mamba_norm_before_gate": "mamba_norm_before_gate: Optional[bool] = True", + "mamba_rms_norm": "mamba_rms_norm: Optional[bool] = False", + "projectors_bias": "projectors_bias: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "lm_head_multiplier": "lm_head_multiplier: Optional[float] = 1.0", + "embedding_multiplier": "embedding_multiplier: Optional[float] = 1.0", + "mlp_multipliers": "mlp_multipliers: Optional[int] = None", + "key_multiplier": "key_multiplier: Optional[int] = None", + "attention_out_multiplier": "attention_out_multiplier: Optional[int] = None", + "attention_in_multiplier": "attention_in_multiplier: Optional[int] = None", + "ssm_multipliers": "ssm_multipliers: Optional[int] = None", + "ssm_in_multiplier": "ssm_in_multiplier: Optional[int] = None", + "ssm_out_multiplier": "ssm_out_multiplier: Optional[int] = None" + }, + "FalconMambaModel": { + "vocab_size": "vocab_size=50280", + "hidden_size": "hidden_size=768", + "state_size": "state_size=16", + "num_hidden_layers": "num_hidden_layers=32", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=0", + "expand": "expand=2", + "conv_kernel": "conv_kernel=4", + "use_bias": "use_bias=False", + "use_conv_bias": "use_conv_bias=True", + "hidden_act": "hidden_act='silu'", + "initializer_range": "initializer_range=0.1", + "residual_in_fp32": "residual_in_fp32=True", + "time_step_rank": "time_step_rank='auto'", + "time_step_scale": "time_step_scale=1.0", + "time_step_min": "time_step_min=0.001", + "time_step_max": "time_step_max=0.1", + "time_step_init_scheme": "time_step_init_scheme='random'", + "time_step_floor": "time_step_floor=0.0001", + "rescale_prenorm_residual": "rescale_prenorm_residual=False", + "use_falcon_mambapy": "use_falcon_mambapy=False", + "mixer_rms_eps": "mixer_rms_eps=1e-06" + }, + "GPTNeoXTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors: str = 'replace'", + "unk_token": "unk_token: str = '<|endoftext|>'", + "bos_token": "bos_token: str = '<|endoftext|>'", + "eos_token": "eos_token: str = '<|endoftext|>'", + "pad_token": "pad_token: str = '<|padding|>'", + "add_prefix_space": "add_prefix_space: bool = False", + "trim_offsets": "trim_offsets: bool = True" + }, + "FastVlmModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_id": "image_token_id=151646", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_select_strategy": "vision_feature_select_strategy='full'", + "vision_feature_layer": "vision_feature_layer=-1", + "multimodal_projector_bias": "multimodal_projector_bias=True" + }, + "FastSpeech2ConformerModel": { + "hidden_size": "hidden_size=384", + "vocab_size": "vocab_size=78", + "num_mel_bins": "num_mel_bins=80", + "encoder_num_attention_heads": "encoder_num_attention_heads=2", + "encoder_layers": "encoder_layers=4", + "encoder_linear_units": "encoder_linear_units=1536", + "decoder_layers": "decoder_layers=4", + "decoder_num_attention_heads": "decoder_num_attention_heads=2", + "decoder_linear_units": "decoder_linear_units=1536", + "speech_decoder_postnet_layers": "speech_decoder_postnet_layers=5", + "speech_decoder_postnet_units": "speech_decoder_postnet_units=256", + "speech_decoder_postnet_kernel": "speech_decoder_postnet_kernel=5", + "positionwise_conv_kernel_size": "positionwise_conv_kernel_size=3", + "encoder_normalize_before": "encoder_normalize_before=False", + "decoder_normalize_before": "decoder_normalize_before=False", + "encoder_concat_after": "encoder_concat_after=False", + "decoder_concat_after": "decoder_concat_after=False", + "reduction_factor": "reduction_factor=1", + "speaking_speed": "speaking_speed=1.0", + "use_macaron_style_in_conformer": "use_macaron_style_in_conformer=True", + "use_cnn_in_conformer": "use_cnn_in_conformer=True", + "encoder_kernel_size": "encoder_kernel_size=7", + "decoder_kernel_size": "decoder_kernel_size=31", + "duration_predictor_layers": "duration_predictor_layers=2", + "duration_predictor_channels": "duration_predictor_channels=256", + "duration_predictor_kernel_size": "duration_predictor_kernel_size=3", + "energy_predictor_layers": "energy_predictor_layers=2", + "energy_predictor_channels": "energy_predictor_channels=256", + "energy_predictor_kernel_size": "energy_predictor_kernel_size=3", + "energy_predictor_dropout": "energy_predictor_dropout=0.5", + "energy_embed_kernel_size": "energy_embed_kernel_size=1", + "energy_embed_dropout": "energy_embed_dropout=0.0", + "stop_gradient_from_energy_predictor": "stop_gradient_from_energy_predictor=False", + "pitch_predictor_layers": "pitch_predictor_layers=5", + "pitch_predictor_channels": "pitch_predictor_channels=256", + "pitch_predictor_kernel_size": "pitch_predictor_kernel_size=5", + "pitch_predictor_dropout": "pitch_predictor_dropout=0.5", + "pitch_embed_kernel_size": "pitch_embed_kernel_size=1", + "pitch_embed_dropout": "pitch_embed_dropout=0.0", + "stop_gradient_from_pitch_predictor": "stop_gradient_from_pitch_predictor=True", + "encoder_dropout_rate": "encoder_dropout_rate=0.2", + "encoder_positional_dropout_rate": "encoder_positional_dropout_rate=0.2", + "encoder_attention_dropout_rate": "encoder_attention_dropout_rate=0.2", + "decoder_dropout_rate": "decoder_dropout_rate=0.2", + "decoder_positional_dropout_rate": "decoder_positional_dropout_rate=0.2", + "decoder_attention_dropout_rate": "decoder_attention_dropout_rate=0.2", + "duration_predictor_dropout_rate": "duration_predictor_dropout_rate=0.2", + "speech_decoder_postnet_dropout": "speech_decoder_postnet_dropout=0.5", + "max_source_positions": "max_source_positions=5000", + "use_masking": "use_masking=True", + "use_weighted_masking": "use_weighted_masking=False", + "num_speakers": "num_speakers=None", + "num_languages": "num_languages=None", + "speaker_embed_dim": "speaker_embed_dim=None", + "is_encoder_decoder": "is_encoder_decoder=True", + "convolution_bias": "convolution_bias=True" + }, + "FastSpeech2ConformerWithHifiGan": { + "model_config": "model_config: Optional[dict] = None", + "vocoder_config": "vocoder_config: Optional[dict] = None" + }, + "FlaubertModel": { + "pre_norm": "pre_norm=False", + "layerdrop": "layerdrop=0.0", + "vocab_size": "vocab_size=30145", + "emb_dim": "emb_dim=2048", + "n_layers": "n_layers=12", + "n_heads": "n_heads=16", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "gelu_activation": "gelu_activation=True", + "sinusoidal_embeddings": "sinusoidal_embeddings=False", + "causal": "causal=False", + "asm": "asm=False", + "n_langs": "n_langs=1", + "use_lang_emb": "use_lang_emb=True", + "max_position_embeddings": "max_position_embeddings=512", + "embed_init_std": "embed_init_std=0.02209708691207961", + "layer_norm_eps": "layer_norm_eps=1e-12", + "init_std": "init_std=0.02", + "bos_index": "bos_index=0", + "eos_index": "eos_index=1", + "pad_index": "pad_index=2", + "unk_index": "unk_index=3", + "mask_index": "mask_index=5", + "is_encoder": "is_encoder=True", + "summary_type": "summary_type='first'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation=None", + "summary_proj_to_labels": "summary_proj_to_labels=True", + "summary_first_dropout": "summary_first_dropout=0.1", + "start_n_top": "start_n_top=5", + "end_n_top": "end_n_top=5", + "mask_token_id": "mask_token_id=0", + "lang_id": "lang_id=0", + "pad_token_id": "pad_token_id=2", + "bos_token_id": "bos_token_id=0" + }, + "FlaubertTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "do_lowercase": "do_lowercase=False", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''", + "cls_token": "cls_token=''", + "mask_token": "mask_token=''", + "additional_special_tokens": "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", + "lang2id": "lang2id=None", + "id2lang": "id2lang=None" + }, + "FlavaModel": { + "image_config": "image_config: Optional[dict[str, Any]] = None", + "text_config": "text_config: Optional[dict[str, Any]] = None", + "multimodal_config": "multimodal_config: Optional[dict[str, Any]] = None", + "image_codebook_config": "image_codebook_config: Optional[dict[str, Any]] = None", + "hidden_size": "hidden_size: int = 768", + "layer_norm_eps": "layer_norm_eps: float = 1e-12", + "projection_dim": "projection_dim: int = 768", + "init_codebook": "init_codebook: bool = True", + "logit_scale_init_value": "logit_scale_init_value: float = 2.6592", + "initializer_range": "initializer_range: float = 0.02", + "ce_ignore_index": "ce_ignore_index: int = -100", + "mim_weight": "mim_weight: float = 1.0", + "mlm_weight": "mlm_weight: float = 1.0", + "global_contrastive_weight": "global_contrastive_weight: float = 1.0", + "itm_weight": "itm_weight: float = 1.0", + "mmm_image_weight": "mmm_image_weight: float = 1.0", + "mmm_text_weight": "mmm_text_weight: float = 1.0", + "global_backprop_contrastive": "global_backprop_contrastive: bool = True", + "skip_unmasked_multimodal_encoder": "skip_unmasked_multimodal_encoder: bool = True", + "return_loss": "return_loss: bool = True" + }, + "FlexOlmoModel": { + "vocab_size": "vocab_size: Optional[int] = 100352", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 100277", + "bos_token_id": "bos_token_id: Optional[int] = None", + "eos_token_id": "eos_token_id: Optional[int] = 100257", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 5", + "num_experts": "num_experts: Optional[int] = 7", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.01", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False" + }, + "Florence2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=51289", + "is_encoder_decoder": "is_encoder_decoder=True" + }, + "FNetModel": { + "vocab_size": "vocab_size=32000", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu_new'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=4", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "use_tpu_fourier_optimizations": "use_tpu_fourier_optimizations=False", + "tpu_short_seq_length": "tpu_short_seq_length=512", + "pad_token_id": "pad_token_id=3", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2" + }, + "FNetTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "do_lower_case": "do_lower_case: bool = True", + "keep_accents": "keep_accents: bool = False", + "bos_token": "bos_token: str = '[CLS]'", + "eos_token": "eos_token: str = '[SEP]'", + "unk_token": "unk_token: str = ''", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = ''", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "add_prefix_space": "add_prefix_space: bool = True", + "trim_offsets": "trim_offsets: bool = True" + }, + "FocalNetModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=96", + "use_conv_embed": "use_conv_embed=False", + "hidden_sizes": "hidden_sizes=[192, 384, 768, 768]", + "depths": "depths=[2, 2, 6, 2]", + "focal_levels": "focal_levels=[2, 2, 2, 2]", + "focal_windows": "focal_windows=[3, 3, 3, 3]", + "hidden_act": "hidden_act='gelu'", + "mlp_ratio": "mlp_ratio=4.0", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "use_layerscale": "use_layerscale=False", + "layerscale_value": "layerscale_value=0.0001", + "use_post_layernorm": "use_post_layernorm=False", + "use_post_layernorm_in_modulation": "use_post_layernorm_in_modulation=False", + "normalize_modulator": "normalize_modulator=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "encoder_stride": "encoder_stride=32", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "FSMTModel": { + "langs": "langs=['en', 'de']", + "src_vocab_size": "src_vocab_size=42024", + "tgt_vocab_size": "tgt_vocab_size=42024", + "activation_function": "activation_function='relu'", + "d_model": "d_model=1024", + "max_length": "max_length=200", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_layers": "encoder_layers=12", + "encoder_attention_heads": "encoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_layers": "decoder_layers=12", + "decoder_attention_heads": "decoder_attention_heads=16", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "attention_dropout": "attention_dropout=0.0", + "dropout": "dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "is_encoder_decoder": "is_encoder_decoder=True", + "scale_embedding": "scale_embedding=True", + "tie_word_embeddings": "tie_word_embeddings=False", + "num_beams": "num_beams=5", + "length_penalty": "length_penalty=1.0", + "early_stopping": "early_stopping=False", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "forced_eos_token_id": "forced_eos_token_id=2", + "common_kwargs": "**common_kwargs" + }, + "FSMTTokenizer": { + "langs": "langs=None", + "src_vocab_file": "src_vocab_file=None", + "tgt_vocab_file": "tgt_vocab_file=None", + "merges_file": "merges_file=None", + "do_lower_case": "do_lower_case=False", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''" + }, + "FunnelModel": null, + "FunnelTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case: bool = True", + "unk_token": "unk_token: str = ''", + "sep_token": "sep_token: str = ''", + "pad_token": "pad_token: str = ''", + "cls_token": "cls_token: str = ''", + "mask_token": "mask_token: str = ''", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "clean_text": "clean_text: bool = True", + "tokenize_chinese_chars": "tokenize_chinese_chars: bool = True", + "strip_accents": "strip_accents: Optional[bool] = None", + "wordpieces_prefix": "wordpieces_prefix: str = '##'" + }, + "FuyuModel": { + "vocab_size": "vocab_size: Optional[int] = 262144", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 16384", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 36", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 16384", + "image_size": "image_size: Optional[int] = 300", + "patch_size": "patch_size: Optional[int] = 30", + "num_channels": "num_channels: Optional[int] = 3", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "qk_layernorm": "qk_layernorm: Optional[bool] = True", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "image_token_id": "image_token_id: Optional[int] = 71011", + "text_config": "text_config: Optional[dict] = None" + }, + "GemmaModel": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 3072", + "intermediate_size": "intermediate_size: Optional[int] = 24576", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 28", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 16", + "head_dim": "head_dim: Optional[int] = 256", + "hidden_act": "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "use_bidirectional_attention": "use_bidirectional_attention: Optional[bool] = None" + }, + "GemmaTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "unk_token": "unk_token: str = ''", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "pad_token": "pad_token: str = ''", + "mask_token": "mask_token: str = ''" + }, + "Gemma2Model": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 2304", + "intermediate_size": "intermediate_size: Optional[int] = 9216", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 26", + "num_attention_heads": "num_attention_heads: Optional[int] = 8", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "head_dim": "head_dim: Optional[int] = 256", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "query_pre_attn_scalar": "query_pre_attn_scalar: Optional[int] = 256", + "sliding_window": "sliding_window: Optional[int] = 4096", + "layer_types": "layer_types: Optional[list[str]] = None", + "final_logit_softcapping": "final_logit_softcapping: Optional[float] = 30.0", + "attn_logit_softcapping": "attn_logit_softcapping: Optional[float] = 50.0", + "use_bidirectional_attention": "use_bidirectional_attention: Optional[bool] = None" + }, + "Gemma3Model": { + "text_config": "text_config: Union[transformers.models.gemma3.configuration_gemma3.Gemma3TextConfig, dict[str, Any], NoneType] = None", + "vision_config": "vision_config: Union[transformers.models.siglip.configuration_siglip.SiglipVisionConfig, dict[str, Any], NoneType] = None", + "mm_tokens_per_image": "mm_tokens_per_image: int = 256", + "boi_token_index": "boi_token_index: int = 255999", + "eoi_token_index": "eoi_token_index: int = 256000", + "image_token_index": "image_token_index: int = 262144", + "initializer_range": "initializer_range: float = 0.02" + }, + "Gemma3TextModel": { + "vocab_size": "vocab_size: Optional[int] = 262208", + "hidden_size": "hidden_size: Optional[int] = 2304", + "intermediate_size": "intermediate_size: Optional[int] = 9216", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 26", + "num_attention_heads": "num_attention_heads: Optional[int] = 8", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "head_dim": "head_dim: Optional[int] = 256", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "query_pre_attn_scalar": "query_pre_attn_scalar: Optional[int] = 256", + "sliding_window": "sliding_window: Optional[int] = 4096", + "layer_types": "layer_types: Optional[list[str]] = None", + "final_logit_softcapping": "final_logit_softcapping: Optional[float] = None", + "attn_logit_softcapping": "attn_logit_softcapping: Optional[float] = None", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_bidirectional_attention": "use_bidirectional_attention: Optional[bool] = False" + }, + "Gemma3nModel": { + "text_config": "text_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nTextConfig, dict[str, Any], NoneType] = None", + "vision_config": "vision_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nVisionConfig, dict[str, Any], NoneType] = None", + "audio_config": "audio_config: Union[transformers.models.gemma3n.configuration_gemma3n.Gemma3nAudioConfig, dict[str, Any], NoneType] = None", + "audio_soft_tokens_per_image": "audio_soft_tokens_per_image: int = 188", + "vision_soft_tokens_per_image": "vision_soft_tokens_per_image: int = 256", + "boi_token_id": "boi_token_id: int = 255999", + "eoi_token_id": "eoi_token_id: int = 262144", + "image_token_id": "image_token_id: int = 262145", + "boa_token_id": "boa_token_id: int = 256000", + "eoa_token_id": "eoa_token_id: int = 262272", + "audio_token_id": "audio_token_id: int = 262273", + "initializer_range": "initializer_range: float = 0.02" + }, + "Gemma3nAudioEncoder": { + "vocab_size": "vocab_size: int = 128", + "vocab_offset": "vocab_offset: int = 262272", + "input_feat_size": "input_feat_size: int = 128", + "hidden_size": "hidden_size: int = 1536", + "rms_norm_eps": "rms_norm_eps: float = 1e-06", + "gradient_clipping": "gradient_clipping: float = 10000000000.0", + "conf_attention_chunk_size": "conf_attention_chunk_size: int = 12", + "conf_attention_context_left": "conf_attention_context_left: int = 13", + "conf_attention_context_right": "conf_attention_context_right: int = 0", + "conf_attention_logit_cap": "conf_attention_logit_cap: float = 50.0", + "conf_num_attention_heads": "conf_num_attention_heads: int = 8", + "conf_num_hidden_layers": "conf_num_hidden_layers: int = 12", + "conf_conv_kernel_size": "conf_conv_kernel_size: int = 5", + "conf_reduction_factor": "conf_reduction_factor: int = 4", + "conf_residual_weight": "conf_residual_weight: float = 0.5", + "sscp_conv_channel_size": "sscp_conv_channel_size: tuple[int, int] = (128, 32)", + "sscp_conv_group_norm_eps": "sscp_conv_group_norm_eps: float = 0.001", + "sscp_conv_kernel_size": "sscp_conv_kernel_size: tuple[tuple[int, int], tuple[int, int]] = ((3, 3), (3, 3))", + "sscp_conv_stride_size": "sscp_conv_stride_size: tuple[tuple[int, int], tuple[int, int]] = ((2, 2), (2, 2))" + }, + "Gemma3nTextModel": { + "vocab_size": "vocab_size: int = 262400", + "vocab_size_per_layer_input": "vocab_size_per_layer_input: int = 262144", + "hidden_size": "hidden_size: int = 2048", + "hidden_size_per_layer_input": "hidden_size_per_layer_input: int = 256", + "intermediate_size": "intermediate_size: Union[int, collections.abc.Sequence[int]] = 16384", + "num_hidden_layers": "num_hidden_layers: int = 35", + "num_attention_heads": "num_attention_heads: int = 8", + "num_key_value_heads": "num_key_value_heads: int = 2", + "head_dim": "head_dim: int = 256", + "hidden_activation": "hidden_activation: str = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: int = 32768", + "initializer_range": "initializer_range: float = 0.02", + "rms_norm_eps": "rms_norm_eps: float = 1e-06", + "pad_token_id": "pad_token_id: int = 0", + "eos_token_id": "eos_token_id: int = 1", + "bos_token_id": "bos_token_id: int = 2", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: bool = False", + "attention_dropout": "attention_dropout: float = 0.0", + "sliding_window": "sliding_window: int = 512", + "layer_types": "layer_types: Optional[collections.abc.Sequence[str]] = None", + "final_logit_softcapping": "final_logit_softcapping: float = 30.0", + "altup_active_idx": "altup_active_idx: int = 0", + "altup_coef_clip": "altup_coef_clip: float = 120.0", + "altup_correct_scale": "altup_correct_scale: bool = True", + "altup_num_inputs": "altup_num_inputs: int = 4", + "num_kv_shared_layers": "num_kv_shared_layers: int = 15", + "laurel_rank": "laurel_rank: int = 64", + "activation_sparsity_pattern": "activation_sparsity_pattern: Union[float, collections.abc.Sequence[float], NoneType] = None" + }, + "TimmWrapperModel": { + "_resnet_": [ + "" + ] + }, + "GitModel": { + "vision_config": "vision_config=None", + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=6", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=1024", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "tie_word_embeddings": "tie_word_embeddings=False", + "bos_token_id": "bos_token_id=101", + "eos_token_id": "eos_token_id=102", + "num_image_with_embedding": "num_image_with_embedding=None" + }, + "GlmModel": { + "vocab_size": "vocab_size: Optional[int] = 151552", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 13696", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 40", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1.5625e-07", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "pad_token_id": "pad_token_id: Optional[int] = 151329", + "eos_token_id": "eos_token_id: Optional[list[int]] = [151329, 151336, 151338]", + "bos_token_id": "bos_token_id: Optional[int] = None", + "attention_bias": "attention_bias: Optional[bool] = True" + }, + "Glm4Model": { + "vocab_size": "vocab_size: Optional[int] = 151552", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 13696", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 40", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1.5625e-07", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "pad_token_id": "pad_token_id: Optional[int] = 151329", + "eos_token_id": "eos_token_id: Optional[list[int]] = [151329, 151336, 151338]", + "bos_token_id": "bos_token_id: Optional[int] = None", + "attention_bias": "attention_bias: Optional[bool] = True" + }, + "Glm46VModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151343", + "video_token_id": "video_token_id=151344", + "image_start_token_id": "image_start_token_id=151339", + "image_end_token_id": "image_end_token_id=151340", + "video_start_token_id": "video_start_token_id=151361", + "video_end_token_id": "video_end_token_id=151362" + }, + "Glm4MoeModel": { + "vocab_size": "vocab_size: Optional[int] = 151552", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 10944", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 46", + "num_attention_heads": "num_attention_heads: Optional[int] = 96", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 8", + "n_shared_experts": "n_shared_experts: Optional[int] = 1", + "n_routed_experts": "n_routed_experts: Optional[int] = 128", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 1.0", + "n_group": "n_group: Optional[int] = 1", + "topk_group": "topk_group: Optional[int] = 1", + "first_k_dense_replace": "first_k_dense_replace: Optional[int] = 1", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = True", + "use_qk_norm": "use_qk_norm: Optional[bool] = False" + }, + "Glm4vModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151343", + "video_token_id": "video_token_id=151344", + "image_start_token_id": "image_start_token_id=151339", + "image_end_token_id": "image_end_token_id=151340", + "video_start_token_id": "video_start_token_id=151341", + "video_end_token_id": "video_end_token_id=151342" + }, + "Glm4vMoeModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151363", + "video_token_id": "video_token_id=151364", + "image_start_token_id": "image_start_token_id=151339", + "image_end_token_id": "image_end_token_id=151340", + "video_start_token_id": "video_start_token_id=151341", + "video_end_token_id": "video_end_token_id=151342" + }, + "Glm4vMoeTextModel": { + "vocab_size": "vocab_size: Optional[int] = 151424", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 10944", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 46", + "num_attention_heads": "num_attention_heads: Optional[int] = 96", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 65536", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = True", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 8", + "n_shared_experts": "n_shared_experts: Optional[int] = 1", + "n_routed_experts": "n_routed_experts: Optional[int] = 128", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 1.0", + "n_group": "n_group: Optional[int] = 1", + "topk_group": "topk_group: Optional[int] = 1", + "first_k_dense_replace": "first_k_dense_replace: Optional[int] = 1", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = True", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.0001" + }, + "Glm4vMoeVisionModel": { + "depth": "depth=24", + "hidden_size": "hidden_size=1536", + "hidden_act": "hidden_act='silu'", + "attention_bias": "attention_bias=False", + "attention_dropout": "attention_dropout=0.0", + "num_heads": "num_heads=12", + "in_channels": "in_channels=3", + "image_size": "image_size=336", + "patch_size": "patch_size=14", + "rms_norm_eps": "rms_norm_eps=1e-05", + "spatial_merge_size": "spatial_merge_size=2", + "temporal_patch_size": "temporal_patch_size=2", + "out_hidden_size": "out_hidden_size=4096", + "intermediate_size": "intermediate_size=13696", + "initializer_range": "initializer_range=0.02" + }, + "Glm4vTextModel": { + "vocab_size": "vocab_size: Optional[int] = 151552", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 13696", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 40", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "Glm4vVisionModel": { + "depth": "depth=24", + "hidden_size": "hidden_size=1536", + "hidden_act": "hidden_act='silu'", + "attention_bias": "attention_bias=False", + "attention_dropout": "attention_dropout=0.0", + "num_heads": "num_heads=12", + "in_channels": "in_channels=3", + "image_size": "image_size=336", + "patch_size": "patch_size=14", + "rms_norm_eps": "rms_norm_eps=1e-05", + "spatial_merge_size": "spatial_merge_size=2", + "temporal_patch_size": "temporal_patch_size=2", + "out_hidden_size": "out_hidden_size=4096", + "intermediate_size": "intermediate_size=13696", + "initializer_range": "initializer_range=0.02" + }, + "GlmAsrForConditionalGeneration": { + "audio_config": "audio_config=None", + "text_config": "text_config=None", + "audio_token_id": "audio_token_id=59260", + "projector_hidden_act": "projector_hidden_act='gelu'" + }, + "GlmAsrEncoder": { + "hidden_size": "hidden_size=1280", + "intermediate_size": "intermediate_size=5120", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=20", + "num_key_value_heads": "num_key_value_heads=None", + "hidden_act": "hidden_act='gelu'", + "max_position_embeddings": "max_position_embeddings=1500", + "initializer_range": "initializer_range=0.02", + "rope_parameters": "rope_parameters=None", + "attention_dropout": "attention_dropout=0.0", + "num_mel_bins": "num_mel_bins=128" + }, + "GLPNModel": { + "num_channels": "num_channels=3", + "num_encoder_blocks": "num_encoder_blocks=4", + "depths": "depths=[2, 2, 2, 2]", + "sr_ratios": "sr_ratios=[8, 4, 2, 1]", + "hidden_sizes": "hidden_sizes=[32, 64, 160, 256]", + "patch_sizes": "patch_sizes=[7, 3, 3, 3]", + "strides": "strides=[4, 2, 2, 2]", + "num_attention_heads": "num_attention_heads=[1, 2, 5, 8]", + "mlp_ratios": "mlp_ratios=[4, 4, 4, 4]", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "drop_path_rate": "drop_path_rate=0.1", + "layer_norm_eps": "layer_norm_eps=1e-06", + "decoder_hidden_size": "decoder_hidden_size=64", + "max_depth": "max_depth=10", + "head_in_index": "head_in_index=-1" + }, + "GotOcr2Model": { + "vision_config": "vision_config: Optional[dict] = None", + "text_config": "text_config: Optional[dict] = None", + "image_token_index": "image_token_index: Optional[int] = 151859", + "image_seq_length": "image_seq_length: Optional[int] = 576", + "pad_token_id": "pad_token_id: Optional[int] = -1" + }, + "GPT2Model": { + "vocab_size": "vocab_size=50257", + "n_positions": "n_positions=1024", + "n_embd": "n_embd=768", + "n_layer": "n_layer=12", + "n_head": "n_head=12", + "n_inner": "n_inner=None", + "activation_function": "activation_function='gelu_new'", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "attn_pdrop": "attn_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "summary_type": "summary_type='cls_index'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation=None", + "summary_proj_to_labels": "summary_proj_to_labels=True", + "summary_first_dropout": "summary_first_dropout=0.1", + "scale_attn_weights": "scale_attn_weights=True", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "scale_attn_by_inverse_layer_idx": "scale_attn_by_inverse_layer_idx=False", + "reorder_and_upcast_attn": "reorder_and_upcast_attn=False" + }, + "GPTBigCodeModel": { + "vocab_size": "vocab_size=50257", + "n_positions": "n_positions=1024", + "n_embd": "n_embd=768", + "n_layer": "n_layer=12", + "n_head": "n_head=12", + "n_inner": "n_inner=None", + "activation_function": "activation_function='gelu_pytorch_tanh'", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "attn_pdrop": "attn_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "scale_attn_weights": "scale_attn_weights=True", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "attention_softmax_in_fp32": "attention_softmax_in_fp32=True", + "scale_attention_softmax_in_fp32": "scale_attention_softmax_in_fp32=True", + "multi_query": "multi_query=True" + }, + "GPTNeoModel": { + "vocab_size": "vocab_size=50257", + "max_position_embeddings": "max_position_embeddings=2048", + "hidden_size": "hidden_size=2048", + "num_layers": "num_layers=24", + "attention_types": "attention_types=[[['global', 'local'], 12]]", + "num_heads": "num_heads=16", + "intermediate_size": "intermediate_size=None", + "window_size": "window_size=256", + "activation_function": "activation_function='gelu_new'", + "resid_dropout": "resid_dropout=0.0", + "embed_dropout": "embed_dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "classifier_dropout": "classifier_dropout=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256" + }, + "GPTNeoXModel": { + "vocab_size": "vocab_size: Optional[int] = 50432", + "hidden_size": "hidden_size: Optional[int] = 6144", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 44", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "intermediate_size": "intermediate_size: Optional[int] = 24576", + "hidden_act": "hidden_act: Optional[str] = 'gelu'", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "classifier_dropout": "classifier_dropout: Optional[float] = 0.1", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "use_parallel_residual": "use_parallel_residual: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = True" + }, + "GPTNeoXJapaneseModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 2560", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "intermediate_multiple_size": "intermediate_multiple_size: Optional[int] = 4", + "hidden_act": "hidden_act: Optional[str] = 'gelu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "bos_token_id": "bos_token_id: Optional[int] = 31996", + "eos_token_id": "eos_token_id: Optional[int] = 31999", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.1", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0" + }, + "GPTNeoXJapaneseTokenizer": { + "vocab_file": "vocab_file", + "emoji_file": "emoji_file", + "unk_token": "unk_token='<|endoftext|>'", + "pad_token": "pad_token='<|endoftext|>'", + "bos_token": "bos_token='<|startoftext|>'", + "eos_token": "eos_token='<|endoftext|>'", + "do_clean_text": "do_clean_text=False" + }, + "GptOssModel": { + "num_hidden_layers": "num_hidden_layers: Optional[int] = 36", + "num_local_experts": "num_local_experts: Optional[int] = 128", + "vocab_size": "vocab_size: Optional[int] = 201088", + "hidden_size": "hidden_size: Optional[int] = 2880", + "intermediate_size": "intermediate_size: Optional[int] = 2880", + "head_dim": "head_dim: Optional[int] = 64", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "sliding_window": "sliding_window: Optional[int] = 128", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "rope_parameters": "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = {'rope_type': 'yarn', 'factor': 32.0, 'beta_fast': 32.0, 'beta_slow': 1.0, 'truncate': False, 'original_max_position_embeddings': 4096}", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 4", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.9", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "GPTJModel": { + "vocab_size": "vocab_size=50400", + "n_positions": "n_positions=2048", + "n_embd": "n_embd=4096", + "n_layer": "n_layer=28", + "n_head": "n_head=16", + "rotary_dim": "rotary_dim=64", + "n_inner": "n_inner=None", + "activation_function": "activation_function='gelu_new'", + "resid_pdrop": "resid_pdrop=0.0", + "embd_pdrop": "embd_pdrop=0.0", + "attn_pdrop": "attn_pdrop=0.0", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "GraniteModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "embedding_multiplier": "embedding_multiplier: Optional[float] = 1.0", + "logits_scaling": "logits_scaling: Optional[float] = 1.0", + "residual_multiplier": "residual_multiplier: Optional[float] = 1.0", + "attention_multiplier": "attention_multiplier: Optional[float] = 1.0" + }, + "GraniteMoeModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "embedding_multiplier": "embedding_multiplier: Optional[float] = 1.0", + "logits_scaling": "logits_scaling: Optional[float] = 1.0", + "residual_multiplier": "residual_multiplier: Optional[float] = 1.0", + "attention_multiplier": "attention_multiplier: Optional[float] = 1.0", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001" + }, + "GraniteMoeHybridModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "embedding_multiplier": "embedding_multiplier: Optional[float] = 1.0", + "logits_scaling": "logits_scaling: Optional[float] = 1.0", + "residual_multiplier": "residual_multiplier: Optional[float] = 1.0", + "attention_multiplier": "attention_multiplier: Optional[float] = 1.0", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "shared_intermediate_size": "shared_intermediate_size: Optional[int] = 1024", + "position_embedding_type": "position_embedding_type: Optional[str] = None", + "layer_types": "layer_types: Optional[list[str]] = None", + "mamba_n_heads": "mamba_n_heads: Optional[int] = 128", + "mamba_n_groups": "mamba_n_groups: Optional[int] = 1", + "mamba_d_state": "mamba_d_state: Optional[int] = 256", + "mamba_d_head": "mamba_d_head: Optional[str] = 'auto'", + "mamba_d_conv": "mamba_d_conv: Optional[int] = 4", + "mamba_expand": "mamba_expand: Optional[int] = 2", + "mamba_chunk_size": "mamba_chunk_size: Optional[int] = 256", + "mamba_conv_bias": "mamba_conv_bias: Optional[bool] = True", + "mamba_proj_bias": "mamba_proj_bias: Optional[bool] = False" + }, + "GraniteMoeSharedModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "embedding_multiplier": "embedding_multiplier: Optional[float] = 1.0", + "logits_scaling": "logits_scaling: Optional[float] = 1.0", + "residual_multiplier": "residual_multiplier: Optional[float] = 1.0", + "attention_multiplier": "attention_multiplier: Optional[float] = 1.0", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "shared_intermediate_size": "shared_intermediate_size: Optional[int] = 0" + }, + "GroundingDinoModel": { + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "backbone_kwargs": "backbone_kwargs=None", + "text_config": "text_config=None", + "num_queries": "num_queries=900", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "num_feature_levels": "num_feature_levels=4", + "encoder_n_points": "encoder_n_points=4", + "decoder_n_points": "decoder_n_points=4", + "two_stage": "two_stage=True", + "class_cost": "class_cost=1.0", + "bbox_cost": "bbox_cost=5.0", + "giou_cost": "giou_cost=2.0", + "bbox_loss_coefficient": "bbox_loss_coefficient=5.0", + "giou_loss_coefficient": "giou_loss_coefficient=2.0", + "focal_alpha": "focal_alpha=0.25", + "disable_custom_kernels": "disable_custom_kernels=False", + "max_text_len": "max_text_len=256", + "text_enhancer_dropout": "text_enhancer_dropout=0.0", + "fusion_droppath": "fusion_droppath=0.1", + "fusion_dropout": "fusion_dropout=0.0", + "embedding_init_target": "embedding_init_target=True", + "query_dim": "query_dim=4", + "decoder_bbox_embed_share": "decoder_bbox_embed_share=True", + "two_stage_bbox_embed_share": "two_stage_bbox_embed_share=False", + "positional_embedding_temperature": "positional_embedding_temperature=20", + "init_std": "init_std=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05" + }, + "GroupViTModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=256", + "projection_intermediate_dim": "projection_intermediate_dim=4096", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "HeliumModel": { + "vocab_size": "vocab_size: Optional[int] = 48000", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 7040", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 20", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 20", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-08", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "pad_token_id": "pad_token_id: Optional[int] = 3", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "attention_bias": "attention_bias: Optional[bool] = False", + "mlp_bias": "mlp_bias: Optional[bool] = False" + }, + "HGNetV2Backbone": { + "num_channels": "num_channels=3", + "embedding_size": "embedding_size=64", + "depths": "depths=[3, 4, 6, 3]", + "hidden_sizes": "hidden_sizes=[256, 512, 1024, 2048]", + "hidden_act": "hidden_act='relu'", + "out_features": "out_features=None", + "out_indices": "out_indices=None", + "stem_channels": "stem_channels=[3, 32, 48]", + "stage_in_channels": "stage_in_channels=[48, 128, 512, 1024]", + "stage_mid_channels": "stage_mid_channels=[48, 96, 192, 384]", + "stage_out_channels": "stage_out_channels=[128, 512, 1024, 2048]", + "stage_num_blocks": "stage_num_blocks=[1, 1, 3, 1]", + "stage_downsample": "stage_downsample=[False, True, True, True]", + "stage_light_block": "stage_light_block=[False, False, True, True]", + "stage_kernel_size": "stage_kernel_size=[3, 3, 5, 5]", + "stage_numb_of_layers": "stage_numb_of_layers=[6, 6, 6, 6]", + "use_learnable_affine_block": "use_learnable_affine_block=False", + "initializer_range": "initializer_range=0.02" + }, + "HieraModel": { + "embed_dim": "embed_dim=96", + "image_size": "image_size=[224, 224]", + "patch_size": "patch_size=[7, 7]", + "patch_stride": "patch_stride=[4, 4]", + "patch_padding": "patch_padding=[3, 3]", + "mlp_ratio": "mlp_ratio=4.0", + "depths": "depths=[2, 3, 16, 3]", + "num_heads": "num_heads=[1, 2, 4, 8]", + "embed_dim_multiplier": "embed_dim_multiplier=2.0", + "num_query_pool": "num_query_pool=3", + "query_stride": "query_stride=[2, 2]", + "masked_unit_size": "masked_unit_size=[8, 8]", + "masked_unit_attention": "masked_unit_attention=[True, True, False, False]", + "drop_path_rate": "drop_path_rate=0.0", + "num_channels": "num_channels=3", + "hidden_act": "hidden_act='gelu'", + "initializer_range": "initializer_range=0.02", + "layer_norm_init": "layer_norm_init=1.0", + "layer_norm_eps": "layer_norm_eps=1e-06", + "decoder_hidden_size": "decoder_hidden_size=None", + "decoder_depth": "decoder_depth=None", + "decoder_num_heads": "decoder_num_heads=None", + "normalize_pixel_loss": "normalize_pixel_loss=True", + "mask_ratio": "mask_ratio=0.6", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "HubertModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_layer_norm": "feat_proj_layer_norm=True", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "conv_pos_batch_norm": "conv_pos_batch_norm=False", + "do_stable_layer_norm": "do_stable_layer_norm=False", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "ctc_loss_reduction": "ctc_loss_reduction='sum'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2" + }, + "HunYuanDenseV1Model": { + "vocab_size": "vocab_size: Optional[int] = 290943", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "eod_token_id": "eod_token_id: Optional[int] = 3", + "pretraining_tp": "pretraining_tp: Optional[int] = 1", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "head_dim": "head_dim: Optional[int] = None" + }, + "HunYuanMoEV1Model": { + "vocab_size": "vocab_size: Optional[int] = 290943", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "eod_token_id": "eod_token_id: Optional[int] = 3", + "sep_token_id": "sep_token_id: Optional[int] = 4", + "pretraining_tp": "pretraining_tp: Optional[int] = 1", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts": "num_experts: Union[int, list] = 1", + "moe_topk": "moe_topk: Union[int, list] = 1", + "head_dim": "head_dim: Optional[int] = None" + }, + "IBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "quant_mode": "quant_mode=False", + "force_dequant": "force_dequant='none'" + }, + "IdeficsModel": { + "vocab_size": "vocab_size=32000", + "additional_vocab_size": "additional_vocab_size=0", + "hidden_size": "hidden_size=4096", + "intermediate_size": "intermediate_size=11008", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=32", + "dropout": "dropout=0.0", + "hidden_act": "hidden_act='silu'", + "initializer_range": "initializer_range=0.02", + "alpha_initializer": "alpha_initializer='zeros'", + "alphas_initializer_range": "alphas_initializer_range=0.0", + "alpha_type": "alpha_type='float'", + "rms_norm_eps": "rms_norm_eps=1e-06", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "tie_word_embeddings": "tie_word_embeddings=False", + "cross_layer_interval": "cross_layer_interval=1", + "qk_layer_norms": "qk_layer_norms=False", + "freeze_text_layers": "freeze_text_layers=True", + "freeze_text_module_exceptions": "freeze_text_module_exceptions=[]", + "freeze_lm_head": "freeze_lm_head=False", + "freeze_vision_layers": "freeze_vision_layers=True", + "freeze_vision_module_exceptions": "freeze_vision_module_exceptions=[]", + "use_resampler": "use_resampler=False", + "vision_config": "vision_config=None", + "perceiver_config": "perceiver_config=None" + }, + "Idefics2Model": { + "image_token_id": "image_token_id=32001", + "tie_word_embeddings": "tie_word_embeddings=False", + "vision_config": "vision_config=None", + "perceiver_config": "perceiver_config=None", + "text_config": "text_config=None" + }, + "Idefics3Model": { + "image_token_id": "image_token_id=128257", + "tie_word_embeddings": "tie_word_embeddings=False", + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "scale_factor": "scale_factor=2", + "pad_token_id": "pad_token_id=128002" + }, + "Idefics3VisionTransformer": { + "hidden_size": "hidden_size=1152", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=16", + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "patch_size": "patch_size=32", + "hidden_act": "hidden_act='gelu_pytorch_tanh'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02" + }, + "IJepaModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "pooler_output_size": "pooler_output_size=None", + "pooler_act": "pooler_act='tanh'" + }, + "ImageGPTModel": { + "vocab_size": "vocab_size=513", + "n_positions": "n_positions=1024", + "n_embd": "n_embd=512", + "n_layer": "n_layer=24", + "n_head": "n_head=8", + "n_inner": "n_inner=None", + "activation_function": "activation_function='quick_gelu'", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "attn_pdrop": "attn_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "scale_attn_weights": "scale_attn_weights=True", + "tie_word_embeddings": "tie_word_embeddings=False", + "scale_attn_by_inverse_layer_idx": "scale_attn_by_inverse_layer_idx=False", + "reorder_and_upcast_attn": "reorder_and_upcast_attn=False" + }, + "InformerModel": { + "prediction_length": "prediction_length: Optional[int] = None", + "context_length": "context_length: Optional[int] = None", + "distribution_output": "distribution_output: str = 'student_t'", + "loss": "loss: str = 'nll'", + "input_size": "input_size: int = 1", + "lags_sequence": "lags_sequence: Optional[list[int]] = None", + "scaling": "scaling: Union[str, bool, NoneType] = 'mean'", + "num_dynamic_real_features": "num_dynamic_real_features: int = 0", + "num_static_real_features": "num_static_real_features: int = 0", + "num_static_categorical_features": "num_static_categorical_features: int = 0", + "num_time_features": "num_time_features: int = 0", + "cardinality": "cardinality: Optional[list[int]] = None", + "embedding_dimension": "embedding_dimension: Optional[list[int]] = None", + "d_model": "d_model: int = 64", + "encoder_ffn_dim": "encoder_ffn_dim: int = 32", + "decoder_ffn_dim": "decoder_ffn_dim: int = 32", + "encoder_attention_heads": "encoder_attention_heads: int = 2", + "decoder_attention_heads": "decoder_attention_heads: int = 2", + "encoder_layers": "encoder_layers: int = 2", + "decoder_layers": "decoder_layers: int = 2", + "is_encoder_decoder": "is_encoder_decoder: bool = True", + "activation_function": "activation_function: str = 'gelu'", + "dropout": "dropout: float = 0.05", + "encoder_layerdrop": "encoder_layerdrop: float = 0.1", + "decoder_layerdrop": "decoder_layerdrop: float = 0.1", + "attention_dropout": "attention_dropout: float = 0.1", + "activation_dropout": "activation_dropout: float = 0.1", + "num_parallel_samples": "num_parallel_samples: int = 100", + "init_std": "init_std: float = 0.02", + "attention_type": "attention_type: str = 'prob'", + "sampling_factor": "sampling_factor: int = 5", + "distil": "distil: bool = True" + }, + "InstructBlipModel": { + "vision_config": "vision_config=None", + "qformer_config": "qformer_config=None", + "text_config": "text_config=None", + "num_query_tokens": "num_query_tokens=32", + "image_token_index": "image_token_index=None" + }, + "InstructBlipVideoModel": { + "vision_config": "vision_config=None", + "qformer_config": "qformer_config=None", + "text_config": "text_config=None", + "num_query_tokens": "num_query_tokens=32", + "video_token_index": "video_token_index=None" + }, + "InternVLModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_id": "image_token_id=151667", + "image_seq_length": "image_seq_length=256", + "downsample_ratio": "downsample_ratio=0.5", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_layer": "vision_feature_layer=-1", + "vision_feature_select_strategy": "vision_feature_select_strategy='default'" + }, + "InternVLVisionModel": { + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "attention_bias": "attention_bias=False", + "use_qk_norm": "use_qk_norm=False", + "intermediate_size": "intermediate_size=4096", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_dropout": "attention_dropout=0.0", + "projection_dropout": "projection_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "norm_type": "norm_type='layer_norm'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=[448, 448]", + "patch_size": "patch_size=[14, 14]", + "num_channels": "num_channels=3", + "use_mask_token": "use_mask_token=False", + "use_absolute_position_embeddings": "use_absolute_position_embeddings=True", + "layer_scale_init_value": "layer_scale_init_value=0.1", + "use_mean_pooling": "use_mean_pooling=True" + }, + "Jais2Model": { + "vocab_size": "vocab_size: Optional[int] = 150272", + "hidden_size": "hidden_size: Optional[int] = 3328", + "intermediate_size": "intermediate_size: Optional[int] = 26624", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 26", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 150024", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "attention_bias": "attention_bias: Optional[bool] = True", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = True", + "head_dim": "head_dim: Optional[int] = None", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "JambaModel": { + "vocab_size": "vocab_size=65536", + "tie_word_embeddings": "tie_word_embeddings=False", + "hidden_size": "hidden_size=4096", + "intermediate_size": "intermediate_size=14336", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=32", + "num_key_value_heads": "num_key_value_heads=8", + "hidden_act": "hidden_act='silu'", + "initializer_range": "initializer_range=0.02", + "rms_norm_eps": "rms_norm_eps=1e-06", + "output_router_logits": "output_router_logits=False", + "router_aux_loss_coef": "router_aux_loss_coef=0.001", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "max_position_embeddings": "max_position_embeddings=262144", + "attention_dropout": "attention_dropout=0.0", + "num_experts_per_tok": "num_experts_per_tok=2", + "num_experts": "num_experts=16", + "expert_layer_period": "expert_layer_period=2", + "expert_layer_offset": "expert_layer_offset=1", + "attn_layer_period": "attn_layer_period=8", + "attn_layer_offset": "attn_layer_offset=4", + "use_mamba_kernels": "use_mamba_kernels=True", + "mamba_d_state": "mamba_d_state=16", + "mamba_d_conv": "mamba_d_conv=4", + "mamba_expand": "mamba_expand=2", + "mamba_dt_rank": "mamba_dt_rank='auto'", + "mamba_conv_bias": "mamba_conv_bias=True", + "mamba_proj_bias": "mamba_proj_bias=False" + }, + "JanusModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "vq_config": "vq_config=None", + "image_token_id": "image_token_id=100581" + }, + "JetMoeModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 2048", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 12", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 16", + "kv_channels": "kv_channels: Optional[int] = 128", + "intermediate_size": "intermediate_size: Optional[int] = 5632", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "activation_function": "activation_function: Optional[str] = 'silu'", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "aux_loss_coef": "aux_loss_coef: Optional[float] = 0.01", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "initializer_range": "initializer_range: Optional[float] = 0.01", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "Kosmos2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "latent_query_num": "latent_query_num=64" + }, + "XLMRobertaTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "add_prefix_space": "add_prefix_space: bool = True", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "sep_token": "sep_token: str = ''", + "cls_token": "cls_token: str = ''", + "unk_token": "unk_token: str = ''", + "pad_token": "pad_token: str = ''", + "mask_token": "mask_token: str = ''" + }, + "Kosmos2_5Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "latent_query_num": "latent_query_num=2048" + }, + "KyutaiSpeechToTextModel": { + "codebook_vocab_size": "codebook_vocab_size: Optional[int] = 2049", + "vocab_size": "vocab_size: Optional[int] = 4001", + "hidden_size": "hidden_size: Optional[int] = 2048", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 48", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 750", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "head_dim": "head_dim: Optional[int] = None", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "sliding_window": "sliding_window: Optional[int] = 375", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "ffn_dim": "ffn_dim: Optional[int] = 11264", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-08", + "num_codebooks": "num_codebooks: Optional[int] = 32", + "audio_bos_token_id": "audio_bos_token_id: Optional[int] = 2048", + "audio_pad_token_id": "audio_pad_token_id: Optional[int] = 69569", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "pad_token_id": "pad_token_id: Optional[int] = 3", + "bos_token_id": "bos_token_id: Optional[int] = 48000", + "codec_config": "codec_config: Optional[dict] = None" + }, + "LasrForCTC": { + "vocab_size": "vocab_size=512", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=True", + "encoder_config": "encoder_config: Union[dict, transformers.models.lasr.configuration_lasr.LasrEncoderConfig] = None", + "pad_token_id": "pad_token_id=0" + }, + "ParakeetTokenizerFast": { + "args": "*args" + }, + "LasrEncoder": { + "hidden_size": "hidden_size=512", + "num_hidden_layers": "num_hidden_layers=17", + "num_attention_heads": "num_attention_heads=8", + "intermediate_size": "intermediate_size=2048", + "hidden_act": "hidden_act='silu'", + "attention_bias": "attention_bias=False", + "convolution_bias": "convolution_bias=False", + "conv_kernel_size": "conv_kernel_size=32", + "subsampling_conv_channels": "subsampling_conv_channels=256", + "subsampling_conv_kernel_size": "subsampling_conv_kernel_size=5", + "subsampling_conv_stride": "subsampling_conv_stride=2", + "num_mel_bins": "num_mel_bins=128", + "dropout": "dropout=0.1", + "dropout_positions": "dropout_positions=0.0", + "layerdrop": "layerdrop=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "max_position_embeddings": "max_position_embeddings=10000", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "feed_forward_residual_weights": "feed_forward_residual_weights=[1.5, 0.5]", + "conv_residual_weights": "conv_residual_weights=[2.0, 1.0]", + "batch_norm_momentum": "batch_norm_momentum=0.01", + "rope_parameters": "rope_parameters=None" + }, + "LayoutLMModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "max_2d_position_embeddings": "max_2d_position_embeddings=1024" + }, + "LayoutLMv2Model": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "max_2d_position_embeddings": "max_2d_position_embeddings=1024", + "max_rel_pos": "max_rel_pos=128", + "rel_pos_bins": "rel_pos_bins=32", + "fast_qkv": "fast_qkv=True", + "max_rel_2d_pos": "max_rel_2d_pos=256", + "rel_2d_pos_bins": "rel_2d_pos_bins=64", + "convert_sync_batchnorm": "convert_sync_batchnorm=True", + "image_feature_pool_shape": "image_feature_pool_shape=[7, 7, 256]", + "coordinate_size": "coordinate_size=128", + "shape_size": "shape_size=128", + "has_relative_attention_bias": "has_relative_attention_bias=True", + "has_spatial_attention_bias": "has_spatial_attention_bias=True", + "has_visual_segment_embedding": "has_visual_segment_embedding=False", + "detectron2_config_args": "detectron2_config_args=None" + }, + "LayoutLMv2Tokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case=True", + "unk_token": "unk_token='[UNK]'", + "sep_token": "sep_token='[SEP]'", + "pad_token": "pad_token='[PAD]'", + "cls_token": "cls_token='[CLS]'", + "mask_token": "mask_token='[MASK]'", + "cls_token_box": "cls_token_box=[0, 0, 0, 0]", + "sep_token_box": "sep_token_box=[1000, 1000, 1000, 1000]", + "pad_token_box": "pad_token_box=[0, 0, 0, 0]", + "pad_token_label": "pad_token_label=-100", + "only_label_first_subword": "only_label_first_subword=True", + "tokenize_chinese_chars": "tokenize_chinese_chars=True", + "strip_accents": "strip_accents=None" + }, + "LayoutLMv3Model": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "max_2d_position_embeddings": "max_2d_position_embeddings=1024", + "coordinate_size": "coordinate_size=128", + "shape_size": "shape_size=128", + "has_relative_attention_bias": "has_relative_attention_bias=True", + "rel_pos_bins": "rel_pos_bins=32", + "max_rel_pos": "max_rel_pos=128", + "rel_2d_pos_bins": "rel_2d_pos_bins=64", + "max_rel_2d_pos": "max_rel_2d_pos=256", + "has_spatial_attention_bias": "has_spatial_attention_bias=True", + "text_embed": "text_embed=True", + "visual_embed": "visual_embed=True", + "input_size": "input_size=224", + "num_channels": "num_channels=3", + "patch_size": "patch_size=16", + "classifier_dropout": "classifier_dropout=None" + }, + "LayoutLMv3Tokenizer": { + "errors": "errors='replace'", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "add_prefix_space": "add_prefix_space=True", + "cls_token_box": "cls_token_box=[0, 0, 0, 0]", + "sep_token_box": "sep_token_box=[0, 0, 0, 0]", + "pad_token_box": "pad_token_box=[0, 0, 0, 0]", + "pad_token_label": "pad_token_label=-100", + "only_label_first_subword": "only_label_first_subword=True", + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None" + }, + "LEDModel": { + "vocab_size": "vocab_size=50265", + "max_encoder_position_embeddings": "max_encoder_position_embeddings=16384", + "max_decoder_position_embeddings": "max_decoder_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "classifier_dropout": "classifier_dropout=0.0", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "attention_window": "attention_window: Union[list[int], int] = 512" + }, + "LevitModel": { + "image_size": "image_size=224", + "num_channels": "num_channels=3", + "kernel_size": "kernel_size=3", + "stride": "stride=2", + "padding": "padding=1", + "patch_size": "patch_size=16", + "hidden_sizes": "hidden_sizes=[128, 256, 384]", + "num_attention_heads": "num_attention_heads=[4, 8, 12]", + "depths": "depths=[4, 4, 4]", + "key_dim": "key_dim=[16, 16, 16]", + "drop_path_rate": "drop_path_rate=0", + "mlp_ratio": "mlp_ratio=[2, 2, 2]", + "attention_ratio": "attention_ratio=[2, 2, 2]", + "initializer_range": "initializer_range=0.02" + }, + "Lfm2Model": { + "vocab_size": "vocab_size: Optional[int] = 65536", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 12288", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 128000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "norm_eps": "norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "conv_bias": "conv_bias: Optional[bool] = False", + "conv_L_cache": "conv_L_cache: Optional[int] = 3", + "block_multiple_of": "block_multiple_of: Optional[int] = 256", + "block_ffn_dim_multiplier": "block_ffn_dim_multiplier: Optional[float] = 1.0", + "block_auto_adjust_ff_dim": "block_auto_adjust_ff_dim: Optional[bool] = True", + "full_attn_idxs": "full_attn_idxs: Optional[list[int]] = None", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Lfm2MoeModel": { + "vocab_size": "vocab_size: int = 65536", + "hidden_size": "hidden_size: int = 2048", + "intermediate_size": "intermediate_size: int = 7168", + "moe_intermediate_size": "moe_intermediate_size: int = 1792", + "num_hidden_layers": "num_hidden_layers: int = 32", + "pad_token_id": "pad_token_id: int = 0", + "bos_token_id": "bos_token_id: int = 1", + "eos_token_id": "eos_token_id: int = 2", + "tie_word_embeddings": "tie_word_embeddings: bool = True", + "rope_parameters": "rope_parameters: transformers.modeling_rope_utils.RopeParameters = None", + "max_position_embeddings": "max_position_embeddings: int = 128000", + "initializer_range": "initializer_range: float = 0.02", + "norm_eps": "norm_eps: float = 1e-05", + "num_attention_heads": "num_attention_heads: int = 32", + "num_key_value_heads": "num_key_value_heads: int = 8", + "conv_bias": "conv_bias: bool = False", + "conv_L_cache": "conv_L_cache: int = 3", + "num_dense_layers": "num_dense_layers: int = 2", + "num_experts_per_tok": "num_experts_per_tok: int = 4", + "num_experts": "num_experts: int = 32", + "use_expert_bias": "use_expert_bias: bool = True", + "routed_scaling_factor": "routed_scaling_factor: float = 1.0", + "norm_topk_prob": "norm_topk_prob: bool = True", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Lfm2VlModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_id": "image_token_id=396", + "projector_hidden_act": "projector_hidden_act='gelu'", + "projector_hidden_size": "projector_hidden_size=2560", + "projector_bias": "projector_bias=True", + "projector_use_layernorm": "projector_use_layernorm=True", + "downsample_factor": "downsample_factor=2" + }, + "LightGlueForKeypointMatching": { + "keypoint_detector_config": "keypoint_detector_config: transformers.models.superpoint.configuration_superpoint.SuperPointConfig = None", + "descriptor_dim": "descriptor_dim: int = 256", + "num_hidden_layers": "num_hidden_layers: int = 9", + "num_attention_heads": "num_attention_heads: int = 4", + "num_key_value_heads": "num_key_value_heads=None", + "depth_confidence": "depth_confidence: float = 0.95", + "width_confidence": "width_confidence: float = 0.99", + "filter_threshold": "filter_threshold: float = 0.1", + "initializer_range": "initializer_range: float = 0.02", + "hidden_act": "hidden_act: str = 'gelu'", + "attention_dropout": "attention_dropout=0.0", + "attention_bias": "attention_bias=True", + "trust_remote_code": "trust_remote_code: bool = False" + }, + "LiltModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "classifier_dropout": "classifier_dropout=None", + "channel_shrink_ratio": "channel_shrink_ratio=4", + "max_2d_position_embeddings": "max_2d_position_embeddings=1024" + }, + "Llama4ForConditionalGeneration": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "boi_token_index": "boi_token_index=200080", + "eoi_token_index": "eoi_token_index=200081", + "image_token_index": "image_token_index=200092", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "Llama4TextModel": { + "vocab_size": "vocab_size=202048", + "hidden_size": "hidden_size=5120", + "intermediate_size": "intermediate_size=8192", + "intermediate_size_mlp": "intermediate_size_mlp=16384", + "num_hidden_layers": "num_hidden_layers=48", + "num_attention_heads": "num_attention_heads=40", + "num_key_value_heads": "num_key_value_heads=8", + "head_dim": "head_dim=128", + "hidden_act": "hidden_act='silu'", + "max_position_embeddings": "max_position_embeddings=131072", + "initializer_range": "initializer_range=0.02", + "rms_norm_eps": "rms_norm_eps=1e-05", + "pad_token_id": "pad_token_id=None", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "tie_word_embeddings": "tie_word_embeddings=False", + "attention_dropout": "attention_dropout=0.0", + "num_experts_per_tok": "num_experts_per_tok=1", + "num_local_experts": "num_local_experts=16", + "moe_layers": "moe_layers=None", + "interleave_moe_layer_step": "interleave_moe_layer_step=1", + "use_qk_norm": "use_qk_norm=True", + "output_router_logits": "output_router_logits=False", + "router_aux_loss_coef": "router_aux_loss_coef=0.001", + "router_jitter_noise": "router_jitter_noise=0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "no_rope_layers": "no_rope_layers=None", + "no_rope_layer_interval": "no_rope_layer_interval=4", + "attention_chunk_size": "attention_chunk_size=8192", + "layer_types": "layer_types=None", + "attn_temperature_tuning": "attn_temperature_tuning=True", + "floor_scale": "floor_scale=8192", + "attn_scale": "attn_scale=0.1" + }, + "LlavaModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=32000", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_select_strategy": "vision_feature_select_strategy='default'", + "vision_feature_layer": "vision_feature_layer=-2", + "image_seq_length": "image_seq_length=576", + "multimodal_projector_bias": "multimodal_projector_bias=True" + }, + "LlavaNextModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=32000", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_select_strategy": "vision_feature_select_strategy='default'", + "vision_feature_layer": "vision_feature_layer=-2", + "image_grid_pinpoints": "image_grid_pinpoints=None", + "tie_word_embeddings": "tie_word_embeddings=False", + "image_seq_length": "image_seq_length=576", + "multimodal_projector_bias": "multimodal_projector_bias=True" + }, + "LlavaNextVideoModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=32001", + "projector_hidden_act": "projector_hidden_act='gelu'", + "multimodal_projector_bias": "multimodal_projector_bias=True", + "vision_feature_select_strategy": "vision_feature_select_strategy='default'", + "vision_feature_layer": "vision_feature_layer=-2", + "image_grid_pinpoints": "image_grid_pinpoints=None", + "video_token_index": "video_token_index=32000", + "spatial_pool_mode": "spatial_pool_mode='average'", + "spatial_pool_stride": "spatial_pool_stride=2", + "image_seq_length": "image_seq_length=576", + "video_seq_length": "video_seq_length=288" + }, + "LlavaOnevisionModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=151646", + "video_token_index": "video_token_index=151647", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_select_strategy": "vision_feature_select_strategy='full'", + "vision_feature_layer": "vision_feature_layer=-1", + "vision_aspect_ratio": "vision_aspect_ratio='anyres_max_9'", + "image_grid_pinpoints": "image_grid_pinpoints=None", + "multimodal_projector_bias": "multimodal_projector_bias=True" + }, + "LongcatFlashModel": { + "vocab_size": "vocab_size: Optional[int] = 131072", + "hidden_size": "hidden_size: Optional[int] = 6144", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 56", + "num_layers": "num_layers: Optional[int] = 28", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "ffn_hidden_size": "ffn_hidden_size: Optional[int] = 12288", + "q_lora_rank": "q_lora_rank: Optional[int] = 1536", + "kv_lora_rank": "kv_lora_rank: Optional[int] = 512", + "qk_nope_head_dim": "qk_nope_head_dim: Optional[int] = 128", + "qk_rope_head_dim": "qk_rope_head_dim: Optional[int] = 64", + "head_dim": "head_dim: Optional[int] = 64", + "v_head_dim": "v_head_dim: Optional[int] = 128", + "qk_head_dim": "qk_head_dim: Optional[int] = None", + "moe_topk": "moe_topk: Optional[int] = 12", + "n_routed_experts": "n_routed_experts: Optional[int] = 512", + "zero_expert_num": "zero_expert_num: Optional[int] = 256", + "expert_ffn_hidden_size": "expert_ffn_hidden_size: Optional[int] = 2048", + "routed_scaling_factor": "routed_scaling_factor: Optional[float] = 6.0" + }, + "LongformerModel": { + "attention_window": "attention_window: Union[list[int], int] = 512", + "sep_token_id": "sep_token_id: int = 2", + "pad_token_id": "pad_token_id: int = 1", + "bos_token_id": "bos_token_id: int = 0", + "eos_token_id": "eos_token_id: int = 2", + "vocab_size": "vocab_size: int = 30522", + "hidden_size": "hidden_size: int = 768", + "num_hidden_layers": "num_hidden_layers: int = 12", + "num_attention_heads": "num_attention_heads: int = 12", + "intermediate_size": "intermediate_size: int = 3072", + "hidden_act": "hidden_act: str = 'gelu'", + "hidden_dropout_prob": "hidden_dropout_prob: float = 0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob: float = 0.1", + "max_position_embeddings": "max_position_embeddings: int = 512", + "type_vocab_size": "type_vocab_size: int = 2", + "initializer_range": "initializer_range: float = 0.02", + "layer_norm_eps": "layer_norm_eps: float = 1e-12", + "onnx_export": "onnx_export: bool = False" + }, + "LongT5Model": { + "vocab_size": "vocab_size=32128", + "d_model": "d_model=512", + "d_kv": "d_kv=64", + "d_ff": "d_ff=2048", + "num_layers": "num_layers=6", + "num_decoder_layers": "num_decoder_layers=None", + "num_heads": "num_heads=8", + "local_radius": "local_radius=127", + "global_block_size": "global_block_size=16", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_factor": "initializer_factor=1.0", + "feed_forward_proj": "feed_forward_proj='relu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "encoder_attention_type": "encoder_attention_type='local'", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1" + }, + "T5Tokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "extra_ids": "extra_ids=100", + "additional_special_tokens": "additional_special_tokens=None" + }, + "LukeModel": { + "vocab_size": "vocab_size=50267", + "entity_vocab_size": "entity_vocab_size=500000", + "hidden_size": "hidden_size=768", + "entity_emb_size": "entity_emb_size=256", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "use_entity_aware_attention": "use_entity_aware_attention=True", + "classifier_dropout": "classifier_dropout=None", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "LukeTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "entity_vocab": "entity_vocab: Union[str, dict, list, NoneType] = None", + "errors": "errors='replace'", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "add_prefix_space": "add_prefix_space=False", + "task": "task=None", + "max_entity_length": "max_entity_length=32", + "max_mention_length": "max_mention_length=30", + "entity_token_1": "entity_token_1=''", + "entity_token_2": "entity_token_2=''", + "entity_unk_token": "entity_unk_token='[UNK]'", + "entity_pad_token": "entity_pad_token='[PAD]'", + "entity_mask_token": "entity_mask_token='[MASK]'", + "entity_mask2_token": "entity_mask2_token='[MASK2]'" + }, + "LxmertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_attention_heads": "num_attention_heads=12", + "num_qa_labels": "num_qa_labels=9500", + "num_object_labels": "num_object_labels=1600", + "num_attr_labels": "num_attr_labels=400", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "l_layers": "l_layers=9", + "x_layers": "x_layers=5", + "r_layers": "r_layers=5", + "visual_feat_dim": "visual_feat_dim=2048", + "visual_pos_dim": "visual_pos_dim=4", + "visual_loss_normalizer": "visual_loss_normalizer=6.67", + "task_matched": "task_matched=True", + "task_mask_lm": "task_mask_lm=True", + "task_obj_predict": "task_obj_predict=True", + "task_qa": "task_qa=True", + "visual_obj_loss": "visual_obj_loss=True", + "visual_attr_loss": "visual_attr_loss=True", + "visual_feat_loss": "visual_feat_loss=True" + }, + "M2M100Model": { + "vocab_size": "vocab_size=128112", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.05", + "decoder_layerdrop": "decoder_layerdrop=0.05", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "scale_embedding": "scale_embedding=True", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "M2M100Tokenizer": { + "vocab_file": "vocab_file", + "spm_file": "spm_file", + "src_lang": "src_lang=None", + "tgt_lang": "tgt_lang=None", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''", + "unk_token": "unk_token=''", + "language_codes": "language_codes='m2m100'", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None", + "num_madeup_words": "num_madeup_words=8" + }, + "MambaModel": { + "vocab_size": "vocab_size=50280", + "hidden_size": "hidden_size=768", + "state_size": "state_size=16", + "num_hidden_layers": "num_hidden_layers=32", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=0", + "expand": "expand=2", + "conv_kernel": "conv_kernel=4", + "use_bias": "use_bias=False", + "use_conv_bias": "use_conv_bias=True", + "hidden_act": "hidden_act='silu'", + "initializer_range": "initializer_range=0.1", + "residual_in_fp32": "residual_in_fp32=True", + "time_step_rank": "time_step_rank='auto'", + "time_step_scale": "time_step_scale=1.0", + "time_step_min": "time_step_min=0.001", + "time_step_max": "time_step_max=0.1", + "time_step_init_scheme": "time_step_init_scheme='random'", + "time_step_floor": "time_step_floor=0.0001", + "rescale_prenorm_residual": "rescale_prenorm_residual=False", + "use_mambapy": "use_mambapy=False" + }, + "Mamba2Model": { + "num_heads": "num_heads=128", + "head_dim": "head_dim=64", + "vocab_size": "vocab_size=32768", + "hidden_size": "hidden_size=4096", + "state_size": "state_size=128", + "num_hidden_layers": "num_hidden_layers=64", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "expand": "expand=2", + "conv_kernel": "conv_kernel=4", + "n_groups": "n_groups=8", + "use_bias": "use_bias=False", + "use_conv_bias": "use_conv_bias=True", + "hidden_act": "hidden_act='silu'", + "initializer_range": "initializer_range=0.1", + "residual_in_fp32": "residual_in_fp32=True", + "time_step_rank": "time_step_rank='auto'", + "time_step_min": "time_step_min=0.001", + "time_step_max": "time_step_max=0.1", + "time_step_floor": "time_step_floor=0.0001", + "time_step_limit": "time_step_limit=(0.0, inf)", + "rescale_prenorm_residual": "rescale_prenorm_residual=False", + "rms_norm": "rms_norm=True", + "chunk_size": "chunk_size=256", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "MarianModel": { + "vocab_size": "vocab_size=58101", + "decoder_vocab_size": "decoder_vocab_size=None", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=58100", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=58100", + "eos_token_id": "eos_token_id=0", + "forced_eos_token_id": "forced_eos_token_id=0", + "share_encoder_decoder_embeddings": "share_encoder_decoder_embeddings=True" + }, + "MarianTokenizer": { + "source_spm": "source_spm", + "target_spm": "target_spm", + "vocab": "vocab", + "target_vocab_file": "target_vocab_file=None", + "source_lang": "source_lang=None", + "target_lang": "target_lang=None", + "unk_token": "unk_token=''", + "eos_token": "eos_token=''", + "pad_token": "pad_token=''", + "model_max_length": "model_max_length=512", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None", + "separate_vocabs": "separate_vocabs=False" + }, + "MarkupLMModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "max_xpath_tag_unit_embeddings": "max_xpath_tag_unit_embeddings=256", + "max_xpath_subs_unit_embeddings": "max_xpath_subs_unit_embeddings=1024", + "tag_pad_id": "tag_pad_id=216", + "subs_pad_id": "subs_pad_id=1001", + "xpath_unit_hidden_size": "xpath_unit_hidden_size=32", + "max_depth": "max_depth=50", + "classifier_dropout": "classifier_dropout=None" + }, + "Mask2FormerModel": { + "backbone_config": "backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "feature_size": "feature_size: int = 256", + "mask_feature_size": "mask_feature_size: int = 256", + "hidden_dim": "hidden_dim: int = 256", + "encoder_feedforward_dim": "encoder_feedforward_dim: int = 1024", + "activation_function": "activation_function: str = 'relu'", + "encoder_layers": "encoder_layers: int = 6", + "decoder_layers": "decoder_layers: int = 10", + "num_attention_heads": "num_attention_heads: int = 8", + "dropout": "dropout: float = 0.0", + "dim_feedforward": "dim_feedforward: int = 2048", + "pre_norm": "pre_norm: bool = False", + "enforce_input_projection": "enforce_input_projection: bool = False", + "common_stride": "common_stride: int = 4", + "ignore_value": "ignore_value: int = 255", + "num_queries": "num_queries: int = 100", + "no_object_weight": "no_object_weight: float = 0.1", + "class_weight": "class_weight: float = 2.0", + "mask_weight": "mask_weight: float = 5.0", + "dice_weight": "dice_weight: float = 5.0", + "train_num_points": "train_num_points: int = 12544", + "oversample_ratio": "oversample_ratio: float = 3.0", + "importance_sample_ratio": "importance_sample_ratio: float = 0.75", + "init_std": "init_std: float = 0.02", + "init_xavier_std": "init_xavier_std: float = 1.0", + "use_auxiliary_loss": "use_auxiliary_loss: bool = True", + "feature_strides": "feature_strides: list[int] = [4, 8, 16, 32]", + "output_auxiliary_logits": "output_auxiliary_logits: Optional[bool] = None", + "backbone": "backbone: Optional[str] = None", + "use_pretrained_backbone": "use_pretrained_backbone: bool = False", + "use_timm_backbone": "use_timm_backbone: bool = False", + "backbone_kwargs": "backbone_kwargs: Optional[dict] = None" + }, + "MaskFormerModel": { + "fpn_feature_size": "fpn_feature_size: int = 256", + "mask_feature_size": "mask_feature_size: int = 256", + "no_object_weight": "no_object_weight: float = 0.1", + "use_auxiliary_loss": "use_auxiliary_loss: bool = False", + "backbone_config": "backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "decoder_config": "decoder_config: Optional[dict] = None", + "init_std": "init_std: float = 0.02", + "init_xavier_std": "init_xavier_std: float = 1.0", + "dice_weight": "dice_weight: float = 1.0", + "cross_entropy_weight": "cross_entropy_weight: float = 1.0", + "mask_weight": "mask_weight: float = 20.0", + "output_auxiliary_logits": "output_auxiliary_logits: Optional[bool] = None", + "backbone": "backbone: Optional[str] = None", + "use_pretrained_backbone": "use_pretrained_backbone: bool = False", + "use_timm_backbone": "use_timm_backbone: bool = False", + "backbone_kwargs": "backbone_kwargs: Optional[dict] = None" + }, + "MaskFormerSwinModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=96", + "depths": "depths=[2, 2, 6, 2]", + "num_heads": "num_heads=[3, 6, 12, 24]", + "window_size": "window_size=7", + "mlp_ratio": "mlp_ratio=4.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "use_absolute_embeddings": "use_absolute_embeddings=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "MBartModel": { + "vocab_size": "vocab_size=50265", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "classifier_dropout": "classifier_dropout=0.0", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "forced_eos_token_id": "forced_eos_token_id=2" + }, + "MBartTokenizer": { + "vocab": "vocab: Union[str, dict, list, NoneType] = None", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "src_lang": "src_lang=None", + "tgt_lang": "tgt_lang=None", + "additional_special_tokens": "additional_special_tokens=None" + }, + "MegatronBertModel": { + "vocab_size": "vocab_size=29056", + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "intermediate_size": "intermediate_size=4096", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0" + }, + "MetaClip2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "MgpstrForSceneTextRecognition": { + "image_size": "image_size=[32, 128]", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "max_token_length": "max_token_length=27", + "num_character_labels": "num_character_labels=38", + "num_bpe_labels": "num_bpe_labels=50257", + "num_wordpiece_labels": "num_wordpiece_labels=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "mlp_ratio": "mlp_ratio=4.0", + "qkv_bias": "qkv_bias=True", + "distilled": "distilled=False", + "layer_norm_eps": "layer_norm_eps=1e-05", + "drop_rate": "drop_rate=0.0", + "attn_drop_rate": "attn_drop_rate=0.0", + "drop_path_rate": "drop_path_rate=0.0", + "output_a3_attentions": "output_a3_attentions=False", + "initializer_range": "initializer_range=0.02" + }, + "MgpstrTokenizer": { + "vocab_file": "vocab_file", + "unk_token": "unk_token='[GO]'", + "bos_token": "bos_token='[GO]'", + "eos_token": "eos_token='[s]'", + "pad_token": "pad_token='[GO]'" + }, + "MimiModel": { + "sampling_rate": "sampling_rate: Optional[int] = 24000", + "frame_rate": "frame_rate: Optional[int] = None", + "audio_channels": "audio_channels: Optional[int] = 1", + "hidden_size": "hidden_size: Optional[int] = 512", + "num_filters": "num_filters: Optional[int] = 64", + "num_residual_layers": "num_residual_layers: Optional[int] = 1", + "upsampling_ratios": "upsampling_ratios: Optional[list[int]] = None", + "kernel_size": "kernel_size: Optional[int] = 7", + "last_kernel_size": "last_kernel_size: Optional[int] = 3", + "residual_kernel_size": "residual_kernel_size: Optional[int] = 3", + "dilation_growth_rate": "dilation_growth_rate: Optional[int] = 2", + "use_causal_conv": "use_causal_conv: Optional[bool] = True", + "pad_mode": "pad_mode: Optional[str] = 'constant'", + "compress": "compress: Optional[int] = 2", + "trim_right_ratio": "trim_right_ratio: Optional[float] = 1.0", + "codebook_size": "codebook_size: Optional[int] = 2048", + "codebook_dim": "codebook_dim: Optional[int] = 256", + "num_quantizers": "num_quantizers: Optional[int] = 32", + "use_conv_shortcut": "use_conv_shortcut: Optional[bool] = False", + "vector_quantization_hidden_dimension": "vector_quantization_hidden_dimension: Optional[int] = 256", + "num_semantic_quantizers": "num_semantic_quantizers: Optional[int] = 1", + "upsample_groups": "upsample_groups: Optional[int] = 512", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 8", + "intermediate_size": "intermediate_size: Optional[int] = 2048", + "num_attention_heads": "num_attention_heads: Optional[int] = 8", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'gelu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "norm_eps": "norm_eps: Optional[int] = 1e-05", + "use_streaming": "use_streaming: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "sliding_window": "sliding_window: Optional[int] = 250", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "layer_scale_initial_scale": "layer_scale_initial_scale: Optional[float] = 0.01", + "attention_bias": "attention_bias: Optional[bool] = False" + }, + "MiniMaxModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "router_jitter_noise": "router_jitter_noise: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "layer_types": "layer_types: Optional[list[str]] = None", + "block_size": "block_size: Optional[int] = 256", + "full_attn_alpha_factor": "full_attn_alpha_factor: Optional[int] = 1", + "full_attn_beta_factor": "full_attn_beta_factor: Optional[int] = 1", + "linear_attn_alpha_factor": "linear_attn_alpha_factor: Optional[int] = 1", + "linear_attn_beta_factor": "linear_attn_beta_factor: Optional[int] = 1", + "mlp_alpha_factor": "mlp_alpha_factor: Optional[int] = 1", + "mlp_beta_factor": "mlp_beta_factor: Optional[int] = 1" + }, + "MinistralModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = None", + "sliding_window": "sliding_window: Optional[int] = 4096", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Ministral3Model": { + "vocab_size": "vocab_size: Optional[int] = 131072", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 34", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 262144", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 11", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "sliding_window": "sliding_window: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "MistralModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "sliding_window": "sliding_window: Optional[int] = 4096", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "Mistral3Model": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=10", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_layer": "vision_feature_layer=-1", + "multimodal_projector_bias": "multimodal_projector_bias=False", + "spatial_merge_size": "spatial_merge_size=2" + }, + "MixtralModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 14336", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "head_dim": "head_dim: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "num_local_experts": "num_local_experts: Optional[int] = 8", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "router_jitter_noise": "router_jitter_noise: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "MLCDVisionModel": { + "hidden_size": "hidden_size=1664", + "intermediate_size": "intermediate_size=8192", + "num_hidden_layers": "num_hidden_layers=48", + "num_attention_heads": "num_attention_heads=16", + "num_key_value_groups": "num_key_value_groups=1", + "num_channels": "num_channels=3", + "image_size": "image_size=336", + "patch_size": "patch_size=14", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-05", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02", + "initializer_factor": "initializer_factor=1.0" + }, + "MllamaModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=128256" + }, + "MMGroundingDinoModel": { + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "backbone_kwargs": "backbone_kwargs=None", + "text_config": "text_config=None", + "num_queries": "num_queries=900", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "num_feature_levels": "num_feature_levels=4", + "encoder_n_points": "encoder_n_points=4", + "decoder_n_points": "decoder_n_points=4", + "two_stage": "two_stage=True", + "class_cost": "class_cost=1.0", + "bbox_cost": "bbox_cost=5.0", + "giou_cost": "giou_cost=2.0", + "bbox_loss_coefficient": "bbox_loss_coefficient=5.0", + "giou_loss_coefficient": "giou_loss_coefficient=2.0", + "focal_alpha": "focal_alpha=0.25", + "disable_custom_kernels": "disable_custom_kernels=False", + "max_text_len": "max_text_len=256", + "text_enhancer_dropout": "text_enhancer_dropout=0.0", + "fusion_droppath": "fusion_droppath=0.1", + "fusion_dropout": "fusion_dropout=0.0", + "embedding_init_target": "embedding_init_target=True", + "query_dim": "query_dim=4", + "positional_embedding_temperature": "positional_embedding_temperature=20", + "init_std": "init_std=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05" + }, + "MobileBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=512", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=4", + "intermediate_size": "intermediate_size=512", + "hidden_act": "hidden_act='relu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "embedding_size": "embedding_size=128", + "trigram_input": "trigram_input=True", + "use_bottleneck": "use_bottleneck=True", + "intra_bottleneck_size": "intra_bottleneck_size=128", + "use_bottleneck_attention": "use_bottleneck_attention=False", + "key_query_shared_bottleneck": "key_query_shared_bottleneck=True", + "num_feedforward_networks": "num_feedforward_networks=4", + "normalization_type": "normalization_type='no_norm'", + "classifier_activation": "classifier_activation=True", + "classifier_dropout": "classifier_dropout=None" + }, + "MobileNetV1Model": { + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "depth_multiplier": "depth_multiplier=1.0", + "min_depth": "min_depth=8", + "hidden_act": "hidden_act='relu6'", + "tf_padding": "tf_padding=True", + "classifier_dropout_prob": "classifier_dropout_prob=0.999", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=0.001" + }, + "MobileNetV2Model": { + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "depth_multiplier": "depth_multiplier=1.0", + "depth_divisible_by": "depth_divisible_by=8", + "min_depth": "min_depth=8", + "expand_ratio": "expand_ratio=6.0", + "output_stride": "output_stride=32", + "first_layer_is_expansion": "first_layer_is_expansion=True", + "finegrained_output": "finegrained_output=True", + "hidden_act": "hidden_act='relu6'", + "tf_padding": "tf_padding=True", + "classifier_dropout_prob": "classifier_dropout_prob=0.8", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=0.001", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255" + }, + "MobileViTModel": { + "num_channels": "num_channels=3", + "image_size": "image_size=256", + "patch_size": "patch_size=2", + "hidden_sizes": "hidden_sizes=[144, 192, 240]", + "neck_hidden_sizes": "neck_hidden_sizes=[16, 32, 64, 96, 128, 160, 640]", + "num_attention_heads": "num_attention_heads=4", + "mlp_ratio": "mlp_ratio=2.0", + "expand_ratio": "expand_ratio=4.0", + "hidden_act": "hidden_act='silu'", + "conv_kernel_size": "conv_kernel_size=3", + "output_stride": "output_stride=32", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "qkv_bias": "qkv_bias=True", + "aspp_out_channels": "aspp_out_channels=256", + "atrous_rates": "atrous_rates=[6, 12, 18]", + "aspp_dropout_prob": "aspp_dropout_prob=0.1", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255" + }, + "MobileViTV2Model": { + "num_channels": "num_channels=3", + "image_size": "image_size=256", + "patch_size": "patch_size=2", + "expand_ratio": "expand_ratio=2.0", + "hidden_act": "hidden_act='swish'", + "conv_kernel_size": "conv_kernel_size=3", + "output_stride": "output_stride=32", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "aspp_out_channels": "aspp_out_channels=512", + "atrous_rates": "atrous_rates=[6, 12, 18]", + "aspp_dropout_prob": "aspp_dropout_prob=0.1", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255", + "n_attn_blocks": "n_attn_blocks=[2, 4, 3]", + "base_attn_unit_dims": "base_attn_unit_dims=[128, 192, 256]", + "width_multiplier": "width_multiplier=1.0", + "ffn_multiplier": "ffn_multiplier=2", + "attn_dropout": "attn_dropout=0.0", + "ffn_dropout": "ffn_dropout=0.0" + }, + "ModernBertModel": { + "vocab_size": "vocab_size: Optional[int] = 50368", + "hidden_size": "hidden_size: Optional[int] = 768", + "intermediate_size": "intermediate_size: Optional[int] = 1152", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 22", + "num_attention_heads": "num_attention_heads: Optional[int] = 12", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "initializer_cutoff_factor": "initializer_cutoff_factor: Optional[float] = 2.0", + "norm_eps": "norm_eps: Optional[int] = 1e-05", + "norm_bias": "norm_bias: Optional[bool] = False", + "pad_token_id": "pad_token_id: Optional[int] = 50283", + "eos_token_id": "eos_token_id: Optional[int] = 50282", + "bos_token_id": "bos_token_id: Optional[int] = 50281", + "cls_token_id": "cls_token_id: Optional[int] = 50281", + "sep_token_id": "sep_token_id: Optional[int] = 50282", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "layer_types": "layer_types: Optional[list[str]] = None", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "local_attention": "local_attention: Optional[int] = 128", + "embedding_dropout": "embedding_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "mlp_dropout": "mlp_dropout: Optional[float] = 0.0", + "decoder_bias": "decoder_bias: Optional[bool] = True", + "classifier_pooling": "classifier_pooling: Literal['cls', 'mean'] = 'cls'", + "classifier_dropout": "classifier_dropout: Optional[float] = 0.0", + "classifier_bias": "classifier_bias: Optional[bool] = False", + "classifier_activation": "classifier_activation: Optional[str] = 'gelu'", + "deterministic_flash_attn": "deterministic_flash_attn: Optional[bool] = False", + "sparse_prediction": "sparse_prediction: Optional[bool] = False", + "sparse_pred_ignore_index": "sparse_pred_ignore_index: Optional[int] = -100", + "reference_compile": "reference_compile: Optional[bool] = None", + "repad_logits_with_grad": "repad_logits_with_grad: Optional[bool] = False" + }, + "ModernBertDecoderModel": { + "vocab_size": "vocab_size: Optional[int] = 50368", + "hidden_size": "hidden_size: Optional[int] = 768", + "intermediate_size": "intermediate_size: Optional[int] = 1152", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 22", + "num_attention_heads": "num_attention_heads: Optional[int] = 12", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "initializer_cutoff_factor": "initializer_cutoff_factor: Optional[float] = 2.0", + "norm_eps": "norm_eps: Optional[int] = 1e-05", + "norm_bias": "norm_bias: Optional[bool] = False", + "pad_token_id": "pad_token_id: Optional[int] = 50283", + "eos_token_id": "eos_token_id: Optional[int] = 50282", + "bos_token_id": "bos_token_id: Optional[int] = 50281", + "cls_token_id": "cls_token_id: Optional[int] = 50281", + "sep_token_id": "sep_token_id: Optional[int] = 50282", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "embedding_dropout": "embedding_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "mlp_dropout": "mlp_dropout: Optional[float] = 0.0", + "decoder_bias": "decoder_bias: Optional[bool] = True", + "classifier_dropout": "classifier_dropout: Optional[float] = 0.0", + "classifier_bias": "classifier_bias: Optional[bool] = False", + "classifier_activation": "classifier_activation: Optional[str] = 'gelu'", + "local_attention": "local_attention: Optional[int] = 128", + "global_attn_every_n_layers": "global_attn_every_n_layers: Optional[int] = 3", + "layer_types": "layer_types: Optional[list[str]] = None", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None" + }, + "MoonshineModel": { + "vocab_size": "vocab_size: Optional[int] = 32768", + "hidden_size": "hidden_size: Optional[int] = 288", + "intermediate_size": "intermediate_size: Optional[int] = 1152", + "encoder_num_hidden_layers": "encoder_num_hidden_layers: Optional[int] = 6", + "decoder_num_hidden_layers": "decoder_num_hidden_layers: Optional[int] = 6", + "encoder_num_attention_heads": "encoder_num_attention_heads: Optional[int] = 8", + "decoder_num_attention_heads": "decoder_num_attention_heads: Optional[int] = 8", + "encoder_num_key_value_heads": "encoder_num_key_value_heads: Optional[int] = None", + "decoder_num_key_value_heads": "decoder_num_key_value_heads: Optional[int] = None", + "pad_head_dim_to_multiple_of": "pad_head_dim_to_multiple_of: Optional[int] = None", + "encoder_hidden_act": "encoder_hidden_act: Optional[str] = 'gelu'", + "decoder_hidden_act": "decoder_hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 512", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "decoder_start_token_id": "decoder_start_token_id: Optional[int] = 1", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "is_encoder_decoder": "is_encoder_decoder: Optional[bool] = True", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2" + }, + "MoshiModel": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "hidden_size": "hidden_size: Optional[int] = 4096", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "audio_vocab_size": "audio_vocab_size: Optional[int] = None", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 3000", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "head_dim": "head_dim: Optional[int] = None", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "sliding_window": "sliding_window: Optional[int] = 3000", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "ffn_dim": "ffn_dim: Optional[int] = 22528", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-08", + "num_codebooks": "num_codebooks: Optional[int] = 8", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False" + }, + "MPNetModel": { + "vocab_size": "vocab_size=30527", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "MPNetTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case=True", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token='[UNK]'", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "tokenize_chinese_chars": "tokenize_chinese_chars=True", + "strip_accents": "strip_accents=None" + }, + "MptModel": { + "d_model": "d_model: int = 2048", + "n_heads": "n_heads: int = 16", + "n_layers": "n_layers: int = 24", + "expansion_ratio": "expansion_ratio: int = 4", + "max_seq_len": "max_seq_len: int = 2048", + "vocab_size": "vocab_size: int = 50368", + "resid_pdrop": "resid_pdrop: float = 0.0", + "layer_norm_epsilon": "layer_norm_epsilon: float = 1e-05", + "emb_pdrop": "emb_pdrop: float = 0.0", + "learned_pos_emb": "learned_pos_emb: bool = True", + "attn_config": "attn_config: transformers.models.mpt.configuration_mpt.MptAttentionConfig = None", + "init_device": "init_device: str = 'cpu'", + "logit_scale": "logit_scale: Union[float, str, NoneType] = None", + "no_bias": "no_bias: bool = True", + "verbose": "verbose: int = 0", + "embedding_fraction": "embedding_fraction: float = 1.0", + "norm_type": "norm_type: str = 'low_precision_layernorm'", + "initializer_range": "initializer_range=0.02" + }, + "MraModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "block_per_row": "block_per_row=4", + "approx_mode": "approx_mode='full'", + "initial_prior_first_n_blocks": "initial_prior_first_n_blocks=0", + "initial_prior_diagonal_n_blocks": "initial_prior_diagonal_n_blocks=0", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "MT5Model": { + "vocab_size": "vocab_size=250112", + "d_model": "d_model=512", + "d_kv": "d_kv=64", + "d_ff": "d_ff=1024", + "num_layers": "num_layers=8", + "num_decoder_layers": "num_decoder_layers=None", + "num_heads": "num_heads=6", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_factor": "initializer_factor=1.0", + "feed_forward_proj": "feed_forward_proj='gated-gelu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "tokenizer_class": "tokenizer_class='T5Tokenizer'", + "tie_word_embeddings": "tie_word_embeddings=False", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "decoder_start_token_id": "decoder_start_token_id=0", + "classifier_dropout": "classifier_dropout=0.0" + }, + "MusicgenModel": { + "text_encoder": "text_encoder", + "audio_encoder": "audio_encoder", + "decoder": "decoder" + }, + "MusicgenMelodyModel": { + "text_encoder": "text_encoder", + "audio_encoder": "audio_encoder", + "decoder": "decoder", + "num_chroma": "num_chroma=12", + "chroma_length": "chroma_length=235" + }, + "MvpModel": { + "vocab_size": "vocab_size=50267", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "classifier_dropout": "classifier_dropout=0.0", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "is_encoder_decoder": "is_encoder_decoder=True", + "decoder_start_token_id": "decoder_start_token_id=2", + "use_prompt": "use_prompt=False", + "prompt_length": "prompt_length=100", + "prompt_mid_dim": "prompt_mid_dim=800" + }, + "NanoChatModel": { + "vocab_size": "vocab_size: int = 50304", + "hidden_size": "hidden_size: int = 768", + "intermediate_size": "intermediate_size: int | None = 8192", + "num_hidden_layers": "num_hidden_layers: int = 12", + "num_attention_heads": "num_attention_heads: int = 6", + "num_key_value_heads": "num_key_value_heads: int | None = None", + "max_position_embeddings": "max_position_embeddings: int = 2048", + "hidden_act": "hidden_act: str = 'relu2'", + "attention_dropout": "attention_dropout: float = 0.0", + "rms_norm_eps": "rms_norm_eps: float = 1e-06", + "initializer_range": "initializer_range: float = 0.02", + "rope_parameters": "rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None", + "final_logit_softcapping": "final_logit_softcapping: float | None = 15.0", + "attention_bias": "attention_bias: bool = False", + "bos_token_id": "bos_token_id: int = 0", + "eos_token_id": "eos_token_id: int = 1", + "pad_token_id": "pad_token_id: int = 1", + "tie_word_embeddings": "tie_word_embeddings: bool = False" + }, + "NemotronModel": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 6144", + "intermediate_size": "intermediate_size: Optional[int] = 24576", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 48", + "head_dim": "head_dim: Optional[int] = None", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.0134", + "norm_eps": "norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "eos_token_id": "eos_token_id: Optional[int] = 3", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False" + }, + "NllbMoeModel": { + "vocab_size": "vocab_size=128112", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.05", + "decoder_layerdrop": "decoder_layerdrop=0.05", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "scale_embedding": "scale_embedding=True", + "router_bias": "router_bias=False", + "router_dtype": "router_dtype='float32'", + "router_ignore_padding_tokens": "router_ignore_padding_tokens=False", + "num_experts": "num_experts=128", + "expert_capacity": "expert_capacity=64", + "encoder_sparse_step": "encoder_sparse_step=4", + "decoder_sparse_step": "decoder_sparse_step=4", + "router_z_loss_coef": "router_z_loss_coef=0.001", + "router_aux_loss_coef": "router_aux_loss_coef=0.001", + "second_expert_policy": "second_expert_policy='all'", + "normalize_router_prob_before_dropping": "normalize_router_prob_before_dropping=False", + "batch_prioritized_routing": "batch_prioritized_routing=False", + "moe_eval_capacity_token_fraction": "moe_eval_capacity_token_fraction=1.0", + "moe_token_dropout": "moe_token_dropout=0.2", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "output_router_logits": "output_router_logits=False" + }, + "NllbTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "src_lang": "src_lang=None", + "tgt_lang": "tgt_lang=None", + "additional_special_tokens": "additional_special_tokens=None", + "legacy_behaviour": "legacy_behaviour=False" + }, + "NystromformerModel": { + "vocab_size": "vocab_size=30000", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu_new'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=510", + "type_vocab_size": "type_vocab_size=2", + "segment_means_seq_len": "segment_means_seq_len=64", + "num_landmarks": "num_landmarks=64", + "conv_kernel_size": "conv_kernel_size=65", + "inv_coeff_init_option": "inv_coeff_init_option=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "OlmoModel": { + "vocab_size": "vocab_size: Optional[int] = 50304", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "pad_token_id": "pad_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = None", + "eos_token_id": "eos_token_id: Optional[int] = 50279", + "tie_word_embeddings": "tie_word_embeddings: Optional[int] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "clip_qkv": "clip_qkv: Optional[bool] = None" + }, + "Olmo2Model": { + "vocab_size": "vocab_size: Optional[int] = 50304", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "pad_token_id": "pad_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = None", + "eos_token_id": "eos_token_id: Optional[int] = 50279", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05" + }, + "Olmo3Model": { + "vocab_size": "vocab_size: Optional[int] = 50304", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "pad_token_id": "pad_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = None", + "eos_token_id": "eos_token_id: Optional[int] = 50279", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "sliding_window": "sliding_window: Optional[int] = 4096", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "OlmoeModel": { + "vocab_size": "vocab_size: Optional[int] = 50304", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 2048", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 16", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = None", + "eos_token_id": "eos_token_id: Optional[int] = 50279", + "tie_word_embeddings": "tie_word_embeddings: Optional[int] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "clip_qkv": "clip_qkv: Optional[bool] = None", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 8", + "num_experts": "num_experts: Optional[int] = 64", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.01", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False" + }, + "OmDetTurboForObjectDetection": { + "text_config": "text_config=None", + "backbone_config": "backbone_config=None", + "use_timm_backbone": "use_timm_backbone=True", + "backbone": "backbone='swin_tiny_patch4_window7_224'", + "backbone_kwargs": "backbone_kwargs=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "apply_layernorm_after_vision_backbone": "apply_layernorm_after_vision_backbone=True", + "image_size": "image_size=640", + "disable_custom_kernels": "disable_custom_kernels=False", + "layer_norm_eps": "layer_norm_eps=1e-05", + "batch_norm_eps": "batch_norm_eps=1e-05", + "init_std": "init_std=0.02", + "text_projection_in_dim": "text_projection_in_dim=512", + "text_projection_out_dim": "text_projection_out_dim=512", + "task_encoder_hidden_dim": "task_encoder_hidden_dim=1024", + "class_embed_dim": "class_embed_dim=512", + "class_distance_type": "class_distance_type='cosine'", + "num_queries": "num_queries=900", + "csp_activation": "csp_activation='silu'", + "conv_norm_activation": "conv_norm_activation='gelu'", + "encoder_feedforward_activation": "encoder_feedforward_activation='relu'", + "encoder_feedforward_dropout": "encoder_feedforward_dropout=0.0", + "encoder_dropout": "encoder_dropout=0.0", + "hidden_expansion": "hidden_expansion=1", + "vision_features_channels": "vision_features_channels=[256, 256, 256]", + "encoder_hidden_dim": "encoder_hidden_dim=256", + "encoder_in_channels": "encoder_in_channels=[192, 384, 768]", + "encoder_projection_indices": "encoder_projection_indices=[2]", + "encoder_attention_heads": "encoder_attention_heads=8", + "encoder_dim_feedforward": "encoder_dim_feedforward=2048", + "encoder_layers": "encoder_layers=1", + "positional_encoding_temperature": "positional_encoding_temperature=10000", + "num_feature_levels": "num_feature_levels=3", + "decoder_hidden_dim": "decoder_hidden_dim=256", + "decoder_num_heads": "decoder_num_heads=8", + "decoder_num_layers": "decoder_num_layers=6", + "decoder_activation": "decoder_activation='relu'", + "decoder_dim_feedforward": "decoder_dim_feedforward=2048", + "decoder_num_points": "decoder_num_points=4", + "decoder_dropout": "decoder_dropout=0.0", + "eval_size": "eval_size=None", + "learn_initial_query": "learn_initial_query=False", + "cache_size": "cache_size=100", + "is_encoder_decoder": "is_encoder_decoder=True" + }, + "OneFormerModel": { + "backbone_config": "backbone_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "backbone": "backbone: Optional[str] = None", + "use_pretrained_backbone": "use_pretrained_backbone: bool = False", + "use_timm_backbone": "use_timm_backbone: bool = False", + "backbone_kwargs": "backbone_kwargs: Optional[dict] = None", + "ignore_value": "ignore_value: int = 255", + "num_queries": "num_queries: int = 150", + "no_object_weight": "no_object_weight: int = 0.1", + "class_weight": "class_weight: float = 2.0", + "mask_weight": "mask_weight: float = 5.0", + "dice_weight": "dice_weight: float = 5.0", + "contrastive_weight": "contrastive_weight: float = 0.5", + "contrastive_temperature": "contrastive_temperature: float = 0.07", + "train_num_points": "train_num_points: int = 12544", + "oversample_ratio": "oversample_ratio: float = 3.0", + "importance_sample_ratio": "importance_sample_ratio: float = 0.75", + "init_std": "init_std: float = 0.02", + "init_xavier_std": "init_xavier_std: float = 1.0", + "layer_norm_eps": "layer_norm_eps: float = 1e-05", + "is_training": "is_training: bool = False", + "use_auxiliary_loss": "use_auxiliary_loss: bool = True", + "output_auxiliary_logits": "output_auxiliary_logits: bool = True", + "strides": "strides: Optional[list] = [4, 8, 16, 32]", + "task_seq_len": "task_seq_len: int = 77", + "text_encoder_width": "text_encoder_width: int = 256", + "text_encoder_context_length": "text_encoder_context_length: int = 77", + "text_encoder_num_layers": "text_encoder_num_layers: int = 6", + "text_encoder_vocab_size": "text_encoder_vocab_size: int = 49408", + "text_encoder_proj_layers": "text_encoder_proj_layers: int = 2", + "text_encoder_n_ctx": "text_encoder_n_ctx: int = 16", + "conv_dim": "conv_dim: int = 256", + "mask_dim": "mask_dim: int = 256", + "hidden_dim": "hidden_dim: int = 256", + "encoder_feedforward_dim": "encoder_feedforward_dim: int = 1024", + "norm": "norm: str = 'GN'", + "encoder_layers": "encoder_layers: int = 6", + "decoder_layers": "decoder_layers: int = 10", + "use_task_norm": "use_task_norm: bool = True", + "num_attention_heads": "num_attention_heads: int = 8", + "dropout": "dropout: float = 0.1", + "dim_feedforward": "dim_feedforward: int = 2048", + "pre_norm": "pre_norm: bool = False", + "enforce_input_proj": "enforce_input_proj: bool = False", + "query_dec_layers": "query_dec_layers: int = 2", + "common_stride": "common_stride: int = 4" + }, + "OpenAIGPTModel": { + "vocab_size": "vocab_size=40478", + "n_positions": "n_positions=512", + "n_embd": "n_embd=768", + "n_layer": "n_layer=12", + "n_head": "n_head=12", + "afn": "afn='gelu'", + "resid_pdrop": "resid_pdrop=0.1", + "embd_pdrop": "embd_pdrop=0.1", + "attn_pdrop": "attn_pdrop=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "initializer_range": "initializer_range=0.02", + "summary_type": "summary_type='cls_index'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation=None", + "summary_proj_to_labels": "summary_proj_to_labels=True", + "summary_first_dropout": "summary_first_dropout=0.1" + }, + "OpenAIGPTTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "unk_token": "unk_token: str = ''" + }, + "OPTModel": { + "vocab_size": "vocab_size=50272", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "ffn_dim": "ffn_dim=3072", + "max_position_embeddings": "max_position_embeddings=2048", + "do_layer_norm_before": "do_layer_norm_before=True", + "_remove_final_layer_norm": "_remove_final_layer_norm=False", + "word_embed_proj_dim": "word_embed_proj_dim=None", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "num_attention_heads": "num_attention_heads=12", + "activation_function": "activation_function='relu'", + "layerdrop": "layerdrop=0.0", + "init_std": "init_std=0.02", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=2", + "enable_bias": "enable_bias=True", + "layer_norm_elementwise_affine": "layer_norm_elementwise_affine=True" + }, + "Ovis2Model": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_id": "image_token_id=151665", + "visual_indicator_token_ids": "visual_indicator_token_ids=[151666, 151667, 151668, 151669, 151670]", + "vocab_size": "vocab_size=151643", + "hidden_size": "hidden_size=1536" + }, + "Owlv2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592", + "return_dict": "return_dict=True" + }, + "OwlViTModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592", + "return_dict": "return_dict=True" + }, + "PaliGemmaModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=256000", + "vocab_size": "vocab_size=257152", + "projection_dim": "projection_dim=2048", + "hidden_size": "hidden_size=2048" + }, + "ParakeetForCTC": { + "vocab_size": "vocab_size=1025", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=True", + "encoder_config": "encoder_config: Union[dict, transformers.models.parakeet.configuration_parakeet.ParakeetEncoderConfig] = None", + "pad_token_id": "pad_token_id=1024" + }, + "ParakeetEncoder": { + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=8", + "intermediate_size": "intermediate_size=4096", + "hidden_act": "hidden_act='silu'", + "attention_bias": "attention_bias=True", + "convolution_bias": "convolution_bias=True", + "conv_kernel_size": "conv_kernel_size=9", + "subsampling_factor": "subsampling_factor=8", + "subsampling_conv_channels": "subsampling_conv_channels=256", + "num_mel_bins": "num_mel_bins=80", + "subsampling_conv_kernel_size": "subsampling_conv_kernel_size=3", + "subsampling_conv_stride": "subsampling_conv_stride=2", + "dropout": "dropout=0.1", + "dropout_positions": "dropout_positions=0.0", + "layerdrop": "layerdrop=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "max_position_embeddings": "max_position_embeddings=5000", + "scale_input": "scale_input=True", + "initializer_range": "initializer_range=0.02" + }, + "PatchTSMixerModel": { + "context_length": "context_length: int = 32", + "patch_length": "patch_length: int = 8", + "num_input_channels": "num_input_channels: int = 1", + "patch_stride": "patch_stride: int = 8", + "num_parallel_samples": "num_parallel_samples: int = 100", + "d_model": "d_model: int = 8", + "expansion_factor": "expansion_factor: int = 2", + "num_layers": "num_layers: int = 3", + "dropout": "dropout: float = 0.2", + "mode": "mode: str = 'common_channel'", + "gated_attn": "gated_attn: bool = True", + "norm_mlp": "norm_mlp: str = 'LayerNorm'", + "self_attn": "self_attn: bool = False", + "self_attn_heads": "self_attn_heads: int = 1", + "use_positional_encoding": "use_positional_encoding: bool = False", + "positional_encoding_type": "positional_encoding_type: str = 'sincos'", + "scaling": "scaling: Union[str, bool, NoneType] = 'std'", + "loss": "loss: str = 'mse'", + "init_std": "init_std: float = 0.02", + "post_init": "post_init: bool = False", + "norm_eps": "norm_eps: float = 1e-05", + "mask_type": "mask_type: str = 'random'", + "random_mask_ratio": "random_mask_ratio: float = 0.5", + "num_forecast_mask_patches": "num_forecast_mask_patches: Union[int, list[int], NoneType] = [2]", + "mask_value": "mask_value: int = 0", + "masked_loss": "masked_loss: bool = True", + "channel_consistent_masking": "channel_consistent_masking: bool = True", + "unmasked_channel_indices": "unmasked_channel_indices: Optional[list[int]] = None", + "head_dropout": "head_dropout: float = 0.2", + "distribution_output": "distribution_output: str = 'student_t'", + "prediction_length": "prediction_length: int = 16", + "prediction_channel_indices": "prediction_channel_indices: Optional[list] = None", + "num_targets": "num_targets: int = 3", + "output_range": "output_range: Optional[list] = None", + "head_aggregation": "head_aggregation: str = 'max_pool'" + }, + "PatchTSTModel": { + "num_input_channels": "num_input_channels: int = 1", + "context_length": "context_length: int = 32", + "distribution_output": "distribution_output: str = 'student_t'", + "loss": "loss: str = 'mse'", + "patch_length": "patch_length: int = 1", + "patch_stride": "patch_stride: int = 1", + "num_hidden_layers": "num_hidden_layers: int = 3", + "d_model": "d_model: int = 128", + "num_attention_heads": "num_attention_heads: int = 4", + "share_embedding": "share_embedding: bool = True", + "channel_attention": "channel_attention: bool = False", + "ffn_dim": "ffn_dim: int = 512", + "norm_type": "norm_type: str = 'batchnorm'", + "norm_eps": "norm_eps: float = 1e-05", + "attention_dropout": "attention_dropout: float = 0.0", + "positional_dropout": "positional_dropout: float = 0.0", + "path_dropout": "path_dropout: float = 0.0", + "ff_dropout": "ff_dropout: float = 0.0", + "bias": "bias: bool = True", + "activation_function": "activation_function: str = 'gelu'", + "pre_norm": "pre_norm: bool = True", + "positional_encoding_type": "positional_encoding_type: str = 'sincos'", + "use_cls_token": "use_cls_token: bool = False", + "init_std": "init_std: float = 0.02", + "share_projection": "share_projection: bool = True", + "scaling": "scaling: Union[str, bool, NoneType] = 'std'", + "do_mask_input": "do_mask_input: Optional[bool] = None", + "mask_type": "mask_type: str = 'random'", + "random_mask_ratio": "random_mask_ratio: float = 0.5", + "num_forecast_mask_patches": "num_forecast_mask_patches: Union[int, list[int], NoneType] = [2]", + "channel_consistent_masking": "channel_consistent_masking: Optional[bool] = False", + "unmasked_channel_indices": "unmasked_channel_indices: Optional[list[int]] = None", + "mask_value": "mask_value: int = 0", + "pooling_type": "pooling_type: str = 'mean'", + "head_dropout": "head_dropout: float = 0.0", + "prediction_length": "prediction_length: int = 24", + "num_targets": "num_targets: int = 1", + "output_range": "output_range: Optional[list] = None", + "num_parallel_samples": "num_parallel_samples: int = 100" + }, + "PeAudioModel": { + "text_config": "text_config=None", + "audio_config": "audio_config=None" + }, + "PeAudioEncoder": { + "dac_config": "dac_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "hidden_size": "hidden_size: Optional[int] = 1792", + "intermediate_size": "intermediate_size: Optional[int] = 4800", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 6", + "num_attention_heads": "num_attention_heads: Optional[int] = 14", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 10000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "PeAudioVideoModel": { + "text_config": "text_config=None", + "audio_video_config": "audio_video_config=None" + }, + "PeAudioVideoEncoder": { + "audio_config": "audio_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "video_config": "video_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "hidden_size": "hidden_size: Optional[int] = 1792", + "intermediate_size": "intermediate_size: Optional[int] = 4800", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 6", + "num_attention_heads": "num_attention_heads: Optional[int] = 14", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 10000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "PeVideoModel": { + "text_config": "text_config=None", + "video_config": "video_config=None" + }, + "PeVideoEncoder": { + "vision_config": "vision_config: Union[dict, transformers.configuration_utils.PreTrainedConfig, NoneType] = None", + "hidden_size": "hidden_size: Optional[int] = 1792", + "intermediate_size": "intermediate_size: Optional[int] = 4800", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 6", + "num_attention_heads": "num_attention_heads: Optional[int] = 14", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 10000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-05", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict, NoneType] = {'rope_theta': 20000}", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "PegasusModel": { + "vocab_size": "vocab_size=50265", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=12", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=0", + "scale_embedding": "scale_embedding=False", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "forced_eos_token_id": "forced_eos_token_id=1" + }, + "PegasusXModel": { + "vocab_size": "vocab_size=96103", + "max_position_embeddings": "max_position_embeddings=16384", + "encoder_layers": "encoder_layers=16", + "encoder_ffn_dim": "encoder_ffn_dim=4096", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=16", + "decoder_ffn_dim": "decoder_ffn_dim=4096", + "decoder_attention_heads": "decoder_attention_heads=16", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=0", + "scale_embedding": "scale_embedding=True", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "forced_eos_token_id": "forced_eos_token_id=1", + "num_global_tokens": "num_global_tokens=32", + "block_size": "block_size=512", + "stagger_local_blocks": "stagger_local_blocks=True" + }, + "PerceiverModel": { + "num_latents": "num_latents=256", + "d_latents": "d_latents=1280", + "d_model": "d_model=768", + "num_blocks": "num_blocks=1", + "num_self_attends_per_block": "num_self_attends_per_block=26", + "num_self_attention_heads": "num_self_attention_heads=8", + "num_cross_attention_heads": "num_cross_attention_heads=8", + "qk_channels": "qk_channels=None", + "v_channels": "v_channels=None", + "cross_attention_shape_for_attention": "cross_attention_shape_for_attention='kv'", + "self_attention_widening_factor": "self_attention_widening_factor=1", + "cross_attention_widening_factor": "cross_attention_widening_factor=1", + "hidden_act": "hidden_act='gelu'", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "use_query_residual": "use_query_residual=True", + "vocab_size": "vocab_size=262", + "max_position_embeddings": "max_position_embeddings=2048", + "image_size": "image_size=56", + "train_size": "train_size=[368, 496]", + "num_frames": "num_frames=16", + "audio_samples_per_frame": "audio_samples_per_frame=1920", + "samples_per_patch": "samples_per_patch=16", + "output_shape": "output_shape=[1, 16, 224, 224]", + "output_num_channels": "output_num_channels=512", + "_label_trainable_num_channels": "_label_trainable_num_channels=1024" + }, + "PerceiverTokenizer": { + "pad_token": "pad_token='[PAD]'", + "bos_token": "bos_token='[BOS]'", + "eos_token": "eos_token='[EOS]'", + "mask_token": "mask_token='[MASK]'", + "cls_token": "cls_token='[CLS]'", + "sep_token": "sep_token='[SEP]'", + "model_max_length": "model_max_length=2048" + }, + "PerceptionLMModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "vision_use_cls_token": "vision_use_cls_token=True", + "projector_pooling_ratio": "projector_pooling_ratio=1", + "image_token_id": "image_token_id=128002", + "video_token_id": "video_token_id=128003" + }, + "PersimmonModel": { + "vocab_size": "vocab_size: Optional[int] = 262144", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 16384", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 36", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "hidden_act": "hidden_act: Optional[str] = 'relu2'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 16384", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "qk_layernorm": "qk_layernorm: Optional[bool] = True", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2" + }, + "PhiModel": { + "vocab_size": "vocab_size: Optional[int] = 51200", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 8192", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "resid_pdrop": "resid_pdrop: Optional[float] = 0.0", + "embd_pdrop": "embd_pdrop: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "hidden_act": "hidden_act: Optional[str] = 'gelu_new'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 2048", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "qk_layernorm": "qk_layernorm: Optional[bool] = False", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2" + }, + "Phi3Model": { + "vocab_size": "vocab_size: Optional[int] = 32064", + "hidden_size": "hidden_size: Optional[int] = 3072", + "intermediate_size": "intermediate_size: Optional[int] = 8192", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "resid_pdrop": "resid_pdrop: Optional[float] = 0.0", + "embd_pdrop": "embd_pdrop: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "original_max_position_embeddings": "original_max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 32000", + "pad_token_id": "pad_token_id: Optional[int] = 32000", + "sliding_window": "sliding_window: Optional[int] = None" + }, + "Phi4MultimodalModel": { + "vocab_size": "vocab_size: Optional[int] = 200064", + "hidden_size": "hidden_size: Optional[int] = 3072", + "intermediate_size": "intermediate_size: Optional[int] = 8192", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "resid_pdrop": "resid_pdrop: Optional[float] = 0.0", + "embd_pdrop": "embd_pdrop: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "bos_token_id": "bos_token_id: Optional[int] = 199999", + "eos_token_id": "eos_token_id: Optional[list[int]] = [199999, 200020]", + "pad_token_id": "pad_token_id: Optional[int] = 199999", + "original_max_position_embeddings": "original_max_position_embeddings: Optional[int] = 4096", + "sliding_window": "sliding_window: Optional[int] = None", + "vision_config": "vision_config: Optional[dict] = None", + "audio_config": "audio_config: Optional[dict] = None" + }, + "PhimoeModel": { + "vocab_size": "vocab_size: Optional[int] = 32064", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 6400", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 131072", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "pad_token_id": "pad_token_id: Optional[int] = None", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[int] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "sliding_window": "sliding_window: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 2", + "num_local_experts": "num_local_experts: Optional[int] = 16", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "router_jitter_noise": "router_jitter_noise: Optional[float] = 0.01", + "input_jitter_noise": "input_jitter_noise: Optional[float] = 0.0", + "attention_bias": "attention_bias: Optional[bool] = False", + "lm_head_bias": "lm_head_bias: Optional[bool] = False" + }, + "PixioModel": { + "hidden_size": "hidden_size=1280", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=16", + "mlp_ratio": "mlp_ratio=4", + "n_cls_tokens": "n_cls_tokens=8", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=256", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "drop_path_rate": "drop_path_rate=0.0", + "out_features": "out_features=None", + "out_indices": "out_indices=None", + "apply_layernorm": "apply_layernorm=True", + "reshape_hidden_states": "reshape_hidden_states=True" + }, + "PixtralVisionModel": { + "hidden_size": "hidden_size: Optional[int] = 1024", + "intermediate_size": "intermediate_size: Optional[int] = 4096", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_channels": "num_channels: Optional[int] = 3", + "image_size": "image_size: Optional[int] = 1024", + "patch_size": "patch_size: Optional[int] = 16", + "hidden_act": "hidden_act: Optional[str] = 'gelu'", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "initializer_range": "initializer_range: Optional[float] = 0.02" + }, + "PLBartModel": { + "vocab_size": "vocab_size=50005", + "max_position_embeddings": "max_position_embeddings=1024", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=3072", + "encoder_attention_heads": "encoder_attention_heads=12", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=3072", + "decoder_attention_heads": "decoder_attention_heads=12", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=768", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "classifier_dropout": "classifier_dropout=0.0", + "scale_embedding": "scale_embedding=True", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "forced_eos_token_id": "forced_eos_token_id=2" + }, + "PLBartTokenizer": { + "vocab_file": "vocab_file", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "mask_token": "mask_token=''", + "language_codes": "language_codes='base'", + "src_lang": "src_lang=None", + "tgt_lang": "tgt_lang=None", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None", + "additional_special_tokens": "additional_special_tokens=None", + "clean_up_tokenization_spaces": "clean_up_tokenization_spaces=True" + }, + "PoolFormerModel": { + "num_channels": "num_channels=3", + "patch_size": "patch_size=16", + "stride": "stride=16", + "pool_size": "pool_size=3", + "mlp_ratio": "mlp_ratio=4.0", + "depths": "depths=[2, 2, 6, 2]", + "hidden_sizes": "hidden_sizes=[64, 128, 320, 512]", + "patch_sizes": "patch_sizes=[7, 3, 3, 3]", + "strides": "strides=[4, 2, 2, 2]", + "padding": "padding=[2, 1, 1, 1]", + "num_encoder_blocks": "num_encoder_blocks=4", + "drop_path_rate": "drop_path_rate=0.0", + "hidden_act": "hidden_act='gelu'", + "use_layer_scale": "use_layer_scale=True", + "layer_scale_init_value": "layer_scale_init_value=1e-05", + "initializer_range": "initializer_range=0.02" + }, + "ProphetNetModel": { + "activation_dropout": "activation_dropout: Optional[float] = 0.1", + "activation_function": "activation_function: Union[str, collections.abc.Callable, NoneType] = 'gelu'", + "vocab_size": "vocab_size: Optional[int] = 30522", + "hidden_size": "hidden_size: Optional[int] = 1024", + "encoder_ffn_dim": "encoder_ffn_dim: Optional[int] = 4096", + "num_encoder_layers": "num_encoder_layers: Optional[int] = 12", + "num_encoder_attention_heads": "num_encoder_attention_heads: Optional[int] = 16", + "decoder_ffn_dim": "decoder_ffn_dim: Optional[int] = 4096", + "num_decoder_layers": "num_decoder_layers: Optional[int] = 12", + "num_decoder_attention_heads": "num_decoder_attention_heads: Optional[int] = 16", + "attention_dropout": "attention_dropout: Optional[float] = 0.1", + "dropout": "dropout: Optional[float] = 0.1", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 512", + "init_std": "init_std: Optional[float] = 0.02", + "is_encoder_decoder": "is_encoder_decoder: Optional[bool] = True", + "add_cross_attention": "add_cross_attention: Optional[bool] = True", + "decoder_start_token_id": "decoder_start_token_id: Optional[int] = 0", + "ngram": "ngram: Optional[int] = 2", + "num_buckets": "num_buckets: Optional[int] = 32", + "relative_max_distance": "relative_max_distance: Optional[int] = 128", + "disable_ngram_loss": "disable_ngram_loss: Optional[bool] = False", + "eps": "eps: Optional[float] = 0.0", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2" + }, + "ProphetNetTokenizer": { + "vocab_file": "vocab_file: str", + "do_lower_case": "do_lower_case: Optional[bool] = True", + "do_basic_tokenize": "do_basic_tokenize: Optional[bool] = True", + "never_split": "never_split: Optional[collections.abc.Iterable] = None", + "unk_token": "unk_token: Optional[str] = '[UNK]'", + "sep_token": "sep_token: Optional[str] = '[SEP]'", + "x_sep_token": "x_sep_token: Optional[str] = '[X_SEP]'", + "pad_token": "pad_token: Optional[str] = '[PAD]'", + "mask_token": "mask_token: Optional[str] = '[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars: Optional[bool] = True", + "strip_accents": "strip_accents: Optional[bool] = None", + "clean_up_tokenization_spaces": "clean_up_tokenization_spaces: bool = True" + }, + "PvtModel": { + "image_size": "image_size: int = 224", + "num_channels": "num_channels: int = 3", + "num_encoder_blocks": "num_encoder_blocks: int = 4", + "depths": "depths: list[int] = [2, 2, 2, 2]", + "sequence_reduction_ratios": "sequence_reduction_ratios: list[int] = [8, 4, 2, 1]", + "hidden_sizes": "hidden_sizes: list[int] = [64, 128, 320, 512]", + "patch_sizes": "patch_sizes: list[int] = [4, 2, 2, 2]", + "strides": "strides: list[int] = [4, 2, 2, 2]", + "num_attention_heads": "num_attention_heads: list[int] = [1, 2, 5, 8]", + "mlp_ratios": "mlp_ratios: list[int] = [8, 8, 4, 4]", + "hidden_act": "hidden_act: collections.abc.Mapping[str, collections.abc.Callable] = 'gelu'", + "hidden_dropout_prob": "hidden_dropout_prob: float = 0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob: float = 0.0", + "initializer_range": "initializer_range: float = 0.02", + "drop_path_rate": "drop_path_rate: float = 0.0", + "layer_norm_eps": "layer_norm_eps: float = 1e-06", + "qkv_bias": "qkv_bias: bool = True", + "num_labels": "num_labels: int = 1000" + }, + "PvtV2Model": { + "image_size": "image_size: Union[int, tuple[int, int]] = 224", + "num_channels": "num_channels: int = 3", + "num_encoder_blocks": "num_encoder_blocks: int = 4", + "depths": "depths: list[int] = [2, 2, 2, 2]", + "sr_ratios": "sr_ratios: list[int] = [8, 4, 2, 1]", + "hidden_sizes": "hidden_sizes: list[int] = [32, 64, 160, 256]", + "patch_sizes": "patch_sizes: list[int] = [7, 3, 3, 3]", + "strides": "strides: list[int] = [4, 2, 2, 2]", + "num_attention_heads": "num_attention_heads: list[int] = [1, 2, 5, 8]", + "mlp_ratios": "mlp_ratios: list[int] = [8, 8, 4, 4]", + "hidden_act": "hidden_act: Union[str, collections.abc.Callable] = 'gelu'", + "hidden_dropout_prob": "hidden_dropout_prob: float = 0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob: float = 0.0", + "initializer_range": "initializer_range: float = 0.02", + "drop_path_rate": "drop_path_rate: float = 0.0", + "layer_norm_eps": "layer_norm_eps: float = 1e-06", + "qkv_bias": "qkv_bias: bool = True", + "linear_attention": "linear_attention: bool = False", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "Qwen2Model": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 22016", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 28", + "layer_types": "layer_types: Optional[list[str]] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "Qwen2_5_VLModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151655", + "video_token_id": "video_token_id=151656", + "vision_start_token_id": "vision_start_token_id=151652", + "vision_end_token_id": "vision_end_token_id=151653" + }, + "Qwen2_5_VLTextModel": { + "vocab_size": "vocab_size: Optional[int] = 152064", + "hidden_size": "hidden_size: Optional[int] = 8192", + "intermediate_size": "intermediate_size: Optional[int] = 29568", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 80", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 80", + "layer_types": "layer_types: Optional[list[str]] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "bos_token_id": "bos_token_id: Optional[int] = 151643", + "eos_token_id": "eos_token_id: Optional[int] = 151645", + "pad_token_id": "pad_token_id: Optional[int] = None" + }, + "Qwen2AudioEncoder": { + "num_mel_bins": "num_mel_bins=128", + "encoder_layers": "encoder_layers=32", + "encoder_attention_heads": "encoder_attention_heads=20", + "encoder_ffn_dim": "encoder_ffn_dim=5120", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "d_model": "d_model=1280", + "dropout": "dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "activation_function": "activation_function='gelu'", + "activation_dropout": "activation_dropout=0.0", + "scale_embedding": "scale_embedding=False", + "initializer_range": "initializer_range=0.02", + "max_source_positions": "max_source_positions=1500" + }, + "Qwen2MoeModel": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 5632", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 16", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 28", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "decoder_sparse_step": "decoder_sparse_step: Optional[int] = 1", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "shared_expert_intermediate_size": "shared_expert_intermediate_size: Optional[int] = 5632", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 4", + "num_experts": "num_experts: Optional[int] = 60", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "mlp_only_layers": "mlp_only_layers: Optional[bool] = None", + "qkv_bias": "qkv_bias: Optional[bool] = True", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Qwen2VLModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151655", + "video_token_id": "video_token_id=151656", + "vision_start_token_id": "vision_start_token_id=151652", + "vision_end_token_id": "vision_end_token_id=151653" + }, + "Qwen2VLTextModel": { + "vocab_size": "vocab_size: Optional[int] = 152064", + "hidden_size": "hidden_size: Optional[int] = 8192", + "intermediate_size": "intermediate_size: Optional[int] = 29568", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 80", + "num_attention_heads": "num_attention_heads: Optional[int] = 64", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 80", + "layer_types": "layer_types: Optional[list[str]] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "bos_token_id": "bos_token_id: Optional[int] = 151643", + "eos_token_id": "eos_token_id: Optional[int] = 151645", + "pad_token_id": "pad_token_id: Optional[int] = None" + }, + "Qwen3Model": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 22016", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "max_window_layers": "max_window_layers: Optional[int] = 28", + "layer_types": "layer_types: Optional[list[str]] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "Qwen3MoeModel": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 6144", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = 4096", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "decoder_sparse_step": "decoder_sparse_step: Optional[int] = 1", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 768", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 8", + "num_experts": "num_experts: Optional[int] = 128", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = False", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "mlp_only_layers": "mlp_only_layers: Optional[bool] = None" + }, + "Qwen3NextModel": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 5632", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 48", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "head_dim": "head_dim: Optional[int] = 256", + "linear_conv_kernel_dim": "linear_conv_kernel_dim: Optional[int] = 4", + "linear_key_head_dim": "linear_key_head_dim: Optional[int] = 128", + "linear_value_head_dim": "linear_value_head_dim: Optional[int] = 128", + "linear_num_key_heads": "linear_num_key_heads: Optional[int] = 16", + "linear_num_value_heads": "linear_num_value_heads: Optional[int] = 32", + "decoder_sparse_step": "decoder_sparse_step: Optional[int] = 1", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 512", + "shared_expert_intermediate_size": "shared_expert_intermediate_size: Optional[int] = 512", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 10", + "num_experts": "num_experts: Optional[int] = 512", + "norm_topk_prob": "norm_topk_prob: Optional[bool] = True", + "output_router_logits": "output_router_logits: Optional[bool] = False", + "router_aux_loss_coef": "router_aux_loss_coef: Optional[float] = 0.001", + "mlp_only_layers": "mlp_only_layers: Optional[list[int]] = []", + "layer_types": "layer_types: Optional[list[str]] = None" + }, + "Qwen3VLModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151655", + "video_token_id": "video_token_id=151656", + "vision_start_token_id": "vision_start_token_id=151652", + "vision_end_token_id": "vision_end_token_id=151653", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "Qwen3VLMoeModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151655", + "video_token_id": "video_token_id=151656", + "vision_start_token_id": "vision_start_token_id=151652", + "vision_end_token_id": "vision_end_token_id=151653", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "Qwen3VLMoeTextModel": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 5632", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 24", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 16", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 128000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "decoder_sparse_step": "decoder_sparse_step: Optional[int] = 1", + "moe_intermediate_size": "moe_intermediate_size: Optional[int] = 1408", + "num_experts_per_tok": "num_experts_per_tok: Optional[int] = 4", + "num_experts": "num_experts: Optional[int] = 60", + "mlp_only_layers": "mlp_only_layers: Optional[list[int]] = None", + "rope_parameters": "rope_parameters: Optional[transformers.modeling_rope_utils.RopeParameters] = None", + "head_dim": "head_dim: Optional[int] = None" + }, + "Qwen3VLTextModel": { + "vocab_size": "vocab_size: Optional[int] = 151936", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 22016", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "head_dim": "head_dim: Optional[int] = 128", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 128000", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0" + }, + "RecurrentGemmaModel": { + "num_hidden_layers": "num_hidden_layers: Optional[int] = 26", + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 2560", + "intermediate_size": "intermediate_size: Optional[int] = 7680", + "num_attention_heads": "num_attention_heads: Optional[int] = 10", + "lru_width": "lru_width: Optional[int] = None", + "attention_window_size": "attention_window_size: Optional[int] = 2048", + "conv1d_width": "conv1d_width: Optional[int] = 4", + "logits_soft_cap": "logits_soft_cap: Optional[float] = 30.0", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "block_types": "block_types: Optional[list[str]] = ('recurrent', 'recurrent', 'attention')", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "attention_bias": "attention_bias: Optional[str] = False", + "w_init_variance_scale": "w_init_variance_scale: Optional[float] = 0.01" + }, + "ReformerModel": { + "attention_head_size": "attention_head_size=64", + "attn_layers": "attn_layers=['local', 'lsh', 'local', 'lsh', 'local', 'lsh']", + "axial_norm_std": "axial_norm_std=1.0", + "axial_pos_embds": "axial_pos_embds=True", + "axial_pos_shape": "axial_pos_shape=[64, 64]", + "axial_pos_embds_dim": "axial_pos_embds_dim=[64, 192]", + "chunk_size_lm_head": "chunk_size_lm_head=0", + "eos_token_id": "eos_token_id=2", + "feed_forward_size": "feed_forward_size=512", + "hash_seed": "hash_seed=None", + "hidden_act": "hidden_act='relu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.05", + "hidden_size": "hidden_size=256", + "initializer_range": "initializer_range=0.02", + "is_decoder": "is_decoder=False", + "layer_norm_eps": "layer_norm_eps=1e-12", + "local_num_chunks_before": "local_num_chunks_before=1", + "local_num_chunks_after": "local_num_chunks_after=0", + "local_attention_probs_dropout_prob": "local_attention_probs_dropout_prob=0.05", + "local_attn_chunk_length": "local_attn_chunk_length=64", + "lsh_attn_chunk_length": "lsh_attn_chunk_length=64", + "lsh_attention_probs_dropout_prob": "lsh_attention_probs_dropout_prob=0.0", + "lsh_num_chunks_before": "lsh_num_chunks_before=1", + "lsh_num_chunks_after": "lsh_num_chunks_after=0", + "max_position_embeddings": "max_position_embeddings=4096", + "num_attention_heads": "num_attention_heads=12", + "num_buckets": "num_buckets=None", + "num_hashes": "num_hashes=1", + "pad_token_id": "pad_token_id=0", + "vocab_size": "vocab_size=320", + "tie_word_embeddings": "tie_word_embeddings=False", + "classifier_dropout": "classifier_dropout=None" + }, + "ReformerTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "eos_token": "eos_token: str = ''", + "unk_token": "unk_token: str = ''", + "additional_special_tokens": "additional_special_tokens: Optional[list] = None" + }, + "RegNetModel": { + "num_channels": "num_channels=3", + "embedding_size": "embedding_size=32", + "hidden_sizes": "hidden_sizes=[128, 192, 512, 1088]", + "depths": "depths=[2, 6, 12, 2]", + "groups_width": "groups_width=64", + "layer_type": "layer_type='y'", + "hidden_act": "hidden_act='relu'" + }, + "RemBertModel": { + "vocab_size": "vocab_size=250300", + "hidden_size": "hidden_size=1152", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=18", + "input_embedding_size": "input_embedding_size=256", + "output_embedding_size": "output_embedding_size=1664", + "intermediate_size": "intermediate_size=4608", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=312", + "eos_token_id": "eos_token_id=313" + }, + "RemBertTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "do_lower_case": "do_lower_case: bool = False", + "keep_accents": "keep_accents: bool = False", + "bos_token": "bos_token: str = '[CLS]'", + "eos_token": "eos_token: str = '[SEP]'", + "unk_token": "unk_token: str = ''", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = ''", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "add_prefix_space": "add_prefix_space: bool = True", + "remove_space": "remove_space: bool = True" + }, + "ResNetModel": { + "num_channels": "num_channels=3", + "embedding_size": "embedding_size=64", + "hidden_sizes": "hidden_sizes=[256, 512, 1024, 2048]", + "depths": "depths=[3, 4, 6, 3]", + "layer_type": "layer_type='bottleneck'", + "hidden_act": "hidden_act='relu'", + "downsample_in_first_stage": "downsample_in_first_stage=False", + "downsample_in_bottleneck": "downsample_in_bottleneck=False", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "RobertaModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "RobertaPreLayerNormModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "RoCBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "classifier_dropout": "classifier_dropout=None", + "enable_pronunciation": "enable_pronunciation=True", + "enable_shape": "enable_shape=True", + "pronunciation_embed_dim": "pronunciation_embed_dim=768", + "pronunciation_vocab_size": "pronunciation_vocab_size=910", + "shape_embed_dim": "shape_embed_dim=512", + "shape_vocab_size": "shape_vocab_size=24858", + "concat_input": "concat_input=True" + }, + "RoCBertTokenizer": { + "vocab_file": "vocab_file", + "word_shape_file": "word_shape_file", + "word_pronunciation_file": "word_pronunciation_file", + "do_lower_case": "do_lower_case=True", + "do_basic_tokenize": "do_basic_tokenize=True", + "never_split": "never_split=None", + "unk_token": "unk_token='[UNK]'", + "sep_token": "sep_token='[SEP]'", + "pad_token": "pad_token='[PAD]'", + "cls_token": "cls_token='[CLS]'", + "mask_token": "mask_token='[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars=True", + "strip_accents": "strip_accents=None" + }, + "RoFormerModel": { + "vocab_size": "vocab_size=50000", + "embedding_size": "embedding_size=None", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=1536", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "rotary_value": "rotary_value=False" + }, + "RoFormerTokenizer": { + "vocab": "vocab: Optional[dict[str, int]] = None", + "do_lower_case": "do_lower_case=True", + "unk_token": "unk_token='[UNK]'", + "sep_token": "sep_token='[SEP]'", + "pad_token": "pad_token='[PAD]'", + "cls_token": "cls_token='[CLS]'", + "mask_token": "mask_token='[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars=True", + "strip_accents": "strip_accents=None" + }, + "RTDetrModel": { + "initializer_range": "initializer_range=0.01", + "initializer_bias_prior_prob": "initializer_bias_prior_prob=None", + "layer_norm_eps": "layer_norm_eps=1e-05", + "batch_norm_eps": "batch_norm_eps=1e-05", + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "freeze_backbone_batch_norms": "freeze_backbone_batch_norms=True", + "backbone_kwargs": "backbone_kwargs=None", + "encoder_hidden_dim": "encoder_hidden_dim=256", + "encoder_in_channels": "encoder_in_channels=[512, 1024, 2048]", + "feat_strides": "feat_strides=[8, 16, 32]", + "encoder_layers": "encoder_layers=1", + "encoder_ffn_dim": "encoder_ffn_dim=1024", + "encoder_attention_heads": "encoder_attention_heads=8", + "dropout": "dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "encode_proj_layers": "encode_proj_layers=[2]", + "positional_encoding_temperature": "positional_encoding_temperature=10000", + "encoder_activation_function": "encoder_activation_function='gelu'", + "activation_function": "activation_function='silu'", + "eval_size": "eval_size=None", + "normalize_before": "normalize_before=False", + "hidden_expansion": "hidden_expansion=1.0", + "d_model": "d_model=256", + "num_queries": "num_queries=300", + "decoder_in_channels": "decoder_in_channels=[256, 256, 256]", + "decoder_ffn_dim": "decoder_ffn_dim=1024", + "num_feature_levels": "num_feature_levels=3", + "decoder_n_points": "decoder_n_points=4", + "decoder_layers": "decoder_layers=6", + "decoder_attention_heads": "decoder_attention_heads=8", + "decoder_activation_function": "decoder_activation_function='relu'", + "attention_dropout": "attention_dropout=0.0", + "num_denoising": "num_denoising=100", + "label_noise_ratio": "label_noise_ratio=0.5", + "box_noise_scale": "box_noise_scale=1.0", + "learn_initial_query": "learn_initial_query=False", + "anchor_image_size": "anchor_image_size=None", + "disable_custom_kernels": "disable_custom_kernels=True", + "with_box_refine": "with_box_refine=True", + "is_encoder_decoder": "is_encoder_decoder=True", + "matcher_alpha": "matcher_alpha=0.25", + "matcher_gamma": "matcher_gamma=2.0", + "matcher_class_cost": "matcher_class_cost=2.0", + "matcher_bbox_cost": "matcher_bbox_cost=5.0", + "matcher_giou_cost": "matcher_giou_cost=2.0", + "use_focal_loss": "use_focal_loss=True", + "auxiliary_loss": "auxiliary_loss=True", + "focal_loss_alpha": "focal_loss_alpha=0.75", + "focal_loss_gamma": "focal_loss_gamma=2.0", + "weight_loss_vfl": "weight_loss_vfl=1.0", + "weight_loss_bbox": "weight_loss_bbox=5.0", + "weight_loss_giou": "weight_loss_giou=2.0", + "eos_coefficient": "eos_coefficient=0.0001" + }, + "RTDetrV2Model": { + "initializer_range": "initializer_range=0.01", + "initializer_bias_prior_prob": "initializer_bias_prior_prob=None", + "layer_norm_eps": "layer_norm_eps=1e-05", + "batch_norm_eps": "batch_norm_eps=1e-05", + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "freeze_backbone_batch_norms": "freeze_backbone_batch_norms=True", + "backbone_kwargs": "backbone_kwargs=None", + "encoder_hidden_dim": "encoder_hidden_dim=256", + "encoder_in_channels": "encoder_in_channels=[512, 1024, 2048]", + "feat_strides": "feat_strides=[8, 16, 32]", + "encoder_layers": "encoder_layers=1", + "encoder_ffn_dim": "encoder_ffn_dim=1024", + "encoder_attention_heads": "encoder_attention_heads=8", + "dropout": "dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "encode_proj_layers": "encode_proj_layers=[2]", + "positional_encoding_temperature": "positional_encoding_temperature=10000", + "encoder_activation_function": "encoder_activation_function='gelu'", + "activation_function": "activation_function='silu'", + "eval_size": "eval_size=None", + "normalize_before": "normalize_before=False", + "hidden_expansion": "hidden_expansion=1.0", + "d_model": "d_model=256", + "num_queries": "num_queries=300", + "decoder_in_channels": "decoder_in_channels=[256, 256, 256]", + "decoder_ffn_dim": "decoder_ffn_dim=1024", + "num_feature_levels": "num_feature_levels=3", + "decoder_n_points": "decoder_n_points=4", + "decoder_layers": "decoder_layers=6", + "decoder_attention_heads": "decoder_attention_heads=8", + "decoder_activation_function": "decoder_activation_function='relu'", + "attention_dropout": "attention_dropout=0.0", + "num_denoising": "num_denoising=100", + "label_noise_ratio": "label_noise_ratio=0.5", + "box_noise_scale": "box_noise_scale=1.0", + "learn_initial_query": "learn_initial_query=False", + "anchor_image_size": "anchor_image_size=None", + "with_box_refine": "with_box_refine=True", + "is_encoder_decoder": "is_encoder_decoder=True", + "matcher_alpha": "matcher_alpha=0.25", + "matcher_gamma": "matcher_gamma=2.0", + "matcher_class_cost": "matcher_class_cost=2.0", + "matcher_bbox_cost": "matcher_bbox_cost=5.0", + "matcher_giou_cost": "matcher_giou_cost=2.0", + "use_focal_loss": "use_focal_loss=True", + "auxiliary_loss": "auxiliary_loss=True", + "focal_loss_alpha": "focal_loss_alpha=0.75", + "focal_loss_gamma": "focal_loss_gamma=2.0", + "weight_loss_vfl": "weight_loss_vfl=1.0", + "weight_loss_bbox": "weight_loss_bbox=5.0", + "weight_loss_giou": "weight_loss_giou=2.0", + "eos_coefficient": "eos_coefficient=0.0001", + "decoder_n_levels": "decoder_n_levels=3", + "decoder_offset_scale": "decoder_offset_scale=0.5", + "decoder_method": "decoder_method='default'" + }, + "RwkvModel": { + "vocab_size": "vocab_size=50277", + "context_length": "context_length=1024", + "hidden_size": "hidden_size=4096", + "num_hidden_layers": "num_hidden_layers=32", + "attention_hidden_size": "attention_hidden_size=None", + "intermediate_size": "intermediate_size=None", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=0", + "rescale_every": "rescale_every=6", + "tie_word_embeddings": "tie_word_embeddings=False" + }, + "SamModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "Sam2Model": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "Sam2HieraDetModel": { + "hidden_size": "hidden_size=96", + "num_attention_heads": "num_attention_heads=1", + "num_channels": "num_channels=3", + "image_size": "image_size=None", + "patch_kernel_size": "patch_kernel_size=None", + "patch_stride": "patch_stride=None", + "patch_padding": "patch_padding=None", + "query_stride": "query_stride=None", + "window_positional_embedding_background_size": "window_positional_embedding_background_size=None", + "num_query_pool_stages": "num_query_pool_stages=3", + "blocks_per_stage": "blocks_per_stage=None", + "embed_dim_per_stage": "embed_dim_per_stage=None", + "num_attention_heads_per_stage": "num_attention_heads_per_stage=None", + "window_size_per_stage": "window_size_per_stage=None", + "global_attention_blocks": "global_attention_blocks=None", + "mlp_ratio": "mlp_ratio=4.0", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "initializer_range": "initializer_range=0.02" + }, + "Sam2VideoModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02", + "num_maskmem": "num_maskmem=7", + "image_size": "image_size=1024", + "sigmoid_scale_for_mem_enc": "sigmoid_scale_for_mem_enc=20.0", + "sigmoid_bias_for_mem_enc": "sigmoid_bias_for_mem_enc=-10.0", + "enable_occlusion_spatial_embedding": "enable_occlusion_spatial_embedding=True", + "multimask_output_in_sam": "multimask_output_in_sam=True", + "multimask_min_pt_num": "multimask_min_pt_num=0", + "multimask_max_pt_num": "multimask_max_pt_num=1", + "multimask_output_for_tracking": "multimask_output_for_tracking=True", + "max_object_pointers_in_encoder": "max_object_pointers_in_encoder=16", + "max_cond_frame_num": "max_cond_frame_num=-1", + "enable_temporal_pos_encoding_for_object_pointers": "enable_temporal_pos_encoding_for_object_pointers=True", + "memory_attention_hidden_size": "memory_attention_hidden_size=256", + "memory_attention_num_layers": "memory_attention_num_layers=4", + "memory_attention_num_attention_heads": "memory_attention_num_attention_heads=1", + "memory_attention_downsample_rate": "memory_attention_downsample_rate=1", + "memory_attention_feed_forward_hidden_size": "memory_attention_feed_forward_hidden_size=2048", + "memory_attention_feed_forward_hidden_act": "memory_attention_feed_forward_hidden_act='relu'", + "memory_attention_dropout": "memory_attention_dropout=0.1", + "memory_attention_rope_theta": "memory_attention_rope_theta=10000", + "memory_attention_rope_feat_sizes": "memory_attention_rope_feat_sizes=None", + "memory_attention_rope_dropout": "memory_attention_rope_dropout=0.1", + "memory_encoder_hidden_size": "memory_encoder_hidden_size=256", + "memory_encoder_output_channels": "memory_encoder_output_channels=64", + "mask_downsampler_embed_dim": "mask_downsampler_embed_dim=256", + "mask_downsampler_kernel_size": "mask_downsampler_kernel_size=3", + "mask_downsampler_stride": "mask_downsampler_stride=2", + "mask_downsampler_padding": "mask_downsampler_padding=1", + "mask_downsampler_total_stride": "mask_downsampler_total_stride=16", + "mask_downsampler_hidden_act": "mask_downsampler_hidden_act='gelu'", + "memory_fuser_num_layers": "memory_fuser_num_layers=2", + "memory_fuser_embed_dim": "memory_fuser_embed_dim=256", + "memory_fuser_intermediate_dim": "memory_fuser_intermediate_dim=1024", + "memory_fuser_kernel_size": "memory_fuser_kernel_size=7", + "memory_fuser_padding": "memory_fuser_padding=3", + "memory_fuser_layer_scale_init_value": "memory_fuser_layer_scale_init_value=1e-06", + "memory_fuser_hidden_act": "memory_fuser_hidden_act='gelu'" + }, + "Sam2VisionModel": { + "backbone_config": "backbone_config=None", + "backbone_channel_list": "backbone_channel_list=None", + "backbone_feature_sizes": "backbone_feature_sizes=None", + "fpn_hidden_size": "fpn_hidden_size=256", + "fpn_kernel_size": "fpn_kernel_size=1", + "fpn_stride": "fpn_stride=1", + "fpn_padding": "fpn_padding=0", + "fpn_top_down_levels": "fpn_top_down_levels=None", + "num_feature_levels": "num_feature_levels=3", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "initializer_range": "initializer_range=0.02" + }, + "Sam3Model": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "geometry_encoder_config": "geometry_encoder_config=None", + "detr_encoder_config": "detr_encoder_config=None", + "detr_decoder_config": "detr_decoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "Sam3TrackerModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "Sam3TrackerVideoModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02", + "num_maskmem": "num_maskmem=7", + "image_size": "image_size=1008", + "sigmoid_scale_for_mem_enc": "sigmoid_scale_for_mem_enc=20.0", + "sigmoid_bias_for_mem_enc": "sigmoid_bias_for_mem_enc=-10.0", + "enable_occlusion_spatial_embedding": "enable_occlusion_spatial_embedding=True", + "multimask_output_in_sam": "multimask_output_in_sam=True", + "multimask_min_pt_num": "multimask_min_pt_num=0", + "multimask_max_pt_num": "multimask_max_pt_num=1", + "multimask_output_for_tracking": "multimask_output_for_tracking=True", + "max_object_pointers_in_encoder": "max_object_pointers_in_encoder=16", + "max_cond_frame_num": "max_cond_frame_num=4", + "enable_temporal_pos_encoding_for_object_pointers": "enable_temporal_pos_encoding_for_object_pointers=True", + "memory_attention_hidden_size": "memory_attention_hidden_size=256", + "memory_attention_num_layers": "memory_attention_num_layers=4", + "memory_attention_num_attention_heads": "memory_attention_num_attention_heads=1", + "memory_attention_downsample_rate": "memory_attention_downsample_rate=1", + "memory_attention_feed_forward_hidden_size": "memory_attention_feed_forward_hidden_size=2048", + "memory_attention_feed_forward_hidden_act": "memory_attention_feed_forward_hidden_act='relu'", + "memory_attention_dropout": "memory_attention_dropout=0.1", + "memory_attention_rope_theta": "memory_attention_rope_theta=10000", + "memory_attention_rope_feat_sizes": "memory_attention_rope_feat_sizes=None", + "memory_attention_rope_dropout": "memory_attention_rope_dropout=0.1", + "memory_encoder_hidden_size": "memory_encoder_hidden_size=256", + "memory_encoder_output_channels": "memory_encoder_output_channels=64", + "mask_downsampler_embed_dim": "mask_downsampler_embed_dim=256", + "mask_downsampler_kernel_size": "mask_downsampler_kernel_size=3", + "mask_downsampler_stride": "mask_downsampler_stride=2", + "mask_downsampler_padding": "mask_downsampler_padding=1", + "mask_downsampler_total_stride": "mask_downsampler_total_stride=16", + "mask_downsampler_hidden_act": "mask_downsampler_hidden_act='gelu'", + "memory_fuser_num_layers": "memory_fuser_num_layers=2", + "memory_fuser_embed_dim": "memory_fuser_embed_dim=256", + "memory_fuser_intermediate_dim": "memory_fuser_intermediate_dim=1024", + "memory_fuser_kernel_size": "memory_fuser_kernel_size=7", + "memory_fuser_padding": "memory_fuser_padding=3", + "memory_fuser_layer_scale_init_value": "memory_fuser_layer_scale_init_value=1e-06", + "memory_fuser_hidden_act": "memory_fuser_hidden_act='gelu'" + }, + "Sam3VideoModel": { + "detector_config": "detector_config=None", + "tracker_config": "tracker_config=None", + "initializer_range": "initializer_range=0.02", + "low_res_mask_size": "low_res_mask_size=288", + "score_threshold_detection": "score_threshold_detection=0.5", + "det_nms_thresh": "det_nms_thresh=0.1", + "assoc_iou_thresh": "assoc_iou_thresh=0.1", + "trk_assoc_iou_thresh": "trk_assoc_iou_thresh=0.5", + "new_det_thresh": "new_det_thresh=0.7", + "recondition_on_trk_masks": "recondition_on_trk_masks=True", + "hotstart_delay": "hotstart_delay=15", + "hotstart_unmatch_thresh": "hotstart_unmatch_thresh=8", + "hotstart_dup_thresh": "hotstart_dup_thresh=8", + "suppress_unmatched_only_within_hotstart": "suppress_unmatched_only_within_hotstart=True", + "init_trk_keep_alive": "init_trk_keep_alive=30", + "max_trk_keep_alive": "max_trk_keep_alive=30", + "min_trk_keep_alive": "min_trk_keep_alive=-1", + "suppress_overlapping_based_on_recent_occlusion_threshold": "suppress_overlapping_based_on_recent_occlusion_threshold=0.7", + "decrease_trk_keep_alive_for_empty_masklets": "decrease_trk_keep_alive_for_empty_masklets=False", + "fill_hole_area": "fill_hole_area=16", + "max_num_objects": "max_num_objects=10000", + "recondition_every_nth_frame": "recondition_every_nth_frame=16", + "high_conf_thresh": "high_conf_thresh=0.8", + "high_iou_thresh": "high_iou_thresh=0.8" + }, + "Sam3VisionModel": { + "backbone_config": "backbone_config=None", + "fpn_hidden_size": "fpn_hidden_size=256", + "backbone_feature_sizes": "backbone_feature_sizes=None", + "scale_factors": "scale_factors=None", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "initializer_range": "initializer_range=0.02" + }, + "Sam3ViTModel": { + "hidden_size": "hidden_size=1024", + "intermediate_size": "intermediate_size=4736", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=16", + "num_channels": "num_channels=3", + "image_size": "image_size=1008", + "patch_size": "patch_size=14", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "rope_theta": "rope_theta=10000.0", + "window_size": "window_size=24", + "global_attn_indexes": "global_attn_indexes=None", + "layer_scale_init_value": "layer_scale_init_value=None", + "pretrain_image_size": "pretrain_image_size=336", + "hidden_dropout": "hidden_dropout=0.0", + "initializer_range": "initializer_range=0.02" + }, + "SamHQModel": { + "vision_config": "vision_config=None", + "prompt_encoder_config": "prompt_encoder_config=None", + "mask_decoder_config": "mask_decoder_config=None", + "initializer_range": "initializer_range=0.02" + }, + "SamHQVisionModel": { + "hidden_size": "hidden_size=768", + "output_channels": "output_channels=256", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "image_size": "image_size=1024", + "patch_size": "patch_size=16", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=1e-10", + "qkv_bias": "qkv_bias=True", + "mlp_ratio": "mlp_ratio=4.0", + "use_abs_pos": "use_abs_pos=True", + "use_rel_pos": "use_rel_pos=True", + "window_size": "window_size=14", + "global_attn_indexes": "global_attn_indexes=[2, 5, 8, 11]", + "num_pos_feats": "num_pos_feats=128", + "mlp_dim": "mlp_dim=None" + }, + "SamVisionModel": { + "hidden_size": "hidden_size=768", + "output_channels": "output_channels=256", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "image_size": "image_size=1024", + "patch_size": "patch_size=16", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=1e-10", + "qkv_bias": "qkv_bias=True", + "mlp_ratio": "mlp_ratio=4.0", + "use_abs_pos": "use_abs_pos=True", + "use_rel_pos": "use_rel_pos=True", + "window_size": "window_size=14", + "global_attn_indexes": "global_attn_indexes=[2, 5, 8, 11]", + "num_pos_feats": "num_pos_feats=128", + "mlp_dim": "mlp_dim=None" + }, + "SeamlessM4TModel": { + "vocab_size": "vocab_size=256102", + "t2u_vocab_size": "t2u_vocab_size=10082", + "hidden_size": "hidden_size=1024", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "max_position_embeddings": "max_position_embeddings=1024", + "is_encoder_decoder": "is_encoder_decoder=True", + "encoder_layerdrop": "encoder_layerdrop=0.05", + "decoder_layerdrop": "decoder_layerdrop=0.05", + "activation_function": "activation_function='relu'", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "scale_embedding": "scale_embedding=True", + "encoder_layers": "encoder_layers=24", + "encoder_ffn_dim": "encoder_ffn_dim=8192", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=24", + "decoder_ffn_dim": "decoder_ffn_dim=8192", + "decoder_attention_heads": "decoder_attention_heads=16", + "decoder_start_token_id": "decoder_start_token_id=3", + "max_new_tokens": "max_new_tokens=256", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=3", + "speech_encoder_layers": "speech_encoder_layers=24", + "speech_encoder_attention_heads": "speech_encoder_attention_heads=16", + "speech_encoder_intermediate_size": "speech_encoder_intermediate_size=4096", + "speech_encoder_hidden_act": "speech_encoder_hidden_act='swish'", + "speech_encoder_dropout": "speech_encoder_dropout=0.0", + "add_adapter": "add_adapter=True", + "speech_encoder_layerdrop": "speech_encoder_layerdrop=0.1", + "feature_projection_input_dim": "feature_projection_input_dim=160", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "adaptor_kernel_size": "adaptor_kernel_size=8", + "adaptor_stride": "adaptor_stride=8", + "adaptor_dropout": "adaptor_dropout=0.1", + "num_adapter_layers": "num_adapter_layers=1", + "position_embeddings_type": "position_embeddings_type='relative'", + "rotary_embedding_base": "rotary_embedding_base=10000", + "max_source_positions": "max_source_positions=4096", + "conv_depthwise_kernel_size": "conv_depthwise_kernel_size=31", + "t2u_bos_token_id": "t2u_bos_token_id=0", + "t2u_pad_token_id": "t2u_pad_token_id=1", + "t2u_eos_token_id": "t2u_eos_token_id=2", + "t2u_decoder_start_token_id": "t2u_decoder_start_token_id=2", + "t2u_max_new_tokens": "t2u_max_new_tokens=1024", + "t2u_encoder_layers": "t2u_encoder_layers=6", + "t2u_encoder_ffn_dim": "t2u_encoder_ffn_dim=8192", + "t2u_encoder_attention_heads": "t2u_encoder_attention_heads=16", + "t2u_decoder_layers": "t2u_decoder_layers=6", + "t2u_decoder_ffn_dim": "t2u_decoder_ffn_dim=8192", + "t2u_decoder_attention_heads": "t2u_decoder_attention_heads=16", + "t2u_max_position_embeddings": "t2u_max_position_embeddings=2048", + "sampling_rate": "sampling_rate=16000", + "upsample_initial_channel": "upsample_initial_channel=512", + "upsample_rates": "upsample_rates=[5, 4, 4, 2, 2]", + "upsample_kernel_sizes": "upsample_kernel_sizes=[11, 8, 8, 4, 4]", + "resblock_kernel_sizes": "resblock_kernel_sizes=[3, 7, 11]", + "resblock_dilation_sizes": "resblock_dilation_sizes=[[1, 3, 5], [1, 3, 5], [1, 3, 5]]", + "leaky_relu_slope": "leaky_relu_slope=0.1", + "unit_hifi_gan_vocab_size": "unit_hifi_gan_vocab_size=10000", + "unit_embed_dim": "unit_embed_dim=1280", + "lang_embed_dim": "lang_embed_dim=256", + "spkr_embed_dim": "spkr_embed_dim=256", + "vocoder_num_langs": "vocoder_num_langs=36", + "vocoder_num_spkrs": "vocoder_num_spkrs=200", + "variance_predictor_kernel_size": "variance_predictor_kernel_size=3", + "var_pred_dropout": "var_pred_dropout=0.5", + "vocoder_offset": "vocoder_offset=4" + }, + "SeamlessM4TTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "cls_token": "cls_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "src_lang": "src_lang='eng'", + "tgt_lang": "tgt_lang='fra'", + "additional_special_tokens": "additional_special_tokens=None", + "keep_accents": "keep_accents=None", + "vocab_file": "vocab_file=None" + }, + "SeamlessM4Tv2Model": { + "vocab_size": "vocab_size=256102", + "t2u_vocab_size": "t2u_vocab_size=10082", + "char_vocab_size": "char_vocab_size=10943", + "hidden_size": "hidden_size=1024", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "max_position_embeddings": "max_position_embeddings=4096", + "is_encoder_decoder": "is_encoder_decoder=True", + "encoder_layerdrop": "encoder_layerdrop=0.05", + "decoder_layerdrop": "decoder_layerdrop=0.05", + "activation_function": "activation_function='relu'", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "scale_embedding": "scale_embedding=True", + "encoder_layers": "encoder_layers=24", + "encoder_ffn_dim": "encoder_ffn_dim=8192", + "encoder_attention_heads": "encoder_attention_heads=16", + "decoder_layers": "decoder_layers=24", + "decoder_ffn_dim": "decoder_ffn_dim=8192", + "decoder_attention_heads": "decoder_attention_heads=16", + "decoder_start_token_id": "decoder_start_token_id=3", + "max_new_tokens": "max_new_tokens=256", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=3", + "speech_encoder_layers": "speech_encoder_layers=24", + "speech_encoder_attention_heads": "speech_encoder_attention_heads=16", + "speech_encoder_intermediate_size": "speech_encoder_intermediate_size=4096", + "speech_encoder_hidden_act": "speech_encoder_hidden_act='swish'", + "speech_encoder_dropout": "speech_encoder_dropout=0.0", + "add_adapter": "add_adapter=True", + "speech_encoder_layerdrop": "speech_encoder_layerdrop=0.1", + "feature_projection_input_dim": "feature_projection_input_dim=160", + "adaptor_kernel_size": "adaptor_kernel_size=8", + "adaptor_stride": "adaptor_stride=8", + "adaptor_dropout": "adaptor_dropout=0.1", + "num_adapter_layers": "num_adapter_layers=1", + "position_embeddings_type": "position_embeddings_type='relative_key'", + "conv_depthwise_kernel_size": "conv_depthwise_kernel_size=31", + "left_max_position_embeddings": "left_max_position_embeddings=64", + "right_max_position_embeddings": "right_max_position_embeddings=8", + "speech_encoder_chunk_size": "speech_encoder_chunk_size=20000", + "speech_encoder_left_chunk_num": "speech_encoder_left_chunk_num=128", + "t2u_bos_token_id": "t2u_bos_token_id=0", + "t2u_pad_token_id": "t2u_pad_token_id=1", + "t2u_eos_token_id": "t2u_eos_token_id=2", + "t2u_encoder_layers": "t2u_encoder_layers=6", + "t2u_encoder_ffn_dim": "t2u_encoder_ffn_dim=8192", + "t2u_encoder_attention_heads": "t2u_encoder_attention_heads=16", + "t2u_decoder_layers": "t2u_decoder_layers=6", + "t2u_decoder_ffn_dim": "t2u_decoder_ffn_dim=8192", + "t2u_decoder_attention_heads": "t2u_decoder_attention_heads=16", + "t2u_max_position_embeddings": "t2u_max_position_embeddings=4096", + "t2u_variance_predictor_embed_dim": "t2u_variance_predictor_embed_dim=1024", + "t2u_variance_predictor_hidden_dim": "t2u_variance_predictor_hidden_dim=256", + "t2u_variance_predictor_kernel_size": "t2u_variance_predictor_kernel_size=3", + "t2u_variance_pred_dropout": "t2u_variance_pred_dropout=0.5", + "sampling_rate": "sampling_rate=16000", + "upsample_initial_channel": "upsample_initial_channel=512", + "upsample_rates": "upsample_rates=[5, 4, 4, 2, 2]", + "upsample_kernel_sizes": "upsample_kernel_sizes=[11, 8, 8, 4, 4]", + "resblock_kernel_sizes": "resblock_kernel_sizes=[3, 7, 11]", + "resblock_dilation_sizes": "resblock_dilation_sizes=[[1, 3, 5], [1, 3, 5], [1, 3, 5]]", + "leaky_relu_slope": "leaky_relu_slope=0.1", + "unit_hifi_gan_vocab_size": "unit_hifi_gan_vocab_size=10000", + "unit_embed_dim": "unit_embed_dim=1280", + "lang_embed_dim": "lang_embed_dim=256", + "spkr_embed_dim": "spkr_embed_dim=256", + "vocoder_num_langs": "vocoder_num_langs=36", + "vocoder_num_spkrs": "vocoder_num_spkrs=200", + "variance_predictor_kernel_size": "variance_predictor_kernel_size=3", + "var_pred_dropout": "var_pred_dropout=0.5", + "vocoder_offset": "vocoder_offset=4" + }, + "SeedOssModel": { + "vocab_size": "vocab_size: Optional[int] = 155136", + "hidden_size": "hidden_size: Optional[int] = 4096", + "intermediate_size": "intermediate_size: Optional[int] = 27648", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 64", + "num_attention_heads": "num_attention_heads: Optional[int] = 80", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 8", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 524288", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[float] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "pretraining_tp": "pretraining_tp: Optional[int] = 1", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = True", + "attention_out_bias": "attention_out_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.1", + "residual_dropout": "residual_dropout: Optional[float] = 0.1", + "mlp_bias": "mlp_bias: Optional[bool] = False", + "head_dim": "head_dim: Optional[int] = 128" + }, + "SegformerModel": { + "num_channels": "num_channels=3", + "num_encoder_blocks": "num_encoder_blocks=4", + "depths": "depths=[2, 2, 2, 2]", + "sr_ratios": "sr_ratios=[8, 4, 2, 1]", + "hidden_sizes": "hidden_sizes=[32, 64, 160, 256]", + "patch_sizes": "patch_sizes=[7, 3, 3, 3]", + "strides": "strides=[4, 2, 2, 2]", + "num_attention_heads": "num_attention_heads=[1, 2, 5, 8]", + "mlp_ratios": "mlp_ratios=[4, 4, 4, 4]", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "initializer_range": "initializer_range=0.02", + "drop_path_rate": "drop_path_rate=0.1", + "layer_norm_eps": "layer_norm_eps=1e-06", + "decoder_hidden_size": "decoder_hidden_size=256", + "semantic_loss_ignore_index": "semantic_loss_ignore_index=255" + }, + "SegGptModel": { + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=[896, 448]", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "mlp_dim": "mlp_dim=None", + "drop_path_rate": "drop_path_rate=0.1", + "pretrain_image_size": "pretrain_image_size=224", + "decoder_hidden_size": "decoder_hidden_size=64", + "use_relative_position_embeddings": "use_relative_position_embeddings=True", + "merge_index": "merge_index=2", + "intermediate_hidden_state_indices": "intermediate_hidden_state_indices=[5, 11, 17, 23]", + "beta": "beta=0.01" + }, + "SEWModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "squeeze_factor": "squeeze_factor=2", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(64, 128, 128, 128, 128, 256, 256, 256, 256, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1)", + "conv_kernel": "conv_kernel=(10, 3, 1, 3, 1, 3, 1, 3, 1, 2, 1, 2, 1)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2" + }, + "SEWDModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "squeeze_factor": "squeeze_factor=2", + "max_position_embeddings": "max_position_embeddings=512", + "position_buckets": "position_buckets=256", + "share_att_key": "share_att_key=True", + "relative_attention": "relative_attention=True", + "pos_att_type": "pos_att_type=('p2c', 'c2p')", + "norm_rel_ebd": "norm_rel_ebd='layer_norm'", + "hidden_act": "hidden_act='gelu_python'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-07", + "feature_layer_norm_eps": "feature_layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(64, 128, 128, 128, 128, 256, 256, 256, 256, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1)", + "conv_kernel": "conv_kernel=(10, 3, 1, 3, 1, 3, 1, 3, 1, 2, 1, 2, 1)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2" + }, + "SiglipModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None" + }, + "SiglipTokenizer": { + "vocab_file": "vocab_file", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "additional_special_tokens": "additional_special_tokens=None", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None", + "model_max_length": "model_max_length=64", + "do_lower_case": "do_lower_case=True" + }, + "Siglip2Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None" + }, + "Siglip2VisionModel": { + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "num_patches": "num_patches=256", + "patch_size": "patch_size=16", + "hidden_act": "hidden_act='gelu_pytorch_tanh'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0" + }, + "SiglipVisionModel": { + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "hidden_act": "hidden_act='gelu_pytorch_tanh'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0" + }, + "SmolLM3Model": { + "vocab_size": "vocab_size: Optional[int] = 128256", + "hidden_size": "hidden_size: Optional[int] = 2048", + "intermediate_size": "intermediate_size: Optional[int] = 11008", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 36", + "num_attention_heads": "num_attention_heads: Optional[int] = 16", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 32768", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 128004", + "bos_token_id": "bos_token_id: Optional[int] = 128000", + "eos_token_id": "eos_token_id: Optional[int] = 128001", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_sliding_window": "use_sliding_window: Optional[bool] = False", + "sliding_window": "sliding_window: Optional[int] = None", + "no_rope_layers": "no_rope_layers: Optional[int] = None", + "no_rope_layer_interval": "no_rope_layer_interval: Optional[int] = 4", + "layer_types": "layer_types: Optional[int] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "mlp_bias": "mlp_bias: Optional[bool] = False" + }, + "SmolVLMModel": { + "image_token_id": "image_token_id=128257", + "tie_word_embeddings": "tie_word_embeddings=False", + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "scale_factor": "scale_factor=2", + "pad_token_id": "pad_token_id=128002" + }, + "SmolVLMVisionTransformer": { + "hidden_size": "hidden_size=1152", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=16", + "num_channels": "num_channels=3", + "image_size": "image_size=224", + "patch_size": "patch_size=32", + "hidden_act": "hidden_act='gelu_pytorch_tanh'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02" + }, + "Speech2TextModel": { + "vocab_size": "vocab_size=10000", + "encoder_layers": "encoder_layers=12", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=4", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=4", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "decoder_start_token_id": "decoder_start_token_id=2", + "scale_embedding": "scale_embedding=True", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "max_source_positions": "max_source_positions=6000", + "max_target_positions": "max_target_positions=1024", + "num_conv_layers": "num_conv_layers=2", + "conv_kernel_sizes": "conv_kernel_sizes=(5, 5)", + "conv_channels": "conv_channels=1024", + "input_feat_per_channel": "input_feat_per_channel=80", + "input_channels": "input_channels=1" + }, + "Speech2TextTokenizer": { + "vocab_file": "vocab_file", + "spm_file": "spm_file", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "pad_token": "pad_token=''", + "unk_token": "unk_token=''", + "do_upper_case": "do_upper_case=False", + "do_lower_case": "do_lower_case=False", + "tgt_lang": "tgt_lang=None", + "lang_codes": "lang_codes=None", + "additional_special_tokens": "additional_special_tokens=None", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None" + }, + "SpeechT5Model": { + "vocab_size": "vocab_size=81", + "hidden_size": "hidden_size=768", + "encoder_layers": "encoder_layers=12", + "encoder_attention_heads": "encoder_attention_heads=12", + "encoder_ffn_dim": "encoder_ffn_dim=3072", + "encoder_layerdrop": "encoder_layerdrop=0.1", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=3072", + "decoder_attention_heads": "decoder_attention_heads=12", + "decoder_layerdrop": "decoder_layerdrop=0.1", + "hidden_act": "hidden_act='gelu'", + "positional_dropout": "positional_dropout=0.1", + "hidden_dropout": "hidden_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "scale_embedding": "scale_embedding=False", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "decoder_start_token_id": "decoder_start_token_id=2", + "num_mel_bins": "num_mel_bins=80", + "speech_decoder_prenet_layers": "speech_decoder_prenet_layers=2", + "speech_decoder_prenet_units": "speech_decoder_prenet_units=256", + "speech_decoder_prenet_dropout": "speech_decoder_prenet_dropout=0.5", + "speaker_embedding_dim": "speaker_embedding_dim=512", + "speech_decoder_postnet_layers": "speech_decoder_postnet_layers=5", + "speech_decoder_postnet_units": "speech_decoder_postnet_units=256", + "speech_decoder_postnet_kernel": "speech_decoder_postnet_kernel=5", + "speech_decoder_postnet_dropout": "speech_decoder_postnet_dropout=0.5", + "reduction_factor": "reduction_factor=2", + "max_speech_positions": "max_speech_positions=4000", + "max_text_positions": "max_text_positions=450", + "encoder_max_relative_position": "encoder_max_relative_position=160", + "use_guided_attention_loss": "use_guided_attention_loss=True", + "guided_attention_loss_num_heads": "guided_attention_loss_num_heads=2", + "guided_attention_loss_sigma": "guided_attention_loss_sigma=0.4", + "guided_attention_loss_scale": "guided_attention_loss_scale=10.0", + "is_encoder_decoder": "is_encoder_decoder=True" + }, + "SpeechT5Tokenizer": { + "vocab_file": "vocab_file", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "normalize": "normalize=False", + "sp_model_kwargs": "sp_model_kwargs: Optional[dict[str, Any]] = None" + }, + "SplinterModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "question_token_id": "question_token_id=104" + }, + "SplinterTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case: bool = True", + "unk_token": "unk_token: str = '[UNK]'", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = '[PAD]'", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "question_token": "question_token: str = '[QUESTION]'", + "tokenize_chinese_chars": "tokenize_chinese_chars: bool = True", + "strip_accents": "strip_accents: Optional[bool] = None" + }, + "SqueezeBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "embedding_size": "embedding_size=768", + "q_groups": "q_groups=4", + "k_groups": "k_groups=4", + "v_groups": "v_groups=4", + "post_attention_groups": "post_attention_groups=1", + "intermediate_groups": "intermediate_groups=4", + "output_groups": "output_groups=4" + }, + "StableLmModel": { + "vocab_size": "vocab_size: Optional[int] = 50304", + "intermediate_size": "intermediate_size: Optional[int] = 6912", + "hidden_size": "hidden_size: Optional[int] = 2560", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 32", + "hidden_act": "hidden_act: Optional[str] = 'silu'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "layer_norm_eps": "layer_norm_eps: Optional[float] = 1e-05", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "use_qkv_bias": "use_qkv_bias: Optional[bool] = False", + "qk_layernorm": "qk_layernorm: Optional[bool] = False", + "use_parallel_residual": "use_parallel_residual: Optional[bool] = False", + "hidden_dropout": "hidden_dropout: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "bos_token_id": "bos_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 0" + }, + "Starcoder2Model": { + "vocab_size": "vocab_size: Optional[int] = 49152", + "hidden_size": "hidden_size: Optional[int] = 3072", + "intermediate_size": "intermediate_size: Optional[int] = 12288", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 30", + "num_attention_heads": "num_attention_heads: Optional[int] = 24", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 2", + "hidden_act": "hidden_act: Optional[str] = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "initializer_range": "initializer_range: Optional[float] = 0.018042", + "norm_epsilon": "norm_epsilon: Optional[int] = 1e-05", + "bos_token_id": "bos_token_id: Optional[int] = 50256", + "eos_token_id": "eos_token_id: Optional[int] = 50256", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "sliding_window": "sliding_window: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "residual_dropout": "residual_dropout: Optional[float] = 0.0", + "embedding_dropout": "embedding_dropout: Optional[float] = 0.0", + "use_bias": "use_bias: Optional[bool] = True" + }, + "SwiftFormerModel": { + "image_size": "image_size=224", + "num_channels": "num_channels=3", + "depths": "depths=[3, 3, 6, 4]", + "embed_dims": "embed_dims=[48, 56, 112, 220]", + "mlp_ratio": "mlp_ratio=4", + "downsamples": "downsamples=[True, True, True, True]", + "hidden_act": "hidden_act='gelu'", + "down_patch_size": "down_patch_size=3", + "down_stride": "down_stride=2", + "down_pad": "down_pad=1", + "drop_path_rate": "drop_path_rate=0.0", + "drop_mlp_rate": "drop_mlp_rate=0.0", + "drop_conv_encoder_rate": "drop_conv_encoder_rate=0.0", + "use_layer_scale": "use_layer_scale=True", + "layer_scale_init_value": "layer_scale_init_value=1e-05", + "batch_norm_eps": "batch_norm_eps=1e-05" + }, + "SwinModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=96", + "depths": "depths=[2, 2, 6, 2]", + "num_heads": "num_heads=[3, 6, 12, 24]", + "window_size": "window_size=7", + "mlp_ratio": "mlp_ratio=4.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "use_absolute_embeddings": "use_absolute_embeddings=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "encoder_stride": "encoder_stride=32", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "Swin2SRModel": { + "image_size": "image_size=64", + "patch_size": "patch_size=1", + "num_channels": "num_channels=3", + "num_channels_out": "num_channels_out=None", + "embed_dim": "embed_dim=180", + "depths": "depths=[6, 6, 6, 6, 6, 6]", + "num_heads": "num_heads=[6, 6, 6, 6, 6, 6]", + "window_size": "window_size=8", + "mlp_ratio": "mlp_ratio=2.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "use_absolute_embeddings": "use_absolute_embeddings=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "upscale": "upscale=2", + "img_range": "img_range=1.0", + "resi_connection": "resi_connection='1conv'", + "upsampler": "upsampler='pixelshuffle'" + }, + "Swinv2Model": { + "image_size": "image_size=224", + "patch_size": "patch_size=4", + "num_channels": "num_channels=3", + "embed_dim": "embed_dim=96", + "depths": "depths=[2, 2, 6, 2]", + "num_heads": "num_heads=[3, 6, 12, 24]", + "window_size": "window_size=7", + "pretrained_window_sizes": "pretrained_window_sizes=[0, 0, 0, 0]", + "mlp_ratio": "mlp_ratio=4.0", + "qkv_bias": "qkv_bias=True", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "drop_path_rate": "drop_path_rate=0.1", + "hidden_act": "hidden_act='gelu'", + "use_absolute_embeddings": "use_absolute_embeddings=False", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "encoder_stride": "encoder_stride=32", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "SwitchTransformersModel": { + "vocab_size": "vocab_size=32128", + "d_model": "d_model=768", + "d_kv": "d_kv=64", + "d_ff": "d_ff=2048", + "expert_capacity": "expert_capacity=64", + "num_layers": "num_layers=12", + "num_sparse_encoder_layers": "num_sparse_encoder_layers=3", + "num_decoder_layers": "num_decoder_layers=12", + "num_sparse_decoder_layers": "num_sparse_decoder_layers=3", + "num_heads": "num_heads=12", + "num_experts": "num_experts=8", + "router_bias": "router_bias=False", + "router_jitter_noise": "router_jitter_noise=0.01", + "router_dtype": "router_dtype='float32'", + "router_ignore_padding_tokens": "router_ignore_padding_tokens=False", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "router_z_loss_coef": "router_z_loss_coef=0.001", + "router_aux_loss_coef": "router_aux_loss_coef=0.001", + "initializer_factor": "initializer_factor=1.0", + "dense_act_fn": "dense_act_fn='relu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "add_router_probs": "add_router_probs=False", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1" + }, + "T5Model": { + "vocab_size": "vocab_size=32128", + "d_model": "d_model=512", + "d_kv": "d_kv=64", + "d_ff": "d_ff=2048", + "num_layers": "num_layers=6", + "num_decoder_layers": "num_decoder_layers=None", + "num_heads": "num_heads=8", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_factor": "initializer_factor=1.0", + "feed_forward_proj": "feed_forward_proj='relu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "classifier_dropout": "classifier_dropout=0.0" + }, + "T5GemmaModel": { + "encoder": "encoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any], NoneType] = None", + "decoder": "decoder: Union[transformers.models.t5gemma.configuration_t5gemma.T5GemmaModuleConfig, dict[Any, Any], NoneType] = None", + "is_encoder_decoder": "is_encoder_decoder: Optional[bool] = True", + "dropout_rate": "dropout_rate: Optional[float] = 0.0", + "classifier_dropout_rate": "classifier_dropout_rate: Optional[float] = 0.0", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "vocab_size": "vocab_size: Optional[int] = 256000" + }, + "T5Gemma2Model": { + "encoder": "encoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2EncoderConfig, dict[str, Any], NoneType] = None", + "decoder": "decoder: Union[transformers.models.t5gemma2.configuration_t5gemma2.T5Gemma2DecoderConfig, dict[str, Any], NoneType] = None", + "is_encoder_decoder": "is_encoder_decoder: bool = True", + "dropout_rate": "dropout_rate: float = 0.0", + "attention_dropout": "attention_dropout: float = 0.0", + "classifier_dropout_rate": "classifier_dropout_rate: float = 0.0", + "initializer_range": "initializer_range: float = 0.02", + "image_token_index": "image_token_index: int = 256001" + }, + "TableTransformerModel": { + "use_timm_backbone": "use_timm_backbone=True", + "backbone_config": "backbone_config=None", + "num_channels": "num_channels=3", + "num_queries": "num_queries=100", + "encoder_layers": "encoder_layers=6", + "encoder_ffn_dim": "encoder_ffn_dim=2048", + "encoder_attention_heads": "encoder_attention_heads=8", + "decoder_layers": "decoder_layers=6", + "decoder_ffn_dim": "decoder_ffn_dim=2048", + "decoder_attention_heads": "decoder_attention_heads=8", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='relu'", + "d_model": "d_model=256", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "init_xavier_std": "init_xavier_std=1.0", + "auxiliary_loss": "auxiliary_loss=False", + "position_embedding_type": "position_embedding_type='sine'", + "backbone": "backbone='resnet50'", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "backbone_kwargs": "backbone_kwargs=None", + "dilation": "dilation=False", + "class_cost": "class_cost=1", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "mask_loss_coefficient": "mask_loss_coefficient=1", + "dice_loss_coefficient": "dice_loss_coefficient=1", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "eos_coefficient": "eos_coefficient=0.1" + }, + "TapasModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=1024", + "type_vocab_sizes": "type_vocab_sizes=[3, 256, 256, 2, 256, 256, 10]", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=0", + "positive_label_weight": "positive_label_weight=10.0", + "num_aggregation_labels": "num_aggregation_labels=0", + "aggregation_loss_weight": "aggregation_loss_weight=1.0", + "use_answer_as_supervision": "use_answer_as_supervision=None", + "answer_loss_importance": "answer_loss_importance=1.0", + "use_normalized_answer_loss": "use_normalized_answer_loss=False", + "huber_loss_delta": "huber_loss_delta=None", + "temperature": "temperature=1.0", + "aggregation_temperature": "aggregation_temperature=1.0", + "use_gumbel_for_cells": "use_gumbel_for_cells=False", + "use_gumbel_for_aggregation": "use_gumbel_for_aggregation=False", + "average_approximation_function": "average_approximation_function='ratio'", + "cell_selection_preference": "cell_selection_preference=None", + "answer_loss_cutoff": "answer_loss_cutoff=None", + "max_num_rows": "max_num_rows=64", + "max_num_columns": "max_num_columns=32", + "average_logits_per_cell": "average_logits_per_cell=False", + "select_one_column": "select_one_column=True", + "allow_empty_column_selection": "allow_empty_column_selection=False", + "init_cell_selection_weights_to_zero": "init_cell_selection_weights_to_zero=False", + "reset_position_index_per_cell": "reset_position_index_per_cell=True", + "disable_per_token_loss": "disable_per_token_loss=False", + "aggregation_labels": "aggregation_labels=None", + "no_aggregation_label_index": "no_aggregation_label_index=None" + }, + "TapasTokenizer": { + "vocab_file": "vocab_file", + "do_lower_case": "do_lower_case=True", + "do_basic_tokenize": "do_basic_tokenize=True", + "never_split": "never_split=None", + "unk_token": "unk_token='[UNK]'", + "sep_token": "sep_token='[SEP]'", + "pad_token": "pad_token='[PAD]'", + "cls_token": "cls_token='[CLS]'", + "mask_token": "mask_token='[MASK]'", + "empty_token": "empty_token='[EMPTY]'", + "tokenize_chinese_chars": "tokenize_chinese_chars=True", + "strip_accents": "strip_accents=None", + "cell_trim_length": "cell_trim_length: int = -1", + "max_column_id": "max_column_id: Optional[int] = None", + "max_row_id": "max_row_id: Optional[int] = None", + "strip_column_names": "strip_column_names: bool = False", + "update_answer_coordinates": "update_answer_coordinates: bool = False", + "min_question_length": "min_question_length=None", + "max_question_length": "max_question_length=None", + "model_max_length": "model_max_length: int = 512", + "additional_special_tokens": "additional_special_tokens: Optional[list[str]] = None", + "clean_up_tokenization_spaces": "clean_up_tokenization_spaces=True" + }, + "TextNetModel": { + "stem_kernel_size": "stem_kernel_size=3", + "stem_stride": "stem_stride=2", + "stem_num_channels": "stem_num_channels=3", + "stem_out_channels": "stem_out_channels=64", + "stem_act_func": "stem_act_func='relu'", + "image_size": "image_size=[640, 640]", + "conv_layer_kernel_sizes": "conv_layer_kernel_sizes=None", + "conv_layer_strides": "conv_layer_strides=None", + "hidden_sizes": "hidden_sizes=[64, 64, 128, 256, 512]", + "batch_norm_eps": "batch_norm_eps=1e-05", + "initializer_range": "initializer_range=0.02", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "TimeSeriesTransformerModel": { + "prediction_length": "prediction_length: Optional[int] = None", + "context_length": "context_length: Optional[int] = None", + "distribution_output": "distribution_output: str = 'student_t'", + "loss": "loss: str = 'nll'", + "input_size": "input_size: int = 1", + "lags_sequence": "lags_sequence: list[int] = [1, 2, 3, 4, 5, 6, 7]", + "scaling": "scaling: Union[str, bool, NoneType] = 'mean'", + "num_dynamic_real_features": "num_dynamic_real_features: int = 0", + "num_static_categorical_features": "num_static_categorical_features: int = 0", + "num_static_real_features": "num_static_real_features: int = 0", + "num_time_features": "num_time_features: int = 0", + "cardinality": "cardinality: Optional[list[int]] = None", + "embedding_dimension": "embedding_dimension: Optional[list[int]] = None", + "encoder_ffn_dim": "encoder_ffn_dim: int = 32", + "decoder_ffn_dim": "decoder_ffn_dim: int = 32", + "encoder_attention_heads": "encoder_attention_heads: int = 2", + "decoder_attention_heads": "decoder_attention_heads: int = 2", + "encoder_layers": "encoder_layers: int = 2", + "decoder_layers": "decoder_layers: int = 2", + "is_encoder_decoder": "is_encoder_decoder: bool = True", + "activation_function": "activation_function: str = 'gelu'", + "d_model": "d_model: int = 64", + "dropout": "dropout: float = 0.1", + "encoder_layerdrop": "encoder_layerdrop: float = 0.1", + "decoder_layerdrop": "decoder_layerdrop: float = 0.1", + "attention_dropout": "attention_dropout: float = 0.1", + "activation_dropout": "activation_dropout: float = 0.1", + "num_parallel_samples": "num_parallel_samples: int = 100", + "init_std": "init_std: float = 0.02" + }, + "TimesFmModel": { + "patch_length": "patch_length: int = 32", + "context_length": "context_length: int = 512", + "horizon_length": "horizon_length: int = 128", + "freq_size": "freq_size: int = 3", + "num_hidden_layers": "num_hidden_layers: int = 50", + "hidden_size": "hidden_size: int = 1280", + "intermediate_size": "intermediate_size: int = 1280", + "head_dim": "head_dim: int = 80", + "num_attention_heads": "num_attention_heads: int = 16", + "tolerance": "tolerance: float = 1e-06", + "rms_norm_eps": "rms_norm_eps: float = 1e-06", + "quantiles": "quantiles: list[float] = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]", + "pad_val": "pad_val: float = 1123581321.0", + "attention_dropout": "attention_dropout: float = 0.0", + "use_positional_embedding": "use_positional_embedding: bool = False", + "initializer_range": "initializer_range: float = 0.02", + "min_timescale": "min_timescale: int = 1", + "max_timescale": "max_timescale: int = 10000" + }, + "TimesformerModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "num_frames": "num_frames=8", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "qkv_bias": "qkv_bias=True", + "attention_type": "attention_type='divided_space_time'", + "drop_path_rate": "drop_path_rate=0" + }, + "TimmBackbone": { + "backbone": "backbone=None", + "num_channels": "num_channels=3", + "features_only": "features_only=True", + "use_pretrained_backbone": "use_pretrained_backbone=True", + "out_indices": "out_indices=None", + "freeze_batch_norm_2d": "freeze_batch_norm_2d=False" + }, + "TvpModel": { + "backbone_config": "backbone_config=None", + "backbone": "backbone=None", + "use_pretrained_backbone": "use_pretrained_backbone=False", + "use_timm_backbone": "use_timm_backbone=False", + "backbone_kwargs": "backbone_kwargs=None", + "distance_loss_weight": "distance_loss_weight=1.0", + "duration_loss_weight": "duration_loss_weight=0.1", + "visual_prompter_type": "visual_prompter_type='framepad'", + "visual_prompter_apply": "visual_prompter_apply='replace'", + "visual_prompt_size": "visual_prompt_size=96", + "max_img_size": "max_img_size=448", + "num_frames": "num_frames=48", + "vocab_size": "vocab_size=30522", + "type_vocab_size": "type_vocab_size=2", + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "max_position_embeddings": "max_position_embeddings=512", + "max_grid_col_position_embeddings": "max_grid_col_position_embeddings=100", + "max_grid_row_position_embeddings": "max_grid_row_position_embeddings=100", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "hidden_act": "hidden_act='gelu'", + "layer_norm_eps": "layer_norm_eps=1e-12", + "initializer_range": "initializer_range=0.02", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1" + }, + "UdopModel": { + "vocab_size": "vocab_size=33201", + "d_model": "d_model=1024", + "d_kv": "d_kv=64", + "d_ff": "d_ff=4096", + "num_layers": "num_layers=24", + "num_decoder_layers": "num_decoder_layers=None", + "num_heads": "num_heads=16", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "relative_bias_args": "relative_bias_args=[{'type': '1d'}, {'type': 'horizontal'}, {'type': 'vertical'}]", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_factor": "initializer_factor=1.0", + "feed_forward_proj": "feed_forward_proj='relu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "max_2d_position_embeddings": "max_2d_position_embeddings=1024", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3" + }, + "UdopTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "eos_token": "eos_token=''", + "sep_token": "sep_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "sep_token_box": "sep_token_box=[1000, 1000, 1000, 1000]", + "pad_token_box": "pad_token_box=[0, 0, 0, 0]", + "pad_token_label": "pad_token_label=-100", + "only_label_first_subword": "only_label_first_subword=True", + "extra_special_tokens": "extra_special_tokens=None" + }, + "UMT5Model": { + "vocab_size": "vocab_size=250112", + "d_model": "d_model=512", + "d_kv": "d_kv=64", + "d_ff": "d_ff=1024", + "num_layers": "num_layers=8", + "num_decoder_layers": "num_decoder_layers=None", + "num_heads": "num_heads=6", + "relative_attention_num_buckets": "relative_attention_num_buckets=32", + "relative_attention_max_distance": "relative_attention_max_distance=128", + "dropout_rate": "dropout_rate=0.1", + "layer_norm_epsilon": "layer_norm_epsilon=1e-06", + "initializer_factor": "initializer_factor=1.0", + "feed_forward_proj": "feed_forward_proj='gated-gelu'", + "is_encoder_decoder": "is_encoder_decoder=True", + "tokenizer_class": "tokenizer_class='T5Tokenizer'", + "pad_token_id": "pad_token_id=0", + "eos_token_id": "eos_token_id=1", + "decoder_start_token_id": "decoder_start_token_id=0", + "classifier_dropout": "classifier_dropout=0.0" + }, + "UniSpeechModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "feat_quantizer_dropout": "feat_quantizer_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "do_stable_layer_norm": "do_stable_layer_norm=False", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "num_codevectors_per_group": "num_codevectors_per_group=320", + "num_codevector_groups": "num_codevector_groups=2", + "contrastive_logits_temperature": "contrastive_logits_temperature=0.1", + "num_negatives": "num_negatives=100", + "codevector_dim": "codevector_dim=256", + "proj_codevector_dim": "proj_codevector_dim=256", + "diversity_loss_weight": "diversity_loss_weight=0.1", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "num_ctc_classes": "num_ctc_classes=80", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "replace_prob": "replace_prob=0.5" + }, + "UniSpeechSatModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "feat_quantizer_dropout": "feat_quantizer_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "do_stable_layer_norm": "do_stable_layer_norm=False", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "num_codevectors_per_group": "num_codevectors_per_group=320", + "num_codevector_groups": "num_codevector_groups=2", + "contrastive_logits_temperature": "contrastive_logits_temperature=0.1", + "num_negatives": "num_negatives=100", + "codevector_dim": "codevector_dim=256", + "proj_codevector_dim": "proj_codevector_dim=256", + "diversity_loss_weight": "diversity_loss_weight=0.1", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "num_clusters": "num_clusters=504" + }, + "UnivNetModel": { + "model_in_channels": "model_in_channels=64", + "model_hidden_channels": "model_hidden_channels=32", + "num_mel_bins": "num_mel_bins=100", + "resblock_kernel_sizes": "resblock_kernel_sizes=[3, 3, 3]", + "resblock_stride_sizes": "resblock_stride_sizes=[8, 8, 4]", + "resblock_dilation_sizes": "resblock_dilation_sizes=[[1, 3, 9, 27], [1, 3, 9, 27], [1, 3, 9, 27]]", + "kernel_predictor_num_blocks": "kernel_predictor_num_blocks=3", + "kernel_predictor_hidden_channels": "kernel_predictor_hidden_channels=64", + "kernel_predictor_conv_size": "kernel_predictor_conv_size=3", + "kernel_predictor_dropout": "kernel_predictor_dropout=0.0", + "initializer_range": "initializer_range=0.01", + "leaky_relu_slope": "leaky_relu_slope=0.2" + }, + "VaultGemmaModel": { + "vocab_size": "vocab_size: Optional[int] = 256000", + "hidden_size": "hidden_size: Optional[int] = 2304", + "intermediate_size": "intermediate_size: Optional[int] = 9216", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 26", + "num_attention_heads": "num_attention_heads: Optional[int] = 8", + "num_key_value_heads": "num_key_value_heads: Optional[int] = 4", + "head_dim": "head_dim: Optional[int] = 256", + "hidden_activation": "hidden_activation: Optional[str] = 'gelu_pytorch_tanh'", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 8192", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-06", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "eos_token_id": "eos_token_id: Optional[int] = 1", + "bos_token_id": "bos_token_id: Optional[int] = 2", + "tie_word_embeddings": "tie_word_embeddings: Optional[bool] = True", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "attention_bias": "attention_bias: Optional[bool] = False", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "query_pre_attn_scalar": "query_pre_attn_scalar: Optional[int] = 256", + "sliding_window": "sliding_window: Optional[int] = 4096", + "layer_types": "layer_types: Optional[list[str]] = None", + "final_logit_softcapping": "final_logit_softcapping: Optional[float] = 30.0", + "attn_logit_softcapping": "attn_logit_softcapping: Optional[float] = 50.0" + }, + "VideoLlama3Model": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "image_token_id": "image_token_id=151655", + "video_token_id": "video_token_id=151656" + }, + "VideoLlama3VisionModel": { + "hidden_size": "hidden_size=768", + "intermediate_size": "intermediate_size=3072", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "num_channels": "num_channels=3", + "patch_size": "patch_size=16", + "hidden_act": "hidden_act='gelu_pytorch_tanh'", + "layer_norm_eps": "layer_norm_eps=1e-06", + "attention_dropout": "attention_dropout=0.0", + "initializer_range": "initializer_range=0.02" + }, + "VideoLlavaModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=32000", + "video_token_index": "video_token_index=32001", + "projector_hidden_act": "projector_hidden_act='gelu'", + "vision_feature_select_strategy": "vision_feature_select_strategy='default'", + "vision_feature_layer": "vision_feature_layer=-2", + "image_seq_length": "image_seq_length=256", + "video_seq_length": "video_seq_length=2056", + "multimodal_projector_bias": "multimodal_projector_bias=True" + }, + "VideoMAEModel": { + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "num_frames": "num_frames=16", + "tubelet_size": "tubelet_size=2", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "qkv_bias": "qkv_bias=True", + "use_mean_pooling": "use_mean_pooling=True", + "decoder_num_attention_heads": "decoder_num_attention_heads=6", + "decoder_hidden_size": "decoder_hidden_size=384", + "decoder_num_hidden_layers": "decoder_num_hidden_layers=4", + "decoder_intermediate_size": "decoder_intermediate_size=1536", + "norm_pix_loss": "norm_pix_loss=True" + }, + "ViltModel": { + "vocab_size": "vocab_size=30522", + "type_vocab_size": "type_vocab_size=2", + "modality_type_vocab_size": "modality_type_vocab_size=2", + "max_position_embeddings": "max_position_embeddings=40", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=384", + "patch_size": "patch_size=32", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "max_image_length": "max_image_length=-1", + "tie_word_embeddings": "tie_word_embeddings=True", + "num_images": "num_images=-1" + }, + "VipLlavaModel": { + "vision_config": "vision_config=None", + "text_config": "text_config=None", + "image_token_index": "image_token_index=32000", + "projector_hidden_act": "projector_hidden_act='gelu'", + "projector_layernorm_eps": "projector_layernorm_eps=1e-05", + "vision_feature_layers": "vision_feature_layers=[-2, -5, -8, -11, 6]", + "image_seq_length": "image_seq_length=576" + }, + "VisionTextDualEncoderModel": { + "projection_dim": "projection_dim=512", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "VisualBertModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "visual_embedding_dim": "visual_embedding_dim=512", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "bypass_transformer": "bypass_transformer=False", + "special_visual_initialize": "special_visual_initialize=True", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "ViTModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "encoder_stride": "encoder_stride=16", + "pooler_output_size": "pooler_output_size=None", + "pooler_act": "pooler_act='tanh'" + }, + "ViTMAEModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "decoder_num_attention_heads": "decoder_num_attention_heads=16", + "decoder_hidden_size": "decoder_hidden_size=512", + "decoder_num_hidden_layers": "decoder_num_hidden_layers=8", + "decoder_intermediate_size": "decoder_intermediate_size=2048", + "mask_ratio": "mask_ratio=0.75", + "norm_pix_loss": "norm_pix_loss=False" + }, + "ViTMSNModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True" + }, + "VitDetModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "mlp_ratio": "mlp_ratio=4", + "hidden_act": "hidden_act='gelu'", + "dropout_prob": "dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "image_size": "image_size=224", + "pretrain_image_size": "pretrain_image_size=224", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "drop_path_rate": "drop_path_rate=0.0", + "window_block_indices": "window_block_indices=[]", + "residual_block_indices": "residual_block_indices=[]", + "use_absolute_position_embeddings": "use_absolute_position_embeddings=True", + "use_relative_position_embeddings": "use_relative_position_embeddings=False", + "window_size": "window_size=0", + "out_features": "out_features=None", + "out_indices": "out_indices=None" + }, + "VitsModel": { + "vocab_size": "vocab_size=38", + "hidden_size": "hidden_size=192", + "num_hidden_layers": "num_hidden_layers=6", + "num_attention_heads": "num_attention_heads=2", + "window_size": "window_size=4", + "use_bias": "use_bias=True", + "ffn_dim": "ffn_dim=768", + "layerdrop": "layerdrop=0.1", + "ffn_kernel_size": "ffn_kernel_size=3", + "flow_size": "flow_size=192", + "spectrogram_bins": "spectrogram_bins=513", + "hidden_act": "hidden_act='relu'", + "hidden_dropout": "hidden_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "use_stochastic_duration_prediction": "use_stochastic_duration_prediction=True", + "num_speakers": "num_speakers=1", + "speaker_embedding_size": "speaker_embedding_size=0", + "upsample_initial_channel": "upsample_initial_channel=512", + "upsample_rates": "upsample_rates=[8, 8, 2, 2]", + "upsample_kernel_sizes": "upsample_kernel_sizes=[16, 16, 4, 4]", + "resblock_kernel_sizes": "resblock_kernel_sizes=[3, 7, 11]", + "resblock_dilation_sizes": "resblock_dilation_sizes=[[1, 3, 5], [1, 3, 5], [1, 3, 5]]", + "leaky_relu_slope": "leaky_relu_slope=0.1", + "depth_separable_channels": "depth_separable_channels=2", + "depth_separable_num_layers": "depth_separable_num_layers=3", + "duration_predictor_flow_bins": "duration_predictor_flow_bins=10", + "duration_predictor_tail_bound": "duration_predictor_tail_bound=5.0", + "duration_predictor_kernel_size": "duration_predictor_kernel_size=3", + "duration_predictor_dropout": "duration_predictor_dropout=0.5", + "duration_predictor_num_flows": "duration_predictor_num_flows=4", + "duration_predictor_filter_channels": "duration_predictor_filter_channels=256", + "prior_encoder_num_flows": "prior_encoder_num_flows=4", + "prior_encoder_num_wavenet_layers": "prior_encoder_num_wavenet_layers=4", + "posterior_encoder_num_wavenet_layers": "posterior_encoder_num_wavenet_layers=16", + "wavenet_kernel_size": "wavenet_kernel_size=5", + "wavenet_dilation_rate": "wavenet_dilation_rate=1", + "wavenet_dropout": "wavenet_dropout=0.0", + "speaking_rate": "speaking_rate=1.0", + "noise_scale": "noise_scale=0.667", + "noise_scale_duration": "noise_scale_duration=0.8", + "sampling_rate": "sampling_rate=16000" + }, + "VitsTokenizer": { + "vocab_file": "vocab_file", + "pad_token": "pad_token=''", + "unk_token": "unk_token=''", + "language": "language=None", + "add_blank": "add_blank=True", + "normalize": "normalize=True", + "phonemize": "phonemize=True", + "is_uroman": "is_uroman=False" + }, + "VivitModel": { + "image_size": "image_size=224", + "num_frames": "num_frames=32", + "tubelet_size": "tubelet_size=[2, 16, 16]", + "num_channels": "num_channels=3", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu_fast'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-06", + "qkv_bias": "qkv_bias=True" + }, + "VJEPA2Model": { + "patch_size": "patch_size=16", + "crop_size": "crop_size=256", + "frames_per_clip": "frames_per_clip=64", + "tubelet_size": "tubelet_size=2", + "hidden_size": "hidden_size=1024", + "in_chans": "in_chans=3", + "num_attention_heads": "num_attention_heads=16", + "num_hidden_layers": "num_hidden_layers=24", + "drop_path_rate": "drop_path_rate=0.0", + "mlp_ratio": "mlp_ratio=4.0", + "layer_norm_eps": "layer_norm_eps=1e-06", + "qkv_bias": "qkv_bias=True", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "hidden_act": "hidden_act='gelu'", + "initializer_range": "initializer_range=0.02", + "attention_dropout": "attention_dropout=0.0", + "num_pooler_layers": "num_pooler_layers=3", + "pred_hidden_size": "pred_hidden_size=384", + "pred_num_attention_heads": "pred_num_attention_heads=12", + "pred_num_hidden_layers": "pred_num_hidden_layers=12", + "pred_num_mask_tokens": "pred_num_mask_tokens=10", + "pred_zero_init_mask_tokens": "pred_zero_init_mask_tokens=True", + "pred_mlp_ratio": "pred_mlp_ratio=4.0" + }, + "VoxtralForConditionalGeneration": { + "audio_config": "audio_config=None", + "text_config": "text_config=None", + "audio_token_id": "audio_token_id=None", + "projector_hidden_act": "projector_hidden_act='gelu'" + }, + "VoxtralEncoder": { + "vocab_size": "vocab_size=51866", + "hidden_size": "hidden_size=1280", + "intermediate_size": "intermediate_size=5120", + "num_hidden_layers": "num_hidden_layers=32", + "num_attention_heads": "num_attention_heads=20", + "scale_embedding": "scale_embedding=False", + "activation_function": "activation_function='gelu'", + "num_mel_bins": "num_mel_bins=128", + "max_source_positions": "max_source_positions=1500", + "initializer_range": "initializer_range=0.02", + "attention_dropout": "attention_dropout=0.0" + }, + "Wav2Vec2Model": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "feat_quantizer_dropout": "feat_quantizer_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "do_stable_layer_norm": "do_stable_layer_norm=False", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "num_codevectors_per_group": "num_codevectors_per_group=320", + "num_codevector_groups": "num_codevector_groups=2", + "contrastive_logits_temperature": "contrastive_logits_temperature=0.1", + "num_negatives": "num_negatives=100", + "codevector_dim": "codevector_dim=256", + "proj_codevector_dim": "proj_codevector_dim=256", + "diversity_loss_weight": "diversity_loss_weight=0.1", + "ctc_loss_reduction": "ctc_loss_reduction='sum'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "add_adapter": "add_adapter=False", + "adapter_kernel_size": "adapter_kernel_size=3", + "adapter_stride": "adapter_stride=2", + "num_adapter_layers": "num_adapter_layers=3", + "output_hidden_size": "output_hidden_size=None", + "adapter_attn_dim": "adapter_attn_dim=None" + }, + "Wav2Vec2BertModel": { + "vocab_size": "vocab_size=None", + "hidden_size": "hidden_size=1024", + "num_hidden_layers": "num_hidden_layers=24", + "num_attention_heads": "num_attention_heads=16", + "intermediate_size": "intermediate_size=4096", + "feature_projection_input_dim": "feature_projection_input_dim=160", + "hidden_act": "hidden_act='swish'", + "hidden_dropout": "hidden_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "ctc_loss_reduction": "ctc_loss_reduction='sum'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=768", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "add_adapter": "add_adapter=False", + "adapter_kernel_size": "adapter_kernel_size=3", + "adapter_stride": "adapter_stride=2", + "num_adapter_layers": "num_adapter_layers=1", + "adapter_act": "adapter_act='relu'", + "use_intermediate_ffn_before_adapter": "use_intermediate_ffn_before_adapter=False", + "output_hidden_size": "output_hidden_size=None", + "position_embeddings_type": "position_embeddings_type='relative_key'", + "rotary_embedding_base": "rotary_embedding_base=10000", + "max_source_positions": "max_source_positions=5000", + "left_max_position_embeddings": "left_max_position_embeddings=64", + "right_max_position_embeddings": "right_max_position_embeddings=8", + "conv_depthwise_kernel_size": "conv_depthwise_kernel_size=31", + "conformer_conv_dropout": "conformer_conv_dropout=0.1" + }, + "Wav2Vec2ConformerModel": { + "vocab_size": "vocab_size=None", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "feat_quantizer_dropout": "feat_quantizer_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "num_codevectors_per_group": "num_codevectors_per_group=320", + "num_codevector_groups": "num_codevector_groups=2", + "contrastive_logits_temperature": "contrastive_logits_temperature=0.1", + "num_negatives": "num_negatives=100", + "codevector_dim": "codevector_dim=256", + "proj_codevector_dim": "proj_codevector_dim=256", + "diversity_loss_weight": "diversity_loss_weight=0.1", + "ctc_loss_reduction": "ctc_loss_reduction='sum'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "add_adapter": "add_adapter=False", + "adapter_kernel_size": "adapter_kernel_size=3", + "adapter_stride": "adapter_stride=2", + "num_adapter_layers": "num_adapter_layers=3", + "output_hidden_size": "output_hidden_size=None", + "position_embeddings_type": "position_embeddings_type='relative'", + "rotary_embedding_base": "rotary_embedding_base=10000", + "max_source_positions": "max_source_positions=5000", + "conv_depthwise_kernel_size": "conv_depthwise_kernel_size=31", + "conformer_conv_dropout": "conformer_conv_dropout=0.1" + }, + "WavLMModel": { + "vocab_size": "vocab_size=32", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout": "hidden_dropout=0.1", + "activation_dropout": "activation_dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "feat_proj_dropout": "feat_proj_dropout=0.0", + "final_dropout": "final_dropout=0.1", + "layerdrop": "layerdrop=0.1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "feat_extract_norm": "feat_extract_norm='group'", + "feat_extract_activation": "feat_extract_activation='gelu'", + "conv_dim": "conv_dim=(512, 512, 512, 512, 512, 512, 512)", + "conv_stride": "conv_stride=(5, 2, 2, 2, 2, 2, 2)", + "conv_kernel": "conv_kernel=(10, 3, 3, 3, 3, 2, 2)", + "conv_bias": "conv_bias=False", + "num_conv_pos_embeddings": "num_conv_pos_embeddings=128", + "num_conv_pos_embedding_groups": "num_conv_pos_embedding_groups=16", + "num_buckets": "num_buckets=320", + "max_bucket_distance": "max_bucket_distance=800", + "do_stable_layer_norm": "do_stable_layer_norm=False", + "apply_spec_augment": "apply_spec_augment=True", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "num_codevectors_per_group": "num_codevectors_per_group=320", + "num_codevector_groups": "num_codevector_groups=2", + "contrastive_logits_temperature": "contrastive_logits_temperature=0.1", + "num_negatives": "num_negatives=100", + "codevector_dim": "codevector_dim=256", + "proj_codevector_dim": "proj_codevector_dim=256", + "diversity_loss_weight": "diversity_loss_weight=0.1", + "ctc_loss_reduction": "ctc_loss_reduction='mean'", + "ctc_zero_infinity": "ctc_zero_infinity=False", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "tdnn_dim": "tdnn_dim=(512, 512, 512, 512, 1500)", + "tdnn_kernel": "tdnn_kernel=(5, 3, 3, 1, 1)", + "tdnn_dilation": "tdnn_dilation=(1, 2, 3, 1, 1)", + "xvector_output_dim": "xvector_output_dim=512", + "num_ctc_classes": "num_ctc_classes=80", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "add_adapter": "add_adapter=False", + "adapter_kernel_size": "adapter_kernel_size=3", + "adapter_stride": "adapter_stride=2", + "num_adapter_layers": "num_adapter_layers=3", + "output_hidden_size": "output_hidden_size=None" + }, + "WhisperModel": { + "vocab_size": "vocab_size=51865", + "num_mel_bins": "num_mel_bins=80", + "encoder_layers": "encoder_layers=4", + "encoder_attention_heads": "encoder_attention_heads=6", + "decoder_layers": "decoder_layers=4", + "decoder_attention_heads": "decoder_attention_heads=6", + "decoder_ffn_dim": "decoder_ffn_dim=1536", + "encoder_ffn_dim": "encoder_ffn_dim=1536", + "encoder_layerdrop": "encoder_layerdrop=0.0", + "decoder_layerdrop": "decoder_layerdrop=0.0", + "decoder_start_token_id": "decoder_start_token_id=50257", + "is_encoder_decoder": "is_encoder_decoder=True", + "activation_function": "activation_function='gelu'", + "d_model": "d_model=384", + "dropout": "dropout=0.0", + "attention_dropout": "attention_dropout=0.0", + "activation_dropout": "activation_dropout=0.0", + "init_std": "init_std=0.02", + "scale_embedding": "scale_embedding=False", + "max_source_positions": "max_source_positions=1500", + "max_target_positions": "max_target_positions=448", + "pad_token_id": "pad_token_id=50256", + "bos_token_id": "bos_token_id=50256", + "eos_token_id": "eos_token_id=50256", + "suppress_tokens": "suppress_tokens=None", + "begin_suppress_tokens": "begin_suppress_tokens=[220, 50256]", + "use_weighted_layer_sum": "use_weighted_layer_sum=False", + "classifier_proj_size": "classifier_proj_size=256", + "apply_spec_augment": "apply_spec_augment=False", + "mask_time_prob": "mask_time_prob=0.05", + "mask_time_length": "mask_time_length=10", + "mask_time_min_masks": "mask_time_min_masks=2", + "mask_feature_prob": "mask_feature_prob=0.0", + "mask_feature_length": "mask_feature_length=10", + "mask_feature_min_masks": "mask_feature_min_masks=0", + "median_filter_width": "median_filter_width=7" + }, + "WhisperTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges=None", + "normalizer_file": "normalizer_file=None", + "unk_token": "unk_token='<|endoftext|>'", + "bos_token": "bos_token='<|endoftext|>'", + "eos_token": "eos_token='<|endoftext|>'", + "add_prefix_space": "add_prefix_space=False", + "language": "language=None", + "task": "task=None", + "predict_timestamps": "predict_timestamps=False" + }, + "XCLIPModel": { + "text_config": "text_config=None", + "vision_config": "vision_config=None", + "projection_dim": "projection_dim=512", + "prompt_layers": "prompt_layers=2", + "prompt_alpha": "prompt_alpha=0.1", + "prompt_hidden_act": "prompt_hidden_act='quick_gelu'", + "prompt_num_attention_heads": "prompt_num_attention_heads=8", + "prompt_attention_dropout": "prompt_attention_dropout=0.0", + "prompt_projection_dropout": "prompt_projection_dropout=0.0", + "logit_scale_init_value": "logit_scale_init_value=2.6592" + }, + "XcodecModel": { + "target_bandwidths": "target_bandwidths: Optional[list[float]] = None", + "sample_rate": "sample_rate: int = 16000", + "kernel_size": "kernel_size: int = 3", + "channel_ratios": "channel_ratios: list[float] = [1, 1]", + "strides": "strides: list[int] = [1, 1]", + "block_dilations": "block_dilations: list[int] = [1, 1]", + "unit_kernel_size": "unit_kernel_size: int = 3", + "codebook_size": "codebook_size: int = 1024", + "codebook_dim": "codebook_dim: Optional[int] = None", + "initializer_range": "initializer_range: float = 0.02", + "acoustic_model_config": "acoustic_model_config: Union[dict, transformers.models.dac.configuration_dac.DacConfig, NoneType] = None", + "semantic_model_config": "semantic_model_config: Union[dict, transformers.models.hubert.configuration_hubert.HubertConfig, NoneType] = None" + }, + "XGLMModel": { + "vocab_size": "vocab_size=256008", + "max_position_embeddings": "max_position_embeddings=2048", + "d_model": "d_model=1024", + "ffn_dim": "ffn_dim=4096", + "num_layers": "num_layers=24", + "attention_heads": "attention_heads=16", + "activation_function": "activation_function='gelu'", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation_dropout": "activation_dropout=0.0", + "layerdrop": "layerdrop=0.0", + "init_std": "init_std=0.02", + "scale_embedding": "scale_embedding=True", + "decoder_start_token_id": "decoder_start_token_id=2", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "XGLMTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "sep_token": "sep_token: str = ''", + "cls_token": "cls_token: str = ''", + "unk_token": "unk_token: str = ''", + "pad_token": "pad_token: str = ''", + "add_prefix_space": "add_prefix_space: bool = True" + }, + "XLMModel": { + "vocab_size": "vocab_size=30145", + "emb_dim": "emb_dim=2048", + "n_layers": "n_layers=12", + "n_heads": "n_heads=16", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "gelu_activation": "gelu_activation=True", + "sinusoidal_embeddings": "sinusoidal_embeddings=False", + "causal": "causal=False", + "asm": "asm=False", + "n_langs": "n_langs=1", + "use_lang_emb": "use_lang_emb=True", + "max_position_embeddings": "max_position_embeddings=512", + "embed_init_std": "embed_init_std=0.02209708691207961", + "layer_norm_eps": "layer_norm_eps=1e-12", + "init_std": "init_std=0.02", + "bos_index": "bos_index=0", + "eos_index": "eos_index=1", + "pad_index": "pad_index=2", + "unk_index": "unk_index=3", + "mask_index": "mask_index=5", + "is_encoder": "is_encoder=True", + "summary_type": "summary_type='first'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation=None", + "summary_proj_to_labels": "summary_proj_to_labels=True", + "summary_first_dropout": "summary_first_dropout=0.1", + "start_n_top": "start_n_top=5", + "end_n_top": "end_n_top=5", + "mask_token_id": "mask_token_id=0", + "lang_id": "lang_id=0", + "pad_token_id": "pad_token_id=2", + "bos_token_id": "bos_token_id=0" + }, + "XLMTokenizer": { + "vocab_file": "vocab_file", + "merges_file": "merges_file", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''", + "cls_token": "cls_token=''", + "mask_token": "mask_token=''", + "additional_special_tokens": "additional_special_tokens=['', '', '', '', '', '', '', '', '', '']", + "lang2id": "lang2id=None", + "id2lang": "id2lang=None", + "do_lowercase_and_remove_accent": "do_lowercase_and_remove_accent=True" + }, + "XLMRobertaModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "XLMRobertaXLModel": { + "vocab_size": "vocab_size=250880", + "hidden_size": "hidden_size=2560", + "num_hidden_layers": "num_hidden_layers=36", + "num_attention_heads": "num_attention_heads=32", + "intermediate_size": "intermediate_size=10240", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=514", + "type_vocab_size": "type_vocab_size=1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-05", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "XLNetModel": { + "vocab_size": "vocab_size=32000", + "d_model": "d_model=1024", + "n_layer": "n_layer=24", + "n_head": "n_head=16", + "d_inner": "d_inner=4096", + "ff_activation": "ff_activation='gelu'", + "attn_type": "attn_type='bi'", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "dropout": "dropout=0.1", + "mem_len": "mem_len=512", + "reuse_len": "reuse_len=None", + "use_mems_eval": "use_mems_eval=True", + "use_mems_train": "use_mems_train=False", + "bi_data": "bi_data=False", + "clamp_len": "clamp_len=-1", + "same_length": "same_length=False", + "summary_type": "summary_type='last'", + "summary_use_proj": "summary_use_proj=True", + "summary_activation": "summary_activation='tanh'", + "summary_last_dropout": "summary_last_dropout=0.1", + "start_n_top": "start_n_top=5", + "end_n_top": "end_n_top=5", + "pad_token_id": "pad_token_id=5", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2" + }, + "XLNetTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "unk_id": "unk_id: int = 0", + "do_lower_case": "do_lower_case=False", + "remove_space": "remove_space=True", + "keep_accents": "keep_accents=False", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "sep_token": "sep_token=''", + "pad_token": "pad_token=''", + "cls_token": "cls_token=''", + "mask_token": "mask_token=''", + "additional_special_tokens": "additional_special_tokens=None" + }, + "xLSTMModel": { + "vocab_size": "vocab_size: int = 50304", + "hidden_size": "hidden_size: int = 4096", + "embedding_dim": "embedding_dim: Optional[int] = None", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 32", + "num_blocks": "num_blocks: Optional[int] = None", + "num_heads": "num_heads: int = 8", + "use_bias": "use_bias: bool = False", + "norm_reduction_force_float32": "norm_reduction_force_float32: bool = True", + "tie_word_embeddings": "tie_word_embeddings: bool = False", + "add_out_norm": "add_out_norm: bool = True", + "norm_eps": "norm_eps: float = 1e-06", + "qk_dim_factor": "qk_dim_factor: float = 0.5", + "v_dim_factor": "v_dim_factor: float = 1.0", + "chunkwise_kernel": "chunkwise_kernel: Literal['chunkwise--native_autograd', 'parallel--native_autograd'] = 'chunkwise--native_autograd'", + "sequence_kernel": "sequence_kernel: Literal['native_sequence__native'] = 'native_sequence__native'", + "step_kernel": "step_kernel: Literal['native'] = 'native'", + "mode": "mode: Literal['train', 'train_with_padding', 'inference'] = 'inference'", + "chunk_size": "chunk_size: int = 64", + "return_last_states": "return_last_states: bool = True", + "autocast_kernel_dtype": "autocast_kernel_dtype: Literal['float32', 'bfloat16', 'float16'] = 'bfloat16'", + "eps": "eps: float = 1e-06", + "inference_state_dtype": "inference_state_dtype: Literal['float32', 'bfloat16', 'float16'] = 'float32'", + "ffn_proj_factor": "ffn_proj_factor: float = 2.667", + "ffn_round_up_to_multiple_of": "ffn_round_up_to_multiple_of: int = 64", + "gate_soft_cap": "gate_soft_cap: float = 15.0", + "output_logit_soft_cap": "output_logit_soft_cap: float = 30.0", + "weight_mode": "weight_mode: Literal['single', 'fused'] = 'single'", + "pad_token_id": "pad_token_id: int = 1", + "bos_token_id": "bos_token_id: int = 0", + "eos_token_id": "eos_token_id: int = 2", + "max_inference_chunksize": "max_inference_chunksize: int = 16384" + }, + "XmodModel": { + "vocab_size": "vocab_size=30522", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None", + "pre_norm": "pre_norm=False", + "adapter_reduction_factor": "adapter_reduction_factor=2", + "adapter_layer_norm": "adapter_layer_norm=False", + "adapter_reuse_layer_norm": "adapter_reuse_layer_norm=True", + "ln_before_adapter": "ln_before_adapter=True", + "languages": "languages=('en_XX',)", + "default_language": "default_language=None" + }, + "YolosModel": { + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.0", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "image_size": "image_size=[512, 864]", + "patch_size": "patch_size=16", + "num_channels": "num_channels=3", + "qkv_bias": "qkv_bias=True", + "num_detection_tokens": "num_detection_tokens=100", + "use_mid_position_embeddings": "use_mid_position_embeddings=True", + "auxiliary_loss": "auxiliary_loss=False", + "class_cost": "class_cost=1", + "bbox_cost": "bbox_cost=5", + "giou_cost": "giou_cost=2", + "bbox_loss_coefficient": "bbox_loss_coefficient=5", + "giou_loss_coefficient": "giou_loss_coefficient=2", + "eos_coefficient": "eos_coefficient=0.1" + }, + "YosoModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=4096", + "type_vocab_size": "type_vocab_size=1", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "use_expectation": "use_expectation=True", + "hash_code_len": "hash_code_len=9", + "num_hash": "num_hash=64", + "conv_window": "conv_window=None", + "use_fast_hash": "use_fast_hash=True", + "lsh_backward": "lsh_backward=True", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2" + }, + "ZambaModel": { + "vocab_size": "vocab_size=32000", + "tie_word_embeddings": "tie_word_embeddings=True", + "hidden_size": "hidden_size=3712", + "attention_hidden_size": "attention_hidden_size=None", + "intermediate_size": "intermediate_size=14848", + "num_hidden_layers": "num_hidden_layers=76", + "num_attention_heads": "num_attention_heads=16", + "attention_head_dim": "attention_head_dim=None", + "num_key_value_heads": "num_key_value_heads=16", + "n_mamba_heads": "n_mamba_heads=2", + "hidden_act": "hidden_act='gelu'", + "hidden_mamba_act": "hidden_mamba_act='silu'", + "initializer_range": "initializer_range=0.02", + "rms_norm_eps": "rms_norm_eps=1e-05", + "num_logits_to_keep": "num_logits_to_keep=1", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=1", + "eos_token_id": "eos_token_id=2", + "max_position_embeddings": "max_position_embeddings=4096", + "attention_dropout": "attention_dropout=0.0", + "attn_layer_period": "attn_layer_period=6", + "attn_layer_offset": "attn_layer_offset=4", + "use_mamba_kernels": "use_mamba_kernels=True", + "mamba_d_state": "mamba_d_state=16", + "mamba_d_conv": "mamba_d_conv=4", + "mamba_expand": "mamba_expand=2", + "mamba_dt_rank": "mamba_dt_rank='auto'", + "time_step_min": "time_step_min=0.001", + "time_step_max": "time_step_max=0.1", + "time_step_floor": "time_step_floor=0.0001", + "mamba_conv_bias": "mamba_conv_bias=True", + "mamba_proj_bias": "mamba_proj_bias=False" + }, + "Zamba2Model": { + "vocab_size": "vocab_size: Optional[int] = 32000", + "max_position_embeddings": "max_position_embeddings: Optional[int] = 4096", + "hidden_size": "hidden_size: Optional[int] = 2560", + "num_hidden_layers": "num_hidden_layers: Optional[int] = 54", + "layers_block_type": "layers_block_type: Optional[list[str]] = None", + "mamba_d_state": "mamba_d_state: Optional[int] = 64", + "mamba_d_conv": "mamba_d_conv: Optional[int] = 4", + "mamba_expand": "mamba_expand: Optional[int] = 2", + "mamba_ngroups": "mamba_ngroups: Optional[int] = 1", + "time_step_min": "time_step_min: Optional[float] = 0.001", + "time_step_max": "time_step_max: Optional[float] = 0.1", + "time_step_floor": "time_step_floor: Optional[int] = 0.0001", + "time_step_limit": "time_step_limit: Optional[int] = None", + "n_mamba_heads": "n_mamba_heads: Optional[int] = 8", + "use_conv_bias": "use_conv_bias: Optional[bool] = True", + "chunk_size": "chunk_size: Optional[int] = 256", + "use_mem_eff_path": "use_mem_eff_path: Optional[bool] = False", + "add_bias_linear": "add_bias_linear: Optional[bool] = False", + "intermediate_size": "intermediate_size: Optional[int] = None", + "hidden_act": "hidden_act: Optional[str] = 'gelu'", + "num_attention_heads": "num_attention_heads: Optional[int] = 32", + "num_key_value_heads": "num_key_value_heads: Optional[int] = None", + "attention_dropout": "attention_dropout: Optional[float] = 0.0", + "num_mem_blocks": "num_mem_blocks: Optional[int] = 1", + "use_shared_attention_adapter": "use_shared_attention_adapter: Optional[bool] = False", + "adapter_rank": "adapter_rank: Optional[int] = 128", + "use_mem_rope": "use_mem_rope: Optional[bool] = False", + "rope_parameters": "rope_parameters: Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None", + "initializer_range": "initializer_range: Optional[float] = 0.02", + "rms_norm_eps": "rms_norm_eps: Optional[int] = 1e-05", + "num_logits_to_keep": "num_logits_to_keep: Optional[int] = 1", + "pad_token_id": "pad_token_id: Optional[int] = 0", + "bos_token_id": "bos_token_id: Optional[int] = 1", + "eos_token_id": "eos_token_id: Optional[int] = 2", + "use_long_context": "use_long_context: Optional[bool] = False" + } + }, + "diffusers": { + "UNet1DModel": null, + "DDPMScheduler": null, + "ValueGuidedRLPipeline": null, + "T5Tokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "extra_ids": "extra_ids=100", + "additional_special_tokens": "additional_special_tokens=None" + }, + "T5EncoderModel": null, + "AutoencoderKLAllegro": null, + "AllegroTransformer3DModel": null, + "KarrasDiffusionSchedulers": null, + "AllegroPipeline": null, + "VQModel": null, + "CLIPTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "unk_token": "unk_token: str = '<|endoftext|>'", + "bos_token": "bos_token: str = '<|startoftext|>'", + "eos_token": "eos_token: str = '<|endoftext|>'", + "pad_token": "pad_token: str = '<|endoftext|>'" + }, + "CLIPTextModelWithProjection": null, + "UVit2DModel": null, + "AmusedScheduler": null, + "AmusedPipeline": null, + "AmusedImg2ImgPipeline": null, + "AmusedInpaintPipeline": null, + "AutoencoderKL": null, + "CLIPTextModel": null, + "Union": null, + "MotionAdapter": null, + "CLIPImageProcessor": null, + "CLIPVisionModelWithProjection": null, + "AnimateDiffPipeline": null, + "Optional": null, + "AnimateDiffControlNetPipeline": null, + "bool": null, + "AnimateDiffSDXLPipeline": null, + "SparseControlNetModel": null, + "AnimateDiffSparseControlNetPipeline": null, + "AnimateDiffVideoToVideoPipeline": null, + "AnimateDiffVideoToVideoControlNetPipeline": null, + "ClapTextModelWithProjection": null, + "UNet2DConditionModel": null, + "SpeechT5HifiGan": null, + "AudioLDMPipeline": null, + "ClapModel": null, + "AudioLDM2ProjectionModel": null, + "GPT2LMHeadModel": null, + "ClapFeatureExtractor": null, + "AudioLDM2UNet2DConditionModel": null, + "AudioLDM2Pipeline": null, + "UMT5EncoderModel": null, + "AuraFlowTransformer2DModel": null, + "FlowMatchEulerDiscreteScheduler": null, + "AuraFlowPipeline": null, + "ContextCLIPTextModel": null, + "PNDMScheduler": null, + "Blip2QFormerModel": null, + "BlipImageProcessor": null, + "int": null, + "List": null, + "BlipDiffusionPipeline": null, + "BriaTransformer2DModel": null, + "BriaPipeline": null, + "BriaFiboTransformer2DModel": null, + "AutoencoderKLWan": null, + "SmolLM3ForCausalLM": null, + "AutoTokenizer": {}, + "BriaFiboPipeline": null, + "ChromaTransformer2DModel": null, + "ChromaPipeline": null, + "ChromaImg2ImgPipeline": null, + "CLIPVisionModel": null, + "ChronoEditTransformer3DModel": null, + "ChronoEditPipeline": null, + "AutoencoderKLCogVideoX": null, + "CogVideoXTransformer3DModel": null, + "CogVideoXPipeline": null, + "CogVideoXFunControlPipeline": null, + "CogVideoXImageToVideoPipeline": null, + "CogVideoXVideoToVideoPipeline": null, + "CogView3PlusTransformer2DModel": null, + "CogView3PlusPipeline": null, + "GlmModel": null, + "CogView4Transformer2DModel": null, + "CogView4Pipeline": null, + "CogView4ControlPipeline": null, + "ConsisIDTransformer3DModel": null, + "CogVideoXDPMScheduler": null, + "ConsisIDPipeline": null, + "UNet2DModel": null, + "CMStochasticIterativeScheduler": null, + "NoneType": null, + "ConsistencyModelPipeline": null, + "StableDiffusionSafetyChecker": null, + "StableDiffusionControlNetPipeline": null, + "ControlNetModel": null, + "BlipDiffusionControlNetPipeline": null, + "StableDiffusionControlNetImg2ImgPipeline": null, + "StableDiffusionControlNetInpaintPipeline": null, + "StableDiffusionXLControlNetInpaintPipeline": null, + "StableDiffusionXLControlNetPipeline": null, + "StableDiffusionXLControlNetImg2ImgPipeline": null, + "StableDiffusionXLControlNetUnionInpaintPipeline": null, + "StableDiffusionXLControlNetUnionPipeline": null, + "StableDiffusionXLControlNetUnionImg2ImgPipeline": null, + "BertModel": null, + "BertTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "do_lower_case": "do_lower_case: bool = False", + "unk_token": "unk_token: str = '[UNK]'", + "sep_token": "sep_token: str = '[SEP]'", + "pad_token": "pad_token: str = '[PAD]'", + "cls_token": "cls_token: str = '[CLS]'", + "mask_token": "mask_token: str = '[MASK]'", + "tokenize_chinese_chars": "tokenize_chinese_chars: bool = True", + "strip_accents": "strip_accents: Optional[bool] = None" + }, + "HunyuanDiT2DModel": null, + "HunyuanDiTControlNetPipeline": null, + "SD3Transformer2DModel": null, + "StableDiffusion3ControlNetPipeline": null, + "SiglipModel": null, + "StableDiffusion3ControlNetInpaintingPipeline": null, + "ControlNetXSAdapter": null, + "StableDiffusionControlNetXSPipeline": null, + "StableDiffusionXLControlNetXSPipeline": null, + "Qwen2_5_VLForConditionalGeneration": null, + "CosmosTransformer3DModel": null, + "UniPCMultistepScheduler": null, + "CosmosSafetyChecker": null, + "Cosmos2_5_PredictBasePipeline": null, + "Cosmos2TextToImagePipeline": null, + "Cosmos2VideoToWorldPipeline": null, + "AutoencoderKLCosmos": null, + "EDMEulerScheduler": null, + "CosmosTextToWorldPipeline": null, + "CosmosVideoToWorldPipeline": null, + "SchedulerMixin": null, + "DanceDiffusionPipeline": null, + "DDIMScheduler": null, + "DDIMPipeline": null, + "DDPMPipeline": null, + "IFPipeline": null, + "IFImg2ImgPipeline": null, + "IFImg2ImgSuperResolutionPipeline": null, + "IFInpaintingPipeline": null, + "IFInpaintingSuperResolutionPipeline": null, + "IFSuperResolutionPipeline": null, + "RobertaSeriesModelWithTransformation": null, + "XLMRobertaTokenizer": { + "vocab": "vocab: Union[str, list[tuple[str, float]], NoneType] = None", + "add_prefix_space": "add_prefix_space: bool = True", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "sep_token": "sep_token: str = ''", + "cls_token": "cls_token: str = ''", + "unk_token": "unk_token: str = ''", + "pad_token": "pad_token: str = ''", + "mask_token": "mask_token: str = ''" + }, + "AltDiffusionPipeline": null, + "AltDiffusionImg2ImgPipeline": null, + "Mel": null, + "AudioDiffusionPipeline": null, + "LDMPipeline": null, + "PNDMPipeline": null, + "RePaintScheduler": null, + "RePaintPipeline": null, + "ScoreSdeVeScheduler": null, + "ScoreSdeVePipeline": null, + "SpectrogramNotesEncoder": null, + "SpectrogramContEncoder": null, + "T5FilmDecoder": null, + "Any": null, + "SpectrogramDiffusionPipeline": null, + "CycleDiffusionPipeline": null, + "OnnxRuntimeModel": null, + "OnnxStableDiffusionInpaintPipelineLegacy": null, + "StableDiffusionInpaintPipelineLegacy": null, + "list": null, + "StableDiffusionModelEditingPipeline": null, + "StableDiffusionParadigmsPipeline": null, + "DDIMInverseScheduler": null, + "BlipForConditionalGeneration": null, + "BlipProcessor": null, + "StableDiffusionPix2PixZeroPipeline": null, + "KarrasVeScheduler": null, + "KarrasVePipeline": null, + "VersatileDiffusionPipeline": null, + "UNetFlatConditionModel": null, + "VersatileDiffusionDualGuidedPipeline": null, + "VersatileDiffusionImageVariationPipeline": null, + "VersatileDiffusionTextToImagePipeline": null, + "Transformer2DModel": null, + "VQDiffusionScheduler": null, + "LearnedClassifierFreeSamplingEmbeddings": null, + "VQDiffusionPipeline": null, + "DiTTransformer2DModel": null, + "DiTPipeline": null, + "AutoencoderKLMagvit": null, + "EasyAnimateTransformer3DModel": null, + "EasyAnimatePipeline": null, + "EasyAnimateControlPipeline": null, + "EasyAnimateInpaintPipeline": null, + "FluxTransformer2DModel": null, + "FluxPipeline": null, + "FluxControlPipeline": null, + "FluxControlImg2ImgPipeline": null, + "FluxControlInpaintPipeline": null, + "FluxControlNetPipeline": null, + "FluxControlNetImg2ImgPipeline": null, + "FluxControlNetInpaintPipeline": null, + "FluxFillPipeline": null, + "FluxImg2ImgPipeline": null, + "FluxInpaintPipeline": null, + "FluxKontextPipeline": null, + "FluxKontextInpaintPipeline": null, + "SiglipVisionModel": null, + "SiglipImageProcessor": null, + "ReduxImageEncoder": null, + "FluxPriorReduxPipeline": null, + "AutoencoderKLFlux2": null, + "Mistral3ForConditionalGeneration": null, + "AutoProcessor": {}, + "Flux2Transformer2DModel": null, + "Flux2Pipeline": null, + "LlamaForCausalLM": null, + "TokenizersBackend": { + "args": "*args" + }, + "HiDreamImageTransformer2DModel": null, + "HiDreamImagePipeline": null, + "AutoencoderKLHunyuanImage": null, + "Qwen2Tokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "vocab_file": "vocab_file=None", + "merges_file": "merges_file=None", + "unk_token": "unk_token: str = '<|endoftext|>'", + "bos_token": "bos_token=None", + "eos_token": "eos_token: str = '<|endoftext|>'", + "pad_token": "pad_token: str = '<|endoftext|>'", + "add_prefix_space": "add_prefix_space=None" + }, + "ByT5Tokenizer": { + "eos_token": "eos_token=''", + "unk_token": "unk_token=''", + "pad_token": "pad_token=''", + "extra_ids": "extra_ids=125", + "additional_special_tokens": "additional_special_tokens=None" + }, + "HunyuanImageTransformer2DModel": null, + "HunyuanImagePipeline": null, + "AutoencoderKLHunyuanImageRefiner": null, + "HunyuanImageRefinerPipeline": null, + "LlamaModel": null, + "LlamaTokenizer": { + "vocab": "vocab: Union[str, dict, list, NoneType] = None", + "merges": "merges: Union[str, list, NoneType] = None", + "clean_up_tokenization_spaces": "clean_up_tokenization_spaces=False", + "unk_token": "unk_token=''", + "bos_token": "bos_token=''", + "eos_token": "eos_token=''", + "use_default_system_prompt": "use_default_system_prompt=False", + "legacy": "legacy=False", + "add_prefix_space": "add_prefix_space=None" + }, + "HunyuanVideoTransformer3DModel": null, + "AutoencoderKLHunyuanVideo": null, + "HunyuanSkyreelsImageToVideoPipeline": null, + "HunyuanVideoPipeline": null, + "HunyuanVideoFramepackTransformer3DModel": null, + "HunyuanVideoFramepackPipeline": null, + "LlavaForConditionalGeneration": null, + "HunyuanVideoImageToVideoPipeline": null, + "Qwen2_5_VLTextModel": null, + "HunyuanVideo15Transformer3DModel": null, + "AutoencoderKLHunyuanVideo15": null, + "ClassifierFreeGuidance": null, + "HunyuanVideo15Pipeline": null, + "HunyuanVideo15ImageToVideoPipeline": null, + "HunyuanDiTPipeline": null, + "I2VGenXLUNet": null, + "I2VGenXLPipeline": null, + "MultilingualCLIP": null, + "KandinskyPipeline": null, + "PriorTransformer": null, + "UnCLIPScheduler": null, + "KandinskyCombinedPipeline": null, + "KandinskyImg2ImgCombinedPipeline": null, + "KandinskyInpaintCombinedPipeline": null, + "KandinskyImg2ImgPipeline": null, + "KandinskyInpaintPipeline": null, + "KandinskyPriorPipeline": null, + "KandinskyV22Pipeline": null, + "KandinskyV22CombinedPipeline": null, + "KandinskyV22Img2ImgCombinedPipeline": null, + "KandinskyV22InpaintCombinedPipeline": null, + "KandinskyV22ControlnetPipeline": null, + "KandinskyV22ControlnetImg2ImgPipeline": null, + "KandinskyV22Img2ImgPipeline": null, + "KandinskyV22InpaintPipeline": null, + "KandinskyV22PriorPipeline": null, + "KandinskyV22PriorEmb2EmbPipeline": null, + "Kandinsky3UNet": null, + "Kandinsky3Pipeline": null, + "Kandinsky3Img2ImgPipeline": null, + "Kandinsky5Transformer3DModel": null, + "Qwen2VLProcessor": null, + "Kandinsky5T2VPipeline": null, + "Kandinsky5I2IPipeline": null, + "Kandinsky5I2VPipeline": null, + "Kandinsky5T2IPipeline": null, + "ChatGLMModel": null, + "ChatGLMTokenizer": null, + "KolorsPipeline": null, + "KolorsImg2ImgPipeline": null, + "LCMScheduler": null, + "LatentConsistencyModelImg2ImgPipeline": null, + "LatentConsistencyModelPipeline": null, + "PreTrainedModel": null, + "PythonBackend": {}, + "LDMTextToImagePipeline": null, + "LDMSuperResolutionPipeline": null, + "LatteTransformer3DModel": null, + "LattePipeline": null, + "LEditsPPPipelineStableDiffusion": null, + "LEditsPPPipelineStableDiffusionXL": null, + "LongCatImageTransformer2DModel": null, + "LongCatImagePipeline": null, + "LongCatImageEditPipeline": null, + "AutoencoderKLLTXVideo": null, + "LTXVideoTransformer3DModel": null, + "LTXPipeline": null, + "LTXConditionPipeline": null, + "LTXImageToVideoPipeline": null, + "LTXLatentUpsamplerModel": null, + "LTXLatentUpsamplePipeline": null, + "LucyEditPipeline": null, + "LuminaNextDiT2DModel": null, + "GemmaPreTrainedModel": null, + "GemmaTokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "unk_token": "unk_token: str = ''", + "bos_token": "bos_token: str = ''", + "eos_token": "eos_token: str = ''", + "pad_token": "pad_token: str = ''", + "mask_token": "mask_token: str = ''" + }, + "LuminaPipeline": null, + "LuminaText2ImgPipeline": null, + "Lumina2Transformer2DModel": null, + "Gemma2PreTrainedModel": null, + "Lumina2Pipeline": null, + "Lumina2Text2ImgPipeline": null, + "MarigoldDepthPipeline": null, + "MarigoldIntrinsicsPipeline": null, + "MarigoldNormalsPipeline": null, + "AutoencoderKLMochi": null, + "MochiTransformer3DModel": null, + "MochiPipeline": null, + "MusicLDMPipeline": null, + "OmniGenTransformer2DModel": null, + "OmniGenPipeline": null, + "Qwen3Model": null, + "OvisImageTransformer2DModel": null, + "OvisImagePipeline": null, + "StableDiffusionControlNetPAGPipeline": null, + "StableDiffusionControlNetPAGInpaintPipeline": null, + "StableDiffusionXLControlNetPAGPipeline": null, + "StableDiffusionXLControlNetPAGImg2ImgPipeline": null, + "HunyuanDiTPAGPipeline": null, + "KolorsPAGPipeline": null, + "PixArtTransformer2DModel": null, + "PixArtSigmaPAGPipeline": null, + "AutoencoderDC": null, + "SanaTransformer2DModel": null, + "SanaPAGPipeline": null, + "StableDiffusionPAGPipeline": null, + "StableDiffusion3PAGPipeline": null, + "StableDiffusion3PAGImg2ImgPipeline": null, + "AnimateDiffPAGPipeline": null, + "StableDiffusionPAGImg2ImgPipeline": null, + "StableDiffusionPAGInpaintPipeline": null, + "StableDiffusionXLPAGPipeline": null, + "StableDiffusionXLPAGImg2ImgPipeline": null, + "StableDiffusionXLPAGInpaintPipeline": null, + "PaintByExampleImageEncoder": null, + "PaintByExamplePipeline": null, + "PIAPipeline": null, + "DPMSolverMultistepScheduler": null, + "PixArtAlphaPipeline": null, + "PixArtSigmaPipeline": null, + "PRXTransformer2DModel": null, + "T5GemmaEncoder": null, + "PRXPipeline": null, + "AutoencoderKLQwenImage": null, + "QwenImageTransformer2DModel": null, + "QwenImagePipeline": null, + "QwenImageControlNetPipeline": null, + "QwenImageControlNetModel": null, + "QwenImageControlNetInpaintPipeline": null, + "QwenImageEditPipeline": null, + "QwenImageEditInpaintPipeline": null, + "QwenImageEditPlusPipeline": null, + "QwenImageImg2ImgPipeline": null, + "QwenImageInpaintPipeline": null, + "QwenImageLayeredPipeline": null, + "SanaPipeline": null, + "SanaControlNetModel": null, + "SanaControlNetPipeline": null, + "SanaSprintPipeline": null, + "SanaSprintImg2ImgPipeline": null, + "SanaVideoTransformer3DModel": null, + "SanaVideoPipeline": null, + "SanaImageToVideoPipeline": null, + "SemanticStableDiffusionPipeline": null, + "HeunDiscreteScheduler": null, + "ShapERenderer": null, + "ShapEPipeline": null, + "ShapEImg2ImgPipeline": null, + "SkyReelsV2Transformer3DModel": null, + "SkyReelsV2Pipeline": null, + "SkyReelsV2DiffusionForcingPipeline": null, + "SkyReelsV2DiffusionForcingImageToVideoPipeline": null, + "SkyReelsV2DiffusionForcingVideoToVideoPipeline": null, + "CLIPProcessor": null, + "SkyReelsV2ImageToVideoPipeline": null, + "AutoencoderOobleck": null, + "StableAudioProjectionModel": null, + "StableAudioDiTModel": null, + "EDMDPMSolverMultistepScheduler": null, + "StableAudioPipeline": null, + "StableCascadeUNet": null, + "DDPMWuerstchenScheduler": null, + "PaellaVQModel": null, + "float": null, + "StableCascadeDecoderPipeline": null, + "StableCascadeCombinedPipeline": null, + "StableCascadePriorPipeline": null, + "OnnxStableDiffusionPipeline": null, + "StableDiffusionOnnxPipeline": null, + "OnnxStableDiffusionImg2ImgPipeline": null, + "OnnxStableDiffusionInpaintPipeline": null, + "OnnxStableDiffusionUpscalePipeline": null, + "StableDiffusionPipeline": null, + "DPTForDepthEstimation": null, + "DPTImageProcessor": null, + "StableDiffusionDepth2ImgPipeline": null, + "StableDiffusionImageVariationPipeline": null, + "StableDiffusionImg2ImgPipeline": null, + "StableDiffusionInpaintPipeline": null, + "StableDiffusionInstructPix2PixPipeline": null, + "EulerDiscreteScheduler": null, + "StableDiffusionLatentUpscalePipeline": null, + "StableDiffusionUpscalePipeline": null, + "StableUnCLIPImageNormalizer": null, + "StableUnCLIPPipeline": null, + "StableUnCLIPImg2ImgPipeline": null, + "StableDiffusion3Pipeline": null, + "StableDiffusion3Img2ImgPipeline": null, + "StableDiffusion3InpaintPipeline": null, + "StableDiffusionAttendAndExcitePipeline": null, + "StableDiffusionDiffEditPipeline": null, + "StableDiffusionGLIGENPipeline": null, + "CLIPImageProjection": null, + "StableDiffusionGLIGENTextImagePipeline": null, + "StableDiffusionLDM3DPipeline": null, + "StableDiffusionPanoramaPipeline": null, + "SafeStableDiffusionSafetyChecker": null, + "StableDiffusionPipelineSafe": null, + "StableDiffusionSAGPipeline": null, + "StableDiffusionXLPipeline": null, + "StableDiffusionXLImg2ImgPipeline": null, + "StableDiffusionXLInpaintPipeline": null, + "StableDiffusionXLInstructPix2PixPipeline": null, + "AutoencoderKLTemporalDecoder": null, + "UNetSpatioTemporalConditionModel": null, + "StableVideoDiffusionPipeline": null, + "StableDiffusionAdapterPipeline": null, + "StableDiffusionXLAdapterPipeline": null, + "UNet3DConditionModel": null, + "TextToVideoSDPipeline": null, + "VideoToVideoSDPipeline": null, + "TextToVideoZeroPipeline": null, + "TextToVideoZeroSDXLPipeline": null, + "UnCLIPTextProjModel": null, + "UnCLIPPipeline": null, + "UnCLIPImageVariationPipeline": null, + "UniDiffuserTextDecoder": null, + "GPT2Tokenizer": { + "vocab": "vocab: Union[str, dict[str, int], NoneType] = None", + "merges": "merges: Union[str, list[str], NoneType] = None", + "errors": "errors: str = 'replace'", + "unk_token": "unk_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "bos_token": "bos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "eos_token": "eos_token: Union[tokenizers.AddedToken, str] = '<|endoftext|>'", + "pad_token": "pad_token: Union[tokenizers.AddedToken, str, NoneType] = None", + "add_prefix_space": "add_prefix_space=False" + }, + "UniDiffuserModel": null, + "UniDiffuserPipeline": null, + "VisualClozePipeline": null, + "VisualClozeGenerationPipeline": null, + "WanPipeline": null, + "WanAnimateTransformer3DModel": null, + "WanAnimatePipeline": null, + "WanTransformer3DModel": null, + "WanImageToVideoPipeline": null, + "WanVACETransformer3DModel": null, + "WanVACEPipeline": null, + "WanVideoToVideoPipeline": null, + "WuerstchenDiffNeXt": null, + "WuerstchenDecoderPipeline": null, + "WuerstchenPrior": null, + "WuerstchenCombinedPipeline": null, + "WuerstchenPriorPipeline": null, + "ZImageTransformer2DModel": null, + "ZImagePipeline": null, + "ZImageControlNetModel": null, + "ZImageControlNetPipeline": null, + "ZImageControlNetInpaintPipeline": null, + "ZImageImg2ImgPipeline": null, + "Siglip2VisionModel": null, + "Siglip2ImageProcessorFast": null, + "ZImageOmniPipeline": null + } +} \ No newline at end of file From 629a7bd9873d8f620b17bd8d8b86b791144707bf Mon Sep 17 00:00:00 2001 From: exdysa <91800957+exdysa@users.noreply.github.com> Date: Mon, 26 Jan 2026 16:46:39 -0500 Subject: [PATCH 16/16] ~nn walk export --- .continue/prompts/new-prompt-1.md | 72 + .continue/prompts/new-prompt.md | 7 + MIR.egg-info/PKG-INFO | 1 + MIR.egg-info/SOURCES.txt | 56 +- MIR.egg-info/entry_points.txt | 1 + MIR.egg-info/requires.txt | 1 + mir/data/nn_filter.json | 56 +- mir/gatherers/diffusers.py | 2 +- mir/gatherers/transformers.py | 2 +- mir/lookups.py | 120 + mir/nn_walk.py | 209 ++ pyproject.toml | 4 +- tests/.test.json | 4 + tests/art_aet_split.json | 168 ++ tests/class_study.txt | 128 + tests/classes_using.py | 43 + tests/mapinput.txt | 3502 +++++++++++++++++++++ tests/nn_module_export.txt | 3224 ++++++++++++++++++++ tests/nn_sources.json | 3 + tests/{test.json => pkg_parameters.json} | 0 tests/subclass_modules.json | 3504 ++++++++++++++++++++++ tests/subclasses_test.py | 18 +- tests/test_nn_lookup.py | 58 + uv.lock | 615 ++-- 24 files changed, 11441 insertions(+), 357 deletions(-) create mode 100644 .continue/prompts/new-prompt-1.md create mode 100644 .continue/prompts/new-prompt.md create mode 100644 mir/nn_walk.py create mode 100644 tests/.test.json create mode 100644 tests/art_aet_split.json create mode 100644 tests/class_study.txt create mode 100644 tests/classes_using.py create mode 100644 tests/mapinput.txt create mode 100644 tests/nn_module_export.txt create mode 100644 tests/nn_sources.json rename tests/{test.json => pkg_parameters.json} (100%) create mode 100644 tests/subclass_modules.json create mode 100644 tests/test_nn_lookup.py diff --git a/.continue/prompts/new-prompt-1.md b/.continue/prompts/new-prompt-1.md new file mode 100644 index 0000000..48b1238 --- /dev/null +++ b/.continue/prompts/new-prompt-1.md @@ -0,0 +1,72 @@ +--- +name: Variable Dictionary +description: Acceptable terms to use for new variables names +invokable: true +--- + +## variable dictionary + +### Tier 1 (shortest <=5) + +#### Action + +_ASSEMBLE Piece / Rig / Item / Chunk +CEILING Limit / Edge / Raise +CLASSIFY Flag / Mark / Label / Stamp / Tag +CLEAN Cure / Clean / Level / Even / Align +COMBINE Join / Cat / Fuse / Bond / Unify / Unite / Blend / Mesh / Merge +COMPARE Ratio / Rank / Range +COMPRESS Zip / Smush +CREATE Make / Form / Shape / Set / New / Extra / More +DETOUR Avoid / Mask +DUPLICATE Clone / Copy +DISASSEMBLE Strip / Trim / Snip / Divvy / Slice +IMMUTABLE Fixed / Safe +LINE UP Sort / Order / Prime / First / Last / Point / Stack +MUTATE Edit / Loop / Slide / Warp / Alter +NULLIFY Empty / Gap / Null / Clear / Erase +PROFILE Time / Bench / Score / Gauge / Grade / Weigh / Test / Rate / Size / Tune +REVEAL Read / Show / Get / Fan +SHUFFLE Skip / Cross / Shift / Mix / Move / Weave +STATUS Try / Check / Poll / Prove / State / Mode / Stage +SWITCH Trade / Swap / Flip +TRAVERSE Crawl / Scan / Trace / Trawl / Look / Query / Find / Index +WAIT Cue / Task / Queue_ + +#### Object + +**SESSSION Ready / Last / Reset / Keep +SESSION IN Start / Init / Begin / Task +SESSION OUT Drop / Exit / Leave / End / Stop +HARDWARE Disk / Net / Audio / Video / Chip +SOFTWARE Path / Code +DISK IN Load / Open +DISK OUT Log / Save / Cache / Store / Stash +CONNECT IN Pull / Fetch / On +CONNECT OUT Push / Send / Feed / Off / Post +TEMPORAL Sync / Pipe / Loop +TEXT Glyph / Form / Frame +CLASSIFIER Host / Guest / Link / Chain / Core / Base / Local** + +### Adjective + +> Modifiers : is/has/have/can/only/maybe> +> Relational : \_at, _to, _in , \_of, \_with, \_for, \_in, \_using +> States : raw / up / down / low / high / valid +> Scale : macro / mini / small / large / giant / mega + +### File and Folder handling + +_file_contents_ - data inside the file +_file_name_ - exclusively +_file_path_ - path leading to file, with no file name +_file_path_absolute_ - absolute path including name +_file_all_suffix_ - all . separated items including extension +_file_extension_ - final suffix +_empty_file_name_ - a file to be created +_empty_file_absolute_ - absolute path including name to be created +_folder_contents_ - file names inside a folder +_folder_name_ - the name of the folder +_folder_name_pathed_ - absolute path, existing folder including name +_empty_folder_name_ - a folder to be created +_empty_folder_absolute_ - absolute path including name to be created diff --git a/.continue/prompts/new-prompt.md b/.continue/prompts/new-prompt.md new file mode 100644 index 0000000..ea73d06 --- /dev/null +++ b/.continue/prompts/new-prompt.md @@ -0,0 +1,7 @@ +--- +name: MIR +description: Machine Intelligence Resource +invokable: true +--- + +MIR is a URI naming schema for referring to and calling models. diff --git a/MIR.egg-info/PKG-INFO b/MIR.egg-info/PKG-INFO index ba67201..8f5db66 100644 --- a/MIR.egg-info/PKG-INFO +++ b/MIR.egg-info/PKG-INFO @@ -37,6 +37,7 @@ Requires-Dist: chanfig>=0.0.114 Requires-Dist: diffusers>=0.35.2 Requires-Dist: ftfy>=6.3.1 Requires-Dist: huggingface-hub[hf-xet]>=1.1.7 +Requires-Dist: numpy>=2.4.1 Requires-Dist: pydantic>=2.12.5 Requires-Dist: sentencepiece>=0.2.1 Requires-Dist: tokenizers>=0.22.1 diff --git a/MIR.egg-info/SOURCES.txt b/MIR.egg-info/SOURCES.txt index 0867f5a..768cf74 100644 --- a/MIR.egg-info/SOURCES.txt +++ b/MIR.egg-info/SOURCES.txt @@ -13,14 +13,19 @@ MIR.egg-info/entry_points.txt MIR.egg-info/requires.txt MIR.egg-info/top_level.txt mir/__init__.py -mir/__main__.py -mir/framework.py +mir/build_entry.py +mir/doc_parse.py mir/json_io.py +mir/lookups.py mir/maid.py mir/mir.json +mir/model.py +mir/nesting.py +mir/nn_walk.py mir/package.py mir/tag.py mir/data/__init__.py +mir/data/component_names.json mir/data/diffusers_adds.json mir/data/exclusions.json mir/data/migrations.json @@ -29,45 +34,16 @@ mir/data/parameters.json mir/data/pipe_markers.json mir/data/tag_scrape.json mir/data/transformers_adds.json -mir/generate/__init__.py -mir/generate/__main__.py -mir/generate/_extras.py -mir/generate/automata.py -mir/generate/from_module.py -mir/generate/indexers.py -mir/generate/tasks.py -mir/generate/diffusers/__init__.py -mir/generate/diffusers/attention.py -mir/generate/diffusers/doc_parse.py -mir/generate/diffusers/guiders.py -mir/generate/diffusers/harvest.py -mir/generate/diffusers/index.py -mir/generate/diffusers/raw_data.py -mir/generate/diffusers/schedulers.py -mir/generate/mlx/__init__.py -mir/generate/mlx/index.py -mir/generate/torch/__init__.py -mir/generate/torch/dtypes.py -mir/generate/transformers/__init__.py -mir/generate/transformers/harvest.py -mir/generate/transformers/raw_data.py +mir/gatherers/__init__.py +mir/gatherers/diffusers.py +mir/gatherers/mlx.py +mir/gatherers/torch.py +mir/gatherers/transformers.py mir/spec/__init__.py mir/spec/regex.json tests/subclasses_test.py +tests/test_gather_diffusers.py +tests/test_gather_transformers.py +tests/test_inspect.py tests/test_mir_generate_diffusers.py -tests/test_mir_generate_transformers.py -tests/old/test_class_parent.py -tests/old/test_deconstructors_root.py -tests/old/test_doc_parser.py -tests/old/test_find_docstring_run.py -tests/old/test_gather_diffusers_metadata.py -tests/old/test_json_io.py -tests/old/test_mir_db_create_restore.py -tests/old/test_mir_merge.py -tests/old/test_mir_search.py -tests/old/test_mir_tagging.py -tests/old/test_regex_constants.py -tests/old/test_resolve_code_names.py -tests/old/test_seek_class.py -tests/old/test_task.py -tests/old/test_taskanalyzer.py \ No newline at end of file +tests/test_mir_generate_transformers.py \ No newline at end of file diff --git a/MIR.egg-info/entry_points.txt b/MIR.egg-info/entry_points.txt index cf321fe..b3b188a 100644 --- a/MIR.egg-info/entry_points.txt +++ b/MIR.egg-info/entry_points.txt @@ -1,2 +1,3 @@ [console_scripts] mir = mir.generate.__main__:main +mir-nn = mir.nn_walk:main diff --git a/MIR.egg-info/requires.txt b/MIR.egg-info/requires.txt index 5f1d4be..8c266d4 100644 --- a/MIR.egg-info/requires.txt +++ b/MIR.egg-info/requires.txt @@ -2,6 +2,7 @@ chanfig>=0.0.114 diffusers>=0.35.2 ftfy>=6.3.1 huggingface-hub[hf-xet]>=1.1.7 +numpy>=2.4.1 pydantic>=2.12.5 sentencepiece>=0.2.1 tokenizers>=0.22.1 diff --git a/mir/data/nn_filter.json b/mir/data/nn_filter.json index 25399b5..5f58361 100644 --- a/mir/data/nn_filter.json +++ b/mir/data/nn_filter.json @@ -77,16 +77,16 @@ "moe_intermediate_size" ], "aet": [ + "act_dropout", + "audio_video_config", + "classifier_pooling", "classifier_proj_size", - "position_embedding_type", - "separate_cls", + "ctc_loss_reduction", "keypoint_detector_config", "local_attention", - "act_dropout", "max_source_positions", - "classifier_pooling", - "ctc_loss_reduction", - "audio_video_config", + "position_embedding_type", + "separate_cls", "video_config" ], "stst": [ @@ -106,37 +106,39 @@ "prompt_length", "audio_config", "convolution_bias", - "rope_parameters", "hotstart_dup_thresh" ], "art": [ - "ffn_dim", - "num_codebooks", - "vq_config", + "act_dim", + "action_tanh", "attn_config", + "attn_pdrop", + "audio_encoder", + "aux_loss_coef", + "decoder_layers", + "decoder_start_token_id", + "embd_pdrop", + "embed_dropout", + "ffn_dim", + "head_dim", + "hidden_dropout_prob", + "layernorm_embedding", + "n_embd", "n_head", - "act_dim", + "n_inner", "n_heads", "n_layer", - "rms_norm_eps", - "rope_theta", - "head_dim", - "layernorm_embedding", - "hidden_dropout_prob", - "rotary_pct", - "audio_encoder", - "embed_dropout", + "n_positions", "nb_priors", + "no_rope_layers", + "num_codebooks", "resid_pdrop", - "embd_pdrop", - "action_tanh", - "n_positions", - "aux_loss_coef", "residual_dropout", - "no_rope_layers", - "decoder_start_token_id", - "decoder_layers", - "tie_codebooks_embeddings" + "rms_norm_eps", + "rope_theta", + "rotary_pct", + "tie_codebooks_embeddings", + "vq_config" ] }, "diffusers": { diff --git a/mir/gatherers/diffusers.py b/mir/gatherers/diffusers.py index 0a7645b..3a24ace 100644 --- a/mir/gatherers/diffusers.py +++ b/mir/gatherers/diffusers.py @@ -23,7 +23,7 @@ def __init__(self) -> None: if module_path.rsplit(".", 1)[-1] not in EXCLUSIONS["exclusion_list"]: build_entries.extend([BuildEntry(model_type=model_type, model=model) for model_type, model in get_type_hints(pipeline.__init__).items()]) build_entries.append(BuildEntry(model_type="pipeline", model=pipeline)) - self.model_db = {x.attributes.model_name: x.attributes.model_parameters for x in build_entries} + self.model_db = {x.attributes.model_name: x.attributes.model.layers for x in build_entries for x in build_entries if hasattr(x.attributes, "layers")} # TODO: for data in prepared_data: def extract_subclass_data(self, package_name: str, base_class_name: str): diff --git a/mir/gatherers/transformers.py b/mir/gatherers/transformers.py index 06c3768..017bf81 100644 --- a/mir/gatherers/transformers.py +++ b/mir/gatherers/transformers.py @@ -30,4 +30,4 @@ def __init__(self) -> None: build_entries.append(BuildEntry("model", model)) if tokenizer := TOKENIZER_MAPPING.get(config, None): build_entries.append(BuildEntry("tokenizer", tokenizer)) - self.model_db = {x.attributes.model_name: x.attributes.model_parameters for x in build_entries} + self.model_db = {x.attributes.model_name: x.attributes.layers for x in build_entries if hasattr(x.attributes, "layers")} diff --git a/mir/lookups.py b/mir/lookups.py index 9e9df60..b960c51 100644 --- a/mir/lookups.py +++ b/mir/lookups.py @@ -5,6 +5,7 @@ import inspect from importlib import import_module +from inspect import getmro from types import ModuleType from typing import Callable @@ -97,3 +98,122 @@ def show_init_fields_for(module: Callable | str, package_name: str | None = None class_names = dict(class_names) return class_names + + +def extract_subclass_data(package_name: str, base_class_name: str, all: bool = False) -> dict[str, Callable] | None: + """Extracts subclasses from a package that inherit from a specified base class.\n + :param package_name: Name of the package to search + :param base_class_name: Name of the base class to inherit from + :return: Dictionary mapping fully qualified class names to class objects""" + + from importlib import import_module + from pkgutil import walk_packages + + subclasses = {} + root_pkg = import_module(package_name) + if package_path := getattr(root_pkg, "__path__", root_pkg.__all__): + for finder, module_name, is_pkg in walk_packages(package_path, root_pkg.__name__ + "."): + try: + module = import_module(module_name) + except (ImportError, ModuleNotFoundError, RuntimeError): + continue + + for name, obj in module.__dict__.items(): + print(obj) + if not isinstance(obj, type): + obj = import_module(obj, root_pkg.__module__) + if obj.__module__ != module_name: + continue + try: + bases = getmro(obj)[1:] # skip the class itself + except ValueError: + continue + for base in bases: + if base.__name__ == base_class_name: + fqcn = f"{module_name}.{name}" + subclasses[fqcn] = obj + break + + return subclasses + + +def get_source_of(class_obj: Callable) -> list[str]: + """Retrieve the source lines of a class definition.\n + :params class_obj: The class object whose source is to be read. + :return: A list of source lines from the class's file.""" + from mir.lookups import get_import_chain + + module = class_obj.__module__ + chain = get_import_chain(module) + file_path_named: str = chain.__file__ # type: ignore + with open(file_path_named) as opened_file: + file_lines = opened_file.readlines() + return file_lines + + +def nn_source_tree(file_lines: list[str]) -> dict[str, str] | None: + """Parse a list of source lines to locate a ModuleList call.\n + :params file_lines: Lines of source code to analyze. + :return: Mapping of class name to the call string if found, otherwise None.""" + + import ast + + target = "ModuleList(" + tree = ast.parse("".join(file_lines)) + node_names = [node.name for node in ast.walk(tree) if isinstance(node, ast.ClassDef)] + for node in ast.walk(tree): + if isinstance(node, ast.ClassDef): + for current_node in ast.walk(node): + if isinstance(current_node, ast.Call) and isinstance(current_node.func, ast.Attribute): + if current_node.func.attr == "ModuleList": + line_number = current_node.lineno + source_code = file_lines[line_number - 1].strip() + if source_code.endswith(target): + source_code = file_lines[line_number].strip() + if class_name := list(name for name in node_names if name + "(" in source_code): + layer_data = source_code.rsplit("range", 1)[-1] + layer_data = layer_data.split(")", 1)[0].split(".", 1)[1] + return {"class_name": class_name[0], "config_attribute": layer_data} + + +def find_nn_modules(module: Callable, prefix: str = ""): + """ + Traverse through the module and its children, collecting all nn.Module instances. + + Args: + module (torch.nn.Module): The module to inspect. + prefix (str): The prefix for the module names during recursion. + + Returns: + List[torch.nn.Module]: A list of all nn.Module tuple instances found. + """ + from torch import nn + + nn_modules = {} + library = module.__module__.split(".", 1)[0] + module_path = get_import_chain(module.__module__) + for attribute in sorted(dir(module_path)): + if attribute.startswith("_"): + continue + attribute_object = getattr(module_path, attribute) + if isinstance(attribute_object, type) and library in attribute_object.__module__ and nn.Module in getmro(attribute_object): + nn_modules.setdefault((attribute, attribute_object)) + return nn_modules + + +def find_config_classes(parameter_filter: str) -> list[str]: + """Show all config classes in the Transformer package with the specified init annotation\n + :param from_match: Narrow the classes to only those with an exact key inside + :return: A list of all Classes""" + + from mir.gatherers.transformers import CONFIG_MAPPING + + # filler = ["bool", "int", "float", "complex", "str", "list", "tuple", "dict", "set"] + config_data = [] + for config_class in CONFIG_MAPPING.values(): + if isinstance(config_class, tuple): + config_class = config_class[0] + signature = inspect.signature(config_class.__init__) + if parameter_filter in list(signature.parameters): + config_data.append(config_class.__name__) + return config_data diff --git a/mir/nn_walk.py b/mir/nn_walk.py new file mode 100644 index 0000000..c6f7a09 --- /dev/null +++ b/mir/nn_walk.py @@ -0,0 +1,209 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +# 從依賴關係中解析nn.module的實驗例程 experimental routines to parse nn.module out of dependencies +import os +import importlib +from importlib.util import find_spec +from inspect import isclass +from types import ModuleType +from typing import List, Tuple, Type, Callable + + +async def find_classes_in_library(library_name: ModuleType, parent_class: Type) -> List[Tuple[str, Type]]: + visited = set() + found = [] + exclude_list = [ + "llvmlite.binding.ffiwatermarking", + "transformers.utils.sentencepiece_model_pb2", + "transformers.kernels.falcon_mamba", + "selective_scan_with_ln_interface", + "transformers.utils.notebook", + "transformers.modeling_flax_utils", + "transformers.modeling_flax_pytorch_utils", + "transformers.models.albert.modeling_flax_albert", + "transformers.models.biogpt.modular_biogpt", + "transformers.models.wavlm.modular_wavlm", + "transformers.models.gemma3.modular_gemma3", + "transformers.models.data2vec.modular_data2vec_audio", + "transformers.models.gemma3n.modular_gemma3n", + "transformers.models.pop2piano.tokenization_pop2piano", + "transformers.models.dinov2_with_registers.modular_dinov2_with_registers", + "transformers.models.kyutai_speech_to_text.modular_kyutai_speech_to_text", + "transformers.models.perception_lm.modular_perception_lm", + "transformers.models.llava_next_video.modular_llava_next_video", + "transformers.models.pe_audio_video.convert_pe_audio_video_to_hf", + "transformers.models.pop2piano.convert_pop2piano_weights_to_hf", + "transformers.cli.transformers", + "transformers.cli.serve", + "transformers.tokenization_mistral_common", + "transformers.integrations", + "transformers.keras_callbacks", + "transformers.tf_utils", + "transformers.generation.tf_logits_process", + "transformers.generation.tf_utils", + "diffusers.utils.import_utils", + "diffusers.pipelines.consisid.consisid_utils", + "diffusers.pipelines.stable_diffusion_safe", + "diffusers.pipelines.skyreels_v2", # demands ftfy dep + "diffusers.pipelines.stable_diffusion.pipeline_onnx_stable_diffusion_inpaint_legacy", + "diffusers.pipelines.stable_diffusion_k_diffusion", # demands kdiffusion + "diffusers.pipelines.deprecated", + "diffusers.schedulers.scheduling_cosine_dpmsolver_multistep", # needs torchsde + "diffusers.schedulers.scheduling_dpmsolver_sde", + "mlx_lm.models.olmo", # demands al-olmo" + "mlx_lm.test", + "mlx_lm.evaluate", + "mlx_audio.server", + "mlx_audio.sts.voice_pipeline", + "mlx_audio.stt.models.whisper.timing", + "mlx_audio.stt.models.whisper.__init__", + "mlx_audio.stt.models.whisper.whisper", + "numba", + "numba.core.configtorch.backends", # demands coreml, onnx_script, etc + "torch.utils.tensorboard", # demands tensorboard + "torch.testing", + ] + class_exclusions = [ + "pipeline_stable_diffusion_k_diffusion", + "pipeline_onnx_stable_diffusion_inpaint", + "CogView4PlusPipelineOutput", + "OnnxStableDiffusionInpaintPipelineLegacy", + "CogView3PlusPipelineOutput", + ] + + async def recurse(module_name: str): + if module_name in visited: + return + visited.add(module_name) + spec = find_spec(module_name) + if not spec or not spec.origin: + return + if module_name not in exclude_list and "_tf" not in module_name and not any([segment.startswith("_") for segment in module_name.split(".")]): + try: + module = importlib.import_module(module_name) + except (ModuleNotFoundError, ImportError): + return + for name in dir(module): + if name not in class_exclusions and not list([exclusion for exclusion in class_exclusions if exclusion in name]): + obj = getattr(module, name) + if isclass(obj) and issubclass(obj, parent_class): + found.append((str(obj).replace("class ", ""), name)) + if spec.submodule_search_locations: + path = spec.submodule_search_locations[0] + for entry in os.listdir(path): + if entry.startswith("__") or entry in {"tests", "assets"}: + continue + full_path = os.path.join(path, entry) + if os.path.isdir(full_path): + await recurse(f"{module_name}.{entry}") + elif entry.endswith(".py"): + mod_name = entry[:-3] + if mod_name != "watermarking" and mod_name != "_VF": + await recurse(f"{module_name}.{mod_name}") + + await recurse(library_name.__name__) + return found + + +async def find_modules(keyword: str, library_name: str, base_class: str) -> None: + from mir.lookups import get_import_chain + from importlib import import_module + + results = [] + + library = import_module(library_name) + parent_class = get_import_chain(base_class) + subclasses: tuple[Callable, str] = await find_classes_in_library(library, parent_class) + for subclass_name in subclasses: + name = subclass_name[1] + if keyword in name and "For" not in name: + results.append(name) + print(results) + + +async def find_nn(): + from importlib import import_module + from mir.json_io import write_json_file + + package_args = { + "mlx_audio": "mlx.nn", + "mlx_lm": "mlx.nn", + "mflux": "mlx.nn", + "transformers": "torch.nn", + "diffusers": "torch.nn", + } + results = [] + for pkg, module in package_args.items(): + pkg_obj = import_module(pkg) + module_obj = import_module(module).Module + results.extend(await find_classes_in_library(pkg_obj, module_obj)) + data = {cls: name for cls, name in results} + write_json_file(".", "nn_modules.json", data) + print(f"Wrote {len(results)} lines.") + + +async def order_nn_modules(): + from mir.json_io import read_json_file + from mir.json_io import write_json_file + from collections import defaultdict + import re + + key_sort = defaultdict(set) + nn_sources: dict[str, str] = read_json_file("nn_sources.json") + pkg_modules: dict[str, str] = read_json_file("nn_modules.json") + for module, name in pkg_modules.items(): + model_name = None + pattern = r"(\b(models.|mflux\.community.|pipelines.|generation.candidate_generator.|time_series_utils.|distributed.fsdp.|activations.|quantizers.base|transformers.loss.|transformers.integrations.|mlx_lm.dwq|nn.modules.loss)\b)" + match = re.search(pattern, module) + if match: + match_segment = match.group() + model_name = module.split(match_segment)[1].partition(".")[0] + for nn_type in nn_sources.keys(): + if nn_type.lower() in name.lower(): + key_sort[model_name].add(nn_type.lower()) + else: + print(module) + key_set = key_sort.copy() + for i in key_set: + key_sort[i] = list(key_set[i]) + write_json_file(".", "nn_order.json", key_sort) + print(f"Wrote {len(key_sort)} lines.") + + +def main(): + import argparse + import asyncio + + default_library = "transformers" + default_base = "torch.nn.Module" + + parser = argparse.ArgumentParser(description="Scan library for child modules") + parser.add_argument("keyword", default="torch.nn.Module", type=str, help="A keyword to match. Search will be case sensitive.") + + parser.add_argument( + "-l", + "--library_name", + default=default_library, + type=str, + required=False, + help=f"Name of the library to scan (default: {default_library})", + ) + parser.add_argument( + "-p", + "--parent_class", + default=default_base, + type=str, + required=False, + help=f"Parent nn class to filter by eg: 'torch.nn.Module','mlx.nn.Module', etc. (default {default_base})", + ) + + args = parser.parse_args() + keyword = args.keyword + library_name = args.library_name + parent_class = args.parent_class + asyncio.run(find_modules(keyword, library_name, parent_class)) + + +if __name__ == "__main__": + main() diff --git a/pyproject.toml b/pyproject.toml index 0b71665..cafbb6b 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -28,6 +28,7 @@ dependencies = [ "diffusers>=0.35.2", "ftfy>=6.3.1", "huggingface-hub[hf-xet]>=1.1.7", + "numpy>=2.4.1", "pydantic>=2.12.5", "sentencepiece>=0.2.1", "tokenizers>=0.22.1", @@ -41,6 +42,7 @@ Documentation = "https://github.com/darkshapes/sdbx/wiki" [project.scripts] mir = "mir.generate.__main__:main" +mir-nn = "mir.nn_walk:main" [tool.setuptools_scm] version_scheme = "guess-next-dev" @@ -74,4 +76,4 @@ ignore = ["E731"] [tool.pytest.ini_options] filterwarnings = [ "ignore::DeprecationWarning", -] \ No newline at end of file +] diff --git a/tests/.test.json b/tests/.test.json new file mode 100644 index 0000000..48d410a --- /dev/null +++ b/tests/.test.json @@ -0,0 +1,4 @@ +{ + "transformers": {}, + "diffusers": {} +} \ No newline at end of file diff --git a/tests/art_aet_split.json b/tests/art_aet_split.json new file mode 100644 index 0000000..09345fd --- /dev/null +++ b/tests/art_aet_split.json @@ -0,0 +1,168 @@ +{ + "GPT": { + "GPT2Model": { + "activation_function": "activation_function='gelu_new'", + "attn_pdrop": "attn_pdrop=0.1", + "bos_token_id": "bos_token_id=50256", + "embd_pdrop": "embd_pdrop=0.1", + "eos_token_id": "eos_token_id=50256", + "initializer_range": "initializer_range=0.02", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "n_embd": "n_embd=768", + "n_head": "n_head=12", + "n_inner": "n_inner=None", + "n_layer": "n_layer=12", + "n_positions": "n_positions=1024", + "reorder_and_upcast_attn": "reorder_and_upcast_attn=False", + "resid_pdrop": "resid_pdrop=0.1", + "scale_attn_by_inverse_layer_idx": "scale_attn_by_inverse_layer_idx=False", + "scale_attn_weights": "scale_attn_weights=True", + "summary_activation": "summary_activation=None", + "summary_first_dropout": "summary_first_dropout=0.1", + "summary_proj_to_labels": "summary_proj_to_labels=True", + "summary_type": "summary_type='cls_index'", + "summary_use_proj": "summary_use_proj=True", + "vocab_size": "vocab_size=50257" + }, + "XLNetModel": { + "attn_type": "attn_type='bi'", + "bi_data": "bi_data=False", + "bos_token_id": "bos_token_id=1", + "clamp_len": "clamp_len=-1", + "d_inner": "d_inner=4096", + "d_model": "d_model=1024", + "dropout": "dropout=0.1", + "end_n_top": "end_n_top=5", + "eos_token_id": "eos_token_id=2", + "ff_activation": "ff_activation='gelu'", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "mem_len": "mem_len=512", + "n_head": "n_head=16", + "n_layer": "n_layer=24", + "pad_token_id": "pad_token_id=5", + "reuse_len": "reuse_len=None", + "same_length": "same_length=False", + "start_n_top": "start_n_top=5", + "summary_activation": "summary_activation='tanh'", + "summary_last_dropout": "summary_last_dropout=0.1", + "summary_type": "summary_type='last'", + "summary_use_proj": "summary_use_proj=True", + "use_mems_eval": "use_mems_eval=True", + "use_mems_train": "use_mems_train=False", + "vocab_size": "vocab_size=32000" + }, + "GPTNeoModel": { + "activation_function": "activation_function='gelu_new'", + "attention_dropout": "attention_dropout=0.0", + "attention_types": "attention_types=[[['global', 'local'], 12]]", + "bos_token_id": "bos_token_id=50256", + "classifier_dropout": "classifier_dropout=0.1", + "embed_dropout": "embed_dropout=0.0", + "eos_token_id": "eos_token_id=50256", + "hidden_size": "hidden_size=2048", + "initializer_range": "initializer_range=0.02", + "intermediate_size": "intermediate_size=None", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "max_position_embeddings": "max_position_embeddings=2048", + "num_heads": "num_heads=16", + "num_layers": "num_layers=24", + "resid_dropout": "resid_dropout=0.0", + "vocab_size": "vocab_size=50257", + "window_size": "window_size=256" + }, + "GPTJModel": { + "activation_function": "activation_function='gelu_new'", + "attn_pdrop": "attn_pdrop=0.0", + "bos_token_id": "bos_token_id=50256", + "embd_pdrop": "embd_pdrop=0.0", + "eos_token_id": "eos_token_id=50256", + "initializer_range": "initializer_range=0.02", + "layer_norm_epsilon": "layer_norm_epsilon=1e-05", + "n_embd": "n_embd=4096", + "n_head": "n_head=16", + "n_inner": "n_inner=None", + "n_layer": "n_layer=28", + "n_positions": "n_positions=2048", + "resid_pdrop": "resid_pdrop=0.0", + "rotary_dim": "rotary_dim=64", + "tie_word_embeddings": "tie_word_embeddings=False", + "vocab_size": "vocab_size=50400" + } + }, + "Bert": { + "ErnieModel": { + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "classifier_dropout": "classifier_dropout=None", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "hidden_size": "hidden_size=768", + "initializer_range": "initializer_range=0.02", + "intermediate_size": "intermediate_size=3072", + "layer_norm_eps": "layer_norm_eps=1e-12", + "max_position_embeddings": "max_position_embeddings=512", + "num_attention_heads": "num_attention_heads=12", + "num_hidden_layers": "num_hidden_layers=12", + "pad_token_id": "pad_token_id=0", + "task_type_vocab_size": "task_type_vocab_size=3", + "type_vocab_size": "type_vocab_size=2", + "use_task_id": "use_task_id=False", + "vocab_size": "vocab_size=30522" + }, + "RobertaModel": { + "vocab_size": "vocab_size=50265", + "hidden_size": "hidden_size=768", + "num_hidden_layers": "num_hidden_layers=12", + "num_attention_heads": "num_attention_heads=12", + "intermediate_size": "intermediate_size=3072", + "hidden_act": "hidden_act='gelu'", + "hidden_dropout_prob": "hidden_dropout_prob=0.1", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0.1", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "pad_token_id": "pad_token_id=1", + "bos_token_id": "bos_token_id=0", + "eos_token_id": "eos_token_id=2", + "classifier_dropout": "classifier_dropout=None" + }, + "AlbertModel": { + "vocab_size": "vocab_size=30000", + "embedding_size": "embedding_size=128", + "hidden_size": "hidden_size=4096", + "num_hidden_layers": "num_hidden_layers=12", + "num_hidden_groups": "num_hidden_groups=1", + "num_attention_heads": "num_attention_heads=64", + "intermediate_size": "intermediate_size=16384", + "inner_group_num": "inner_group_num=1", + "hidden_act": "hidden_act='gelu_new'", + "hidden_dropout_prob": "hidden_dropout_prob=0", + "attention_probs_dropout_prob": "attention_probs_dropout_prob=0", + "max_position_embeddings": "max_position_embeddings=512", + "type_vocab_size": "type_vocab_size=2", + "initializer_range": "initializer_range=0.02", + "layer_norm_eps": "layer_norm_eps=1e-12", + "classifier_dropout_prob": "classifier_dropout_prob=0.1", + "pad_token_id": "pad_token_id=0", + "bos_token_id": "bos_token_id=2", + "eos_token_id": "eos_token_id=3" + }, + "DistilBertModel": { + "vocab_size": "vocab_size=30522", + "max_position_embeddings": "max_position_embeddings=512", + "sinusoidal_pos_embds": "dsoidal_pos_embds=False", + "n_layers": "n_layers=6", + "n_heads": "n_heads=12", + "dim": "dim=768", + "hidden_dim": "hidden_dim=3072", + "dropout": "dropout=0.1", + "attention_dropout": "attention_dropout=0.1", + "activation": "activation='gelu'", + "initializer_range": "initializer_range=0.02", + "qa_dropout": "qa_dropout=0.1", + "seq_classif_dropout": "seq_classif_dropout=0.2", + "pad_token_id": "pad_token_id=0" + } + } +} \ No newline at end of file diff --git a/tests/class_study.txt b/tests/class_study.txt new file mode 100644 index 0000000..0db4665 --- /dev/null +++ b/tests/class_study.txt @@ -0,0 +1,128 @@ +"BertAttention": +"BertEmbeddings": +"BertEncoder": +"BertIntermediate": +"BertLayer": +"BertOutput": +"BertPooler": +"BertSdpaSelfAttention": +"BertSelfAttention": +"BertSelfOutput": + +"BertLMPredictionHead": "<'transformers.models.bert.modeling_bert.BertLMPredictionHead'>", +"BertOnlyMLMHead": "<'transformers.models.bert.modeling_bert.BertOnlyMLMHead'>", +"BertOnlyNSPHead": "<'transformers.models.bert.modeling_bert.BertOnlyNSPHead'>", +"BertPredictionHeadTransform": "<'transformers.models.bert.modeling_bert.BertPredictionHeadTransform'>", +"BertPreTrainingHeads": "<'transformers.models.bert.modeling_bert.BertPreTrainingHeads'>", + +"BertGenerationAttention": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationAttention'>", +"BertGenerationEmbeddings": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationEmbeddings'>", +"BertGenerationIntermediate": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationIntermediate'>", +"BertGenerationLayer": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationLayer'>", +"BertGenerationOnlyLMHead": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationOnlyLMHead'>", +"BertGenerationOutput": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationOutput'>", +"BertGenerationSelfAttention": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationSelfAttention'>", +"BertGenerationSelfOutput": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationSelfOutput'>", + +"AlbertAttention": "<'transformers.models.albert.modeling_albert.AlbertAttention'>", +"AlbertEmbeddings": "<'transformers.models.albert.modeling_albert.AlbertEmbeddings'>", +"AlbertLayer": "<'transformers.models.albert.modeling_albert.AlbertLayer'>", +"AlbertLayerGroup": "<'transformers.models.albert.modeling_albert.AlbertLayerGroup'>", +"AlbertMLMHead": "<'transformers.models.albert.modeling_albert.AlbertMLMHead'>", +"AlbertSdpaAttention": "<'transformers.models.albert.modeling_albert.AlbertSdpaAttention'>", +"AlbertSOPHead": "<'transformers.models.albert.modeling_albert.AlbertSOPHead'>", +"AlbertTransformer": "<'transformers.models.albert.modeling_albert.AlbertTransformer'>", + + +"XLNetFeedForward": "<'transformers.models.xlnet.modeling_xlnet.XLNetFeedForward'>", +"XLNetLayer": "<'transformers.models.xlnet.modeling_xlnet.XLNetLayer'>", +"XLNetPoolerAnswerClass": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerAnswerClass'>", +"XLNetPoolerEndLogits": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerEndLogits'>", +"XLNetPoolerStartLogits": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerStartLogits'>", +"XLNetRelativeAttention": "<'transformers.models.xlnet.modeling_xlnet.XLNetRelativeAttention'>", +"XLNetSequenceSummary": "<'transformers.models.xlnet.modeling_xlnet.XLNetSequenceSummary'>", + + +"GPT2Attention": +"GPT2Block": +"GPT2MLP": +"GPT2SequenceSummary": + + +"CLIPAttention": "<'transformers.models.clip.modeling_clip.CLIPAttention'>", +"CLIPEncoder": "<'transformers.models.clip.modeling_clip.CLIPEncoder'>", +"CLIPEncoderLayer": "<'transformers.models.clip.modeling_clip.CLIPEncoderLayer'>", +"CLIPMLP": "<'transformers.models.clip.modeling_clip.CLIPMLP'>", + + +"LlamaAttention": "<'transformers.models.llama.modeling_llama.LlamaAttention'>", +"LlamaDecoderLayer": "<'transformers.models.llama.modeling_llama.LlamaDecoderLayer'>", +"LlamaMLP": "<'transformers.models.llama.modeling_llama.LlamaMLP'>", +"LlamaRMSNorm": "<'transformers.models.llama.modeling_llama.LlamaRMSNorm'>", +"LlamaRotaryEmbedding": "<'transformers.models.llama.modeling_llama.LlamaRotaryEmbedding'>", + + + + + +"ViTAttention": "<'transformers.models.vit.modeling_vit.ViTAttention'>", +"VitDetAttention": "<'transformers.models.vitdet.modeling_vitdet.VitDetAttention'>", +"VitDetDropPath": "<'transformers.models.vitdet.modeling_vitdet.VitDetDropPath'>", +"VitDetEmbeddings": "<'transformers.models.vitdet.modeling_vitdet.VitDetEmbeddings'>", +"VitDetEncoder": "<'transformers.models.vitdet.modeling_vitdet.VitDetEncoder'>", +"VitDetLayer": "<'transformers.models.vitdet.modeling_vitdet.VitDetLayer'>", +"VitDetLayerNorm": "<'transformers.models.vitdet.modeling_vitdet.VitDetLayerNorm'>", +"VitDetMlp": "<'transformers.models.vitdet.modeling_vitdet.VitDetMlp'>", +"VitDetResBottleneckBlock": "<'transformers.models.vitdet.modeling_vitdet.VitDetResBottleneckBlock'>", +"ViTEmbeddings": "<'transformers.models.vit.modeling_vit.ViTEmbeddings'>", +"ViTEncoder": "<'transformers.models.vit.modeling_vit.ViTEncoder'>", +"ViTLayer": "<'transformers.models.vit.modeling_vit.ViTLayer'>", +"ViTOutput": "<'transformers.models.vit.modeling_vit.ViTOutput'>", +"ViTPooler": "<'transformers.models.vit.modeling_vit.ViTPooler'>", + + +"EsmAttention": "<'transformers.models.esm.modeling_esm.EsmAttention'>", +"EsmClassificationHead": "<'transformers.models.esm.modeling_esm.EsmClassificationHead'>", +"EsmContactPredictionHead": "<'transformers.models.esm.modeling_esm.EsmContactPredictionHead'>", +"EsmEmbeddings": "<'transformers.models.esm.modeling_esm.EsmEmbeddings'>", +"EsmEncoder": "<'transformers.models.esm.modeling_esm.EsmEncoder'>", +"EsmIntermediate": "<'transformers.models.esm.modeling_esm.EsmIntermediate'>", +"EsmLayer": "<'transformers.models.esm.modeling_esm.EsmLayer'>", +"EsmLMHead": "<'transformers.models.esm.modeling_esm.EsmLMHead'>", +"EsmOutput": "<'transformers.models.esm.modeling_esm.EsmOutput'>", +"EsmPooler": "<'transformers.models.esm.modeling_esm.EsmPooler'>", +"EsmSelfAttention": "<'transformers.models.esm.modeling_esm.EsmSelfAttention'>", +"EsmSelfOutput": "<'transformers.models.esm.modeling_esm.EsmSelfOutput'>", + + +modeling_layers.GradientCheckpointingLayer +time_series_utils.ParameterProjection +time_series_utils.LambdaLayer + +{ + "LayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "SqueezeBertLayerNorm": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertLayerNorm'>", + "ChameleonLayerNorm": "<'transformers.models.chameleon.modeling_chameleon.ChameleonLayerNorm'>", + "EomtLayerNorm2d": "<'transformers.models.eomt.modeling_eomt.EomtLayerNorm2d'>", + "LayoutLMLayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "NemotronLayerNorm1P": "<'transformers.models.nemotron.modeling_nemotron.NemotronLayerNorm1P'>", + "FusedLayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "JukeboxLayerNorm": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxLayerNorm'>" +} + +{ + "ModuleList": "<'torch.nn.modules.container.ModuleList'>", + "SequentialLlama4TextExperts": "<'transformers.quantizers.base.SequentialLlama4TextExperts'>", + "AfmoeExperts": "<'transformers.models.afmoe.modeling_afmoe.AfmoeExperts'>", + "VitPoseNaiveMoe": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseNaiveMoe'>" +} + +{ + "BertEncoder": "<'transformers.models.bert.modeling_bert.BertEncoder'>", + "ErnieEncoder": "<'transformers.models.ernie.modular_ernie.ErnieEncoder'>" +} + + + +['ContextPooler', 'VisualBertPooler', 'FlavaPooler', 'SqueezeBertPooler', 'PoolFormerFinalPooler', 'ViltPooler', 'EsmPooler', 'EvollaSaProtPooler', 'EvollaSaProtPooler', 'LukePooler', 'ContextPooler', 'MarkupLMPooler', 'VJEPA2AttentivePooler', 'VJEPA2PoolerCrossAttention', 'VJEPA2PoolerCrossAttentionLayer', 'VJEPA2PoolerSelfAttention', 'VJEPA2PoolerSelfAttentionLayer', 'EsmPooler', 'LxmertPooler', 'LlavaNextVideoPooler', 'TapasPooler', 'Data2VecVisionPooler', 'Data2VecTextPooler', 'LayoutLMv2Pooler', 'XLMRobertaPooler', 'MobileBertPooler', 'BlipTextPooler', 'DeiTPooler', 'DPTViTPooler', 'CamembertPooler', 'AlignTextPooler', 'ViTPooler', 'XLMPoolerAnswerClass', 'XLMPoolerEndLogits', 'XLMPoolerStartLogits', 'BertPooler', 'IJepaPooler', 'ClapTextPooler', 'HieraPooler', 'ChineseCLIPTextPooler', 'VivitPooler', 'XLMRobertaXLPooler', 'AltRobertaPooler', 'LongformerPooler', 'YolosPooler', 'BeitPooler', 'RobertaPooler', 'TvpPooler', 'BridgeTowerPooler', 'ContextPooler', 'RobertaPreLayerNormPooler', 'XLNetPoolerAnswerClass', 'XLNetPoolerEndLogits', 'XLNetPoolerStartLogits', 'MPNetPooler', 'BertPooler', 'ErniePooler', 'ErniePooler', 'BrosPooler', 'IBertPooler', 'FlaubertPoolerAnswerClass', 'FlaubertPoolerEndLogits', 'FlaubertPoolerStartLogits', 'RoCBertPooler', 'MegatronBertPooler', 'XmodPooler', 'LayoutLMPooler', 'FNetPooler', 'CaninePooler', 'LiltPooler', 'RemBertPooler',] +['SEWDIntermediate', 'VisualBertIntermediate', 'Blip2QFormerIntermediate', 'FlavaIntermediate', 'VideoMAEIntermediate', 'SwinIntermediate', 'ViltIntermediate', 'ElectraIntermediate', 'EsmIntermediate', 'EvollaSaProtIntermediate', 'EvollaSaProtIntermediate', 'LukeIntermediate', 'DebertaIntermediate', 'DonutSwinIntermediate', 'MaskFormerSwinIntermediate', 'MarkupLMIntermediate', 'CpmAntIntermediate', 'EsmIntermediate', 'BigBirdIntermediate', 'BertGenerationIntermediate', 'ViTMSNIntermediate', 'LxmertIntermediate', 'TapasIntermediate', 'Data2VecVisionIntermediate', 'Data2VecTextIntermediate', 'DinatIntermediate', 'LayoutLMv2Intermediate', 'LayoutLMv3Intermediate', 'XLMRobertaIntermediate', 'MobileBertIntermediate', 'BlipTextIntermediate', 'DeiTIntermediate', 'DPTViTIntermediate', 'YosoIntermediate', 'CamembertIntermediate', 'RoFormerIntermediate', 'TimesformerIntermediate', 'AlignTextIntermediate', 'ViTIntermediate', 'BertIntermediate', 'IJepaIntermediate', 'ClapAudioIntermediate', 'ClapTextIntermediate', 'MobileViTIntermediate', 'ConvBertIntermediate', 'ChineseCLIPTextIntermediate', 'VivitIntermediate', 'XLMRobertaXLIntermediate', 'AltRobertaIntermediate', 'SplinterIntermediate', 'LongformerIntermediate', 'YolosIntermediate', 'NystromformerIntermediate', 'BeitIntermediate', 'CvtIntermediate', 'RobertaIntermediate', 'TvpIntermediate', 'ASTIntermediate', 'BridgeTowerIntermediate', 'DebertaV2Intermediate', 'Swinv2Intermediate', 'RobertaPreLayerNormIntermediate', 'MPNetIntermediate', 'ErnieIntermediate', 'InstructBlipQFormerIntermediate', 'BrosIntermediate', 'MraIntermediate', 'InstructBlipVideoQFormerIntermediate', 'IBertIntermediate', 'ViTMAEIntermediate', 'RoCBertIntermediate', 'MegatronBertIntermediate', 'XmodIntermediate', 'LayoutLMIntermediate', 'GitIntermediate', 'FNetIntermediate', 'CanineIntermediate', 'LiltIntermediate', 'RemBertIntermediate', 'Swin2SRIntermediate',] \ No newline at end of file diff --git a/tests/classes_using.py b/tests/classes_using.py new file mode 100644 index 0000000..987a21c --- /dev/null +++ b/tests/classes_using.py @@ -0,0 +1,43 @@ +Apply +import inspect +import torch.nn as nn + +def find_classes_with_module_list(module_or_class): + """ + Finds classes in a module or a script that use nn.ModuleList. + + Args: + module_or_class (module or class): The module or class to inspect. + + Returns: + List of class names that use nn.ModuleList. + """ + classes_with_module_list = [] + if isinstance(module_or_class, type): + # If it's a class, just inspect that class + for name, obj in inspect.getmembers(module_or_class): + if inspect.isclass(obj) and 'nn.ModuleList' in inspect.getsource(obj): + classes_with_module_list.append(name) + else: + # If it's a module, inspect all classes within it + for name, obj in inspect.getmembers(module_or_class): + if inspect.isclass(obj): + if 'nn.ModuleList' in inspect.getsource(obj): + classes_with_module_list.append(name) + + return classes_with_module_list + +# Example usage: +from torch.nn import ModuleList + +# Assuming you have a module named 'y_module' +class MyModule(nn.Module): + def __init__(self): + super(MyModule, self).__init__() + self.modules = ModuleList([nn.Linear(10, 20)]) + +# Find classes using nn.ModuleList +classes_with_module_list = find_classes_with_module_list(nn) +print("Classes using nn.ModuleList:", classes_with_module_list) + +Classes using nn.ModuleList: ['ModuleList'] diff --git a/tests/mapinput.txt b/tests/mapinput.txt new file mode 100644 index 0000000..41c6157 --- /dev/null +++ b/tests/mapinput.txt @@ -0,0 +1,3502 @@ +("_MapInputEmbedding", + "_PruneReindexingLMHead", + "AbstractPreprocessor", + "AccurateGELUActivation", + "AdaptiveEmbedding", + "Aimv2Attention", + "Aimv2AttentionPoolingHead", + "Aimv2Encoder", + "Aimv2EncoderLayer", + "Aimv2MLP", + "Aimv2RMSNorm", + "Aimv2TextEmbeddings", + "Aimv2VisionEmbeddings", + "AlbertAttention", + "AlbertEmbeddings", + "AlbertLayer", + "AlbertLayerGroup", + "AlbertMLMHead", + "AlbertSdpaAttention", + "AlbertSOPHead", + "AlbertTransformer", + "AlignTextAttention", + "AlignTextEmbeddings", + "AlignTextEncoder", + "AlignTextIntermediate", + "AlignTextLayer", + "AlignTextOutput", + "AlignTextPooler", + "AlignTextSelfAttention", + "AlignTextSelfOutput", + "AlignVisionBlock", + "AlignVisionDepthwiseConv2d", + "AlignVisionDepthwiseLayer", + "AlignVisionEmbeddings", + "AlignVisionEncoder", + "AlignVisionExpansionLayer", + "AlignVisionFinalBlockLayer", + "AlignVisionSqueezeExciteLayer", + "AltCLIPAttention", + "AltCLIPEncoder", + "AltCLIPEncoderLayer", + "AltCLIPMLP", + "AltCLIPVisionEmbeddings", + "AltCLIPVisionTransformer", + "AltRobertaAttention", + "AltRobertaEmbeddings", + "AltRobertaEncoder", + "AltRobertaIntermediate", + "AltRobertaLayer", + "AltRobertaModel", + "AltRobertaOutput", + "AltRobertaPooler", + "AltRobertaSelfAttention", + "AltRobertaSelfOutput", + "AMPBlock", + "AMSoftmaxLoss", + "ArceeAttention", + "ArceeDecoderLayer", + "ArceeMLP", + "ArceeRMSNorm", + "ArceeRotaryEmbedding", + "AriaCrossAttention", + "AriaGroupedExpertsGemm", + "AriaGroupedExpertsMLP", + "AriaProjector", + "AriaProjectorMLP", + "AriaSharedExpertsMLP", + "AriaTextAttention", + "AriaTextDecoderLayer", + "AriaTextMoELayer", + "AriaTextRMSNorm", + "AriaTextRotaryEmbedding", + "ASTAttention", + "ASTEmbeddings", + "ASTEncoder", + "ASTIntermediate", + "ASTLayer", + "ASTMLPHead", + "ASTOutput", + "ASTPatchEmbeddings", + "ASTSelfAttention", + "ASTSelfOutput", + "Attention", + "AttentiveStatisticsPooling", + "AutoformerAttention", + "AutoformerDecoder", + "AutoformerDecoderLayer", + "AutoformerEncoder", + "AutoformerEncoderLayer", + "AutoformerFeatureEmbedder", + "AutoformerLayernorm", + "AutoformerMeanScaler", + "AutoformerNOPScaler", + "AutoformerSeriesDecompositionLayer", + "AutoformerSinusoidalPositionalEmbedding", + "AutoformerStdScaler", + "AutoformerValueEmbedding", + "AxialPositionEmbeddings", + "AyaVisionMultiModalProjector", + "BambaAttention", + "BambaDecoderLayer", + "BambaMixer", + "BambaMLP", + "BambaRMSNorm", + "BambaRMSNormGated", + "BambaRotaryEmbedding", + "BarkBlock", + "BarkMLP", + "BarkSelfAttention", + "BarkSelfFlashAttention2", + "BartAttention", + "BartClassificationHead", + "BartDecoder", + "BartDecoderLayer", + "BartDecoderWrapper", + "BartEncoder", + "BartEncoderLayer", + "BartLearnedPositionalEmbedding", + "BartScaledWordEmbedding", + "BCEWithLogitsLoss", + "BeitAttention", + "BeitConvModule", + "BeitDropPath", + "BeitEmbeddings", + "BeitEncoder", + "BeitFCNHead", + "BeitIntermediate", + "BeitLayer", + "BeitOutput", + "BeitPatchEmbeddings", + "BeitPooler", + "BeitPyramidPoolingBlock", + "BeitPyramidPoolingModule", + "BeitRelativePositionBias", + "BeitSdpaSelfAttention", + "BeitSelfAttention", + "BeitSelfOutput", + "BeitUperHead", + "BertAttention", + "BertEmbeddings", + "BertEncoder", + "BertGenerationAttention", + "BertGenerationEmbeddings", + "BertGenerationIntermediate", + "BertGenerationLayer", + "BertGenerationOnlyLMHead", + "BertGenerationOutput", + "BertGenerationSelfAttention", + "BertGenerationSelfOutput", + "BertIntermediate", + "BertLayer", + "BertLMPredictionHead", + "BertOnlyMLMHead", + "BertOnlyNSPHead", + "BertOutput", + "BertPooler", + "BertPredictionHeadTransform", + "BertPreTrainingHeads", + "BertSdpaSelfAttention", + "BertSelfAttention", + "BertSelfOutput", + "BigBirdAttention", + "BigBirdBlockSparseAttention", + "BigBirdClassificationHead", + "BigBirdEmbeddings", + "BigBirdEncoder", + "BigBirdForQuestionAnsweringHead", + "BigBirdIntermediate", + "BigBirdLayer", + "BigBirdLMPredictionHead", + "BigBirdOnlyMLMHead", + "BigBirdOnlyNSPHead", + "BigBirdOutput", + "BigBirdPegasusBlockSparseAttention", + "BigBirdPegasusClassificationHead", + "BigBirdPegasusDecoder", + "BigBirdPegasusDecoderAttention", + "BigBirdPegasusDecoderLayer", + "BigBirdPegasusDecoderWrapper", + "BigBirdPegasusEncoder", + "BigBirdPegasusEncoderAttention", + "BigBirdPegasusEncoderLayer", + "BigBirdPegasusLearnedPositionalEmbedding", + "BigBirdPegasusScaledWordEmbedding", + "BigBirdPegasusSelfAttention", + "BigBirdPredictionHeadTransform", + "BigBirdPreTrainingHeads", + "BigBirdSelfAttention", + "BigBirdSelfOutput", + "BioGptAttention", + "BioGptDecoderLayer", + "BioGptLearnedPositionalEmbedding", + "BioGptScaledWordEmbedding", + "BitBottleneckLayer", + "BitDownsampleConv", + "BitDropPath", + "BitEmbeddings", + "BitEncoder", + "BitGroupNormActivation", + "BitMaxPool2d", + "BitNetAttention", + "BitNetDecoderLayer", + "BitNetMLP", + "BitNetRMSNorm", + "BitNetRotaryEmbedding", + "BitPreActivationBottleneckLayer", + "BitStage", + "BlenderbotAttention", + "BlenderbotDecoder", + "BlenderbotDecoderLayer", + "BlenderbotDecoderWrapper", + "BlenderbotEncoder", + "BlenderbotEncoderLayer", + "BlenderbotLearnedPositionalEmbedding", + "BlenderbotScaledWordEmbedding", + "BlenderbotSmallAttention", + "BlenderbotSmallDecoder", + "BlenderbotSmallDecoderLayer", + "BlenderbotSmallDecoderWrapper", + "BlenderbotSmallEncoder", + "BlenderbotSmallEncoderLayer", + "BlenderbotSmallLearnedPositionalEmbedding", + "Blip2Attention", + "Blip2Encoder", + "Blip2EncoderLayer", + "Blip2MLP", + "Blip2QFormerAttention", + "Blip2QFormerEncoder", + "Blip2QFormerIntermediate", + "Blip2QFormerLayer", + "Blip2QFormerMultiHeadAttention", + "Blip2QFormerOutput", + "Blip2QFormerSelfOutput", + "Blip2TextEmbeddings", + "Blip2VisionEmbeddings", + "BlipAttention", + "BlipEncoder", + "BlipEncoderLayer", + "BlipMLP", + "BlipTextAttention", + "BlipTextEmbeddings", + "BlipTextEncoder", + "BlipTextIntermediate", + "BlipTextLayer", + "BlipTextLMPredictionHead", + "BlipTextOnlyMLMHead", + "BlipTextOutput", + "BlipTextPooler", + "BlipTextPredictionHeadTransform", + "BlipTextSelfAttention", + "BlipTextSelfOutput", + "BlipVisionEmbeddings", + "Block", + "BloomAttention", + "BloomBlock", + "BloomGelu", + "BloomMLP", + "Bottleneck", + "BottleneckLayer", + "BridgeTowerAttention", + "BridgeTowerBertCrossLayer", + "BridgeTowerContrastiveHead", + "BridgeTowerIntermediate", + "BridgeTowerITMHead", + "BridgeTowerLinkTower", + "BridgeTowerMLMHead", + "BridgeTowerOutput", + "BridgeTowerPooler", + "BridgeTowerPredictionHeadTransform", + "BridgeTowerResidualAttention", + "BridgeTowerSelfAttention", + "BridgeTowerSelfOutput", + "BridgeTowerTextEmbeddings", + "BridgeTowerTextEncoder", + "BridgeTowerTextLayer", + "BridgeTowerTextModel", + "BridgeTowerTransformer", + "BridgeTowerVisionEmbeddings", + "BridgeTowerVisionModel", + "BridgeTowerVisionTransformer", + "BrosAttention", + "BrosBboxEmbeddings", + "BrosEncoder", + "BrosIntermediate", + "BrosLayer", + "BrosOutput", + "BrosPooler", + "BrosPositionalEmbedding1D", + "BrosPositionalEmbedding2D", + "BrosRelationExtractor", + "BrosSelfAttention", + "BrosSelfOutput", + "BrosTextEmbeddings", + "CamembertAttention", + "CamembertClassificationHead", + "CamembertEmbeddings", + "CamembertEncoder", + "CamembertIntermediate", + "CamembertLayer", + "CamembertLMHead", + "CamembertOutput", + "CamembertPooler", + "CamembertSdpaSelfAttention", + "CamembertSelfAttention", + "CamembertSelfOutput", + "CanineAttention", + "CanineEmbeddings", + "CanineEncoder", + "CanineIntermediate", + "CanineLayer", + "CanineLMPredictionHead", + "CanineOnlyMLMHead", + "CanineOutput", + "CaninePooler", + "CaninePredictionHeadTransform", + "CanineSelfAttention", + "CanineSelfOutput", + "CausalSelfAttention", + "ChameleonAttention", + "ChameleonDecoderLayer", + "ChameleonDynamicNTKScalingRotaryEmbedding", + "ChameleonLayerNorm", + "ChameleonLinearScalingRotaryEmbedding", + "ChameleonMLP", + "ChameleonRMSNorm", + "ChameleonRotaryEmbedding", + "ChameleonSwinDecoderLayer", + "ChameleonVQVAEEncoder", + "ChameleonVQVAEEncoderAttnBlock", + "ChameleonVQVAEEncoderConvDownsample", + "ChameleonVQVAEEncoderResnetBlock", + "ChameleonVQVAEVectorQuantizer", + "CharactersToMolecules", + "ChineseCLIPTextAttention", + "ChineseCLIPTextEmbeddings", + "ChineseCLIPTextEncoder", + "ChineseCLIPTextIntermediate", + "ChineseCLIPTextLayer", + "ChineseCLIPTextOutput", + "ChineseCLIPTextPooler", + "ChineseCLIPTextSelfAttention", + "ChineseCLIPTextSelfOutput", + "ChineseCLIPVisionAttention", + "ChineseCLIPVisionEmbeddings", + "ChineseCLIPVisionEncoder", + "ChineseCLIPVisionLayer", + "ChineseCLIPVisionMLP", + "ChineseCLIPVisionTransformer", + "ChunkReformerFeedForward", + "ClapAudioAFFBlock", + "ClapAudioAttention", + "ClapAudioEncoder", + "ClapAudioIntermediate", + "ClapAudioLayer", + "ClapAudioOutput", + "ClapAudioPatchEmbed", + "ClapAudioPatchMerging", + "ClapAudioSelfAttention", + "ClapAudioSelfOutput", + "ClapAudioStage", + "ClapDropPath", + "ClapProjectionLayer", + "ClapTextAttention", + "ClapTextEmbeddings", + "ClapTextEncoder", + "ClapTextIntermediate", + "ClapTextLayer", + "ClapTextOutput", + "ClapTextPooler", + "ClapTextSelfAttention", + "ClapTextSelfOutput", + "CLIPAttention", + "CLIPEncoder", + "CLIPEncoderLayer", + "CLIPMLP", + "ClippedGELUActivation", + "CLIPSegAttention", + "CLIPSegDecoder", + "CLIPSegDecoderLayer", + "CLIPSegEncoder", + "CLIPSegEncoderLayer", + "CLIPSegMLP", + "CLIPSegTextEmbeddings", + "CLIPSegTextTransformer", + "CLIPSegVisionEmbeddings", + "CLIPSegVisionTransformer", + "CLIPTextEmbeddings", + "CLIPTextTransformer", + "CLIPVisionEmbeddings", + "CLIPVisionTransformer", + "ClvpConditioningEncoder", + "ClvpDecoderLayer", + "ClvpDecoderMLP", + "ClvpEncoderLayer", + "ClvpEncoderMLP", + "ClvpGatedLinearUnit", + "ClvpRMSNorm", + "ClvpRotaryPositionalEmbedding", + "ClvpSelfAttention", + "ClvpSequenceSummary", + "CodeGenAttention", + "CodeGenBlock", + "CodeGenMLP", + "Cohere2Attention", + "Cohere2DecoderLayer", + "Cohere2LayerNorm", + "Cohere2MLP", + "Cohere2RotaryEmbedding", + "Cohere2VisionMultiModalProjector", + "CohereAttention", + "CohereDecoderLayer", + "CohereLayerNorm", + "CohereMLP", + "CohereRotaryEmbedding", + "ConditionalDetrAttention", + "ConditionalDetrConvEncoder", + "ConditionalDetrConvModel", + "ConditionalDetrDecoder", + "ConditionalDetrDecoderLayer", + "ConditionalDetrEncoder", + "ConditionalDetrEncoderLayer", + "ConditionalDetrFrozenBatchNorm2d", + "ConditionalDetrLearnedPositionEmbedding", + "ConditionalDetrMaskHeadSmallConv", + "ConditionalDetrMHAttentionMap", + "ConditionalDetrMLPPredictionHead", + "ConditionalDetrSinePositionEmbedding", + "ContextPooler", + "Conv1dSubsampler", + "Conv2DDownsample", + "Conv2dSamePadding", + "ConvActivation", + "ConvBertAttention", + "ConvBertClassificationHead", + "ConvBertEmbeddings", + "ConvBertEncoder", + "ConvBertGeneratorPredictions", + "ConvBertIntermediate", + "ConvBertLayer", + "ConvBertOutput", + "ConvBertPredictionHeadTransform", + "ConvBertSelfAttention", + "ConvBertSelfOutput", + "ConvBertSequenceSummary", + "ConvDropoutLayerNorm", + "ConvLayer", + "ConvNextDropPath", + "ConvNextEmbeddings", + "ConvNextEncoder", + "ConvNextLayer", + "ConvNextLayerNorm", + "ConvNextStage", + "ConvNextV2DropPath", + "ConvNextV2Embeddings", + "ConvNextV2Encoder", + "ConvNextV2GRN", + "ConvNextV2Layer", + "ConvNextV2LayerNorm", + "ConvNextV2Stage", + "ConvProjection", + "CpmAntAttention", + "CpmAntDenseGatedACT", + "CpmAntEncoder", + "CpmAntFeedForward", + "CpmAntFFNBlock", + "CpmAntIntermediate", + "CpmAntLayerNorm", + "CpmAntOutput", + "CpmAntSegmentPositionEmbedding", + "CpmAntSelfAttentionBlock", + "CpmAntTransformerBlock", + "CrossEntropyLoss", + "CsmAttention", + "CsmBackboneModelEmbeddings", + "CsmCodebooksHead", + "CsmDecoderLayer", + "CsmMLP", + "CsmRMSNorm", + "CsmRotaryEmbedding", + "CvtAttention", + "CvtConvEmbeddings", + "CvtDropPath", + "CvtEmbeddings", + "CvtEncoder", + "CvtIntermediate", + "CvtLayer", + "CvtOutput", + "CvtSelfAttention", + "CvtSelfAttentionConvProjection", + "CvtSelfAttentionLinearProjection", + "CvtSelfAttentionProjection", + "CvtSelfOutput", + "CvtStage", + "DabDetrAttention", + "DabDetrConvEncoder", + "DabDetrConvModel", + "DabDetrDecoder", + "DabDetrDecoderLayer", + "DabDetrDecoderLayerCrossAttention", + "DabDetrDecoderLayerFFN", + "DabDetrDecoderLayerSelfAttention", + "DabDetrEncoder", + "DabDetrEncoderLayer", + "DabDetrFrozenBatchNorm2d", + "DabDetrMHAttentionMap", + "DabDetrMLP", + "DabDetrSinePositionEmbedding", + "DacDecoder", + "DacDecoderBlock", + "DacEncoder", + "DacEncoderBlock", + "DacResidualUnit", + "DacResidualVectorQuantize", + "DacVectorQuantize", + "Data2VecAudioAdapter", + "Data2VecAudioAdapterLayer", + "Data2VecAudioAttention", + "Data2VecAudioConvLayer", + "Data2VecAudioEncoder", + "Data2VecAudioEncoderLayer", + "Data2VecAudioFeatureEncoder", + "Data2VecAudioFeatureProjection", + "Data2VecAudioFeedForward", + "Data2VecAudioPadLayer", + "Data2VecAudioPositionalConvEmbedding", + "Data2VecAudioPositionalConvLayer", + "Data2VecTextAttention", + "Data2VecTextClassificationHead", + "Data2VecTextEncoder", + "Data2VecTextForTextEmbeddings", + "Data2VecTextIntermediate", + "Data2VecTextLayer", + "Data2VecTextLMHead", + "Data2VecTextOutput", + "Data2VecTextPooler", + "Data2VecTextSelfAttention", + "Data2VecTextSelfOutput", + "Data2VecVisionAttention", + "Data2VecVisionConvModule", + "Data2VecVisionDropPath", + "Data2VecVisionEmbeddings", + "Data2VecVisionEncoder", + "Data2VecVisionFCNHead", + "Data2VecVisionIntermediate", + "Data2VecVisionLayer", + "Data2VecVisionOutput", + "Data2VecVisionPatchEmbeddings", + "Data2VecVisionPooler", + "Data2VecVisionPyramidPoolingBlock", + "Data2VecVisionPyramidPoolingModule", + "Data2VecVisionRelativePositionBias", + "Data2VecVisionSdpaSelfAttention", + "Data2VecVisionSelfAttention", + "Data2VecVisionSelfOutput", + "Data2VecVisionUperHead", + "DbrxAttention", + "DbrxBlock", + "DbrxExpertGLU", + "DbrxExperts", + "DbrxFFN", + "DbrxFlashAttention2", + "DbrxNormAttentionNorm", + "DbrxRotaryEmbedding", + "DbrxRouter", + "DbrxSdpaAttention", + "DebertaAttention", + "DebertaEmbeddings", + "DebertaEncoder", + "DebertaIntermediate", + "DebertaLayer", + "DebertaLayerNorm", + "DebertaLMPredictionHead", + "DebertaOnlyMLMHead", + "DebertaOutput", + "DebertaSelfOutput", + "DebertaV2Attention", + "DebertaV2Embeddings", + "DebertaV2Encoder", + "DebertaV2Intermediate", + "DebertaV2Layer", + "DebertaV2LMPredictionHead", + "DebertaV2OnlyMLMHead", + "DebertaV2Output", + "DebertaV2SelfOutput", + "DecisionTransformerGPT2Attention", + "DecisionTransformerGPT2Block", + "DecisionTransformerGPT2MLP", + "DecoderLayer", + "DeepseekV2Attention", + "DeepseekV2DecoderLayer", + "DeepseekV2MLP", + "DeepseekV2MoE", + "DeepseekV2MoEGate", + "DeepseekV2RMSNorm", + "DeepseekV2RotaryEmbedding", + "DeepseekV3Attention", + "DeepseekV3DecoderLayer", + "DeepseekV3MLP", + "DeepseekV3MoE", + "DeepseekV3RMSNorm", + "DeepseekV3RotaryEmbedding", + "DeepseekV3TopkRouter", + "DeepseekVLAligner", + "DeepseekVLHybridAligner", + "DeepseekVLHybridLayerNorm", + "DeepseekVLSamVisionNeck", + "DeepseekVLSamVisionProj", + "DeformableDetrConvEncoder", + "DeformableDetrConvModel", + "DeformableDetrDecoder", + "DeformableDetrDecoderLayer", + "DeformableDetrEncoder", + "DeformableDetrEncoderLayer", + "DeformableDetrFrozenBatchNorm2d", + "DeformableDetrHungarianMatcher", + "DeformableDetrImageLoss", + "DeformableDetrLearnedPositionEmbedding", + "DeformableDetrMLPPredictionHead", + "DeformableDetrMultiheadAttention", + "DeformableDetrMultiscaleDeformableAttention", + "DeformableDetrSinePositionEmbedding", + "DeiTAttention", + "DeiTEmbeddings", + "DeiTEncoder", + "DeiTIntermediate", + "DeiTLayer", + "DeiTOutput", + "DeiTPatchEmbeddings", + "DeiTPooler", + "DeiTSelfAttention", + "DeiTSelfOutput", + "DepthAnythingDepthEstimationHead", + "DepthAnythingFeatureFusionLayer", + "DepthAnythingFeatureFusionStage", + "DepthAnythingNeck", + "DepthAnythingPreActResidualLayer", + "DepthAnythingReassembleLayer", + "DepthAnythingReassembleStage", + "DepthProDepthEstimationHead", + "DepthProEncoder", + "DepthProFeatureFusionLayer", + "DepthProFeatureFusionStage", + "DepthProFeatureProjection", + "DepthProFeatureUpsample", + "DepthProFeatureUpsampleBlock", + "DepthProFovEncoder", + "DepthProFovHead", + "DepthProFovModel", + "DepthProImageEncoder", + "DepthProNeck", + "DepthProPatchEncoder", + "DepthProPreActResidualLayer", + "DetaBackboneWithPositionalEncodings", + "DetaDecoder", + "DetaDecoderLayer", + "DetaEncoder", + "DetaEncoderLayer", + "DetaFrozenBatchNorm2d", + "DetaHungarianMatcher", + "DetaLearnedPositionEmbedding", + "DetaLoss", + "DetaMLPPredictionHead", + "DetaMultiheadAttention", + "DetaMultiscaleDeformableAttention", + "DetaSinePositionEmbedding", + "DetaStage1Assigner", + "DetaStage2Assigner", + "DetrAttention", + "DetrConvEncoder", + "DetrConvModel", + "DetrDecoder", + "DetrDecoderLayer", + "DetrEncoder", + "DetrEncoderLayer", + "DetrFrozenBatchNorm2d", + "DetrLearnedPositionEmbedding", + "DetrMaskHeadSmallConv", + "DetrMHAttentionMap", + "DetrMLPPredictionHead", + "DetrSinePositionEmbedding", + "DFineConvEncoder", + "DFineConvNormLayer", + "DFineCSPRepLayer", + "DFineDecoder", + "DFineDecoderLayer", + "DFineEncoder", + "DFineEncoderLayer", + "DFineFrozenBatchNorm2d", + "DFineGate", + "DFineHybridEncoder", + "DFineIntegral", + "DFineLoss", + "DFineLQE", + "DFineMLP", + "DFineMLPPredictionHead", + "DFineMultiheadAttention", + "DFineMultiscaleDeformableAttention", + "DFineRepNCSPELAN4", + "DFineRepVggBlock", + "DFineSCDown", + "DiaCrossAttention", + "DiaDecoder", + "DiaDecoderLayer", + "DiaEncoder", + "DiaEncoderLayer", + "DiaMLP", + "DiaMultiChannelEmbedding", + "DiaRMSNorm", + "DiaRotaryEmbedding", + "DiaSelfAttention", + "DiffLlamaAttention", + "DiffLlamaDecoderLayer", + "DiffLlamaFlashAttention2", + "DiffLlamaMLP", + "DiffLlamaRMSNorm", + "DiffLlamaRotaryEmbedding", + "DiffLlamaSdpaAttention", + "DinatDownsampler", + "DinatDropPath", + "DinatEmbeddings", + "DinatEncoder", + "DinatIntermediate", + "DinatLayer", + "DinatOutput", + "DinatPatchEmbeddings", + "DinatStage", + "Dinov2Attention", + "Dinov2DropPath", + "Dinov2Embeddings", + "Dinov2Encoder", + "Dinov2Layer", + "Dinov2LayerScale", + "Dinov2MLP", + "Dinov2PatchEmbeddings", + "Dinov2SelfAttention", + "Dinov2SelfOutput", + "Dinov2SwiGLUFFN", + "Dinov2WithRegistersAttention", + "Dinov2WithRegistersDropPath", + "Dinov2WithRegistersEmbeddings", + "Dinov2WithRegistersEncoder", + "Dinov2WithRegistersLayer", + "Dinov2WithRegistersLayerScale", + "Dinov2WithRegistersMLP", + "Dinov2WithRegistersPatchEmbeddings", + "Dinov2WithRegistersSelfAttention", + "Dinov2WithRegistersSelfOutput", + "Dinov2WithRegistersSwiGLUFFN", + "DisentangledSelfAttention", + "DistilBertFlashAttention2", + "DistilBertSdpaAttention", + "DiTAttention", + "DiTCodecEmbedding", + "DiTDecoderLayer", + "DiTInputEmbedding", + "DiTMLP", + "DiTTimestepEmbedding", + "DogeAttention", + "DogeCDMoE", + "DogeDecoderLayer", + "DogeMLP", + "DogeRMSNorm", + "DogeRotaryEmbedding", + "DonutSwinAttention", + "DonutSwinDropPath", + "DonutSwinEmbeddings", + "DonutSwinEncoder", + "DonutSwinIntermediate", + "DonutSwinLayer", + "DonutSwinOutput", + "DonutSwinPatchEmbeddings", + "DonutSwinPatchMerging", + "DonutSwinSelfAttention", + "DonutSwinSelfOutput", + "DonutSwinStage", + "Dots1Attention", + "Dots1DecoderLayer", + "Dots1MLP", + "Dots1MoE", + "Dots1RMSNorm", + "Dots1RotaryEmbedding", + "Dots1TopkRouter", + "DownSample1d", + "DPREncoder", + "DPRSpanPredictor", + "DPTAuxiliaryHead", + "DPTDepthEstimationHead", + "DPTFeatureFusionLayer", + "DPTFeatureFusionStage", + "DPTNeck", + "DPTPreActResidualLayer", + "DPTReassembleLayer", + "DPTReassembleStage", + "DPTSelfAttention", + "DPTSemanticSegmentationHead", + "DPTViTAttention", + "DPTViTEmbeddings", + "DPTViTEncoder", + "DPTViTHybridEmbeddings", + "DPTViTIntermediate", + "DPTViTLayer", + "DPTViTOutput", + "DPTViTPatchEmbeddings", + "DPTViTPooler", + "DPTViTSelfOutput", + "DynamicPad2d", + "ECAPA_TimeDelayNet", + "EfficientFormerConvMlp", + "EfficientFormerConvStem", + "EfficientFormerDenseMlp", + "EfficientFormerDropPath", + "EfficientFormerEncoder", + "EfficientFormerFlat", + "EfficientFormerIntermediateStage", + "EfficientFormerLastStage", + "EfficientFormerMeta3D", + "EfficientFormerMeta3DLayers", + "EfficientFormerMeta4D", + "EfficientFormerMeta4DLayers", + "EfficientFormerPatchEmbeddings", + "EfficientFormerPooling", + "EfficientFormerSelfAttention", + "EfficientLoFTRAggregatedAttention", + "EfficientLoFTRAggregationLayer", + "EfficientLoFTRAttention", + "EfficientLoFTRConvNormLayer", + "EfficientLoFTRepVGG", + "EfficientLoFTRFineFusionLayer", + "EfficientLoFTRLocalFeatureTransformer", + "EfficientLoFTRLocalFeatureTransformerLayer", + "EfficientLoFTRMLP", + "EfficientLoFTROutConvBlock", + "EfficientLoFTRRepVGGBlock", + "EfficientLoFTRRepVGGStage", + "EfficientLoFTRRotaryEmbedding", + "EfficientNetBlock", + "EfficientNetDepthwiseConv2d", + "EfficientNetDepthwiseLayer", + "EfficientNetEmbeddings", + "EfficientNetEncoder", + "EfficientNetExpansionLayer", + "EfficientNetFinalBlockLayer", + "EfficientNetSqueezeExciteLayer", + "EinLinear", + "ElectraAttention", + "ElectraClassificationHead", + "ElectraDiscriminatorPredictions", + "ElectraEmbeddings", + "ElectraEncoder", + "ElectraGeneratorPredictions", + "ElectraIntermediate", + "ElectraLayer", + "ElectraOutput", + "ElectraSelfAttention", + "ElectraSelfOutput", + "ElectraSequenceSummary", + "Embeddings", + "Emu3Attention", + "Emu3DecoderLayer", + "Emu3MLP", + "Emu3RMSNorm", + "Emu3RotaryEmbedding", + "Emu3VQVAEAttentionBlock", + "Emu3VQVAEConv3d", + "Emu3VQVAEDecoder", + "Emu3VQVAEDownBlock", + "Emu3VQVAEEncoder", + "Emu3VQVAEEncoderConvDownsample", + "Emu3VQVAEEncoderConvUpsample", + "Emu3VQVAEGroupNorm", + "Emu3VQVAEMiddleBlock", + "Emu3VQVAEResnetBlock", + "Emu3VQVAESpatialNorm", + "Emu3VQVAETemporalDownsample", + "Emu3VQVAETemporalResnetBlock", + "Emu3VQVAETemporalUpsample", + "Emu3VQVAEUpBlock", + "Emu3VQVAEVectorQuantizer", + "EncodecConv1d", + "EncodecConvTranspose1d", + "EncodecDecoder", + "EncodecEncoder", + "EncodecEuclideanCodebook", + "EncodecLSTM", + "EncodecResidualVectorQuantizer", + "EncodecResnetBlock", + "EncodecVectorQuantization", + "EncoderLayer", + "EntityPredictionHead", + "EntityPredictionHeadTransform", + "EomtAttention", + "EomtDropPath", + "EomtEmbeddings", + "EomtHungarianMatcher", + "EomtLayer", + "EomtLayerNorm2d", + "EomtLayerScale", + "EomtLoss", + "EomtMaskHead", + "EomtMLP", + "EomtPatchEmbeddings", + "EomtScaleBlock", + "EomtScaleLayer", + "EomtSwiGLUFFN", + "Ernie4_5_MoeAttention", + "Ernie4_5_MoeDecoderLayer", + "Ernie4_5_MoeMLP", + "Ernie4_5_MoeRMSNorm", + "Ernie4_5_MoeRotaryEmbedding", + "Ernie4_5_MoeSparseMoeBlock", + "Ernie4_5_MoeStatics", + "Ernie4_5Attention", + "Ernie4_5DecoderLayer", + "Ernie4_5MLP", + "Ernie4_5RMSNorm", + "Ernie4_5RotaryEmbedding", + "ErnieAttention", + "ErnieEmbeddings", + "ErnieEncoder", + "ErnieIntermediate", + "ErnieLayer", + "ErnieLMPredictionHead", + "ErnieMAttention", + "ErnieMEmbeddings", + "ErnieMEncoder", + "ErnieMEncoderLayer", + "ErnieMPooler", + "ErnieMSelfAttention", + "ErnieOnlyMLMHead", + "ErnieOnlyNSPHead", + "ErnieOutput", + "ErniePooler", + "ErniePredictionHeadTransform", + "ErniePreTrainingHeads", + "ErnieSelfAttention", + "ErnieSelfOutput", + "EsmAttention", + "EsmClassificationHead", + "EsmContactPredictionHead", + "EsmEmbeddings", + "EsmEncoder", + "EsmFlashAttention2", + "EsmFoldAngleResnet", + "EsmFoldAngleResnetBlock", + "EsmFoldAttention", + "EsmFoldBackboneUpdate", + "EsmFoldDropout", + "EsmFoldingTrunk", + "EsmFoldInvariantPointAttention", + "EsmFoldLayerNorm", + "EsmFoldLinear", + "EsmFoldPairToSequence", + "EsmFoldRelativePosition", + "EsmFoldResidueMLP", + "EsmFoldSelfAttention", + "EsmFoldSequenceToPair", + "EsmFoldStructureModule", + "EsmFoldStructureModuleTransition", + "EsmFoldStructureModuleTransitionLayer", + "EsmFoldTriangleAttention", + "EsmFoldTriangleMultiplicativeUpdate", + "EsmFoldTriangularSelfAttentionBlock", + "EsmIntermediate", + "EsmLayer", + "EsmLMHead", + "EsmOutput", + "EsmPooler", + "EsmSelfAttention", + "EsmSelfOutput", + "EvollaAttention", + "EvollaDecoderLayer", + "EvollaFeedForward", + "EvollaMLP", + "EvollaProteinEncoder", + "EvollaRMSNorm", + "EvollaRotaryEmbedding", + "EvollaSaProtAttention", + "EvollaSaProtEmbeddings", + "EvollaSaProtEncoder", + "EvollaSaProtFlashAttention2", + "EvollaSaProtIntermediate", + "EvollaSaProtLayer", + "EvollaSaProtOutput", + "EvollaSaProtPooler", + "EvollaSaProtPreTrainedModel", + "EvollaSaProtProteinEncoder", + "EvollaSaProtRotaryEmbedding", + "EvollaSaProtSelfAttention", + "EvollaSaProtSelfOutput", + "EvollaSequenceAlignerCrossAttention", + "EvollaSequenceCompressorAttention", + "EvollaSequenceCompressorResampler", + "Exaone4Attention", + "Exaone4DecoderLayer", + "Exaone4MLP", + "Exaone4RMSNorm", + "Exaone4RotaryEmbedding", + "FalconAttention", + "FalconDecoderLayer", + "FalconFlashAttention2", + "FalconH1Attention", + "FalconH1DecoderLayer", + "FalconH1Mixer", + "FalconH1MLP", + "FalconH1RMSNorm", + "FalconH1RMSNormGated", + "FalconH1RotaryEmbedding", + "FalconLinear", + "FalconMambaBlock", + "FalconMambaMixer", + "FalconMambaRMSNorm", + "FalconMLP", + "FalconRotaryEmbedding", + "FastGELUActivation", + "FastSpeech2ConformerAttention", + "FastSpeech2ConformerBatchNormConvLayer", + "FastSpeech2ConformerConvolutionModule", + "FastSpeech2ConformerDurationPredictor", + "FastSpeech2ConformerEncoder", + "FastSpeech2ConformerEncoderLayer", + "FastSpeech2ConformerLoss", + "FastSpeech2ConformerMultiLayeredConv1d", + "FastSpeech2ConformerPredictorLayer", + "FastSpeech2ConformerRelPositionalEncoding", + "FastSpeech2ConformerSpeechDecoderPostnet", + "FastSpeech2ConformerVarianceEmbedding", + "FastSpeech2ConformerVariancePredictor", + "FeatureMixerBlock", + "FFN", + "FFNLayer", + "FFNOutput", + "FlaubertPoolerAnswerClass", + "FlaubertPoolerEndLogits", + "FlaubertPoolerStartLogits", + "FlaubertPredLayer", + "FlaubertSequenceSummary", + "FlaubertSQuADHead", + "FlavaAttention", + "FlavaEncoder", + "FlavaGlobalContrastiveHead", + "FlavaImageCodebookBlock", + "FlavaImageCodebookLayerGroup", + "FlavaImageCodebookResPath", + "FlavaImageEmbeddings", + "FlavaIntermediate", + "FlavaITMHead", + "FlavaLayer", + "FlavaMaskedPredictionHead", + "FlavaOutput", + "FlavaPooler", + "FlavaPredictionHeadTransform", + "FlavaSelfAttention", + "FlavaSelfOutput", + "FlavaTextEmbeddings", + "FNetBasicFourierTransform", + "FNetBasicOutput", + "FNetEmbeddings", + "FNetEncoder", + "FNetFourierTransform", + "FNetIntermediate", + "FNetLayer", + "FNetLMPredictionHead", + "FNetOnlyMLMHead", + "FNetOnlyNSPHead", + "FNetOutput", + "FNetPooler", + "FNetPredictionHeadTransform", + "FNetPreTrainingHeads", + "FocalNetDropPath", + "FocalNetEmbeddings", + "FocalNetEncoder", + "FocalNetLayer", + "FocalNetMlp", + "FocalNetModulation", + "FocalNetPatchEmbeddings", + "FocalNetStage", + "FSMTDecoder", + "FSMTEncoder", + "FullyShardedDataParallel", + "FunnelAttentionStructure", + "FunnelClassificationHead", + "FunnelDecoder", + "FunnelDiscriminatorPredictions", + "FunnelEmbeddings", + "FunnelEncoder", + "FunnelLayer", + "FunnelPositionwiseFFN", + "FunnelRelMultiheadAttention", + "FusedLayerNorm", + "GeLU", + "GELUActivation", + "Gemma2Attention", + "Gemma2DecoderLayer", + "Gemma2MLP", + "Gemma2RMSNorm", + "Gemma2RotaryEmbedding", + "Gemma3Attention", + "Gemma3DecoderLayer", + "Gemma3MLP", + "Gemma3MultiModalProjector", + "Gemma3nAudioAttention", + "Gemma3nAudioConformerAttention", + "Gemma3nAudioConformerBlock", + "Gemma3nAudioConformerFeedForward", + "Gemma3nAudioConformerLightConv1d", + "Gemma3nAudioCumulativeGroupNorm", + "Gemma3nAudioRelativePositionEmbedding", + "Gemma3nAudioSSCPConvBlock", + "Gemma3nAudioSubSampleConvProjection", + "Gemma3nMultimodalEmbedder", + "Gemma3nRMSNorm", + "Gemma3nTextAltUp", + "Gemma3nTextAttention", + "Gemma3nTextDecoderLayer", + "Gemma3nTextLaurelBlock", + "Gemma3nTextMLP", + "Gemma3nTextRotaryEmbedding", + "Gemma3nTextScaledWordEmbedding", + "Gemma3RMSNorm", + "Gemma3RotaryEmbedding", + "Gemma3TextScaledWordEmbedding", + "GemmaAttention", + "GemmaDecoderLayer", + "GemmaMLP", + "GemmaRMSNorm", + "GemmaRotaryEmbedding", + "GitAttention", + "GitEmbeddings", + "GitEncoder", + "GitIntermediate", + "GitLayer", + "GitOutput", + "GitProjection", + "GitSelfAttention", + "GitSelfOutput", + "GitVisionAttention", + "GitVisionEmbeddings", + "GitVisionEncoder", + "GitVisionEncoderLayer", + "GitVisionMLP", + "GitVisionTransformer", + "Glm4Attention", + "Glm4DecoderLayer", + "Glm4MLP", + "Glm4MoeAttention", + "Glm4MoeDecoderLayer", + "Glm4MoeMLP", + "Glm4MoeMoE", + "Glm4MoeRMSNorm", + "Glm4MoeRotaryEmbedding", + "Glm4MoeTopkRouter", + "Glm4RMSNorm", + "Glm4RotaryEmbedding", + "Glm4VisionMlp", + "Glm4vRMSNorm", + "Glm4vTextAttention", + "Glm4vTextDecoderLayer", + "Glm4vTextMLP", + "Glm4vTextRotaryEmbedding", + "Glm4vVisionAttention", + "Glm4vVisionBlock", + "Glm4vVisionEmbeddings", + "Glm4vVisionModel", + "Glm4vVisionPatchEmbed", + "Glm4vVisionPatchMerger", + "Glm4vVisionRotaryEmbedding", + "GlmAttention", + "GlmDecoderLayer", + "GlmMLP", + "GlmRMSNorm", + "GlmRotaryEmbedding", + "GLPNAttention", + "GLPNDecoder", + "GLPNDecoderStage", + "GLPNDepthEstimationHead", + "GLPNDropPath", + "GLPNDWConv", + "GLPNEfficientSelfAttention", + "GLPNEncoder", + "GLPNLayer", + "GLPNMixFFN", + "GLPNOverlapPatchEmbeddings", + "GLPNSelectiveFeatureFusion", + "GLPNSelfOutput", + "GotOcr2LayerNorm", + "GotOcr2MLPBlock", + "GotOcr2MultiModalProjector", + "GotOcr2PatchEmbeddings", + "GotOcr2VisionAttention", + "GotOcr2VisionEncoder", + "GotOcr2VisionLayer", + "GotOcr2VisionNeck", + "GPT2Attention", + "GPT2Block", + "GPT2MLP", + "GPT2SequenceSummary", + "GPTBigCodeAttention", + "GPTBigCodeBlock", + "GPTBigCodeMLP", + "GPTJAttention", + "GPTJBlock", + "GPTJFlashAttention2", + "GPTJMLP", + "GPTNeoAttention", + "GPTNeoBlock", + "GPTNeoFlashAttention2", + "GPTNeoMLP", + "GPTNeoSelfAttention", + "GPTNeoXAttention", + "GPTNeoXDecoderLayer", + "GPTNeoXJapaneseAttention", + "GPTNeoXJapaneseLayer", + "GPTNeoXJapaneseMLP", + "GPTNeoXJapaneseRotaryEmbedding", + "GPTNeoXLayer", + "GPTNeoXMLP", + "GPTNeoXRMSNorm", + "GPTNeoXRotaryEmbedding", + "GptOssAttention", + "GptOssDecoderLayer", + "GptOssExperts", + "GptOssMLP", + "GptOssRMSNorm", + "GptOssRotaryEmbedding", + "GptOssTopKRouter", + "GPTSanJapaneseAttention", + "GPTSanJapaneseBlock", + "GPTSanJapaneseDenseActDense", + "GPTSanJapaneseLayerDenseFF", + "GPTSanJapaneseLayerSelfAttention", + "GPTSanJapaneseLayerSparseFF", + "GPTSanJapaneseSparseMLP", + "GPTSanJapaneseTop1Router", + "GradientCheckpointingLayer", + "GraniteAttention", + "GraniteDecoderLayer", + "GraniteMLP", + "GraniteMoeAttention", + "GraniteMoeDecoderLayer", + "GraniteMoeHybridAttention", + "GraniteMoeHybridDecoderLayer", + "GraniteMoeHybridMambaLayer", + "GraniteMoeHybridMLP", + "GraniteMoeHybridMoE", + "GraniteMoeHybridParallelExperts", + "GraniteMoeHybridRMSNorm", + "GraniteMoeHybridRMSNormGated", + "GraniteMoeHybridRotaryEmbedding", + "GraniteMoeHybridTopKGating", + "GraniteMoeMoE", + "GraniteMoeParallelExperts", + "GraniteMoeRMSNorm", + "GraniteMoeRotaryEmbedding", + "GraniteMoeSharedAttention", + "GraniteMoeSharedDecoderLayer", + "GraniteMoeSharedMLP", + "GraniteMoeSharedMoE", + "GraniteMoeSharedParallelExperts", + "GraniteMoeSharedRMSNorm", + "GraniteMoeSharedRotaryEmbedding", + "GraniteMoeSharedTopKGating", + "GraniteMoeTopKGating", + "GraniteRMSNorm", + "GraniteRotaryEmbedding", + "GraniteSpeechConformerAttention", + "GraniteSpeechConformerBlock", + "GraniteSpeechConformerConvModule", + "GraniteSpeechConformerDepthWiseConv1d", + "GraniteSpeechConformerFeedForward", + "GraniteSpeechEncoderProjector", + "GraphModule", + "GraphormerDecoderHead", + "GraphormerGraphAttnBias", + "GraphormerGraphEncoder", + "GraphormerGraphEncoderLayer", + "GraphormerGraphNodeFeature", + "GraphormerMultiheadAttention", + "GroundingDinoBiMultiHeadAttention", + "GroundingDinoContrastiveEmbedding", + "GroundingDinoConvEncoder", + "GroundingDinoConvModel", + "GroundingDinoDecoder", + "GroundingDinoDecoderLayer", + "GroundingDinoDeformableLayer", + "GroundingDinoDropPath", + "GroundingDinoEncoder", + "GroundingDinoEncoderLayer", + "GroundingDinoFrozenBatchNorm2d", + "GroundingDinoFusionLayer", + "GroundingDinoHungarianMatcher", + "GroundingDinoImageLoss", + "GroundingDinoLearnedPositionEmbedding", + "GroundingDinoMLPPredictionHead", + "GroundingDinoMultiheadAttention", + "GroundingDinoMultiscaleDeformableAttention", + "GroundingDinoSinePositionEmbedding", + "GroundingDinoTextEnhancerLayer", + "GroupedLinearLayer", + "GroupViTAssignAttention", + "GroupViTAttention", + "GroupViTCrossAttentionLayer", + "GroupViTEncoderLayer", + "GroupViTMixerMLP", + "GroupViTMLP", + "GroupViTPatchEmbeddings", + "GroupViTStage", + "GroupViTTextEmbeddings", + "GroupViTTextEncoder", + "GroupViTTextTransformer", + "GroupViTTokenAssign", + "GroupViTVisionEmbeddings", + "GroupViTVisionEncoder", + "GroupViTVisionTransformer", + "HeliumAttention", + "HeliumDecoderLayer", + "HeliumMLP", + "HeliumRMSNorm", + "HeliumRotaryEmbedding", + "HGNetV2BasicLayer", + "HGNetV2ConvLayer", + "HGNetV2ConvLayerLight", + "HGNetV2Embeddings", + "HGNetV2Encoder", + "HGNetV2LearnableAffineBlock", + "HGNetV2Stage", + "HieraDecoder", + "HieraDropPath", + "HieraEmbeddings", + "HieraEncoder", + "HieraLayer", + "HieraMaskUnitAttention", + "HieraMlp", + "HieraMultiScaleHead", + "HieraPatchEmbeddings", + "HieraPooler", + "HieraStage", + "HifiGanResidualBlock", + "HubertAttention", + "HubertAttnAdapterLayer", + "HubertEncoder", + "HubertEncoderLayer", + "HubertEncoderLayerStableLayerNorm", + "HubertEncoderStableLayerNorm", + "HubertFeatureEncoder", + "HubertFeatureProjection", + "HubertFeedForward", + "HubertGroupNormConvLayer", + "HubertLayerNormConvLayer", + "HubertNoLayerNormConvLayer", + "HubertPositionalConvEmbedding", + "HubertSamePadLayer", + "HungarianMatcher", + "IBertAttention", + "IBertClassificationHead", + "IBertEmbeddings", + "IBertEncoder", + "IBertIntermediate", + "IBertLayer", + "IBertLMHead", + "IBertOutput", + "IBertPooler", + "IBertSelfAttention", + "IBertSelfOutput", + "Idefics2Connector", + "Idefics2Encoder", + "Idefics2EncoderLayer", + "Idefics2MLP", + "Idefics2MultiheadAttentionPoolingHead", + "Idefics2PerceiverAttention", + "Idefics2PerceiverLayer", + "Idefics2PerceiverResampler", + "Idefics2RMSNorm", + "Idefics2VisionAttention", + "Idefics2VisionEmbeddings", + "Idefics2VisionMLP", + "Idefics2VisionTransformer", + "Idefics3Connector", + "Idefics3Encoder", + "Idefics3EncoderLayer", + "Idefics3RMSNorm", + "Idefics3SimpleMLP", + "Idefics3VisionAttention", + "Idefics3VisionEmbeddings", + "Idefics3VisionMLP", + "IdeficsAttention", + "IdeficsDecoderLayer", + "IdeficsDecoupledEmbedding", + "IdeficsDecoupledLinear", + "IdeficsEmbedding", + "IdeficsGatedCrossAttentionLayer", + "IdeficsMLP", + "IdeficsPerceiverAttention", + "IdeficsPerceiverResampler", + "IdeficsRMSNorm", + "IdeficsVisionAttention", + "IdeficsVisionEmbeddings", + "IdeficsVisionEncoder", + "IdeficsVisionEncoderLayer", + "IdeficsVisionMLP", + "IdeficsVisionTransformer", + "IJepaAttention", + "IJepaEmbeddings", + "IJepaEncoder", + "IJepaIntermediate", + "IJepaLayer", + "IJepaOutput", + "IJepaPatchEmbeddings", + "IJepaPooler", + "IJepaSelfAttention", + "IJepaSelfOutput", + "ImageGPTAttention", + "ImageGPTBlock", + "ImageGPTLayerNorm", + "ImageGPTMLP", + "ImageLoss", + "InformerAttention", + "InformerConvLayer", + "InformerDecoder", + "InformerDecoderLayer", + "InformerEncoder", + "InformerEncoderLayer", + "InformerFeatureEmbedder", + "InformerMeanScaler", + "InformerNOPScaler", + "InformerProbSparseAttention", + "InformerSinusoidalPositionalEmbedding", + "InformerStdScaler", + "InformerValueEmbedding", + "InjectScalerStatistics4D", + "InstructBlipAttention", + "InstructBlipEncoder", + "InstructBlipEncoderLayer", + "InstructBlipMLP", + "InstructBlipQFormerAttention", + "InstructBlipQFormerEmbeddings", + "InstructBlipQFormerEncoder", + "InstructBlipQFormerIntermediate", + "InstructBlipQFormerLayer", + "InstructBlipQFormerMultiHeadAttention", + "InstructBlipQFormerOutput", + "InstructBlipQFormerSelfOutput", + "InstructBlipVideoAttention", + "InstructBlipVideoEncoder", + "InstructBlipVideoEncoderLayer", + "InstructBlipVideoMLP", + "InstructBlipVideoQFormerAttention", + "InstructBlipVideoQFormerEmbeddings", + "InstructBlipVideoQFormerEncoder", + "InstructBlipVideoQFormerIntermediate", + "InstructBlipVideoQFormerLayer", + "InstructBlipVideoQFormerMultiHeadAttention", + "InstructBlipVideoQFormerOutput", + "InstructBlipVideoQFormerSelfOutput", + "InstructBlipVideoVisionEmbeddings", + "InstructBlipVisionEmbeddings", + "InternVLMultiModalProjector", + "InternVLVisionAttention", + "InternVLVisionEmbeddings", + "InternVLVisionEncoder", + "InternVLVisionLayer", + "InternVLVisionMLP", + "InternVLVisionPatchEmbeddings", + "InternVLVisionRMSNorm", + "InterpolateInitialPositionEmbeddings", + "InterpolateMidPositionEmbeddings", + "IntGELU", + "IntLayerNorm", + "IntSoftmax", + "JambaAttention", + "JambaAttentionDecoderLayer", + "JambaFlashAttention2", + "JambaMambaDecoderLayer", + "JambaMambaMixer", + "JambaMLP", + "JambaRMSNorm", + "JambaSdpaAttention", + "JambaSparseMoeBlock", + "JanusVisionAlignerMLP", + "JanusVisionAttention", + "JanusVisionEmbeddings", + "JanusVisionEncoder", + "JanusVisionEncoderLayer", + "JanusVisionMLP", + "JanusVQVAEAlignerMLP", + "JanusVQVAEAttnBlock", + "JanusVQVAEConvDownsample", + "JanusVQVAEConvUpsample", + "JanusVQVAEDecoder", + "JanusVQVAEEncoder", + "JanusVQVAEHead", + "JanusVQVAEMidBlock", + "JanusVQVAEResnetBlock", + "JanusVQVAEVectorQuantizer", + "JetMoeAttention", + "JetMoeBlock", + "JetMoeFlashAttention2", + "JetMoeMoA", + "JetMoeMoE", + "JetMoeParallelExperts", + "JetMoeRMSNorm", + "JetMoeRotaryEmbedding", + "JetMoeSdpaAttention", + "JetMoeTopKGating", + "JukeboxAttention", + "JukeboxBlock", + "JukeboxBottleneck", + "JukeboxBottleneckBlock", + "JukeboxConditionalAutoregressive", + "JukeboxConv1D", + "JukeboxDecoder", + "JukeboxDecoderConvBock", + "JukeboxEncoder", + "JukeboxEncoderConvBlock", + "JukeboxLabelConditioner", + "JukeboxLayerNorm", + "JukeboxLayerStack", + "JukeboxMLP", + "JukeboxMusicTokenConditioner", + "JukeboxPositionalEmbedding", + "JukeboxRangeEmbedding", + "JukeboxResConv1DBlock", + "JukeboxResnet1D", + "KLDivLoss", + "Kosmos2ImageToTextProjection", + "Kosmos2TextBlock", + "Kosmos2TextFFN", + "Kosmos2TextForCausalLM", + "Kosmos2TextModel", + "Kosmos2TextSinusoidalPositionalEmbedding", + "Kosmos2TextTransformer", + "Kosmos2VisionAttention", + "Kosmos2VisionEmbeddings", + "Kosmos2VisionEncoder", + "Kosmos2VisionEncoderLayer", + "Kosmos2VisionMLP", + "Kosmos2VisionModel", + "Kosmos2VisionTransformer", + "KosmosTextAttention", + "KyutaiSpeechToTextAttention", + "KyutaiSpeechToTextDecoderLayer", + "KyutaiSpeechToTextEmbeddings", + "KyutaiSpeechToTextFlashAttention2", + "KyutaiSpeechToTextFlexibleLinear", + "KyutaiSpeechToTextGatingMLP", + "KyutaiSpeechToTextLinear", + "KyutaiSpeechToTextRMSNorm", + "KyutaiSpeechToTextRotaryEmbedding", + "KyutaiSpeechToTextSdpaAttention", + "L1Loss", + "LambdaLayer", + "LaplaceActivation", + "LayerDropModuleList", + "LayerNorm", + "LayoutLMAttention", + "LayoutLMEmbeddings", + "LayoutLMEncoder", + "LayoutLMIntermediate", + "LayoutLMLayer", + "LayoutLMLayerNorm", + "LayoutLMLMPredictionHead", + "LayoutLMOnlyMLMHead", + "LayoutLMOutput", + "LayoutLMPooler", + "LayoutLMPredictionHeadTransform", + "LayoutLMSelfAttention", + "LayoutLMSelfOutput", + "LayoutLMv2Attention", + "LayoutLMv2Embeddings", + "LayoutLMv2Encoder", + "LayoutLMv2Intermediate", + "LayoutLMv2Layer", + "LayoutLMv2Output", + "LayoutLMv2Pooler", + "LayoutLMv2SelfAttention", + "LayoutLMv2SelfOutput", + "LayoutLMv2VisualBackbone", + "LayoutLMv3Attention", + "LayoutLMv3ClassificationHead", + "LayoutLMv3Encoder", + "LayoutLMv3Intermediate", + "LayoutLMv3Layer", + "LayoutLMv3Output", + "LayoutLMv3PatchEmbeddings", + "LayoutLMv3SelfAttention", + "LayoutLMv3SelfOutput", + "LayoutLMv3TextEmbeddings", + "LEDClassificationHead", + "LEDDecoder", + "LEDDecoderAttention", + "LEDDecoderLayer", + "LEDEncoder", + "LEDEncoderAttention", + "LEDEncoderLayer", + "LEDEncoderSelfAttention", + "LEDLearnedPositionalEmbedding", + "LegacyDebertaLMPredictionHead", + "LegacyDebertaOnlyMLMHead", + "LegacyDebertaPredictionHeadTransform", + "LegacyDebertaV2LMPredictionHead", + "LegacyDebertaV2OnlyMLMHead", + "LegacyDebertaV2PredictionHeadTransform", + "LevitAttention", + "LevitAttentionSubsample", + "LevitClassificationLayer", + "LevitConvEmbeddings", + "LevitEncoder", + "LevitMLPLayer", + "LevitPatchEmbeddings", + "LevitResidualLayer", + "LevitStage", + "LevitSubsample", + "Lfm2Attention", + "Lfm2DecoderLayer", + "Lfm2MLP", + "Lfm2RMSNorm", + "Lfm2RotaryEmbedding", + "Lfm2ShortConv", + "LightGlueAttention", + "LightGlueMatchAssignmentLayer", + "LightGlueMLP", + "LightGluePositionalEncoder", + "LightGlueTokenConfidenceLayer", + "LightGlueTransformerLayer", + "LiltAttention", + "LiltClassificationHead", + "LiltEncoder", + "LiltIntermediate", + "LiltLayer", + "LiltLayoutEmbeddings", + "LiltOutput", + "LiltPooler", + "LiltSelfAttention", + "LiltSelfOutput", + "LiltTextEmbeddings", + "LinearActivation", + "Llama4MultiModalProjector", + "Llama4Router", + "Llama4TextAttention", + "Llama4TextDecoderLayer", + "Llama4TextExperts", + "Llama4TextL2Norm", + "Llama4TextMLP", + "Llama4TextMoe", + "Llama4TextRMSNorm", + "Llama4TextRotaryEmbedding", + "Llama4UnfoldConvolution", + "Llama4VisionAttention", + "Llama4VisionEncoder", + "Llama4VisionEncoderLayer", + "Llama4VisionMLP", + "Llama4VisionMLP2", + "Llama4VisionPixelShuffleMLP", + "Llama4VisionRotaryEmbedding", + "LlamaAttention", + "LlamaDecoderLayer", + "LlamaMLP", + "LlamaRMSNorm", + "LlamaRotaryEmbedding", + "LlavaMultiModalProjector", + "LlavaNextMultiModalProjector", + "LlavaNextVideoMultiModalProjector", + "LlavaNextVideoPooler", + "LlavaOnevisionMultiModalProjector", + "LlavaOnevisionPooler", + "LocalSelfAttention", + "LogBinomialSoftmax", + "LogSoftmax", + "LongformerAttention", + "LongformerClassificationHead", + "LongformerEmbeddings", + "LongformerEncoder", + "LongformerIntermediate", + "LongformerLayer", + "LongformerLMHead", + "LongformerOutput", + "LongformerPooler", + "LongformerSelfAttention", + "LongformerSelfOutput", + "LongT5Attention", + "LongT5Block", + "LongT5DenseActDense", + "LongT5DenseGatedActDense", + "LongT5LayerCrossAttention", + "LongT5LayerFF", + "LongT5LayerLocalSelfAttention", + "LongT5LayerNorm", + "LongT5LayerSelfAttention", + "LongT5LayerTransientGlobalSelfAttention", + "LongT5LocalAttention", + "LongT5Stack", + "LongT5TransientGlobalAttention", + "LSHSelfAttention", + "LukeAttention", + "LukeEmbeddings", + "LukeEncoder", + "LukeEntityEmbeddings", + "LukeIntermediate", + "LukeLayer", + "LukeLMHead", + "LukeOutput", + "LukePooler", + "LukeSelfAttention", + "LukeSelfOutput", + "LxmertAttention", + "LxmertAttentionOutput", + "LxmertCrossAttentionLayer", + "LxmertEmbeddings", + "LxmertIntermediate", + "LxmertLayer", + "LxmertLMPredictionHead", + "LxmertOutput", + "LxmertPooler", + "LxmertPredictionHeadTransform", + "LxmertPreTrainingHeads", + "LxmertSelfAttentionLayer", + "LxmertVisualAnswerHead", + "LxmertVisualObjHead", + "LxmertXLayer", + "M2M100Attention", + "M2M100Decoder", + "M2M100DecoderLayer", + "M2M100Encoder", + "M2M100EncoderLayer", + "M2M100ScaledWordEmbedding", + "M2M100SinusoidalPositionalEmbedding", + "Mamba2Block", + "Mamba2Mixer", + "Mamba2RMSNorm", + "MambaBlock", + "MambaMixer", + "MambaRMSNorm", + "MambaRMSNormGated", + "MarianAttention", + "MarianDecoder", + "MarianDecoderLayer", + "MarianDecoderWrapper", + "MarianEncoder", + "MarianEncoderLayer", + "MarianSinusoidalPositionalEmbedding", + "MarkupLMAttention", + "MarkupLMEmbeddings", + "MarkupLMEncoder", + "MarkupLMIntermediate", + "MarkupLMLayer", + "MarkupLMLMPredictionHead", + "MarkupLMOnlyMLMHead", + "MarkupLMOutput", + "MarkupLMPooler", + "MarkupLMPredictionHeadTransform", + "MarkupLMSelfAttention", + "MarkupLMSelfOutput", + "Mask2FormerAttention", + "Mask2FormerHungarianMatcher", + "Mask2FormerLoss", + "Mask2FormerMaskedAttentionDecoder", + "Mask2FormerMaskedAttentionDecoderLayer", + "Mask2FormerMaskPredictor", + "Mask2FormerMLPPredictionHead", + "Mask2FormerPixelDecoder", + "Mask2FormerPixelDecoderEncoderLayer", + "Mask2FormerPixelDecoderEncoderMultiscaleDeformableAttention", + "Mask2FormerPixelDecoderEncoderOnly", + "Mask2FormerPixelLevelModule", + "Mask2FormerPredictionBlock", + "Mask2FormerSinePositionEmbedding", + "Mask2FormerTransformerModule", + "MaskFormerFPNConvLayer", + "MaskFormerFPNLayer", + "MaskFormerFPNModel", + "MaskFormerHungarianMatcher", + "MaskFormerLoss", + "MaskformerMLPPredictionHead", + "MaskFormerPixelDecoder", + "MaskFormerPixelLevelModule", + "MaskFormerSinePositionEmbedding", + "MaskFormerSwinAttention", + "MaskFormerSwinDropPath", + "MaskFormerSwinEmbeddings", + "MaskFormerSwinEncoder", + "MaskFormerSwinIntermediate", + "MaskFormerSwinLayer", + "MaskFormerSwinOutput", + "MaskFormerSwinPatchEmbeddings", + "MaskFormerSwinPatchMerging", + "MaskFormerSwinSelfAttention", + "MaskFormerSwinSelfOutput", + "MaskFormerSwinStage", + "MaskFormerTransformerModule", + "MatMulWrapper", + "MBartAttention", + "MBartClassificationHead", + "MBartDecoder", + "MBartDecoderLayer", + "MBartDecoderWrapper", + "MBartEncoder", + "MBartEncoderLayer", + "MBartLearnedPositionalEmbedding", + "MBartScaledWordEmbedding", + "MCTCTAttention", + "MCTCTConv1dSubsampler", + "MCTCTEmbeddings", + "MCTCTEncoder", + "MCTCTIntermediate", + "MCTCTLayer", + "MCTCTLayerNorm", + "MCTCTOutput", + "MCTCTSelfAttention", + "MCTCTSelfOutput", + "MegaBlock", + "MegaClassificationHead", + "MegaDropout", + "MegaEmbeddings", + "MegaGatedCrossAttention", + "MegaMovingAverageGatedAttention", + "MegaMultiDimensionDampedEma", + "MegaNormalizedFeedForwardNetwork", + "MegaPooler", + "MegaRMSNorm", + "MegaRotaryRelativePositionalBias", + "MegaScaleNorm", + "MegaSequenceNorm", + "MegaSimpleRelativePositionalBias", + "MegatronBertAttention", + "MegatronBertEmbeddings", + "MegatronBertEncoder", + "MegatronBertIntermediate", + "MegatronBertLayer", + "MegatronBertLMPredictionHead", + "MegatronBertOnlyMLMHead", + "MegatronBertOnlyNSPHead", + "MegatronBertOutput", + "MegatronBertPooler", + "MegatronBertPredictionHeadTransform", + "MegatronBertPreTrainingHeads", + "MegatronBertSelfAttention", + "MegatronBertSelfOutput", + "MgpstrA3Module", + "MgpstrAttention", + "MgpstrDropPath", + "MgpstrEmbeddings", + "MgpstrEncoder", + "MgpstrLayer", + "MgpstrMlp", + "MimiAttention", + "MimiConv1d", + "MimiConvTranspose1d", + "MimiDecoder", + "MimiEncoder", + "MimiEuclideanCodebook", + "MimiFlashAttention2", + "MimiLayerScale", + "MimiMLP", + "MimiResidualVectorQuantizer", + "MimiResnetBlock", + "MimiRotaryEmbedding", + "MimiSdpaAttention", + "MimiSplitResidualVectorQuantizer", + "MimiTransformerLayer", + "MimiTransformerModel", + "MimiVectorQuantization", + "MiniMaxAttention", + "MiniMaxBlockSparseTop2MLP", + "MiniMaxDecoderLayer", + "MiniMaxLightningAttention", + "MiniMaxRMSNorm", + "MiniMaxRotaryEmbedding", + "MiniMaxSparseMoeBlock", + "MishActivation", + "Mistral3MultiModalProjector", + "Mistral3PatchMerger", + "Mistral3RMSNorm", + "MistralAttention", + "MistralDecoderLayer", + "MistralMLP", + "MistralRMSNorm", + "MistralRotaryEmbedding", + "MixtralAttention", + "MixtralBlockSparseTop2MLP", + "MixtralDecoderLayer", + "MixtralRMSNorm", + "MixtralRotaryEmbedding", + "MixtralSparseMoeBlock", + "MLCDAttention", + "MLCDEncoder", + "MLCDEncoderLayer", + "MLCDMLP", + "MLCDRotaryEmbedding", + "MLCDVisionEmbeddings", + "MLCDVisionTransformer", + "MllamaCrossAttentionDecoderLayer", + "MllamaPrecomputedAspectRatioEmbedding", + "MllamaPrecomputedPositionEmbedding", + "MllamaRotaryEmbedding", + "MllamaSelfAttentionDecoderLayer", + "MllamaTextCrossAttention", + "MllamaTextMLP", + "MllamaTextRMSNorm", + "MllamaTextSelfAttention", + "MllamaVisionAttention", + "MllamaVisionEncoder", + "MllamaVisionEncoderLayer", + "MllamaVisionMLP", + "MLP", + "MLPLayerWithBN", + "MMGroundingDinoBiMultiHeadAttention", + "MMGroundingDinoContrastiveEmbedding", + "MMGroundingDinoConvEncoder", + "MMGroundingDinoConvModel", + "MMGroundingDinoDecoder", + "MMGroundingDinoDecoderLayer", + "MMGroundingDinoDeformableLayer", + "MMGroundingDinoDropPath", + "MMGroundingDinoEncoder", + "MMGroundingDinoEncoderLayer", + "MMGroundingDinoFrozenBatchNorm2d", + "MMGroundingDinoFusionLayer", + "MMGroundingDinoLearnedPositionEmbedding", + "MMGroundingDinoMLPPredictionHead", + "MMGroundingDinoMultiheadAttention", + "MMGroundingDinoMultiscaleDeformableAttention", + "MMGroundingDinoSinePositionEmbedding", + "MMGroundingDinoTextEnhancerLayer", + "MobileBertAttention", + "MobileBertEmbeddings", + "MobileBertEncoder", + "MobileBertIntermediate", + "MobileBertLayer", + "MobileBertLMPredictionHead", + "MobileBertOnlyMLMHead", + "MobileBertOnlyNSPHead", + "MobileBertOutput", + "MobileBertPooler", + "MobileBertPredictionHeadTransform", + "MobileBertPreTrainingHeads", + "MobileBertSelfAttention", + "MobileBertSelfOutput", + "MobileNetV1ConvLayer", + "MobileNetV2ConvLayer", + "MobileNetV2DeepLabV3Plus", + "MobileNetV2InvertedResidual", + "MobileNetV2Stem", + "MobileViTASPP", + "MobileViTASPPPooling", + "MobileViTAttention", + "MobileViTConvLayer", + "MobileViTDeepLabV3", + "MobileViTEncoder", + "MobileViTIntermediate", + "MobileViTInvertedResidual", + "MobileViTLayer", + "MobileViTMobileNetLayer", + "MobileViTOutput", + "MobileViTSelfAttention", + "MobileViTSelfOutput", + "MobileViTTransformer", + "MobileViTTransformerLayer", + "MobileViTV2ASPP", + "MobileViTV2ASPPPooling", + "MobileViTV2ConvLayer", + "MobileViTV2DeepLabV3", + "MobileViTV2Encoder", + "MobileViTV2FFN", + "MobileViTV2InvertedResidual", + "MobileViTV2Layer", + "MobileViTV2LinearSelfAttention", + "MobileViTV2MobileNetLayer", + "MobileViTV2Transformer", + "MobileViTV2TransformerLayer", + "ModalEmbeddings", + "ModernBertAttention", + "ModernBertDecoderAttention", + "ModernBertDecoderLayer", + "ModernBertEmbeddings", + "ModernBertEncoderLayer", + "ModernBertMLP", + "ModernBertPredictionHead", + "ModernBertRotaryEmbedding", + "ModuleList", + "MoonshineAttention", + "MoonshineDecoder", + "MoonshineDecoderLayer", + "MoonshineDecoderMLP", + "MoonshineEncoder", + "MoonshineEncoderLayer", + "MoonshineEncoderMLP", + "MoonshineRotaryEmbedding", + "MoshiAttention", + "MoshiDecoderLayer", + "MoshiDepthDecoder", + "MoshiFlashAttention2", + "MoshiFlexibleLinear", + "MoshiGatingMLP", + "MoshiLinear", + "MoshiRMSNorm", + "MoshiRotaryEmbedding", + "MoshiSdpaAttention", + "MPNetAttention", + "MPNetClassificationHead", + "MPNetEmbeddings", + "MPNetEncoder", + "MPNetIntermediate", + "MPNetLayer", + "MPNetLMHead", + "MPNetOutput", + "MPNetPooler", + "MPNetSelfAttention", + "MptAttention", + "MptBlock", + "MptMLP", + "MraAttention", + "MraClassificationHead", + "MraEmbeddings", + "MraEncoder", + "MraIntermediate", + "MraLayer", + "MraLMPredictionHead", + "MraOnlyMLMHead", + "MraOutput", + "MraPredictionHeadTransform", + "MraSelfAttention", + "MraSelfOutput", + "MSELoss", + "MT5Attention", + "MT5Block", + "MT5ClassificationHead", + "MT5DenseActDense", + "MT5DenseGatedActDense", + "MT5LayerCrossAttention", + "MT5LayerFF", + "MT5LayerNorm", + "MT5LayerSelfAttention", + "MT5Stack", + "MultiHeadAttention", + "MultiHeadSelfAttention", + "MultiScaleDeformableAttention", + "MusicgenAttention", + "MusicgenDecoder", + "MusicgenDecoderLayer", + "MusicgenMelodyAttention", + "MusicgenMelodyDecoder", + "MusicgenMelodyDecoderLayer", + "MusicgenMelodySinusoidalPositionalEmbedding", + "MusicgenSinusoidalPositionalEmbedding", + "MvpAttention", + "MvpClassificationHead", + "MvpDecoder", + "MvpDecoderLayer", + "MvpDecoderWrapper", + "MvpEncoder", + "MvpEncoderLayer", + "MvpLearnedPositionalEmbedding", + "MvpPrompt", + "NatDownsampler", + "NatDropPath", + "NatEmbeddings", + "NatEncoder", + "NatIntermediate", + "NatLayer", + "NatOutput", + "NatPatchEmbeddings", + "NatStage", + "NearestConvUpsampler", + "NeighborhoodAttention", + "NeighborhoodAttentionModule", + "NeighborhoodAttentionOutput", + "NemotronAttention", + "NemotronDecoderLayer", + "NemotronFlashAttention2", + "NemotronLayerNorm1P", + "NemotronMLP", + "NemotronRotaryEmbedding", + "NemotronSdpaAttention", + "NewGELUActivation", + "NezhaAttention", + "NezhaEmbeddings", + "NezhaEncoder", + "NezhaIntermediate", + "NezhaLayer", + "NezhaLMPredictionHead", + "NezhaOnlyMLMHead", + "NezhaOnlyNSPHead", + "NezhaOutput", + "NezhaPooler", + "NezhaPredictionHeadTransform", + "NezhaPreTrainingHeads", + "NezhaRelativePositionsEncoding", + "NezhaSelfAttention", + "NezhaSelfOutput", + "NllbMoeAttention", + "NllbMoeDecoder", + "NllbMoeDecoderLayer", + "NllbMoeDenseActDense", + "NllbMoeEncoder", + "NllbMoeEncoderLayer", + "NllbMoeScaledWordEmbedding", + "NllbMoeSinusoidalPositionalEmbedding", + "NllbMoeSparseMLP", + "NllbMoeTop2Router", + "NoNorm", + "NystromformerAttention", + "NystromformerClassificationHead", + "NystromformerEmbeddings", + "NystromformerEncoder", + "NystromformerIntermediate", + "NystromformerLayer", + "NystromformerLMPredictionHead", + "NystromformerOnlyMLMHead", + "NystromformerOutput", + "NystromformerPredictionHeadTransform", + "NystromformerSelfAttention", + "NystromformerSelfOutput", + "Olmo2Attention", + "Olmo2DecoderLayer", + "Olmo2MLP", + "Olmo2RMSNorm", + "Olmo2RotaryEmbedding", + "OlmoAttention", + "OlmoDecoderLayer", + "OlmoeAttention", + "OlmoeDecoderLayer", + "OlmoeFlashAttention2", + "OlmoeMLP", + "OlmoeRMSNorm", + "OlmoeRotaryEmbedding", + "OlmoeSdpaAttention", + "OlmoeSparseMoeBlock", + "OlmoLayerNorm", + "OlmoMLP", + "OlmoRotaryEmbedding", + "OmDetTurboConvNormLayer", + "OmDetTurboCSPRepLayer", + "OmDetTurboDecoder", + "OmDetTurboDeformableTransformerDecoderLayer", + "OmDetTurboEncoder", + "OmDetTurboEncoderLayer", + "OmDetTurboHybridEncoder", + "OmDetTurboLanguageBackbone", + "OmDetTurboMLP", + "OmDetTurboMLPWithDropout", + "OmDetTurboMultiheadAttention", + "OmDetTurboMultiscaleDeformableAttention", + "OmDetTurboRepVggBlock", + "OmDetTurboResidualLayer", + "OmDetTurboTaskEncoder", + "OmDetTurboVisionBackbone", + "OneFormerAttention", + "OneFormerHungarianMatcher", + "OneFormerLoss", + "OneFormerMLPPredictionHead", + "OneFormerPixelDecoder", + "OneFormerPixelDecoderEncoderLayer", + "OneFormerPixelDecoderEncoderMultiscaleDeformableAttention", + "OneFormerPixelDecoderEncoderOnly", + "OneFormerPixelDecoderFrozenBatchNorm2d", + "OneFormerPixelLevelModule", + "OneFormerSinePositionEmbedding", + "OneFormerTaskModel", + "OneFormerTextContextDecoder", + "OneFormerTextEncoder", + "OneFormerTextMapper", + "OneFormerTextMapperAttention", + "OneFormerTextMLP", + "OneFormerTextTransformer", + "OneFormerTextTransformerDecoderLayer", + "OneFormerTextTransformerLayer", + "OneFormerTransformerDecoder", + "OneFormerTransformerDecoderCrossAttentionLayer", + "OneFormerTransformerDecoderFFNLayer", + "OneFormerTransformerDecoderLayer", + "OneFormerTransformerDecoderQueryTransformer", + "OneFormerTransformerDecoderQueryTransformerDecoder", + "OneFormerTransformerDecoderQueryTransformerDecoderLayer", + "OneFormerTransformerDecoderSelfAttentionLayer", + "OneFormerTransformerModule", + "OpenAIGPTSequenceSummary", + "OpenLlamaAttention", + "OpenLlamaDecoderLayer", + "OpenLlamaDynamicNTKScalingRotaryEmbedding", + "OpenLlamaLinearScalingRotaryEmbedding", + "OpenLlamaMLP", + "OpenLlamaRMSNorm", + "OpenLlamaRotaryEmbedding", + "OPTAttention", + "OPTDecoder", + "OPTDecoderLayer", + "OPTLearnedPositionalEmbedding", + "OutputBottleneck", + "Owlv2Attention", + "Owlv2BoxPredictionHead", + "Owlv2ClassPredictionHead", + "Owlv2Encoder", + "Owlv2EncoderLayer", + "Owlv2MLP", + "Owlv2TextEmbeddings", + "Owlv2TextTransformer", + "Owlv2VisionEmbeddings", + "Owlv2VisionTransformer", + "OwlViTAttention", + "OwlViTBoxPredictionHead", + "OwlViTClassPredictionHead", + "OwlViTEncoder", + "OwlViTEncoderLayer", + "OwlViTMLP", + "OwlViTTextEmbeddings", + "OwlViTTextTransformer", + "OwlViTVisionEmbeddings", + "OwlViTVisionTransformer", + "PaliGemmaMultiModalProjector", + "ParameterProjection", + "PatchEmbed", + "PatchEmbeddings", + "PatchMerger", + "PatchMixerBlock", + "PatchTSMixerAttention", + "PatchTSMixerBatchNorm", + "PatchTSMixerBlock", + "PatchTSMixerChannelFeatureMixerBlock", + "PatchTSMixerEncoder", + "PatchTSMixerForPredictionHead", + "PatchTSMixerGatedAttention", + "PatchTSMixerLayer", + "PatchTSMixerLinearHead", + "PatchTSMixerMasking", + "PatchTSMixerMeanScaler", + "PatchTSMixerMLP", + "PatchTSMixerNOPScaler", + "PatchTSMixerNormLayer", + "PatchTSMixerPatchify", + "PatchTSMixerPositionalEncoding", + "PatchTSMixerPretrainHead", + "PatchTSMixerStdScaler", + "PatchTSTAttention", + "PatchTSTBatchNorm", + "PatchTSTClassificationHead", + "PatchTSTEmbedding", + "PatchTSTEncoder", + "PatchTSTEncoderLayer", + "PatchTSTMasking", + "PatchTSTMaskPretrainHead", + "PatchTSTMeanScaler", + "PatchTSTNOPScaler", + "PatchTSTPatchify", + "PatchTSTPositionalEncoding", + "PatchTSTPredictionHead", + "PatchTSTRegressionHead", + "PatchTSTScaler", + "PatchTSTStdScaler", + "PeftModel", + "PegasusAttention", + "PegasusDecoder", + "PegasusDecoderLayer", + "PegasusDecoderWrapper", + "PegasusEncoder", + "PegasusEncoderLayer", + "PegasusSinusoidalPositionalEmbedding", + "PegasusXAttention", + "PegasusXDecoder", + "PegasusXDecoderLayer", + "PegasusXDecoderWrapper", + "PegasusXEncoder", + "PegasusXEncoderLayer", + "PegasusXGlobalLocalAttention", + "PegasusXScaledWordEmbedding", + "PegasusXSinusoidalPositionalEmbedding", + "PerceiverAbstractDecoder", + "PerceiverAbstractPositionEncoding", + "PerceiverAttention", + "PerceiverAudioPostprocessor", + "PerceiverAudioPreprocessor", + "PerceiverBasicDecoder", + "PerceiverBasicVideoAutoencodingDecoder", + "PerceiverClassificationDecoder", + "PerceiverClassificationPostprocessor", + "PerceiverEmbeddingDecoder", + "PerceiverEmbeddings", + "PerceiverEncoder", + "PerceiverFourierPositionEncoding", + "PerceiverImagePreprocessor", + "PerceiverLayer", + "PerceiverMLP", + "PerceiverMultimodalDecoder", + "PerceiverMultimodalPostprocessor", + "PerceiverMultimodalPreprocessor", + "PerceiverOneHotPreprocessor", + "PerceiverOpticalFlowDecoder", + "PerceiverProjectionDecoder", + "PerceiverProjectionPostprocessor", + "PerceiverSelfAttention", + "PerceiverSelfOutput", + "PerceiverTextPreprocessor", + "PerceiverTrainablePositionEncoding", + "PerceptionLMAdaptiveAvgPooling", + "PerceptionLMMultiModalProjector", + "PersimmonAttention", + "PersimmonDecoderLayer", + "PersimmonMLP", + "PersimmonRotaryEmbedding", + "Phi3Attention", + "Phi3DecoderLayer", + "Phi3MLP", + "Phi3RMSNorm", + "Phi3RotaryEmbedding", + "Phi4MultimodalAttention", + "Phi4MultimodalAudioAttention", + "Phi4MultimodalAudioConformerEncoderLayer", + "Phi4MultimodalAudioConvModule", + "Phi4MultimodalAudioDepthWiseSeperableConv1d", + "Phi4MultimodalAudioEmbedding", + "Phi4MultimodalAudioGluPointWiseConv", + "Phi4MultimodalAudioMeanVarianceNormLayer", + "Phi4MultimodalAudioMLP", + "Phi4MultimodalAudioNemoConvSubsampling", + "Phi4MultimodalAudioRelativeAttentionBias", + "Phi4MultimodalDecoderLayer", + "Phi4MultimodalFeatureEmbedding", + "Phi4MultimodalImageEmbedding", + "Phi4MultimodalMLP", + "Phi4MultimodalRMSNorm", + "Phi4MultimodalRotaryEmbedding", + "Phi4MultimodalVisionAttention", + "Phi4MultimodalVisionEmbeddings", + "Phi4MultimodalVisionEncoder", + "Phi4MultimodalVisionEncoderLayer", + "Phi4MultimodalVisionMLP", + "Phi4MultimodalVisionMultiheadAttentionPoolingHead", + "PhiAttention", + "PhiDecoderLayer", + "PhiMLP", + "PhimoeAttention", + "PhimoeBlockSparseTop2MLP", + "PhimoeDecoderLayer", + "PhimoeFlashAttention2", + "PhimoeRotaryEmbedding", + "PhimoeSdpaAttention", + "PhimoeSparseMoeBlock", + "PhiRotaryEmbedding", + "Pix2StructLayerNorm", + "Pix2StructTextAttention", + "Pix2StructTextBlock", + "Pix2StructTextDenseGatedActDense", + "Pix2StructTextLayerCrossAttention", + "Pix2StructTextLayerFF", + "Pix2StructTextLayerSelfAttention", + "Pix2StructVisionAttention", + "Pix2StructVisionEmbeddings", + "Pix2StructVisionEncoder", + "Pix2StructVisionLayer", + "Pix2StructVisionMlp", + "PixelShuffleAuxUpsampler", + "PixelShuffleUpsampler", + "PixtralAttention", + "PixtralAttentionLayer", + "PixtralMLP", + "PixtralRMSNorm", + "PixtralRotaryEmbedding", + "PixtralTransformer", + "PLBartAttention", + "PLBartClassificationHead", + "PLBartDecoder", + "PLBartDecoderLayer", + "PLBartDecoderWrapper", + "PLBartEncoder", + "PLBartEncoderLayer", + "PLBartLearnedPositionalEmbedding", + "PLBartScaledWordEmbedding", + "PoolFormerDropPath", + "PoolFormerEmbeddings", + "PoolFormerEncoder", + "PoolFormerFinalPooler", + "PoolFormerGroupNorm", + "PoolFormerLayer", + "PoolFormerOutput", + "PoolFormerPooling", + "Pop2PianoAttention", + "Pop2PianoBlock", + "Pop2PianoConcatEmbeddingToMel", + "Pop2PianoDenseActDense", + "Pop2PianoDenseGatedActDense", + "Pop2PianoLayerCrossAttention", + "Pop2PianoLayerFF", + "Pop2PianoLayerNorm", + "Pop2PianoLayerSelfAttention", + "Pop2PianoStack", + "PositionalEmbedding", + "PositionEmbeddings", + "PositionwiseFF", + "PredictionBlock", + "PreTrainedAudioTokenizerBase", + "ProjectedAdaptiveLogSoftmax", + "PromptDepthAnythingDepthEstimationHead", + "PromptDepthAnythingFeatureFusionLayer", + "PromptDepthAnythingFeatureFusionStage", + "PromptDepthAnythingLayer", + "PromptDepthAnythingNeck", + "PromptDepthAnythingPreActResidualLayer", + "PromptDepthAnythingReassembleLayer", + "PromptDepthAnythingReassembleStage", + "PromptGeneratorLayer", + "ProphetNetAttention", + "ProphetNetDecoderLayer", + "ProphetNetDecoderWrapper", + "ProphetNetEncoderLayer", + "ProphetNetFeedForward", + "ProphetNetNgramSelfAttention", + "ProphetNetPositionalEmbeddings", + "PvtAttention", + "PvtDropPath", + "PvtEfficientSelfAttention", + "PvtEncoder", + "PvtFFN", + "PvtLayer", + "PvtPatchEmbeddings", + "PvtSelfOutput", + "PvtV2BlockLayer", + "PvtV2ConvFeedForwardNetwork", + "PvtV2DepthWiseConv", + "PvtV2DropPath", + "PvtV2Encoder", + "PvtV2EncoderLayer", + "PvtV2OverlapPatchEmbeddings", + "PvtV2SelfAttention", + "PytorchGELUTanh", + "QDQBertAttention", + "QDQBertEmbeddings", + "QDQBertEncoder", + "QDQBertIntermediate", + "QDQBertLayer", + "QDQBertLMPredictionHead", + "QDQBertOnlyMLMHead", + "QDQBertOnlyNSPHead", + "QDQBertOutput", + "QDQBertPooler", + "QDQBertPredictionHeadTransform", + "QDQBertPreTrainingHeads", + "QDQBertSelfAttention", + "QDQBertSelfOutput", + "QuantAct", + "QuantEmbedding", + "QuantLinear", + "QuestionAwareSpanSelectionHead", + "QuickGELUActivation", + "Qwen2_5_OmniAdaLayerNormZero_Final", + "Qwen2_5_OmniAdaLayerNormZero", + "Qwen2_5_VisionPatchEmbed", + "Qwen2_5_VisionRotaryEmbedding", + "Qwen2_5_VisionTransformerPretrainedModel", + "Qwen2_5_VLAttention", + "Qwen2_5_VLDecoderLayer", + "Qwen2_5_VLMLP", + "Qwen2_5_VLPatchMerger", + "Qwen2_5_VLRotaryEmbedding", + "Qwen2_5_VLVisionAttention", + "Qwen2_5_VLVisionBlock", + "Qwen2_5OmniAttention", + "Qwen2_5OmniAudioAttention", + "Qwen2_5OmniAudioEncoder", + "Qwen2_5OmniAudioEncoderLayer", + "Qwen2_5OmniDecoderLayer", + "Qwen2_5OmniDiTRotaryEmbedding", + "Qwen2_5OmniMLP", + "Qwen2_5OmniPatchMerger", + "Qwen2_5OmniRotaryEmbedding", + "Qwen2_5OmniVisionAttention", + "Qwen2_5OmniVisionBlock", + "Qwen2_5OmniVisionEncoder", + "Qwen2Attention", + "Qwen2AudioAttention", + "Qwen2AudioEncoderLayer", + "Qwen2AudioMultiModalProjector", + "Qwen2DecoderLayer", + "Qwen2MLP", + "Qwen2MoeAttention", + "Qwen2MoeDecoderLayer", + "Qwen2MoeFlashAttention2", + "Qwen2MoeMLP", + "Qwen2MoeRMSNorm", + "Qwen2MoeRotaryEmbedding", + "Qwen2MoeSdpaAttention", + "Qwen2MoeSparseMoeBlock", + "Qwen2RMSNorm", + "Qwen2RotaryEmbedding", + "Qwen2VisionTransformerPretrainedModel", + "Qwen2VLAttention", + "Qwen2VLDecoderLayer", + "Qwen2VLRotaryEmbedding", + "Qwen2VLVisionBlock", + "Qwen3Attention", + "Qwen3DecoderLayer", + "Qwen3MLP", + "Qwen3MoeAttention", + "Qwen3MoeDecoderLayer", + "Qwen3MoeMLP", + "Qwen3MoeRMSNorm", + "Qwen3MoeRotaryEmbedding", + "Qwen3MoeSparseMoeBlock", + "Qwen3RMSNorm", + "Qwen3RotaryEmbedding", + "RealmAttention", + "RealmBertModel", + "RealmEmbeddings", + "RealmEncoder", + "RealmIntermediate", + "RealmLayer", + "RealmLMPredictionHead", + "RealmOnlyMLMHead", + "RealmOutput", + "RealmPooler", + "RealmPredictionHeadTransform", + "RealmReaderProjection", + "RealmScorerProjection", + "RealmSelfAttention", + "RealmSelfOutput", + "RecurrentGemmaDecoderLayer", + "RecurrentGemmaMlp", + "RecurrentGemmaRecurrentBlock", + "RecurrentGemmaRglru", + "RecurrentGemmaRMSNorm", + "RecurrentGemmaRotaryEmbedding", + "RecurrentGemmaSdpaAttention", + "ReformerAttention", + "ReformerClassificationHead", + "ReformerEmbeddings", + "ReformerEncoder", + "ReformerFeedForwardDense", + "ReformerFeedForwardOutput", + "ReformerLayer", + "ReformerOnlyLMHead", + "ReformerSelfOutput", + "RegNetConvLayer", + "RegNetEmbeddings", + "RegNetEncoder", + "RegNetSELayer", + "RegNetShortCut", + "RegNetStage", + "RegNetXLayer", + "RegNetYLayer", + "RelativePositionBias1D", + "RelativePositionBiasAggregated", + "RelativePositionBiasBase", + "RelativePositionBiasHorizontal", + "RelativePositionBiasVertical", + "RelPartialLearnableDecoderLayer", + "RelPartialLearnableMultiHeadAttn", + "ReLUSquaredActivation", + "RemBertAttention", + "RemBertEmbeddings", + "RemBertEncoder", + "RemBertIntermediate", + "RemBertLayer", + "RemBertLMPredictionHead", + "RemBertOnlyMLMHead", + "RemBertOutput", + "RemBertPooler", + "RemBertPredictionHeadTransform", + "RemBertSelfAttention", + "RemBertSelfOutput", + "Res2NetBlock", + "ResNetBasicLayer", + "ResNetBottleNeckLayer", + "ResNetConvLayer", + "ResNetEmbeddings", + "ResNetEncoder", + "ResNetShortCut", + "ResNetStage", + "RobertaAttention", + "RobertaClassificationHead", + "RobertaEmbeddings", + "RobertaEncoder", + "RobertaIntermediate", + "RobertaLayer", + "RobertaLMHead", + "RobertaOutput", + "RobertaPooler", + "RobertaPreLayerNormAttention", + "RobertaPreLayerNormClassificationHead", + "RobertaPreLayerNormEmbeddings", + "RobertaPreLayerNormEncoder", + "RobertaPreLayerNormIntermediate", + "RobertaPreLayerNormLayer", + "RobertaPreLayerNormLMHead", + "RobertaPreLayerNormOutput", + "RobertaPreLayerNormPooler", + "RobertaPreLayerNormSelfAttention", + "RobertaPreLayerNormSelfOutput", + "RobertaSdpaSelfAttention", + "RobertaSelfAttention", + "RobertaSelfOutput", + "RoCBertAttention", + "RoCBertEmbeddings", + "RoCBertEncoder", + "RoCBertIntermediate", + "RoCBertLayer", + "RoCBertLMPredictionHead", + "RoCBertOnlyMLMHead", + "RoCBertOutput", + "RoCBertPooler", + "RoCBertPredictionHeadTransform", + "RoCBertSelfAttention", + "RoCBertSelfOutput", + "RoFormerAttention", + "RoFormerClassificationHead", + "RoFormerEmbeddings", + "RoFormerEncoder", + "RoFormerIntermediate", + "RoFormerLayer", + "RoFormerLMPredictionHead", + "RoFormerOnlyMLMHead", + "RoFormerOutput", + "RoFormerPredictionHeadTransform", + "RoFormerSelfAttention", + "RoFormerSelfOutput", + "RoFormerSequenceSummary", + "RoFormerSinusoidalPositionalEmbedding", + "RotaryEmbedding", + "RTDetrConvEncoder", + "RTDetrConvNormLayer", + "RTDetrCSPRepLayer", + "RTDetrDecoder", + "RTDetrDecoderLayer", + "RTDetrEncoder", + "RTDetrEncoderLayer", + "RTDetrFrozenBatchNorm2d", + "RTDetrHungarianMatcher", + "RTDetrHybridEncoder", + "RTDetrLoss", + "RTDetrMLPPredictionHead", + "RTDetrMultiheadAttention", + "RTDetrMultiscaleDeformableAttention", + "RTDetrRepVggBlock", + "RTDetrResNetBasicLayer", + "RTDetrResNetBottleNeckLayer", + "RTDetrResNetConvLayer", + "RTDetrResNetEmbeddings", + "RTDetrResNetEncoder", + "RTDetrResNetShortCut", + "RTDetrResNetStage", + "RTDetrV2ConvEncoder", + "RTDetrV2ConvNormLayer", + "RTDetrV2CSPRepLayer", + "RTDetrV2Decoder", + "RTDetrV2DecoderLayer", + "RTDetrV2Encoder", + "RTDetrV2EncoderLayer", + "RTDetrV2FrozenBatchNorm2d", + "RTDetrV2HybridEncoder", + "RTDetrV2MLPPredictionHead", + "RTDetrV2MultiheadAttention", + "RTDetrV2MultiscaleDeformableAttention", + "RTDetrV2RepVggBlock", + "RwkvBlock", + "RwkvFeedForward", + "RwkvSelfAttention", + "SamAttention", + "SamFeedForward", + "SamHQAttention", + "SamHQFeedForward", + "SamHQLayerNorm", + "SamHQMaskDecoder", + "SamHQMaskEmbedding", + "SamHQMLPBlock", + "SamHQPatchEmbeddings", + "SamHQPositionalEmbedding", + "SamHQPromptEncoder", + "SamHQTwoWayAttentionBlock", + "SamHQTwoWayTransformer", + "SamHQVisionAttention", + "SamHQVisionEncoder", + "SamHQVisionLayer", + "SamHQVisionNeck", + "SamHQVisionSdpaAttention", + "SamLayerNorm", + "SamMaskDecoder", + "SamMaskEmbedding", + "SamMLPBlock", + "SamPatchEmbeddings", + "SamPositionalEmbedding", + "SamPromptEncoder", + "SamTwoWayAttentionBlock", + "SamTwoWayTransformer", + "SamVisionAttention", + "SamVisionEncoder", + "SamVisionLayer", + "SamVisionNeck", + "SamVisionSdpaAttention", + "SeamlessM4TAttention", + "SeamlessM4TConformerAdapter", + "SeamlessM4TConformerAdapterLayer", + "SeamlessM4TConformerConvolutionModule", + "SeamlessM4TConformerEncoder", + "SeamlessM4TConformerEncoderLayer", + "SeamlessM4TConformerFeatureProjection", + "SeamlessM4TConformerFeedForward", + "SeamlessM4TConformerPositionalConvEmbedding", + "SeamlessM4TConformerRelPositionalEmbedding", + "SeamlessM4TConformerRotaryPositionalEmbedding", + "SeamlessM4TConformerSamePadLayer", + "SeamlessM4TConformerSelfAttention", + "SeamlessM4TDecoder", + "SeamlessM4TDecoderLayer", + "SeamlessM4TEncoder", + "SeamlessM4TEncoderLayer", + "SeamlessM4TFeedForwardNetwork", + "SeamlessM4TScaledWordEmbedding", + "SeamlessM4TSinusoidalPositionalEmbedding", + "SeamlessM4TSpeechEncoder", + "SeamlessM4Tv2Attention", + "SeamlessM4Tv2CodeHifiGan", + "SeamlessM4Tv2ConformerAdapter", + "SeamlessM4Tv2ConformerAdapterLayer", + "SeamlessM4Tv2ConformerConvolutionModule", + "SeamlessM4Tv2ConformerEncoder", + "SeamlessM4Tv2ConformerEncoderLayer", + "SeamlessM4Tv2ConformerFeatureProjection", + "SeamlessM4Tv2ConformerFeedForward", + "SeamlessM4Tv2ConformerSelfAttention", + "SeamlessM4Tv2Decoder", + "SeamlessM4Tv2DecoderLayer", + "SeamlessM4Tv2Encoder", + "SeamlessM4Tv2EncoderLayer", + "SeamlessM4Tv2FeedForwardNetwork", + "SeamlessM4Tv2HifiGan", + "SeamlessM4Tv2ScaledWordEmbedding", + "SeamlessM4Tv2SinusoidalPositionalEmbedding", + "SeamlessM4Tv2SpeechEncoder", + "SeamlessM4Tv2TextToUnitDecoder", + "SeamlessM4Tv2TextToUnitDecoderLayer", + "SeamlessM4Tv2TextToUnitForConditionalGeneration", + "SeamlessM4Tv2TextToUnitModel", + "SeamlessM4Tv2VariancePredictor", + "SeamlessM4TVariancePredictor", + "SegformerAttention", + "SegformerDropPath", + "SegformerDWConv", + "SegformerEfficientSelfAttention", + "SegformerEncoder", + "SegformerLayer", + "SegformerMixFFN", + "SegformerMLP", + "SegformerOverlapPatchEmbeddings", + "SegformerSelfOutput", + "SegGptAttention", + "SegGptDecoder", + "SegGptDecoderHead", + "SegGptDropPath", + "SegGptEmbeddings", + "SegGptEncoder", + "SegGptLayer", + "SegGptLayerNorm", + "SegGptLoss", + "SegGptMlp", + "SegGptPatchEmbeddings", + "SeparableConv1D", + "SequentialLlama4TextExperts", + "SEWAttention", + "SEWDAttention", + "SEWDEncoder", + "SEWDFeatureEncoder", + "SEWDFeatureExtractor", + "SEWDGroupNormConvLayer", + "SEWDIntermediate", + "SEWDLayer", + "SEWDLayerNormConvLayer", + "SEWDNoLayerNormConvLayer", + "SEWDOutput", + "SEWDPositionalConvEmbedding", + "SEWDSamePadLayer", + "SEWDSelfOutput", + "SEWDTransformerEncoder", + "SEWDUpsampling", + "SEWEncoder", + "SEWEncoderLayer", + "SEWFeatureEncoder", + "SEWFeatureExtractor", + "SEWFeedForward", + "SEWGroupNormConvLayer", + "SEWLayerNormConvLayer", + "SEWNoLayerNormConvLayer", + "SEWPositionalConvEmbedding", + "SEWSamePadLayer", + "SEWUpsampling", + "Siglip2Attention", + "Siglip2Encoder", + "Siglip2EncoderLayer", + "Siglip2MLP", + "Siglip2MultiheadAttentionPoolingHead", + "Siglip2TextEmbeddings", + "Siglip2TextTransformer", + "Siglip2VisionEmbeddings", + "Siglip2VisionTransformer", + "SiglipAttention", + "SiglipEncoder", + "SiglipEncoderLayer", + "SiglipMLP", + "SiglipMultiheadAttentionPoolingHead", + "SiglipTextEmbeddings", + "SiglipTextTransformer", + "SiglipVisionEmbeddings", + "SiglipVisionTransformer", + "SiLogLoss", + "SinusoidalPositionalEmbedding", + "SinusoidsPositionEmbedding", + "SinusPositionEmbedding", + "SmolLM3Attention", + "SmolLM3DecoderLayer", + "SmolLM3MLP", + "SmolLM3RMSNorm", + "SmolLM3RotaryEmbedding", + "SmolVLMConnector", + "SmolVLMEncoder", + "SmolVLMEncoderLayer", + "SmolVLMRMSNorm", + "SmolVLMSimpleMLP", + "SmolVLMVisionAttention", + "SmolVLMVisionEmbeddings", + "SmolVLMVisionMLP", + "SmoothL1Loss", + "Snake1d", + "SnakeBeta", + "Speech2Text2Attention", + "Speech2Text2Decoder", + "Speech2Text2DecoderLayer", + "Speech2Text2DecoderWrapper", + "Speech2Text2SinusoidalPositionalEmbedding", + "Speech2TextAttention", + "Speech2TextDecoder", + "Speech2TextDecoderLayer", + "Speech2TextEncoder", + "Speech2TextEncoderLayer", + "Speech2TextSinusoidalPositionalEmbedding", + "SpeechT5Attention", + "SpeechT5BatchNormConvLayer", + "SpeechT5Decoder", + "SpeechT5DecoderLayer", + "SpeechT5DecoderWithoutPrenet", + "SpeechT5DecoderWithSpeechPrenet", + "SpeechT5DecoderWithTextPrenet", + "SpeechT5Encoder", + "SpeechT5EncoderLayer", + "SpeechT5EncoderWithoutPrenet", + "SpeechT5EncoderWithSpeechPrenet", + "SpeechT5EncoderWithTextPrenet", + "SpeechT5FeatureEncoder", + "SpeechT5FeatureProjection", + "SpeechT5FeedForward", + "SpeechT5GroupNormConvLayer", + "SpeechT5GuidedMultiheadAttentionLoss", + "SpeechT5LayerNormConvLayer", + "SpeechT5NoLayerNormConvLayer", + "SpeechT5PositionalConvEmbedding", + "SpeechT5RelativePositionalEncoding", + "SpeechT5SamePadLayer", + "SpeechT5ScaledPositionalEncoding", + "SpeechT5SinusoidalPositionalEmbedding", + "SpeechT5SpectrogramLoss", + "SpeechT5SpeechDecoderPostnet", + "SpeechT5SpeechDecoderPrenet", + "SpeechT5SpeechEncoderPrenet", + "SpeechT5TextDecoderPostnet", + "SpeechT5TextDecoderPrenet", + "SpeechT5TextEncoderPrenet", + "SplinterAttention", + "SplinterEmbeddings", + "SplinterEncoder", + "SplinterFullyConnectedLayer", + "SplinterIntermediate", + "SplinterLayer", + "SplinterOutput", + "SplinterSelfAttention", + "SplinterSelfOutput", + "SqueezeBertEmbeddings", + "SqueezeBertEncoder", + "SqueezeBertLayerNorm", + "SqueezeBertLMPredictionHead", + "SqueezeBertOnlyMLMHead", + "SqueezeBertPooler", + "SqueezeBertPredictionHeadTransform", + "SqueezeBertSelfAttention", + "SqueezeExcitationBlock", + "SqueezeExcitationRes2NetBlock", + "StableDropout", + "StableLmAttention", + "StableLmDecoderLayer", + "StableLmFlashAttention2", + "StableLmLayerNormPerHead", + "StableLmMLP", + "StableLmRotaryEmbedding", + "StableLmSdpaAttention", + "Starcoder2Attention", + "Starcoder2DecoderLayer", + "Starcoder2MLP", + "Starcoder2RotaryEmbedding", + "SuperGlueAttention", + "SuperGlueAttentionalGNN", + "SuperGlueAttentionalPropagation", + "SuperGlueFinalProjection", + "SuperGlueKeypointEncoder", + "SuperGlueMultiLayerPerceptron", + "SuperGlueSelfAttention", + "SuperGlueSelfOutput", + "SuperPointConvBlock", + "SuperPointDescriptorDecoder", + "SuperPointEncoder", + "SuperPointInterestPointDecoder", + "SwiftFormerConvEncoder", + "SwiftFormerDropPath", + "SwiftFormerEfficientAdditiveAttention", + "SwiftFormerEmbeddings", + "SwiftFormerEncoder", + "SwiftFormerEncoderBlock", + "SwiftFormerLocalRepresentation", + "SwiftFormerMlp", + "SwiftFormerPatchEmbedding", + "SwiftFormerStage", + "Swin2SRAttention", + "Swin2SRDropPath", + "Swin2SREmbeddings", + "Swin2SREncoder", + "Swin2SRIntermediate", + "Swin2SRLayer", + "Swin2SROutput", + "Swin2SRPatchEmbeddings", + "Swin2SRPatchMerging", + "Swin2SRPatchUnEmbeddings", + "Swin2SRSelfAttention", + "Swin2SRSelfOutput", + "Swin2SRStage", + "SwinAttention", + "SwinDropPath", + "SwinEmbeddings", + "SwinEncoder", + "SwinIntermediate", + "SwinLayer", + "SwinOutput", + "SwinPatchEmbeddings", + "SwinPatchMerging", + "SwinSelfAttention", + "SwinSelfOutput", + "SwinStage", + "Swinv2Attention", + "Swinv2DropPath", + "Swinv2Embeddings", + "Swinv2Encoder", + "Swinv2Intermediate", + "Swinv2Layer", + "Swinv2Output", + "Swinv2PatchEmbeddings", + "Swinv2PatchMerging", + "Swinv2SelfAttention", + "Swinv2SelfOutput", + "Swinv2Stage", + "SwitchTransformersAttention", + "SwitchTransformersBlock", + "SwitchTransformersDenseActDense", + "SwitchTransformersLayerCrossAttention", + "SwitchTransformersLayerFF", + "SwitchTransformersLayerNorm", + "SwitchTransformersLayerSelfAttention", + "SwitchTransformersSparseMLP", + "SwitchTransformersStack", + "SwitchTransformersTop1Router", + "T5Attention", + "T5Block", + "T5ClassificationHead", + "T5DenseActDense", + "T5DenseGatedActDense", + "T5GemmaAttention", + "T5GemmaClassificationHead", + "T5GemmaCrossAttention", + "T5GemmaDecoder", + "T5GemmaDecoderLayer", + "T5GemmaEncoder", + "T5GemmaEncoderLayer", + "T5GemmaLMHead", + "T5GemmaMLP", + "T5GemmaRMSNorm", + "T5GemmaRotaryEmbedding", + "T5GemmaSelfAttention", + "T5LayerCrossAttention", + "T5LayerFF", + "T5LayerNorm", + "T5LayerSelfAttention", + "T5Stack", + "TableTransformerAttention", + "TableTransformerConvEncoder", + "TableTransformerConvModel", + "TableTransformerDecoder", + "TableTransformerDecoderLayer", + "TableTransformerEncoder", + "TableTransformerEncoderLayer", + "TableTransformerFrozenBatchNorm2d", + "TableTransformerLearnedPositionEmbedding", + "TableTransformerMLPPredictionHead", + "TableTransformerSinePositionEmbedding", + "TapasAttention", + "TapasEmbeddings", + "TapasEncoder", + "TapasIntermediate", + "TapasLayer", + "TapasLMPredictionHead", + "TapasOnlyMLMHead", + "TapasOutput", + "TapasPooler", + "TapasPredictionHeadTransform", + "TapasSelfAttention", + "TapasSelfOutput", + "TDNNLayer", + "TextEmbeddings", + "TextNetConvLayer", + "TextNetEncoder", + "TextNetRepConvLayer", + "TextNetStage", + "TimeDelayNetBlock", + "TimeSeriesFeatureEmbedder", + "TimeSeriesMeanScaler", + "TimeSeriesNOPScaler", + "TimeSeriesSinusoidalPositionalEmbedding", + "TimeSeriesStdScaler", + "TimeSeriesTransformerAttention", + "TimeSeriesTransformerDecoder", + "TimeSeriesTransformerDecoderLayer", + "TimeSeriesTransformerEncoder", + "TimeSeriesTransformerEncoderLayer", + "TimeSeriesValueEmbedding", + "TimesFmAttention", + "TimesFmDecoderLayer", + "TimesFmMLP", + "TimesFmPositionalEmbedding", + "TimesFmResidualBlock", + "TimesFmRMSNorm", + "TimeSformerAttention", + "TimeSformerDropPath", + "TimesformerEmbeddings", + "TimesformerEncoder", + "TimesformerIntermediate", + "TimesformerLayer", + "TimesformerOutput", + "TimesformerPatchEmbeddings", + "TimesformerSelfAttention", + "TimesformerSelfOutput", + "TorchActivation1d", + "Transformer", + "TransformerBlock", + "TransformerFFN", + "TrOCRAttention", + "TrOCRDecoder", + "TrOCRDecoderLayer", + "TrOCRDecoderWrapper", + "TrOCRLearnedPositionalEmbedding", + "TrOCRScaledWordEmbedding", + "TrOCRSinusoidalPositionalEmbedding", + "TvltAttention", + "TvltAudioEmbeddings", + "TvltAudioPatchEmbeddings", + "TvltDecoder", + "TvltEncoder", + "TvltIntermediate", + "TvltLayer", + "TvltMAEHead", + "TvltMatchingHead", + "TvltOutput", + "TvltPixelEmbeddings", + "TvltPixelPatchEmbeddings", + "TvltPooler", + "TvltSelfAttention", + "TvltSelfOutput", + "TvpAttention", + "TvpEncodeLayer", + "TvpEncoder", + "TvpFrameDownPadPrompter", + "TvpFramePadPrompter", + "TvpIntermediate", + "TvpLoss", + "TvpOutputLayer", + "TvpPooler", + "TvpTextInputEmbeddings", + "TvpVideoGroundingHead", + "TvpVisionModel", + "TvpVisualInputEmbedding", + "UdopAttention", + "UdopBlock", + "UdopCellEmbeddings", + "UdopDenseActDense", + "UdopDenseGatedActDense", + "UdopLayerCrossAttention", + "UdopLayerFF", + "UdopLayerNorm", + "UdopLayerSelfAttention", + "UdopPatchEmbeddings", + "UdopStack", + "UMT5Attention", + "UMT5Block", + "UMT5ClassificationHead", + "UMT5DenseActDense", + "UMT5DenseGatedActDense", + "UMT5LayerCrossAttention", + "UMT5LayerFF", + "UMT5LayerNorm", + "UMT5LayerSelfAttention", + "UMT5Stack", + "UniSpeechAttention", + "UniSpeechAttnAdapterLayer", + "UniSpeechEncoder", + "UniSpeechEncoderLayer", + "UniSpeechEncoderLayerStableLayerNorm", + "UniSpeechEncoderStableLayerNorm", + "UniSpeechFeatureEncoder", + "UniSpeechFeatureProjection", + "UniSpeechFeedForward", + "UniSpeechGroupNormConvLayer", + "UniSpeechGumbelVectorQuantizer", + "UniSpeechLayerNormConvLayer", + "UniSpeechNoLayerNormConvLayer", + "UniSpeechPositionalConvEmbedding", + "UniSpeechSamePadLayer", + "UniSpeechSatAttention", + "UniSpeechSatAttnAdapterLayer", + "UniSpeechSatEncoder", + "UniSpeechSatEncoderLayer", + "UniSpeechSatEncoderLayerStableLayerNorm", + "UniSpeechSatEncoderStableLayerNorm", + "UniSpeechSatFeatureEncoder", + "UniSpeechSatFeatureProjection", + "UniSpeechSatFeedForward", + "UniSpeechSatGroupNormConvLayer", + "UniSpeechSatGumbelVectorQuantizer", + "UniSpeechSatLayerNormConvLayer", + "UniSpeechSatNoLayerNormConvLayer", + "UniSpeechSatPositionalConvEmbedding", + "UniSpeechSatSamePadLayer", + "UnivNetKernelPredictor", + "UnivNetKernelPredictorResidualBlock", + "UnivNetLvcBlock", + "UnivNetLvcResidualBlock", + "UperNetConvModule", + "UperNetFCNHead", + "UperNetHead", + "UperNetPyramidPoolingBlock", + "UperNetPyramidPoolingModule", + "Upsample", + "UpSample1d", + "UpsampleOneStep", + "VanDropPath", + "VanEncoder", + "VanLargeKernelAttention", + "VanLargeKernelAttentionLayer", + "VanLayer", + "VanLayerScaling", + "VanMlpLayer", + "VanOverlappingPatchEmbedder", + "VanSpatialAttentionLayer", + "VanStage", + "VideoLlavaMultiModalProjector", + "VideoMAEAttention", + "VideoMAEDecoder", + "VideoMAEEmbeddings", + "VideoMAEEncoder", + "VideoMAEIntermediate", + "VideoMAELayer", + "VideoMAEOutput", + "VideoMAEPatchEmbeddings", + "VideoMAESelfAttention", + "VideoMAESelfOutput", + "ViltAttention", + "ViltEmbeddings", + "ViltEncoder", + "ViltIntermediate", + "ViltMLMHead", + "ViltOutput", + "ViltPatchEmbeddings", + "ViltPooler", + "ViltPredictionHeadTransform", + "ViltSelfAttention", + "ViltSelfOutput", + "VipLlavaMultiModalProjector", + "VisionAttention", + "VisionMlp", + "VisionRotaryEmbedding", + "VisualBertAttention", + "VisualBertEmbeddings", + "VisualBertEncoder", + "VisualBertIntermediate", + "VisualBertLMPredictionHead", + "VisualBertOutput", + "VisualBertPooler", + "VisualBertPredictionHeadTransform", + "VisualBertPreTrainingHeads", + "VisualBertRegionToPhraseAttention", + "VisualBertSelfAttention", + "VisualBertSelfOutput", + "ViTAttention", + "VitDetAttention", + "VitDetDropPath", + "VitDetEmbeddings", + "VitDetEncoder", + "VitDetLayer", + "VitDetLayerNorm", + "VitDetMlp", + "VitDetResBottleneckBlock", + "ViTEmbeddings", + "ViTEncoder", + "ViTHybridAttention", + "ViTHybridEmbeddings", + "ViTHybridEncoder", + "ViTHybridIntermediate", + "ViTHybridLayer", + "ViTHybridOutput", + "ViTHybridPatchEmbeddings", + "ViTHybridPooler", + "ViTHybridSdpaAttention", + "ViTHybridSdpaSelfAttention", + "ViTHybridSelfAttention", + "ViTHybridSelfOutput", + "ViTIntermediate", + "ViTLayer", + "ViTMAEAttention", + "ViTMAEDecoder", + "ViTMAEEmbeddings", + "ViTMAEEncoder", + "ViTMAEIntermediate", + "ViTMAEOutput", + "ViTMAEPatchEmbeddings", + "ViTMAESelfAttention", + "ViTMAESelfOutput", + "VitMatteBasicConv3x3", + "VitMatteConvStream", + "VitMatteDetailCaptureModule", + "VitMatteFusionBlock", + "VitMatteHead", + "ViTMSNAttention", + "ViTMSNEmbeddings", + "ViTMSNEncoder", + "ViTMSNIntermediate", + "ViTMSNLayer", + "ViTMSNOutput", + "ViTMSNPatchEmbeddings", + "ViTMSNSelfAttention", + "ViTMSNSelfOutput", + "ViTOutput", + "ViTPatchEmbeddings", + "ViTPooler", + "VitPoseBackboneAttention", + "VitPoseBackboneEmbeddings", + "VitPoseBackboneEncoder", + "VitPoseBackboneLayer", + "VitPoseBackboneMLP", + "VitPoseBackboneMoeMLP", + "VitPoseBackbonePatchEmbeddings", + "VitPoseBackboneSelfAttention", + "VitPoseBackboneSelfOutput", + "VitPoseClassicDecoder", + "VitPoseSimpleDecoder", + "VitsAttention", + "VitsConvFlow", + "VitsDilatedDepthSeparableConv", + "VitsDurationPredictor", + "VitsElementwiseAffine", + "ViTSelfAttention", + "ViTSelfOutput", + "VitsEncoder", + "VitsEncoderLayer", + "VitsFeedForward", + "VitsHifiGan", + "VitsPosteriorEncoder", + "VitsResidualCouplingBlock", + "VitsResidualCouplingLayer", + "VitsStochasticDurationPredictor", + "VitsTextEncoder", + "VitsWaveNet", + "VivitAttention", + "VivitEmbeddings", + "VivitEncoder", + "VivitIntermediate", + "VivitLayer", + "VivitOutput", + "VivitPooler", + "VivitSelfAttention", + "VivitSelfOutput", + "VivitTubeletEmbeddings", + "VJEPA2AttentivePooler", + "VJEPA2DropPath", + "VJEPA2Embeddings", + "VJEPA2Encoder", + "VJEPA2Layer", + "VJEPA2MLP", + "VJEPA2PatchEmbeddings3D", + "VJEPA2PoolerCrossAttention", + "VJEPA2PoolerCrossAttentionLayer", + "VJEPA2PoolerSelfAttention", + "VJEPA2PoolerSelfAttentionLayer", + "VJEPA2Predictor", + "VJEPA2PredictorEmbeddings", + "VJEPA2RopeAttention", + "VoxtralAttention", + "VoxtralEncoderLayer", + "VoxtralMultiModalProjector", + "Wav2Vec2Adapter", + "Wav2Vec2AdapterLayer", + "Wav2Vec2Attention", + "Wav2Vec2AttnAdapterLayer", + "Wav2Vec2BertAdapter", + "Wav2Vec2BertAdapterLayer", + "Wav2Vec2BertConvolutionModule", + "Wav2Vec2BertEncoder", + "Wav2Vec2BertEncoderLayer", + "Wav2Vec2BertFeatureProjection", + "Wav2Vec2BertFeedForward", + "Wav2Vec2BertRelPositionalEmbedding", + "Wav2Vec2BertRotaryPositionalEmbedding", + "Wav2Vec2BertSelfAttention", + "Wav2Vec2ConformerAdapter", + "Wav2Vec2ConformerAdapterLayer", + "Wav2Vec2ConformerConvolutionModule", + "Wav2Vec2ConformerEncoder", + "Wav2Vec2ConformerEncoderLayer", + "Wav2Vec2ConformerFeatureEncoder", + "Wav2Vec2ConformerFeatureProjection", + "Wav2Vec2ConformerFeedForward", + "Wav2Vec2ConformerGroupNormConvLayer", + "Wav2Vec2ConformerGumbelVectorQuantizer", + "Wav2Vec2ConformerLayerNormConvLayer", + "Wav2Vec2ConformerNoLayerNormConvLayer", + "Wav2Vec2ConformerPositionalConvEmbedding", + "Wav2Vec2ConformerRelPositionalEmbedding", + "Wav2Vec2ConformerRotaryPositionalEmbedding", + "Wav2Vec2ConformerSamePadLayer", + "Wav2Vec2ConformerSelfAttention", + "Wav2Vec2Encoder", + "Wav2Vec2EncoderLayer", + "Wav2Vec2EncoderLayerStableLayerNorm", + "Wav2Vec2EncoderStableLayerNorm", + "Wav2Vec2FeatureEncoder", + "Wav2Vec2FeatureExtractor", + "Wav2Vec2FeatureProjection", + "Wav2Vec2FeedForward", + "Wav2Vec2GroupNormConvLayer", + "Wav2Vec2GumbelVectorQuantizer", + "Wav2Vec2LayerNormConvLayer", + "Wav2Vec2NoLayerNormConvLayer", + "Wav2Vec2PositionalConvEmbedding", + "Wav2Vec2SamePadLayer", + "WavLMAdapter", + "WavLMAdapterLayer", + "WavLMAttention", + "WavLMEncoder", + "WavLMEncoderLayer", + "WavLMEncoderLayerStableLayerNorm", + "WavLMEncoderStableLayerNorm", + "WavLMFeatureEncoder", + "WavLMFeatureProjection", + "WavLMFeedForward", + "WavLMGroupNormConvLayer", + "WavLMGumbelVectorQuantizer", + "WavLMLayerNormConvLayer", + "WavLMNoLayerNormConvLayer", + "WavLMPositionalConvEmbedding", + "WavLMSamePadLayer", + "WeightStandardizedConv2d", + "WhisperAttention", + "WhisperDecoder", + "WhisperDecoderLayer", + "WhisperDecoderWrapper", + "WhisperEncoder", + "WhisperEncoderLayer", + "WhisperPositionalEmbedding", + "XCLIPAttention", + "XCLIPCrossAttention", + "XCLIPDropPath", + "XCLIPEncoder", + "XCLIPEncoderLayer", + "XCLIPMLP", + "XCLIPMultiframeIntegrationTransformer", + "XCLIPPromptGenerator", + "XCLIPTextEmbeddings", + "XCLIPTextTransformer", + "XCLIPVisionEmbeddings", + "XCLIPVisionEncoder", + "XCLIPVisionEncoderLayer", + "XCLIPVisionTransformer", + "XGLMAttention", + "XGLMDecoderLayer", + "XGLMScaledWordEmbedding", + "XGLMSinusoidalPositionalEmbedding", + "XLMPoolerAnswerClass", + "XLMPoolerEndLogits", + "XLMPoolerStartLogits", + "XLMPredLayer", + "XLMProphetNetAttention", + "XLMProphetNetDecoderLayer", + "XLMProphetNetDecoderWrapper", + "XLMProphetNetEncoderLayer", + "XLMProphetNetFeedForward", + "XLMProphetNetNgramSelfAttention", + "XLMProphetNetPositionalEmbeddings", + "XLMRobertaAttention", + "XLMRobertaClassificationHead", + "XLMRobertaEmbeddings", + "XLMRobertaEncoder", + "XLMRobertaIntermediate", + "XLMRobertaLayer", + "XLMRobertaLMHead", + "XLMRobertaOutput", + "XLMRobertaPooler", + "XLMRobertaSdpaSelfAttention", + "XLMRobertaSelfAttention", + "XLMRobertaSelfOutput", + "XLMRobertaXLAttention", + "XLMRobertaXLClassificationHead", + "XLMRobertaXLEmbeddings", + "XLMRobertaXLEncoder", + "XLMRobertaXLIntermediate", + "XLMRobertaXLLayer", + "XLMRobertaXLLMHead", + "XLMRobertaXLOutput", + "XLMRobertaXLPooler", + "XLMRobertaXLSdpaSelfAttention", + "XLMRobertaXLSelfAttention", + "XLMRobertaXLSelfOutput", + "XLMSequenceSummary", + "XLMSQuADHead", + "XLNetFeedForward", + "XLNetLayer", + "XLNetPoolerAnswerClass", + "XLNetPoolerEndLogits", + "XLNetPoolerStartLogits", + "XLNetRelativeAttention", + "XLNetSequenceSummary", + "xLSTMBackend", + "xLSTMBlock", + "xLSTMFeedForward", + "xLSTMLayer", + "xLSTMMultiHeadLayerNorm", + "xLSTMRMSNorm", + "XmodAdapter", + "XmodAttention", + "XmodClassificationHead", + "XmodEmbeddings", + "XmodEncoder", + "XmodIntermediate", + "XmodLayer", + "XmodLMHead", + "XmodOutput", + "XmodPooler", + "XmodSelfAttention", + "XmodSelfOutput", + "XPathEmbeddings", + "YolosAttention", + "YolosEmbeddings", + "YolosEncoder", + "YolosIntermediate", + "YolosLayer", + "YolosMLPPredictionHead", + "YolosOutput", + "YolosPatchEmbeddings", + "YolosPooler", + "YolosSelfAttention", + "YolosSelfOutput", + "YosoAttention", + "YosoClassificationHead", + "YosoEmbeddings", + "YosoEncoder", + "YosoIntermediate", + "YosoLayer", + "YosoLMPredictionHead", + "YosoOnlyMLMHead", + "YosoOutput", + "YosoPredictionHeadTransform", + "YosoSelfAttention", + "YosoSelfOutput", + "Zamba2Attention", + "Zamba2AttentionDecoderLayer", + "Zamba2HybridLayer", + "Zamba2MambaDecoderLayer", + "Zamba2MambaMixer", + "Zamba2MLP", + "Zamba2RMSNorm", + "Zamba2RMSNormGated", + "Zamba2RotaryEmbedding", + "ZambaAttention", + "ZambaAttentionDecoderLayer", + "ZambaHybridLayer", + "ZambaMambaDecoderLayer", + "ZambaMambaMixer", + "ZambaMLP", + "ZambaRMSNorm", + "ZoeDepthAttractorLayer", + "ZoeDepthAttractorLayerUnnormed", + "ZoeDepthConditionalLogBinomialSoftmax", + "ZoeDepthFeatureFusionLayer", + "ZoeDepthFeatureFusionStage", + "ZoeDepthMetricDepthEstimationHead", + "ZoeDepthMLPClassifier", + "ZoeDepthMultiheadAttention", + "ZoeDepthMultipleMetricDepthEstimationHeads", + "ZoeDepthNeck", + "ZoeDepthPatchTransformerEncoder", + "ZoeDepthPreActResidualLayer", + "ZoeDepthProjector", + "ZoeDepthReassembleLayer", + "ZoeDepthReassembleStage", + "ZoeDepthRelativeDepthEstimationHead", + "ZoeDepthSeedBinRegressor", + "ZoeDepthTransformerEncoderLayer"); diff --git a/tests/nn_module_export.txt b/tests/nn_module_export.txt new file mode 100644 index 0000000..855c7fb --- /dev/null +++ b/tests/nn_module_export.txt @@ -0,0 +1,3224 @@ +[ModuleList( + (0-11): 12 x Aimv2EncoderLayer( + (attention): Aimv2Attention( + (k_proj): Linear(in_features=768, out_features=768, bias=False) + (v_proj): Linear(in_features=768, out_features=768, bias=False) + (q_proj): Linear(in_features=768, out_features=768, bias=False) + (out_proj): Linear(in_features=768, out_features=768, bias=False) + ) + (ffn): Aimv2MLP( + (gate_proj): Linear(in_features=768, out_features=2048, bias=False) + (up_proj): Linear(in_features=768, out_features=2048, bias=False) + (down_proj): Linear(in_features=2048, out_features=768, bias=False) + (act_fn): SiLUActivation() + ) + (rms_norm1): Aimv2RMSNorm((768,), eps=1e-05) + (rms_norm2): Aimv2RMSNorm((768,), eps=1e-05) + ) +), ModuleList( + (0-23): 24 x Aimv2EncoderLayer( + (attention): Aimv2Attention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=False) + (v_proj): Linear(in_features=1024, out_features=1024, bias=False) + (q_proj): Linear(in_features=1024, out_features=1024, bias=False) + (out_proj): Linear(in_features=1024, out_features=1024, bias=False) + ) + (ffn): Aimv2MLP( + (gate_proj): Linear(in_features=1024, out_features=2816, bias=False) + (up_proj): Linear(in_features=1024, out_features=2816, bias=False) + (down_proj): Linear(in_features=2816, out_features=1024, bias=False) + (act_fn): SiLUActivation() + ) + (rms_norm1): Aimv2RMSNorm((1024,), eps=1e-05) + (rms_norm2): Aimv2RMSNorm((1024,), eps=1e-05) + ) +), ModuleList( + (0): AlbertLayer( + (full_layer_layer_norm): LayerNorm((4096,), eps=1e-12, elementwise_affine=True) + (attention): AlbertAttention( + (attention_dropout): Dropout(p=0, inplace=False) + (output_dropout): Dropout(p=0, inplace=False) + (query): Linear(in_features=4096, out_features=4096, bias=True) + (key): Linear(in_features=4096, out_features=4096, bias=True) + (value): Linear(in_features=4096, out_features=4096, bias=True) + (dense): Linear(in_features=4096, out_features=4096, bias=True) + (LayerNorm): LayerNorm((4096,), eps=1e-12, elementwise_affine=True) + ) + (ffn): Linear(in_features=4096, out_features=16384, bias=True) + (ffn_output): Linear(in_features=16384, out_features=4096, bias=True) + (activation): NewGELUActivation() + (dropout): Dropout(p=0, inplace=False) + ) +), ModuleList( + (0-11): 12 x ASTLayer( + (attention): ASTAttention( + (attention): ASTSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): ASTSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): ASTIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ASTOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-31): 32 x AudioFlamingo3EncoderLayer( + (self_attn): AudioFlamingo3Attention( + (k_proj): Linear(in_features=1280, out_features=1280, bias=False) + (v_proj): Linear(in_features=1280, out_features=1280, bias=True) + (q_proj): Linear(in_features=1280, out_features=1280, bias=True) + (out_proj): Linear(in_features=1280, out_features=1280, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1280, out_features=5120, bias=True) + (fc2): Linear(in_features=5120, out_features=1280, bias=True) + (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-1): 2 x AutoformerEncoderLayer( + (self_attn): AutoformerAttention( + (k_proj): Linear(in_features=64, out_features=64, bias=True) + (v_proj): Linear(in_features=64, out_features=64, bias=True) + (q_proj): Linear(in_features=64, out_features=64, bias=True) + (out_proj): Linear(in_features=64, out_features=64, bias=True) + ) + (self_attn_layer_norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=64, out_features=32, bias=True) + (fc2): Linear(in_features=32, out_features=64, bias=True) + (final_layer_norm): AutoformerLayernorm( + (layernorm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + ) + (decomp1): AutoformerSeriesDecompositionLayer( + (avg): AvgPool1d(kernel_size=(25,), stride=(1,), padding=(0,)) + ) + (decomp2): AutoformerSeriesDecompositionLayer( + (avg): AvgPool1d(kernel_size=(25,), stride=(1,), padding=(0,)) + ) + ) +), ModuleList( + (0-11): 12 x BartEncoderLayer( + (self_attn): BartAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x BertLayer( + (attention): BertAttention( + (self): BertSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): BertSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): BertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): BertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-23): 24 x BertGenerationLayer( + (attention): BertGenerationAttention( + (self): BertGenerationSelfAttention( + (query): Linear(in_features=1024, out_features=1024, bias=True) + (key): Linear(in_features=1024, out_features=1024, bias=True) + (value): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): BertGenerationSelfOutput( + (dense): Linear(in_features=1024, out_features=1024, bias=True) + (LayerNorm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): BertGenerationIntermediate( + (dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): BertGenerationOutput( + (dense): Linear(in_features=4096, out_features=1024, bias=True) + (LayerNorm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x BigBirdLayer( + (attention): BigBirdAttention( + (self): BigBirdBlockSparseAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): BigBirdSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): BigBirdIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): NewGELUActivation() + ) + (output): BigBirdOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-15): 16 x BigBirdPegasusEncoderLayer( + (self_attn): BigBirdPegasusEncoderAttention( + (self): BigBirdPegasusBlockSparseAttention( + (query): Linear(in_features=1024, out_features=1024, bias=False) + (key): Linear(in_features=1024, out_features=1024, bias=False) + (value): Linear(in_features=1024, out_features=1024, bias=False) + ) + (output): Linear(in_features=1024, out_features=1024, bias=False) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): NewGELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x BioGptDecoderLayer( + (self_attn): BioGptAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (activation_fn): GELUActivation() + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-1): 2 x BlenderbotEncoderLayer( + (self_attn): BlenderbotAttention( + (k_proj): Linear(in_features=2560, out_features=2560, bias=True) + (v_proj): Linear(in_features=2560, out_features=2560, bias=True) + (q_proj): Linear(in_features=2560, out_features=2560, bias=True) + (out_proj): Linear(in_features=2560, out_features=2560, bias=True) + ) + (self_attn_layer_norm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=2560, out_features=10240, bias=True) + (fc2): Linear(in_features=10240, out_features=2560, bias=True) + (final_layer_norm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-7): 8 x BlenderbotSmallEncoderLayer( + (self_attn): BlenderbotSmallAttention( + (k_proj): Linear(in_features=512, out_features=512, bias=True) + (v_proj): Linear(in_features=512, out_features=512, bias=True) + (q_proj): Linear(in_features=512, out_features=512, bias=True) + (out_proj): Linear(in_features=512, out_features=512, bias=True) + ) + (self_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=512, bias=True) + (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-1): 2 x BloomBlock( + (input_layernorm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (self_attention): BloomAttention( + (query_key_value): Linear(in_features=64, out_features=192, bias=True) + (dense): Linear(in_features=64, out_features=64, bias=True) + (attention_dropout): Dropout(p=0.0, inplace=False) + ) + (post_attention_layernorm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (mlp): BloomMLP( + (dense_h_to_4h): Linear(in_features=64, out_features=256, bias=True) + (gelu_impl): BloomGelu() + (dense_4h_to_h): Linear(in_features=256, out_features=64, bias=True) + ) + ) +), ModuleList( + (0-1): 2 x BridgeTowerResidualAttention( + (attn): MultiheadAttention( + (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True) + ) + (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): ModuleDict( + (c_fc): Linear(in_features=768, out_features=3072, bias=True) + (gelu): QuickGELUActivation() + (c_proj): Linear(in_features=3072, out_features=768, bias=True) + ) + (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x BrosLayer( + (attention): BrosAttention( + (self): BrosSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): BrosSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): BrosIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): BrosOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x CamembertLayer( + (attention): CamembertAttention( + (self): CamembertSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): CamembertSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): CamembertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): CamembertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x CLIPEncoderLayer( + (self_attn): CLIPAttention( + (k_proj): Linear(in_features=512, out_features=512, bias=True) + (v_proj): Linear(in_features=512, out_features=512, bias=True) + (q_proj): Linear(in_features=512, out_features=512, bias=True) + (out_proj): Linear(in_features=512, out_features=512, bias=True) + ) + (layer_norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) + (mlp): CLIPMLP( + (activation_fn): QuickGELUActivation() + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (layer_norm2): LayerNorm((512,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x CLIPEncoderLayer( + (self_attn): CLIPAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (layer_norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): CLIPMLP( + (activation_fn): QuickGELUActivation() + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (layer_norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-27): 28 x CodeGenBlock( + (ln_1): LayerNorm((4096,), eps=1e-05, elementwise_affine=True) + (attn): CodeGenAttention( + (attn_dropout): Dropout(p=0.0, inplace=False) + (resid_dropout): Dropout(p=0.0, inplace=False) + (qkv_proj): Linear(in_features=4096, out_features=12288, bias=False) + (out_proj): Linear(in_features=4096, out_features=4096, bias=False) + ) + (mlp): CodeGenMLP( + (fc_in): Linear(in_features=4096, out_features=16384, bias=True) + (fc_out): Linear(in_features=16384, out_features=4096, bias=True) + (act): NewGELUActivation() + (dropout): Dropout(p=0.0, inplace=False) + ) + ) +), ModuleList( + (0-5): 6 x ConditionalDetrEncoderLayer( + (self_attn): DetrAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x ConvBertLayer( + (attention): ConvBertAttention( + (self): ConvBertSelfAttention( + (query): Linear(in_features=768, out_features=384, bias=True) + (key): Linear(in_features=768, out_features=384, bias=True) + (value): Linear(in_features=768, out_features=384, bias=True) + (key_conv_attn_layer): SeparableConv1D( + (depthwise): Conv1d(768, 768, kernel_size=(9,), stride=(1,), padding=(4,), groups=768, bias=False) + (pointwise): Conv1d(768, 384, kernel_size=(1,), stride=(1,), bias=False) + ) + (conv_kernel_layer): Linear(in_features=384, out_features=54, bias=True) + (conv_out_layer): Linear(in_features=768, out_features=384, bias=True) + (unfold): Unfold(kernel_size=[9, 1], dilation=1, padding=[4, 0], stride=1) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): ConvBertSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): ConvBertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ConvBertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x CpmAntTransformerBlock( + (self_att): CpmAntSelfAttentionBlock( + (layernorm_before_attention): CpmAntLayerNorm() + (self_attention): CpmAntAttention( + (project_q): Linear(in_features=4096, out_features=4096, bias=False) + (project_k): Linear(in_features=4096, out_features=4096, bias=False) + (project_v): Linear(in_features=4096, out_features=4096, bias=False) + (attention_out): Linear(in_features=4096, out_features=4096, bias=False) + (softmax): Softmax(dim=-1) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (ffn): CpmAntFFNBlock( + (layernorm_before_ffn): CpmAntLayerNorm() + (ffn): CpmAntFeedForward( + (w_in): CpmAntDenseGatedACT( + (w_0): Linear(in_features=4096, out_features=10240, bias=False) + (w_1): Linear(in_features=4096, out_features=10240, bias=False) + (act): GELU(approximate='none') + ) + (dropout): Dropout(p=0.0, inplace=False) + (w_out): Linear(in_features=10240, out_features=4096, bias=False) + ) + ) + ) +), ModuleList( + (0-5): 6 x DFineDecoderLayer( + (self_attn): DFineMultiheadAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (activation_fn): ReLU() + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (encoder_attn): DFineMultiscaleDeformableAttention( + (sampling_offsets): Linear(in_features=256, out_features=192, bias=True) + (attention_weights): Linear(in_features=256, out_features=96, bias=True) + ) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (gateway): DFineGate( + (gate): Linear(in_features=512, out_features=512, bias=True) + (norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) + ) +), ModuleList( + (0-5): 6 x DabDetrEncoderLayer( + (self_attn): DetrAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): PReLU(num_parameters=1) + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-8): 9 x DacVectorQuantize( + (in_proj): Conv1d(1024, 8, kernel_size=(1,), stride=(1,)) + (out_proj): Conv1d(8, 1024, kernel_size=(1,), stride=(1,)) + (codebook): Embedding(1024, 8) + ) +), ModuleList( + (0-4): 5 x Data2VecAudioPositionalConvLayer( + (conv): Conv1d(768, 768, kernel_size=(19,), stride=(1,), padding=(9,), groups=16) + (padding): Data2VecAudioPadLayer() + (activation): GELUActivation() + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=False) + ) +), ModuleList( + (0-11): 12 x Data2VecTextLayer( + (attention): Data2VecTextAttention( + (self): Data2VecTextSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): Data2VecTextSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): Data2VecTextIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): Data2VecTextOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x DebertaLayer( + (attention): DebertaAttention( + (self): DisentangledSelfAttention( + (in_proj): Linear(in_features=768, out_features=2304, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): DebertaSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): DebertaLayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): DebertaIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): DebertaOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): DebertaLayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-23): 24 x DebertaV2Layer( + (attention): DebertaV2Attention( + (self): DisentangledSelfAttention( + (query_proj): Linear(in_features=1536, out_features=1536, bias=True) + (key_proj): Linear(in_features=1536, out_features=1536, bias=True) + (value_proj): Linear(in_features=1536, out_features=1536, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): DebertaV2SelfOutput( + (dense): Linear(in_features=1536, out_features=1536, bias=True) + (LayerNorm): LayerNorm((1536,), eps=1e-07, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): DebertaV2Intermediate( + (dense): Linear(in_features=1536, out_features=6144, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): DebertaV2Output( + (dense): Linear(in_features=6144, out_features=1536, bias=True) + (LayerNorm): LayerNorm((1536,), eps=1e-07, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-2): 3 x DecisionTransformerGPT2Block( + (ln_1): LayerNorm((128,), eps=1e-05, elementwise_affine=True) + (attn): DecisionTransformerGPT2Attention( + (c_attn): Conv1D(nf=384, nx=128) + (c_proj): Conv1D(nf=128, nx=128) + (attn_dropout): Dropout(p=0.1, inplace=False) + (resid_dropout): Dropout(p=0.1, inplace=False) + ) + (ln_2): LayerNorm((128,), eps=1e-05, elementwise_affine=True) + (mlp): DecisionTransformerGPT2MLP( + (c_fc): Conv1D(nf=512, nx=128) + (c_proj): Conv1D(nf=128, nx=512) + (act): ReLU() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-5): 6 x DeformableDetrEncoderLayer( + (self_attn): DeformableDetrMultiscaleDeformableAttention( + (attn): MultiScaleDeformableAttention() + (sampling_offsets): Linear(in_features=256, out_features=256, bias=True) + (attention_weights): Linear(in_features=256, out_features=128, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x DeiTLayer( + (attention): DeiTAttention( + (attention): DeiTSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): DeiTSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): DeiTIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): DeiTOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x DetrEncoderLayer( + (self_attn): DetrAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x Dinov2Layer( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attention): Dinov2Attention( + (attention): Dinov2SelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): Dinov2SelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (layer_scale1): Dinov2LayerScale() + (drop_path): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Dinov2MLP( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (activation): GELUActivation() + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (layer_scale2): Dinov2LayerScale() + ) +), ModuleList( + (0-11): 12 x Dinov2WithRegistersLayer( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attention): Dinov2WithRegistersAttention( + (attention): Dinov2WithRegistersSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): Dinov2WithRegistersSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (layer_scale1): Dinov2WithRegistersLayerScale() + (drop_path): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Dinov2WithRegistersMLP( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (activation): GELUActivation() + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (layer_scale2): Dinov2WithRegistersLayerScale() + ) +), ModuleList( + (0-11): 12 x DINOv3ViTLayer( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attention): DINOv3ViTAttention( + (k_proj): Linear(in_features=384, out_features=384, bias=False) + (v_proj): Linear(in_features=384, out_features=384, bias=True) + (q_proj): Linear(in_features=384, out_features=384, bias=True) + (o_proj): Linear(in_features=384, out_features=384, bias=True) + ) + (layer_scale1): DINOv3ViTLayerScale() + (drop_path): Identity() + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): DINOv3ViTMLP( + (up_proj): Linear(in_features=384, out_features=1536, bias=True) + (down_proj): Linear(in_features=1536, out_features=384, bias=True) + (act_fn): GELUActivation() + ) + (layer_scale2): DINOv3ViTLayerScale() + ) +), ModuleList( + (0-5): 6 x TransformerBlock( + (attention): DistilBertSelfAttention( + (q_lin): Linear(in_features=768, out_features=768, bias=True) + (k_lin): Linear(in_features=768, out_features=768, bias=True) + (v_lin): Linear(in_features=768, out_features=768, bias=True) + (out_lin): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (ffn): FFN( + (dropout): Dropout(p=0.1, inplace=False) + (lin1): Linear(in_features=768, out_features=3072, bias=True) + (lin2): Linear(in_features=3072, out_features=768, bias=True) + (activation): GELUActivation() + ) + (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-31): 32 x DogeDecoderLayer( + (input_layernorm): DogeRMSNorm((1024,), eps=1e-06) + (self_attn): DogeAttention( + (q_proj): Linear(in_features=1024, out_features=1024, bias=False) + (k_proj): Linear(in_features=1024, out_features=1024, bias=False) + (v_proj): Linear(in_features=1024, out_features=1024, bias=False) + (dt_proj): Linear(in_features=1024, out_features=8, bias=False) + (o_proj): Linear(in_features=1024, out_features=1024, bias=False) + (q_norm): DogeRMSNorm((128,), eps=1e-06) + (k_norm): DogeRMSNorm((128,), eps=1e-06) + ) + (post_attention_layernorm): DogeRMSNorm((1024,), eps=1e-06) + (mlp): DogeMLP( + (gate_proj): Linear(in_features=1024, out_features=2048, bias=False) + (up_proj): Linear(in_features=1024, out_features=2048, bias=False) + (down_proj): Linear(in_features=2048, out_features=1024, bias=False) + (act_fn): SiLUActivation() + ) + ) +), ModuleList( + (0-11): 12 x DPTViTLayer( + (attention): DPTViTAttention( + (attention): DPTSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): DPTViTSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): DPTViTIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): DPTViTOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-1): 2 x EdgeTamVideoMemoryFuserCXBlock( + (depthwise_conv): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256) + (layer_norm): EdgeTamVideoLayerNorm((256,), eps=1e-06, elementwise_affine=True) + (activation): GELUActivation() + (pointwise_conv1): Linear(in_features=256, out_features=1024, bias=True) + (pointwise_conv2): Linear(in_features=1024, out_features=256, bias=True) + ) +), ModuleList( + (0-11): 12 x ElectraLayer( + (attention): ElectraAttention( + (self): ElectraSelfAttention( + (query): Linear(in_features=256, out_features=256, bias=True) + (key): Linear(in_features=256, out_features=256, bias=True) + (value): Linear(in_features=256, out_features=256, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): ElectraSelfOutput( + (dense): Linear(in_features=256, out_features=256, bias=True) + (LayerNorm): LayerNorm((256,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): ElectraIntermediate( + (dense): Linear(in_features=256, out_features=1024, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ElectraOutput( + (dense): Linear(in_features=1024, out_features=256, bias=True) + (LayerNorm): LayerNorm((256,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-31): 32 x EncodecVectorQuantization( + (codebook): EncodecEuclideanCodebook() + ) +), ModuleList( + (0-11): 12 x ErnieLayer( + (attention): ErnieAttention( + (self): ErnieSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): ErnieSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): ErnieIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ErnieOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x EsmLayer( + (attention): EsmAttention( + (self): EsmSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): EsmSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) + (intermediate): EsmIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + ) + (output): EsmOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-4): 5 x FastSpeech2ConformerBatchNormConvLayer( + (conv): Conv1d(80, 256, kernel_size=(5,), stride=(1,), padding=(2,), bias=False) + (batch_norm): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activation): Tanh() + (dropout): Dropout(p=0.5, inplace=False) + ) +), ModuleList( + (0-11): 12 x FNetLayer( + (fourier): FNetFourierTransform( + (self): FNetBasicFourierTransform() + (output): FNetBasicOutput( + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) + ) + (intermediate): FNetIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): NewGELUActivation() + ) + (output): FNetOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x EncoderLayer( + (self_attn): Attention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x Gemma3nAudioConformerBlock( + (ffw_layer_start): Gemma3nAudioConformerFeedForward( + (pre_layer_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + (ffw_layer_1): Linear(in_features=1536, out_features=6144, bias=False) + (ffw_layer_2): Linear(in_features=6144, out_features=1536, bias=False) + (post_layer_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + ) + (attention): Gemma3nAudioConformerAttention( + (pre_attn_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + (attn): Gemma3nAudioAttention( + (relative_position_embedding): Gemma3nAudioRelativePositionEmbedding( + (pos_proj): Linear(in_features=1536, out_features=1536, bias=False) + ) + (q_proj): Linear(in_features=1536, out_features=1536, bias=False) + (k_proj): Linear(in_features=1536, out_features=1536, bias=False) + (v_proj): Linear(in_features=1536, out_features=1536, bias=False) + ) + (post): Linear(in_features=1536, out_features=1536, bias=False) + (post_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + ) + (lconv1d): Gemma3nAudioConformerLightConv1d( + (pre_layer_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + (linear_start): Linear(in_features=1536, out_features=3072, bias=False) + (depthwise_conv1d): Conv1d(1536, 1536, kernel_size=(5,), stride=(1,), groups=1536, bias=False) + (conv_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + (linear_end): Linear(in_features=1536, out_features=1536, bias=False) + ) + (ffw_layer_end): Gemma3nAudioConformerFeedForward( + (pre_layer_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + (ffw_layer_1): Linear(in_features=1536, out_features=6144, bias=False) + (ffw_layer_2): Linear(in_features=6144, out_features=1536, bias=False) + (post_layer_norm): Gemma3nRMSNorm((1536,), eps=1e-06) + ) + (norm): Gemma3nRMSNorm((1536,), eps=1e-06) + ) +), ModuleList( + (0-23): 24 x Glm4vMoeVisionBlock( + (norm1): Glm4vMoeRMSNorm((1536,), eps=1e-05) + (norm2): Glm4vMoeRMSNorm((1536,), eps=1e-05) + (attn): Glm4vMoeVisionAttention( + (qkv): Linear(in_features=1536, out_features=4608, bias=False) + (proj): Linear(in_features=1536, out_features=1536, bias=False) + ) + (mlp): Glm4vMoeisionMlp( + (gate_proj): Linear(in_features=1536, out_features=4096, bias=False) + (up_proj): Linear(in_features=1536, out_features=4096, bias=False) + (down_proj): Linear(in_features=4096, out_features=1536, bias=False) + (act_fn): SiLUActivation() + ) + ) +), ModuleList( + (0-23): 24 x Glm4vVisionBlock( + (norm1): Glm4vRMSNorm((1536,), eps=1e-05) + (norm2): Glm4vRMSNorm((1536,), eps=1e-05) + (attn): Glm4vVisionAttention( + (qkv): Linear(in_features=1536, out_features=4608, bias=False) + (proj): Linear(in_features=1536, out_features=1536, bias=False) + ) + (mlp): Glm4VisionMlp( + (gate_proj): Linear(in_features=1536, out_features=4096, bias=False) + (up_proj): Linear(in_features=1536, out_features=4096, bias=False) + (down_proj): Linear(in_features=4096, out_features=1536, bias=False) + (act_fn): SiLUActivation() + ) + ) +), ModuleList( + (0-39): 40 x GlmImageVisionBlock( + (norm1): LayerNorm((1536,), eps=1e-06, elementwise_affine=True) + (norm2): LayerNorm((1536,), eps=1e-06, elementwise_affine=True) + (attn): GlmImageVisionAttention( + (qkv): Linear(in_features=1536, out_features=4608, bias=True) + (proj): Linear(in_features=1536, out_features=1536, bias=True) + ) + (mlp): GlmImageVisionMLP( + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1536, out_features=6144, bias=True) + (fc2): Linear(in_features=6144, out_features=1536, bias=True) + ) + ) +), ModuleList( + (0-11): 12 x GPT2Block( + (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): GPT2Attention( + (c_attn): Conv1D(nf=2304, nx=768) + (c_proj): Conv1D(nf=768, nx=768) + (attn_dropout): Dropout(p=0.1, inplace=False) + (resid_dropout): Dropout(p=0.1, inplace=False) + ) + (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): GPT2MLP( + (c_fc): Conv1D(nf=3072, nx=768) + (c_proj): Conv1D(nf=768, nx=3072) + (act): NewGELUActivation() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x GPT2Block( + (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): GPT2Attention( + (c_attn): Conv1D(nf=2304, nx=768) + (c_proj): Conv1D(nf=768, nx=768) + (attn_dropout): Dropout(p=0.1, inplace=False) + (resid_dropout): Dropout(p=0.1, inplace=False) + ) + (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): GPT2MLP( + (c_fc): Conv1D(nf=3072, nx=768) + (c_proj): Conv1D(nf=768, nx=3072) + (act): NewGELUActivation() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x GPTBigCodeBlock( + (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): GPTBigCodeAttention( + (c_attn): Linear(in_features=768, out_features=896, bias=True) + (c_proj): Linear(in_features=768, out_features=768, bias=True) + (resid_dropout): Dropout(p=0.1, inplace=False) + ) + (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): GPTBigCodeMLP( + (c_fc): Linear(in_features=768, out_features=3072, bias=True) + (c_proj): Linear(in_features=3072, out_features=768, bias=True) + (act): GELUTanh() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-5): 6 x GroundingDinoEncoderLayer( + (text_enhancer_layer): GroundingDinoTextEnhancerLayer( + (self_attn): GroundingDinoMultiheadAttention( + (query): Linear(in_features=256, out_features=256, bias=True) + (key): Linear(in_features=256, out_features=256, bias=True) + (value): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (layer_norm_before): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm_after): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation): ReLU() + ) + (fusion_layer): GroundingDinoFusionLayer( + (layer_norm_vision): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm_text): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (attn): GroundingDinoBiMultiHeadAttention( + (vision_proj): Linear(in_features=256, out_features=1024, bias=True) + (text_proj): Linear(in_features=256, out_features=1024, bias=True) + (values_vision_proj): Linear(in_features=256, out_features=1024, bias=True) + (values_text_proj): Linear(in_features=256, out_features=1024, bias=True) + (out_vision_proj): Linear(in_features=1024, out_features=256, bias=True) + (out_text_proj): Linear(in_features=1024, out_features=256, bias=True) + ) + (drop_path): GroundingDinoDropPath(p=0.1) + ) + (deformable_layer): GroundingDinoDeformableLayer( + (self_attn): GroundingDinoMultiscaleDeformableAttention( + (attn): MultiScaleDeformableAttention() + (sampling_offsets): Linear(in_features=256, out_features=256, bias=True) + (attention_weights): Linear(in_features=256, out_features=128, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) + ) +), ModuleList( + (0-23): 24 x HeliumDecoderLayer( + (self_attn): HeliumAttention( + (q_proj): Linear(in_features=2560, out_features=2560, bias=False) + (k_proj): Linear(in_features=2560, out_features=2560, bias=False) + (v_proj): Linear(in_features=2560, out_features=2560, bias=False) + (o_proj): Linear(in_features=2560, out_features=2560, bias=False) + ) + (mlp): HeliumMLP( + (gate_proj): Linear(in_features=2560, out_features=7040, bias=False) + (up_proj): Linear(in_features=2560, out_features=7040, bias=False) + (down_proj): Linear(in_features=7040, out_features=2560, bias=False) + (act_fn): SiLUActivation() + ) + (input_layernorm): HeliumRMSNorm((2560,), eps=1e-08) + (post_attention_layernorm): HeliumRMSNorm((2560,), eps=1e-08) + ) +), ModuleList( + (0-11): 12 x HubertEncoderLayer( + (attention): HubertAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): HubertFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x IBertLayer( + (attention): IBertAttention( + (self): IBertSelfAttention( + (query): (QuantLinear() weight_bit=8, quant_mode=False) + (key): (QuantLinear() weight_bit=8, quant_mode=False) + (value): (QuantLinear() weight_bit=8, quant_mode=False) + (query_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (key_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (value_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (output_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (dropout): Dropout(p=0.1, inplace=False) + (softmax): IntSoftmax( + (act): QuantAct(activation_bit=16, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + ) + ) + (output): IBertSelfOutput( + (dense): (QuantLinear() weight_bit=8, quant_mode=False) + (ln_input_act): QuantAct(activation_bit=22, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (LayerNorm): IntLayerNorm( + (activation): QuantAct(activation_bit=32, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + ) + (output_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): IBertIntermediate( + (dense): (QuantLinear() weight_bit=8, quant_mode=False) + (intermediate_act_fn): IntGELU( + (activation_fn): GELU(approximate='none') + ) + (output_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + ) + (output): IBertOutput( + (dense): (QuantLinear() weight_bit=8, quant_mode=False) + (ln_input_act): QuantAct(activation_bit=22, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (LayerNorm): IntLayerNorm( + (activation): QuantAct(activation_bit=32, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + ) + (output_activation): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (dropout): Dropout(p=0.1, inplace=False) + ) + (pre_intermediate_act): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + (pre_output_act): QuantAct(activation_bit=8, quant_mode: False, Act_min: -0.00, Act_max: 0.00) + ) +), ModuleList( + (0-31): 32 x IdeficsDecoderLayer( + (self_attn): IdeficsAttention( + (q_proj): Linear(in_features=4096, out_features=4096, bias=False) + (k_proj): Linear(in_features=4096, out_features=4096, bias=False) + (v_proj): Linear(in_features=4096, out_features=4096, bias=False) + (o_proj): Linear(in_features=4096, out_features=4096, bias=False) + (rotary_emb): IdeficsEmbedding() + ) + (mlp): IdeficsMLP( + (gate_proj): Linear(in_features=4096, out_features=11008, bias=False) + (down_proj): Linear(in_features=11008, out_features=4096, bias=False) + (up_proj): Linear(in_features=4096, out_features=11008, bias=False) + (act_fn): SiLUActivation() + ) + (input_layernorm): IdeficsRMSNorm((4096,), eps=1e-06) + (post_attention_layernorm): IdeficsRMSNorm((4096,), eps=1e-06) + ) +), ModuleList( + (0-11): 12 x Idefics3EncoderLayer( + (self_attn): Idefics3VisionAttention( + (k_proj): Linear(in_features=1152, out_features=1152, bias=True) + (v_proj): Linear(in_features=1152, out_features=1152, bias=True) + (q_proj): Linear(in_features=1152, out_features=1152, bias=True) + (out_proj): Linear(in_features=1152, out_features=1152, bias=True) + ) + (layer_norm1): LayerNorm((1152,), eps=1e-06, elementwise_affine=True) + (mlp): Idefics3VisionMLP( + (activation_fn): GELUTanh() + (fc1): Linear(in_features=1152, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=1152, bias=True) + ) + (layer_norm2): LayerNorm((1152,), eps=1e-06, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x IJepaLayer( + (attention): IJepaAttention( + (attention): IJepaSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): IJepaSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): IJepaIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): IJepaOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x ImageGPTBlock( + (ln_1): ImageGPTLayerNorm() + (attn): ImageGPTAttention( + (c_attn): Conv1D(nf=1536, nx=512) + (c_proj): Conv1D(nf=512, nx=512) + (attn_dropout): Dropout(p=0.1, inplace=False) + (resid_dropout): Dropout(p=0.1, inplace=False) + ) + (ln_2): ImageGPTLayerNorm() + (mlp): ImageGPTMLP( + (c_fc): Conv1D(nf=2048, nx=512) + (c_proj): Conv1D(nf=512, nx=2048) + (act): QuickGELUActivation() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-1): 2 x InformerEncoderLayer( + (self_attn_layer_norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=64, out_features=32, bias=True) + (fc2): Linear(in_features=32, out_features=64, bias=True) + (final_layer_norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (self_attn): InformerProbSparseAttention( + (k_proj): Linear(in_features=64, out_features=64, bias=True) + (v_proj): Linear(in_features=64, out_features=64, bias=True) + (q_proj): Linear(in_features=64, out_features=64, bias=True) + (out_proj): Linear(in_features=64, out_features=64, bias=True) + ) + ) +), ModuleList( + (0-23): 24 x InternVLVisionLayer( + (attention): InternVLVisionAttention( + (q_proj): Linear(in_features=1024, out_features=1024, bias=False) + (k_proj): Linear(in_features=1024, out_features=1024, bias=False) + (v_proj): Linear(in_features=1024, out_features=1024, bias=False) + (projection_layer): Linear(in_features=1024, out_features=1024, bias=True) + (projection_dropout): Identity() + (q_norm): Identity() + (k_norm): Identity() + ) + (mlp): InternVLVisionMLP( + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + ) + (layernorm_before): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (layernorm_after): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (dropout): Dropout(p=0.0, inplace=False) + ) +), ModuleList( + (0-11): 12 x JetMoeDecoderLayer( + (mlp): JetMoeMoE( + (activation): SiLUActivation() + (input_linear): JetMoeParallelExperts() + (output_linear): JetMoeParallelExperts() + (router): JetMoeTopKGating( + (layer): Linear(in_features=2048, out_features=8, bias=False) + ) + ) + (input_layernorm): JetMoeRMSNorm((2048,), eps=1e-06) + (post_attention_layernorm): JetMoeRMSNorm((2048,), eps=1e-06) + (self_attention): JetMoeAttention( + (experts): JetMoeMoA( + (input_linear): JetMoeParallelExperts() + (output_linear): JetMoeParallelExperts() + (router): JetMoeTopKGating( + (layer): Linear(in_features=2048, out_features=8, bias=False) + ) + ) + (kv_proj): Linear(in_features=2048, out_features=4096, bias=False) + ) + ) +), ModuleList( + (0-11): 12 x LayoutLMLayer( + (attention): LayoutLMAttention( + (self): LayoutLMSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LayoutLMSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LayoutLMIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LayoutLMOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x LayoutLMv2Layer( + (attention): LayoutLMv2Attention( + (self): LayoutLMv2SelfAttention( + (qkv_linear): Linear(in_features=768, out_features=2304, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LayoutLMv2SelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LayoutLMv2Intermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LayoutLMv2Output( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x LayoutLMv3Layer( + (attention): LayoutLMv3Attention( + (self): LayoutLMv3SelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LayoutLMv3SelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LayoutLMv3Intermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LayoutLMv3Output( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x LiltLayer( + (attention): LiltAttention( + (self): LiltSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (layout_query): Linear(in_features=192, out_features=192, bias=True) + (layout_key): Linear(in_features=192, out_features=192, bias=True) + (layout_value): Linear(in_features=192, out_features=192, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LiltSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (layout_output): LiltSelfOutput( + (dense): Linear(in_features=192, out_features=192, bias=True) + (LayerNorm): LayerNorm((192,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LiltIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LiltOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (layout_intermediate): LiltIntermediate( + (dense): Linear(in_features=192, out_features=768, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (layout_output): LiltOutput( + (dense): Linear(in_features=768, out_features=192, bias=True) + (LayerNorm): LayerNorm((192,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x LukeLayer( + (attention): LukeAttention( + (self): LukeSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (w2e_query): Linear(in_features=768, out_features=768, bias=True) + (e2w_query): Linear(in_features=768, out_features=768, bias=True) + (e2e_query): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LukeSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LukeIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LukeOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x LxmertLayer( + (attention): LxmertSelfAttentionLayer( + (self): LxmertAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): LxmertAttentionOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): LxmertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): LxmertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x M2M100EncoderLayer( + (self_attn): M2M100Attention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x MarianEncoderLayer( + (self_attn): MarianAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x MarkupLMLayer( + (attention): MarkupLMAttention( + (self): MarkupLMSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): MarkupLMSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): MarkupLMIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): MarkupLMOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-5): 6 x Mask2FormerPixelDecoderEncoderLayer( + (self_attn): Mask2FormerPixelDecoderEncoderMultiscaleDeformableAttention( + (sampling_offsets): Linear(in_features=256, out_features=192, bias=True) + (attention_weights): Linear(in_features=256, out_features=96, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x MBartEncoderLayer( + (self_attn): MBartAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x MegatronBertLayer( + (attention): MegatronBertAttention( + (ln): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (self): MegatronBertSelfAttention( + (query): Linear(in_features=1024, out_features=1024, bias=True) + (key): Linear(in_features=1024, out_features=1024, bias=True) + (value): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): MegatronBertSelfOutput( + (dense): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (ln): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (intermediate): MegatronBertIntermediate( + (dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): MegatronBertOutput( + (dense): Linear(in_features=4096, out_features=1024, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-47): 48 x MLCDEncoderLayer( + (self_attn): MLCDAttention( + (k_proj): Linear(in_features=1664, out_features=1664, bias=True) + (v_proj): Linear(in_features=1664, out_features=1664, bias=True) + (q_proj): Linear(in_features=1664, out_features=1664, bias=True) + (out_proj): Linear(in_features=1664, out_features=1664, bias=True) + ) + (layer_norm1): LayerNorm((1664,), eps=1e-05, elementwise_affine=True) + (mlp): MLCDMLP( + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1664, out_features=8192, bias=True) + (fc2): Linear(in_features=8192, out_features=1664, bias=True) + ) + (layer_norm2): LayerNorm((1664,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x MMGroundingDinoEncoderLayer( + (text_enhancer_layer): MMGroundingDinoTextEnhancerLayer( + (self_attn): MMGroundingDinoMultiheadAttention( + (query): Linear(in_features=256, out_features=256, bias=True) + (key): Linear(in_features=256, out_features=256, bias=True) + (value): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (layer_norm_before): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm_after): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation): ReLU() + ) + (fusion_layer): MMGroundingDinoFusionLayer( + (layer_norm_vision): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm_text): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (attn): MMGroundingDinoBiMultiHeadAttention( + (vision_proj): Linear(in_features=256, out_features=1024, bias=True) + (text_proj): Linear(in_features=256, out_features=1024, bias=True) + (values_vision_proj): Linear(in_features=256, out_features=1024, bias=True) + (values_text_proj): Linear(in_features=256, out_features=1024, bias=True) + (out_vision_proj): Linear(in_features=1024, out_features=256, bias=True) + (out_text_proj): Linear(in_features=1024, out_features=256, bias=True) + ) + (drop_path): MMGroundingDinoDropPath(p=0.1) + ) + (deformable_layer): MMGroundingDinoDeformableLayer( + (self_attn): MMGroundingDinoMultiscaleDeformableAttention( + (attn): MultiScaleDeformableAttention() + (sampling_offsets): Linear(in_features=256, out_features=256, bias=True) + (attention_weights): Linear(in_features=256, out_features=128, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) + ) +), ModuleList( + (0-5): 6 x FFNLayer( + (intermediate): MobileBertIntermediate( + (dense): Linear(in_features=128, out_features=512, bias=True) + (intermediate_act_fn): ReLU() + ) + (output): FFNOutput( + (dense): Linear(in_features=512, out_features=128, bias=True) + (LayerNorm): NoNorm() + ) + ) +), ModuleList( + (0-11): 12 x MPNetLayer( + (attention): MPNetAttention( + (attn): MPNetSelfAttention( + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (o): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (intermediate): MPNetIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): MPNetOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-23): 24 x MptBlock( + (norm_1): LayerNorm((2048,), eps=1e-05, elementwise_affine=True) + (attn): MptAttention( + (Wqkv): Linear(in_features=2048, out_features=6144, bias=False) + (out_proj): Linear(in_features=2048, out_features=2048, bias=False) + ) + (norm_2): LayerNorm((2048,), eps=1e-05, elementwise_affine=True) + (ffn): MptMLP( + (up_proj): Linear(in_features=2048, out_features=8192, bias=False) + (act): GELU(approximate='none') + (down_proj): Linear(in_features=8192, out_features=2048, bias=False) + ) + (resid_attn_dropout): Dropout(p=0, inplace=False) + ) +), ModuleList( + (0-11): 12 x MraLayer( + (attention): MraAttention( + (self): MraSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): MraSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): MraIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): MraOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-7): 8 x MT5Block( + (layer): ModuleList( + (0): MT5LayerSelfAttention( + (SelfAttention): MT5Attention( + (q): Linear(in_features=512, out_features=384, bias=False) + (k): Linear(in_features=512, out_features=384, bias=False) + (v): Linear(in_features=512, out_features=384, bias=False) + (o): Linear(in_features=384, out_features=512, bias=False) + ) + (layer_norm): MT5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + (1): MT5LayerFF( + (DenseReluDense): MT5DenseGatedActDense( + (wi_0): Linear(in_features=512, out_features=1024, bias=False) + (wi_1): Linear(in_features=512, out_features=1024, bias=False) + (wo): Linear(in_features=1024, out_features=512, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + (act): NewGELUActivation() + ) + (layer_norm): MT5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + ) +), ModuleList( + (0-11): 12 x MvpEncoderLayer( + (self_attn): MvpAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x NystromformerLayer( + (attention): NystromformerAttention( + (self): NystromformerSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + (conv): Conv2d(12, 12, kernel_size=(65, 1), stride=(1, 1), padding=(32, 0), groups=12, bias=False) + ) + (output): NystromformerSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): NystromformerIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): NewGELUActivation() + ) + (output): NystromformerOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0): OmDetTurboEncoderLayer( + (self_attn): OmDetTurboMultiheadAttention( + (query): Linear(in_features=256, out_features=256, bias=True) + (key): Linear(in_features=256, out_features=256, bias=True) + (value): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (dropout): Dropout(p=0.0, inplace=False) + (activation_fn): ReLU() + (encoder_feedforward_dropout): Dropout(p=0.0, inplace=False) + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x OneFormerPixelDecoderEncoderLayer( + (self_attn): OneFormerPixelDecoderEncoderMultiscaleDeformableAttention( + (sampling_offsets): Linear(in_features=256, out_features=192, bias=True) + (attention_weights): Linear(in_features=256, out_features=96, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x OPTDecoderLayer( + (self_attn): OPTAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (activation_fn): ReLU() + (self_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x ParakeetEncoderBlock( + (feed_forward1): ParakeetEncoderFeedForward( + (linear1): Linear(in_features=1024, out_features=4096, bias=True) + (activation): SiLUActivation() + (linear2): Linear(in_features=4096, out_features=1024, bias=True) + ) + (self_attn): ParakeetEncoderAttention( + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (o_proj): Linear(in_features=1024, out_features=1024, bias=True) + (relative_k_proj): Linear(in_features=1024, out_features=1024, bias=False) + ) + (conv): ParakeetEncoderConvolutionModule( + (activation): SiLUActivation() + (pointwise_conv1): Conv1d(1024, 2048, kernel_size=(1,), stride=(1,)) + (depthwise_conv): Conv1d(1024, 1024, kernel_size=(9,), stride=(1,), padding=(4,), groups=1024) + (norm): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (pointwise_conv2): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,)) + ) + (feed_forward2): ParakeetEncoderFeedForward( + (linear1): Linear(in_features=1024, out_features=4096, bias=True) + (activation): SiLUActivation() + (linear2): Linear(in_features=4096, out_features=1024, bias=True) + ) + (norm_feed_forward1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (norm_self_att): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (norm_conv): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (norm_feed_forward2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (norm_out): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-2): 3 x PatchTSTEncoderLayer( + (self_attn): PatchTSTAttention( + (k_proj): Linear(in_features=128, out_features=128, bias=True) + (v_proj): Linear(in_features=128, out_features=128, bias=True) + (q_proj): Linear(in_features=128, out_features=128, bias=True) + (out_proj): Linear(in_features=128, out_features=128, bias=True) + ) + (dropout_path1): Identity() + (norm_sublayer1): PatchTSTBatchNorm( + (batchnorm): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + (ff): Sequential( + (0): Linear(in_features=128, out_features=512, bias=True) + (1): GELUActivation() + (2): Identity() + (3): Linear(in_features=512, out_features=128, bias=True) + ) + (dropout_path3): Identity() + (norm_sublayer3): PatchTSTBatchNorm( + (batchnorm): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) +), ModuleList( + (0-11): 12 x PegasusEncoderLayer( + (self_attn): PegasusAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-15): 16 x PegasusXDecoderLayer( + (self_attn): PegasusXAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=False) + (v_proj): Linear(in_features=1024, out_features=1024, bias=False) + (q_proj): Linear(in_features=1024, out_features=1024, bias=False) + (out_proj): Linear(in_features=1024, out_features=1024, bias=False) + ) + (activation_fn): GELUActivation() + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (encoder_attn): PegasusXAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=False) + (v_proj): Linear(in_features=1024, out_features=1024, bias=False) + (q_proj): Linear(in_features=1024, out_features=1024, bias=False) + (out_proj): Linear(in_features=1024, out_features=1024, bias=False) + ) + (encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-31): 32 x PixioLayer( + (norm1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True) + (attention): PixioAttention( + (attention): PixioSelfAttention( + (query): Linear(in_features=1280, out_features=1280, bias=True) + (key): Linear(in_features=1280, out_features=1280, bias=True) + (value): Linear(in_features=1280, out_features=1280, bias=True) + ) + (output): PixioSelfOutput( + (dense): Linear(in_features=1280, out_features=1280, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (drop_path): Identity() + (norm2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True) + (mlp): PixioMLP( + (fc1): Linear(in_features=1280, out_features=5120, bias=True) + (activation): GELUActivation() + (fc2): Linear(in_features=5120, out_features=1280, bias=True) + ) + ) +), ModuleList( + (0-5): 6 x PLBartEncoderLayer( + (self_attn): PLBartAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (self_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x ProphetNetEncoderLayer( + (self_attn): ProphetNetAttention( + (key_proj): Linear(in_features=1024, out_features=1024, bias=True) + (value_proj): Linear(in_features=1024, out_features=1024, bias=True) + (query_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (feed_forward): ProphetNetFeedForward( + (activation_fn): GELUActivation() + (intermediate): Linear(in_features=1024, out_features=4096, bias=True) + (output): Linear(in_features=4096, out_features=1024, bias=True) + ) + (feed_forward_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-31): 32 x Qwen2AudioEncoderLayer( + (self_attn): Qwen2AudioAttention( + (k_proj): Linear(in_features=1280, out_features=1280, bias=False) + (v_proj): Linear(in_features=1280, out_features=1280, bias=True) + (q_proj): Linear(in_features=1280, out_features=1280, bias=True) + (out_proj): Linear(in_features=1280, out_features=1280, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1280, out_features=5120, bias=True) + (fc2): Linear(in_features=5120, out_features=1280, bias=True) + (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x ReformerLayer( + (attention): ReformerAttention( + (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True) + (self_attention): LocalSelfAttention( + (query): Linear(in_features=256, out_features=768, bias=False) + (key): Linear(in_features=256, out_features=768, bias=False) + (value): Linear(in_features=256, out_features=768, bias=False) + ) + (output): ReformerSelfOutput( + (dense): Linear(in_features=768, out_features=256, bias=False) + ) + ) + (feed_forward): ChunkReformerFeedForward( + (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True) + (dense): ReformerFeedForwardDense( + (act_fn): ReLU() + (dense): Linear(in_features=256, out_features=512, bias=True) + ) + (output): ReformerFeedForwardOutput( + (dense): Linear(in_features=512, out_features=256, bias=True) + ) + ) + ) +), ModuleList( + (0-31): 32 x RemBertLayer( + (attention): RemBertAttention( + (self): RemBertSelfAttention( + (query): Linear(in_features=1152, out_features=1152, bias=True) + (key): Linear(in_features=1152, out_features=1152, bias=True) + (value): Linear(in_features=1152, out_features=1152, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (output): RemBertSelfOutput( + (dense): Linear(in_features=1152, out_features=1152, bias=True) + (LayerNorm): LayerNorm((1152,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): RemBertIntermediate( + (dense): Linear(in_features=1152, out_features=4608, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): RemBertOutput( + (dense): Linear(in_features=4608, out_features=1152, bias=True) + (LayerNorm): LayerNorm((1152,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x RobertaLayer( + (attention): RobertaAttention( + (self): RobertaSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): RobertaSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): RobertaIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): RobertaOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x RobertaPreLayerNormLayer( + (attention): RobertaPreLayerNormAttention( + (self): RobertaPreLayerNormSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): RobertaPreLayerNormSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) + (intermediate): RobertaPreLayerNormIntermediate( + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): RobertaPreLayerNormOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x RoCBertLayer( + (attention): RoCBertAttention( + (self): RoCBertSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): RoCBertSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): RoCBertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): RoCBertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x RoFormerLayer( + (attention): RoFormerAttention( + (self): RoFormerSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): RoFormerSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): RoFormerIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): RoFormerOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0): RTDetrEncoderLayer( + (self_attn): RTDetrMultiheadAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x RTDetrV2DecoderLayer( + (self_attn): RTDetrV2MultiheadAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (activation_fn): ReLU() + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (encoder_attn): RTDetrV2MultiscaleDeformableAttention( + (sampling_offsets): Linear(in_features=256, out_features=192, bias=True) + (attention_weights): Linear(in_features=256, out_features=96, bias=True) + (value_proj): Linear(in_features=256, out_features=256, bias=True) + (output_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (encoder_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=256, out_features=1024, bias=True) + (fc2): Linear(in_features=1024, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-3): 4 x Sam2VideoMemoryAttentionLayer( + (self_attn): Sam2VideoRoPEAttention( + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (o_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (cross_attn_image): Sam2VideoRoPEAttention( + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (k_proj): Linear(in_features=64, out_features=256, bias=True) + (v_proj): Linear(in_features=64, out_features=256, bias=True) + (o_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (linear1): Linear(in_features=256, out_features=2048, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + (linear2): Linear(in_features=2048, out_features=256, bias=True) + (layer_norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm3): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (dropout1): Dropout(p=0.1, inplace=False) + (dropout2): Dropout(p=0.1, inplace=False) + (dropout3): Dropout(p=0.1, inplace=False) + (activation): ReLU() + ) +), ModuleList( + (0-3): 4 x Sam3TrackerVideoMemoryAttentionLayer( + (self_attn): Sam3TrackerVideoRoPEAttention( + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (o_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (cross_attn_image): Sam3TrackerVideoRoPEAttention( + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (k_proj): Linear(in_features=64, out_features=256, bias=True) + (v_proj): Linear(in_features=64, out_features=256, bias=True) + (o_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (linear1): Linear(in_features=256, out_features=2048, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + (linear2): Linear(in_features=2048, out_features=256, bias=True) + (layer_norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (layer_norm3): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (dropout1): Dropout(p=0.1, inplace=False) + (dropout2): Dropout(p=0.1, inplace=False) + (dropout3): Dropout(p=0.1, inplace=False) + (activation): ReLU() + ) +), ModuleList( + (0-23): 24 x SeamlessM4TConformerEncoderLayer( + (ffn1_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn1): SeamlessM4TConformerFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (self_attn_dropout): Dropout(p=0.0, inplace=False) + (self_attn): SeamlessM4TConformerSelfAttention( + (linear_q): Linear(in_features=1024, out_features=1024, bias=True) + (linear_k): Linear(in_features=1024, out_features=1024, bias=True) + (linear_v): Linear(in_features=1024, out_features=1024, bias=True) + (linear_out): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + (linear_pos): Linear(in_features=1024, out_features=1024, bias=False) + ) + (conv_module): SeamlessM4TConformerConvolutionModule( + (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (pointwise_conv1): Conv1d(1024, 2048, kernel_size=(1,), stride=(1,), bias=False) + (glu): GLU(dim=1) + (depthwise_conv): Conv1d(1024, 1024, kernel_size=(31,), stride=(1,), padding=same, groups=1024, bias=False) + (batch_norm): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activation): SiLU() + (pointwise_conv2): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), bias=False) + (dropout): Dropout(p=0.0, inplace=False) + ) + (ffn2_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn2): SeamlessM4TConformerFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x SeamlessM4Tv2ConformerEncoderLayer( + (ffn1_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn1): SeamlessM4Tv2ConformerFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (self_attn_dropout): Dropout(p=0.0, inplace=False) + (self_attn): SeamlessM4Tv2ConformerSelfAttention( + (linear_q): Linear(in_features=1024, out_features=1024, bias=True) + (linear_k): Linear(in_features=1024, out_features=1024, bias=True) + (linear_v): Linear(in_features=1024, out_features=1024, bias=True) + (linear_out): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + (distance_embedding): Embedding(73, 64) + ) + (conv_module): SeamlessM4Tv2ConformerConvolutionModule( + (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (pointwise_conv1): Conv1d(1024, 2048, kernel_size=(1,), stride=(1,), bias=False) + (glu): GLU(dim=1) + (depthwise_conv): Conv1d(1024, 1024, kernel_size=(31,), stride=(1,), groups=1024, bias=False) + (depthwise_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation): SiLU() + (pointwise_conv2): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), bias=False) + (dropout): Dropout(p=0.0, inplace=False) + ) + (ffn2_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn2): SeamlessM4Tv2ConformerFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x SEWEncoderLayer( + (attention): SEWAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): SEWFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x SEWDLayer( + (attention): SEWDAttention( + (self): DisentangledSelfAttention( + (query_proj): Linear(in_features=768, out_features=768, bias=True) + (key_proj): Linear(in_features=768, out_features=768, bias=True) + (value_proj): Linear(in_features=768, out_features=768, bias=True) + (pos_dropout): StableDropout() + (dropout): StableDropout() + ) + (output): SEWDSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-07, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): SEWDIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): SEWDOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-07, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x Siglip2EncoderLayer( + (layer_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (self_attn): Siglip2Attention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (layer_norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Siglip2MLP( + (activation_fn): GELUTanh() + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + ) +), ModuleList( + (0-11): 12 x SiglipEncoderLayer( + (layer_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (self_attn): SiglipAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (layer_norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): SiglipMLP( + (activation_fn): GELUTanh() + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + ) +), ModuleList( + (0-11): 12 x SmolVLMEncoderLayer( + (self_attn): SmolVLMVisionAttention( + (k_proj): Linear(in_features=1152, out_features=1152, bias=True) + (v_proj): Linear(in_features=1152, out_features=1152, bias=True) + (q_proj): Linear(in_features=1152, out_features=1152, bias=True) + (out_proj): Linear(in_features=1152, out_features=1152, bias=True) + ) + (layer_norm1): LayerNorm((1152,), eps=1e-06, elementwise_affine=True) + (mlp): SmolVLMVisionMLP( + (activation_fn): GELUTanh() + (fc1): Linear(in_features=1152, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=1152, bias=True) + ) + (layer_norm2): LayerNorm((1152,), eps=1e-06, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x Speech2TextEncoderLayer( + (self_attn): Speech2TextAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-4): 5 x SpeechT5BatchNormConvLayer( + (conv): Conv1d(80, 256, kernel_size=(5,), stride=(1,), padding=(2,), bias=False) + (batch_norm): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activation): Tanh() + (dropout): Dropout(p=0.5, inplace=False) + ) +), ModuleList( + (0-11): 12 x SplinterLayer( + (attention): SplinterAttention( + (self): SplinterSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): SplinterSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): SplinterIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): SplinterOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x SqueezeBertModule( + (attention): SqueezeBertSelfAttention( + (query): Conv1d(768, 768, kernel_size=(1,), stride=(1,), groups=4) + (key): Conv1d(768, 768, kernel_size=(1,), stride=(1,), groups=4) + (value): Conv1d(768, 768, kernel_size=(1,), stride=(1,), groups=4) + (dropout): Dropout(p=0.1, inplace=False) + (softmax): Softmax(dim=-1) + (matmul_qk): MatMulWrapper() + (matmul_qkv): MatMulWrapper() + ) + (post_attention): ConvDropoutLayerNorm( + (conv1d): Conv1d(768, 768, kernel_size=(1,), stride=(1,)) + (layernorm): SqueezeBertLayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (intermediate): ConvActivation( + (conv1d): Conv1d(768, 3072, kernel_size=(1,), stride=(1,), groups=4) + (act): GELUActivation() + ) + (output): ConvDropoutLayerNorm( + (conv1d): Conv1d(3072, 768, kernel_size=(1,), stride=(1,), groups=4) + (layernorm): SqueezeBertLayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-5): 6 x T5Block( + (layer): ModuleList( + (0): T5LayerSelfAttention( + (SelfAttention): T5Attention( + (q): Linear(in_features=512, out_features=512, bias=False) + (k): Linear(in_features=512, out_features=512, bias=False) + (v): Linear(in_features=512, out_features=512, bias=False) + (o): Linear(in_features=512, out_features=512, bias=False) + ) + (layer_norm): T5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + (1): T5LayerFF( + (DenseReluDense): T5DenseActDense( + (wi): Linear(in_features=512, out_features=2048, bias=False) + (wo): Linear(in_features=2048, out_features=512, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + (act): ReLU() + ) + (layer_norm): T5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + ) +), ModuleList( + (0-5): 6 x TableTransformerEncoderLayer( + (self_attn): TableTransformerAttention( + (k_proj): Linear(in_features=256, out_features=256, bias=True) + (v_proj): Linear(in_features=256, out_features=256, bias=True) + (q_proj): Linear(in_features=256, out_features=256, bias=True) + (out_proj): Linear(in_features=256, out_features=256, bias=True) + ) + (self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + (activation_fn): ReLU() + (fc1): Linear(in_features=256, out_features=2048, bias=True) + (fc2): Linear(in_features=2048, out_features=256, bias=True) + (final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x TapasLayer( + (attention): TapasAttention( + (self): TapasSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): TapasSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): TapasIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): TapasOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-1): 2 x TimeSeriesTransformerEncoderLayer( + (self_attn): TimeSeriesTransformerAttention( + (k_proj): Linear(in_features=64, out_features=64, bias=True) + (v_proj): Linear(in_features=64, out_features=64, bias=True) + (q_proj): Linear(in_features=64, out_features=64, bias=True) + (out_proj): Linear(in_features=64, out_features=64, bias=True) + ) + (self_attn_layer_norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=64, out_features=32, bias=True) + (fc2): Linear(in_features=32, out_features=64, bias=True) + (final_layer_norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x TvpEncodeLayer( + (attention): TvpAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (attn_dropout): Dropout(p=0.1, inplace=False) + (dense): Linear(in_features=768, out_features=768, bias=True) + (layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (intermediate): TvpIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): TvpOutputLayer( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-23): 24 x UdopBlock( + (layer): ModuleList( + (0): UdopLayerSelfAttention( + (SelfAttention): UdopAttention( + (q): Linear(in_features=1024, out_features=1024, bias=False) + (k): Linear(in_features=1024, out_features=1024, bias=False) + (v): Linear(in_features=1024, out_features=1024, bias=False) + (o): Linear(in_features=1024, out_features=1024, bias=False) + ) + (layer_norm): UdopLayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + (1): UdopLayerFF( + (DenseReluDense): UdopDenseActDense( + (wi): Linear(in_features=1024, out_features=4096, bias=False) + (wo): Linear(in_features=4096, out_features=1024, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + (act): ReLU() + ) + (layer_norm): UdopLayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + ) +), ModuleList( + (0-7): 8 x UMT5Block( + (layer): ModuleList( + (0): UMT5LayerSelfAttention( + (SelfAttention): UMT5Attention( + (q): Linear(in_features=512, out_features=384, bias=False) + (k): Linear(in_features=512, out_features=384, bias=False) + (v): Linear(in_features=512, out_features=384, bias=False) + (o): Linear(in_features=384, out_features=512, bias=False) + (relative_attention_bias): Embedding(32, 6) + ) + (layer_norm): UMT5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + (1): UMT5LayerFF( + (DenseReluDense): UMT5DenseGatedActDense( + (wi_0): Linear(in_features=512, out_features=1024, bias=False) + (wi_1): Linear(in_features=512, out_features=1024, bias=False) + (wo): Linear(in_features=1024, out_features=512, bias=False) + (dropout): Dropout(p=0.1, inplace=False) + (act): NewGELUActivation() + ) + (layer_norm): UMT5LayerNorm() + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + ) +), ModuleList( + (0-11): 12 x UniSpeechEncoderLayer( + (attention): UniSpeechAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): UniSpeechFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x UniSpeechSatEncoderLayer( + (attention): UniSpeechSatAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): UniSpeechSatFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x UnivNetKernelPredictorResidualBlock( + (dropout): Dropout(p=0.0, inplace=False) + (conv1): Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(1,)) + (conv2): Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(1,)) + ) +), ModuleList( + (0-11): 12 x VideoLlama3VisionEncoderLayer( + (layer_norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (self_attn): VideoLlama3VisionAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (layer_norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): VideoLlama3VisionMLP( + (activation_fn): GELUTanh() + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + ) +), ModuleList( + (0-11): 12 x VideoMAELayer( + (attention): VideoMAEAttention( + (attention): VideoMAESelfAttention( + (query): Linear(in_features=768, out_features=768, bias=False) + (key): Linear(in_features=768, out_features=768, bias=False) + (value): Linear(in_features=768, out_features=768, bias=False) + ) + (output): VideoMAESelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): VideoMAEIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): VideoMAEOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x ViltLayer( + (attention): ViltAttention( + (attention): ViltSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (output): ViltSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): ViltIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ViltOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x VisualBertLayer( + (attention): VisualBertAttention( + (self): VisualBertSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): VisualBertSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): VisualBertIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): VisualBertOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-11): 12 x ViTLayer( + (attention): ViTAttention( + (attention): ViTSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): ViTSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): ViTIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ViTOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x ViTMAELayer( + (attention): ViTMAEAttention( + (attention): ViTMAESelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): ViTMAESelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): ViTMAEIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ViTMAEOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x ViTMSNLayer( + (attention): ViTMSNAttention( + (attention): ViTMSNSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): ViTMSNSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): ViTMSNIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): ViTMSNOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +), ModuleList( + (0-5): 6 x VitsEncoderLayer( + (attention): VitsAttention( + (k_proj): Linear(in_features=192, out_features=192, bias=True) + (v_proj): Linear(in_features=192, out_features=192, bias=True) + (q_proj): Linear(in_features=192, out_features=192, bias=True) + (out_proj): Linear(in_features=192, out_features=192, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (feed_forward): VitsFeedForward( + (conv_1): Conv1d(192, 768, kernel_size=(3,), stride=(1,)) + (conv_2): Conv1d(768, 192, kernel_size=(3,), stride=(1,)) + (dropout): Dropout(p=0.1, inplace=False) + (act_fn): ReLU() + ) + (final_layer_norm): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x VivitLayer( + (attention): VivitAttention( + (attention): VivitSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): VivitSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): VivitIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + (intermediate_act_fn): FastGELUActivation() + ) + (output): VivitOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +), ModuleList( + (0-2): 3 x VJEPA2PoolerSelfAttentionLayer( + (layer_norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (self_attn): VJEPA2PoolerSelfAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (layer_norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): VJEPA2MLP( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (activation): GELUActivation() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + ) + ) +), ModuleList( + (0-31): 32 x VoxtralEncoderLayer( + (self_attn): VoxtralAttention( + (k_proj): Linear(in_features=1280, out_features=1280, bias=False) + (v_proj): Linear(in_features=1280, out_features=1280, bias=True) + (q_proj): Linear(in_features=1280, out_features=1280, bias=True) + (out_proj): Linear(in_features=1280, out_features=1280, bias=True) + ) + (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=1280, out_features=5120, bias=True) + (fc2): Linear(in_features=5120, out_features=1280, bias=True) + (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x Wav2Vec2EncoderLayer( + (attention): Wav2Vec2Attention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): Wav2Vec2FeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x Wav2Vec2BertEncoderLayer( + (ffn1_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn1): Wav2Vec2BertFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (self_attn_dropout): Dropout(p=0.0, inplace=False) + (self_attn): Wav2Vec2BertSelfAttention( + (linear_q): Linear(in_features=1024, out_features=1024, bias=True) + (linear_k): Linear(in_features=1024, out_features=1024, bias=True) + (linear_v): Linear(in_features=1024, out_features=1024, bias=True) + (linear_out): Linear(in_features=1024, out_features=1024, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + (distance_embedding): Embedding(73, 64) + ) + (conv_module): Wav2Vec2BertConvolutionModule( + (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (pointwise_conv1): Conv1d(1024, 2048, kernel_size=(1,), stride=(1,), bias=False) + (glu): GLU(dim=1) + (depthwise_conv): Conv1d(1024, 1024, kernel_size=(31,), stride=(1,), groups=1024, bias=False) + (depthwise_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (activation): SiLU() + (pointwise_conv2): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), bias=False) + (dropout): Dropout(p=0.1, inplace=False) + ) + (ffn2_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (ffn2): Wav2Vec2BertFeedForward( + (intermediate_dropout): Dropout(p=0.0, inplace=False) + (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True) + (intermediate_act_fn): SiLU() + (output_dense): Linear(in_features=4096, out_features=1024, bias=True) + (output_dropout): Dropout(p=0.0, inplace=False) + ) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x Wav2Vec2ConformerEncoderLayer( + (ffn1_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (ffn1): Wav2Vec2ConformerFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (self_attn_dropout): Dropout(p=0.1, inplace=False) + (self_attn): Wav2Vec2ConformerSelfAttention( + (linear_q): Linear(in_features=768, out_features=768, bias=True) + (linear_k): Linear(in_features=768, out_features=768, bias=True) + (linear_v): Linear(in_features=768, out_features=768, bias=True) + (linear_out): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + (linear_pos): Linear(in_features=768, out_features=768, bias=False) + ) + (conv_module): Wav2Vec2ConformerConvolutionModule( + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (pointwise_conv1): Conv1d(768, 1536, kernel_size=(1,), stride=(1,), bias=False) + (glu): GLU(dim=1) + (depthwise_conv): Conv1d(768, 768, kernel_size=(31,), stride=(1,), padding=(15,), groups=768, bias=False) + (batch_norm): BatchNorm1d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activation): GELUActivation() + (pointwise_conv2): Conv1d(768, 768, kernel_size=(1,), stride=(1,), bias=False) + (dropout): Dropout(p=0.1, inplace=False) + ) + (ffn2_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (ffn2): Wav2Vec2ConformerFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x WavLMEncoderLayer( + (attention): WavLMAttention( + (k_proj): Linear(in_features=768, out_features=768, bias=True) + (v_proj): Linear(in_features=768, out_features=768, bias=True) + (q_proj): Linear(in_features=768, out_features=768, bias=True) + (out_proj): Linear(in_features=768, out_features=768, bias=True) + (gru_rel_pos_linear): Linear(in_features=64, out_features=8, bias=True) + (rel_attn_embed): Embedding(320, 12) + ) + (dropout): Dropout(p=0.1, inplace=False) + (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (feed_forward): WavLMFeedForward( + (intermediate_dropout): Dropout(p=0.1, inplace=False) + (intermediate_dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + (output_dense): Linear(in_features=3072, out_features=768, bias=True) + (output_dropout): Dropout(p=0.1, inplace=False) + ) + (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-3): 4 x WhisperEncoderLayer( + (self_attn): WhisperAttention( + (k_proj): Linear(in_features=384, out_features=384, bias=False) + (v_proj): Linear(in_features=384, out_features=384, bias=True) + (q_proj): Linear(in_features=384, out_features=384, bias=True) + (out_proj): Linear(in_features=384, out_features=384, bias=True) + ) + (self_attn_layer_norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (activation_fn): GELUActivation() + (fc1): Linear(in_features=384, out_features=1536, bias=True) + (fc2): Linear(in_features=1536, out_features=384, bias=True) + (final_layer_norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x XGLMDecoderLayer( + (self_attn): XGLMAttention( + (k_proj): Linear(in_features=1024, out_features=1024, bias=True) + (v_proj): Linear(in_features=1024, out_features=1024, bias=True) + (q_proj): Linear(in_features=1024, out_features=1024, bias=True) + (out_proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (activation_fn): GELUActivation() + (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x XLMRobertaLayer( + (attention): XLMRobertaAttention( + (self): XLMRobertaSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): XLMRobertaSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): XLMRobertaIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): XLMRobertaOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +), ModuleList( + (0-35): 36 x XLMRobertaXLLayer( + (attention): XLMRobertaXLAttention( + (self): XLMRobertaXLSelfAttention( + (query): Linear(in_features=2560, out_features=2560, bias=True) + (key): Linear(in_features=2560, out_features=2560, bias=True) + (value): Linear(in_features=2560, out_features=2560, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): XLMRobertaXLSelfOutput( + (dense): Linear(in_features=2560, out_features=2560, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (self_attn_layer_norm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True) + ) + (intermediate): XLMRobertaXLIntermediate( + (dense): Linear(in_features=2560, out_features=10240, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): XLMRobertaXLOutput( + (dense): Linear(in_features=10240, out_features=2560, bias=True) + ) + (LayerNorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True) + ) +), ModuleList( + (0-23): 24 x XLNetLayer( + (rel_attn): XLNetRelativeAttention( + (layer_norm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (ff): XLNetFeedForward( + (layer_norm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) + (layer_1): Linear(in_features=1024, out_features=4096, bias=True) + (layer_2): Linear(in_features=4096, out_features=1024, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + (activation_function): GELUActivation() + ) + (dropout): Dropout(p=0.1, inplace=False) + ) +), ModuleList( + (0-31): 32 x xLSTMBlock( + (norm_mlstm): xLSTMRMSNorm() + (mlstm_layer): xLSTMLayer( + (q): Linear(in_features=4096, out_features=2048, bias=False) + (k): Linear(in_features=4096, out_features=2048, bias=False) + (v): Linear(in_features=4096, out_features=4096, bias=False) + (ogate_preact): Linear(in_features=4096, out_features=4096, bias=False) + (igate_preact): Linear(in_features=4096, out_features=8, bias=True) + (fgate_preact): Linear(in_features=4096, out_features=8, bias=True) + (ogate_act_fn): Sigmoid() + (mlstm_backend): xLSTMBackend( + xLSTMConfig { + "add_out_norm": true, + "autocast_kernel_dtype": "bfloat16", + "bos_token_id": 0, + "chunk_size": 64, + "chunkwise_kernel": "chunkwise--native_autograd", + "embedding_dim": 4096, + "eos_token_id": 2, + "eps": 1e-06, + "ffn_proj_factor": 2.667, + "ffn_round_up_to_multiple_of": 64, + "gate_soft_cap": 15.0, + "hidden_size": 4096, + "inference_state_dtype": "float32", + "max_inference_chunksize": 16384, + "mode": "inference", + "model_type": "xlstm", + "norm_eps": 1e-06, + "norm_reduction_force_float32": true, + "num_blocks": 32, + "num_heads": 8, + "num_hidden_layers": 32, + "output_logit_soft_cap": 30.0, + "pad_token_id": 1, + "qk_dim_factor": 0.5, + "return_last_states": true, + "sequence_kernel": "native_sequence__native", + "step_kernel": "native", + "tie_word_embeddings": false, + "transformers_version": "5.0.0.dev0", + "use_bias": false, + "use_cache": true, + "v_dim_factor": 1.0, + "vocab_size": 50304, + "weight_mode": "single" + } + + ) + (multihead_norm): xLSTMMultiHeadLayerNorm() + (out_proj): Linear(in_features=4096, out_features=4096, bias=False) + ) + (norm_ffn): xLSTMRMSNorm() + (ffn): xLSTMFeedForward( + (proj_up_gate): Linear(in_features=4096, out_features=10944, bias=False) + (proj_up): Linear(in_features=4096, out_features=10944, bias=False) + (proj_down): Linear(in_features=10944, out_features=4096, bias=False) + (act_fn): SiLU() + ) + ) +), ModuleList( + (0-11): 12 x XmodLayer( + (attention): XmodAttention( + (self): XmodSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): XmodSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): XmodIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): XmodOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + (adapter_modules): ModuleDict( + (en_XX): XmodAdapter( + (dense1): Linear(in_features=768, out_features=384, bias=True) + (dense2): Linear(in_features=384, out_features=768, bias=True) + (adapter_act_fn): GELUActivation() + ) + ) + ) + ) +), ModuleList( + (0-11): 12 x YolosLayer( + (attention): YolosAttention( + (attention): YolosSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + ) + (output): YolosSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + ) + (intermediate): YolosIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): YolosOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (dropout): Dropout(p=0.0, inplace=False) + ) + (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + ) +), ModuleList( + (0-11): 12 x YosoLayer( + (attention): YosoAttention( + (self): YosoSelfAttention( + (query): Linear(in_features=768, out_features=768, bias=True) + (key): Linear(in_features=768, out_features=768, bias=True) + (value): Linear(in_features=768, out_features=768, bias=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + (output): YosoSelfOutput( + (dense): Linear(in_features=768, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) + (intermediate): YosoIntermediate( + (dense): Linear(in_features=768, out_features=3072, bias=True) + (intermediate_act_fn): GELUActivation() + ) + (output): YosoOutput( + (dense): Linear(in_features=3072, out_features=768, bias=True) + (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) + (dropout): Dropout(p=0.1, inplace=False) + ) + ) +)] \ No newline at end of file diff --git a/tests/nn_sources.json b/tests/nn_sources.json new file mode 100644 index 0000000..99e0d29 --- /dev/null +++ b/tests/nn_sources.json @@ -0,0 +1,3 @@ +{ + "SwinEncoder": "<'transformers.models.swin.modeling_swin.SwinEncoder'>" +} \ No newline at end of file diff --git a/tests/test.json b/tests/pkg_parameters.json similarity index 100% rename from tests/test.json rename to tests/pkg_parameters.json diff --git a/tests/subclass_modules.json b/tests/subclass_modules.json new file mode 100644 index 0000000..d470c3e --- /dev/null +++ b/tests/subclass_modules.json @@ -0,0 +1,3504 @@ +{ + "_MapInputEmbedding": "<'transformers.generation.candidate_generator._MapInputEmbedding'>", + "_PruneReindexingLMHead": "<'transformers.generation.candidate_generator._PruneReindexingLMHead'>", + "AbstractPreprocessor": "<'transformers.models.perceiver.modeling_perceiver.AbstractPreprocessor'>", + "AccurateGELUActivation": "<'transformers.activations.AccurateGELUActivation'>", + "AdaptiveEmbedding": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl.AdaptiveEmbedding'>", + "Aimv2Attention": "<'transformers.models.aimv2.modeling_aimv2.Aimv2Attention'>", + "Aimv2AttentionPoolingHead": "<'transformers.models.aimv2.modeling_aimv2.Aimv2AttentionPoolingHead'>", + "Aimv2Encoder": "<'transformers.models.aimv2.modeling_aimv2.Aimv2Encoder'>", + "Aimv2EncoderLayer": "<'transformers.models.aimv2.modeling_aimv2.Aimv2EncoderLayer'>", + "Aimv2MLP": "<'transformers.models.aimv2.modeling_aimv2.Aimv2MLP'>", + "Aimv2RMSNorm": "<'transformers.models.aimv2.modeling_aimv2.Aimv2RMSNorm'>", + "Aimv2TextEmbeddings": "<'transformers.models.aimv2.modeling_aimv2.Aimv2TextEmbeddings'>", + "Aimv2VisionEmbeddings": "<'transformers.models.aimv2.modeling_aimv2.Aimv2VisionEmbeddings'>", + "AlbertAttention": "<'transformers.models.albert.modeling_albert.AlbertAttention'>", + "AlbertEmbeddings": "<'transformers.models.albert.modeling_albert.AlbertEmbeddings'>", + "AlbertLayer": "<'transformers.models.albert.modeling_albert.AlbertLayer'>", + "AlbertLayerGroup": "<'transformers.models.albert.modeling_albert.AlbertLayerGroup'>", + "AlbertMLMHead": "<'transformers.models.albert.modeling_albert.AlbertMLMHead'>", + "AlbertSdpaAttention": "<'transformers.models.albert.modeling_albert.AlbertSdpaAttention'>", + "AlbertSOPHead": "<'transformers.models.albert.modeling_albert.AlbertSOPHead'>", + "AlbertTransformer": "<'transformers.models.albert.modeling_albert.AlbertTransformer'>", + "AlignTextAttention": "<'transformers.models.align.modeling_align.AlignTextAttention'>", + "AlignTextEmbeddings": "<'transformers.models.align.modeling_align.AlignTextEmbeddings'>", + "AlignTextEncoder": "<'transformers.models.align.modeling_align.AlignTextEncoder'>", + "AlignTextIntermediate": "<'transformers.models.align.modeling_align.AlignTextIntermediate'>", + "AlignTextLayer": "<'transformers.models.align.modeling_align.AlignTextLayer'>", + "AlignTextOutput": "<'transformers.models.align.modeling_align.AlignTextOutput'>", + "AlignTextPooler": "<'transformers.models.align.modeling_align.AlignTextPooler'>", + "AlignTextSelfAttention": "<'transformers.models.align.modeling_align.AlignTextSelfAttention'>", + "AlignTextSelfOutput": "<'transformers.models.align.modeling_align.AlignTextSelfOutput'>", + "AlignVisionBlock": "<'transformers.models.align.modeling_align.AlignVisionBlock'>", + "AlignVisionDepthwiseConv2d": "<'transformers.models.align.modeling_align.AlignVisionDepthwiseConv2d'>", + "AlignVisionDepthwiseLayer": "<'transformers.models.align.modeling_align.AlignVisionDepthwiseLayer'>", + "AlignVisionEmbeddings": "<'transformers.models.align.modeling_align.AlignVisionEmbeddings'>", + "AlignVisionEncoder": "<'transformers.models.align.modeling_align.AlignVisionEncoder'>", + "AlignVisionExpansionLayer": "<'transformers.models.align.modeling_align.AlignVisionExpansionLayer'>", + "AlignVisionFinalBlockLayer": "<'transformers.models.align.modeling_align.AlignVisionFinalBlockLayer'>", + "AlignVisionSqueezeExciteLayer": "<'transformers.models.align.modeling_align.AlignVisionSqueezeExciteLayer'>", + "AltCLIPAttention": "<'transformers.models.altclip.modeling_altclip.AltCLIPAttention'>", + "AltCLIPEncoder": "<'transformers.models.altclip.modeling_altclip.AltCLIPEncoder'>", + "AltCLIPEncoderLayer": "<'transformers.models.altclip.modeling_altclip.AltCLIPEncoderLayer'>", + "AltCLIPMLP": "<'transformers.models.altclip.modeling_altclip.AltCLIPMLP'>", + "AltCLIPVisionEmbeddings": "<'transformers.models.altclip.modeling_altclip.AltCLIPVisionEmbeddings'>", + "AltCLIPVisionTransformer": "<'transformers.models.altclip.modeling_altclip.AltCLIPVisionTransformer'>", + "AltRobertaAttention": "<'transformers.models.altclip.modeling_altclip.AltRobertaAttention'>", + "AltRobertaEmbeddings": "<'transformers.models.altclip.modeling_altclip.AltRobertaEmbeddings'>", + "AltRobertaEncoder": "<'transformers.models.altclip.modeling_altclip.AltRobertaEncoder'>", + "AltRobertaIntermediate": "<'transformers.models.altclip.modeling_altclip.AltRobertaIntermediate'>", + "AltRobertaLayer": "<'transformers.models.altclip.modeling_altclip.AltRobertaLayer'>", + "AltRobertaModel": "<'transformers.models.altclip.modeling_altclip.AltRobertaModel'>", + "AltRobertaOutput": "<'transformers.models.altclip.modeling_altclip.AltRobertaOutput'>", + "AltRobertaPooler": "<'transformers.models.altclip.modeling_altclip.AltRobertaPooler'>", + "AltRobertaSelfAttention": "<'transformers.models.altclip.modeling_altclip.AltRobertaSelfAttention'>", + "AltRobertaSelfOutput": "<'transformers.models.altclip.modeling_altclip.AltRobertaSelfOutput'>", + "AMPBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.AMPBlock'>", + "AMSoftmaxLoss": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.AMSoftmaxLoss'>", + "ArceeAttention": "<'transformers.models.arcee.modeling_arcee.ArceeAttention'>", + "ArceeDecoderLayer": "<'transformers.models.arcee.modeling_arcee.ArceeDecoderLayer'>", + "ArceeMLP": "<'transformers.models.arcee.modular_arcee.ArceeMLP'>", + "ArceeRMSNorm": "<'transformers.models.arcee.modeling_arcee.ArceeRMSNorm'>", + "ArceeRotaryEmbedding": "<'transformers.models.arcee.modeling_arcee.ArceeRotaryEmbedding'>", + "AriaCrossAttention": "<'transformers.models.aria.modeling_aria.AriaCrossAttention'>", + "AriaGroupedExpertsGemm": "<'transformers.models.aria.modeling_aria.AriaGroupedExpertsGemm'>", + "AriaGroupedExpertsMLP": "<'transformers.models.aria.modeling_aria.AriaGroupedExpertsMLP'>", + "AriaProjector": "<'transformers.models.aria.modeling_aria.AriaProjector'>", + "AriaProjectorMLP": "<'transformers.models.aria.modeling_aria.AriaProjectorMLP'>", + "AriaSharedExpertsMLP": "<'transformers.models.aria.modeling_aria.AriaSharedExpertsMLP'>", + "AriaTextAttention": "<'transformers.models.aria.modeling_aria.AriaTextAttention'>", + "AriaTextDecoderLayer": "<'transformers.models.aria.modeling_aria.AriaTextDecoderLayer'>", + "AriaTextMoELayer": "<'transformers.models.aria.modeling_aria.AriaTextMoELayer'>", + "AriaTextRMSNorm": "<'transformers.models.aria.modeling_aria.AriaTextRMSNorm'>", + "AriaTextRotaryEmbedding": "<'transformers.models.aria.modeling_aria.AriaTextRotaryEmbedding'>", + "ASTAttention": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTAttention'>", + "ASTEmbeddings": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTEmbeddings'>", + "ASTEncoder": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTEncoder'>", + "ASTIntermediate": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTIntermediate'>", + "ASTLayer": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTLayer'>", + "ASTMLPHead": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTMLPHead'>", + "ASTOutput": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTOutput'>", + "ASTPatchEmbeddings": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTPatchEmbeddings'>", + "ASTSelfAttention": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTSelfAttention'>", + "ASTSelfOutput": "<'transformers.models.audio_spectrogram_transformer.modeling_audio_spectrogram_transformer.ASTSelfOutput'>", + "Attention": "<'transformers.models.openai.modeling_openai.Attention'>", + "AttentiveStatisticsPooling": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.AttentiveStatisticsPooling'>", + "AutoformerAttention": "<'transformers.models.autoformer.modeling_autoformer.AutoformerAttention'>", + "AutoformerDecoder": "<'transformers.models.autoformer.modeling_autoformer.AutoformerDecoder'>", + "AutoformerDecoderLayer": "<'transformers.models.autoformer.modeling_autoformer.AutoformerDecoderLayer'>", + "AutoformerEncoder": "<'transformers.models.autoformer.modeling_autoformer.AutoformerEncoder'>", + "AutoformerEncoderLayer": "<'transformers.models.autoformer.modeling_autoformer.AutoformerEncoderLayer'>", + "AutoformerFeatureEmbedder": "<'transformers.models.autoformer.modeling_autoformer.AutoformerFeatureEmbedder'>", + "AutoformerLayernorm": "<'transformers.models.autoformer.modeling_autoformer.AutoformerLayernorm'>", + "AutoformerMeanScaler": "<'transformers.models.autoformer.modeling_autoformer.AutoformerMeanScaler'>", + "AutoformerNOPScaler": "<'transformers.models.autoformer.modeling_autoformer.AutoformerNOPScaler'>", + "AutoformerSeriesDecompositionLayer": "<'transformers.models.autoformer.modeling_autoformer.AutoformerSeriesDecompositionLayer'>", + "AutoformerSinusoidalPositionalEmbedding": "<'transformers.models.autoformer.modeling_autoformer.AutoformerSinusoidalPositionalEmbedding'>", + "AutoformerStdScaler": "<'transformers.models.autoformer.modeling_autoformer.AutoformerStdScaler'>", + "AutoformerValueEmbedding": "<'transformers.models.autoformer.modeling_autoformer.AutoformerValueEmbedding'>", + "AxialPositionEmbeddings": "<'transformers.models.reformer.modeling_reformer.AxialPositionEmbeddings'>", + "AyaVisionMultiModalProjector": "<'transformers.models.aya_vision.modeling_aya_vision.AyaVisionMultiModalProjector'>", + "BambaAttention": "<'transformers.models.bamba.modeling_bamba.BambaAttention'>", + "BambaDecoderLayer": "<'transformers.models.bamba.modeling_bamba.BambaDecoderLayer'>", + "BambaMixer": "<'transformers.models.bamba.modeling_bamba.BambaMixer'>", + "BambaMLP": "<'transformers.models.bamba.modeling_bamba.BambaMLP'>", + "BambaRMSNorm": "<'transformers.models.bamba.modeling_bamba.BambaRMSNorm'>", + "BambaRMSNormGated": "<'transformers.models.bamba.modeling_bamba.BambaRMSNormGated'>", + "BambaRotaryEmbedding": "<'transformers.models.bamba.modeling_bamba.BambaRotaryEmbedding'>", + "BarkBlock": "<'transformers.models.bark.modeling_bark.BarkBlock'>", + "BarkMLP": "<'transformers.models.bark.modeling_bark.BarkMLP'>", + "BarkSelfAttention": "<'transformers.models.bark.modeling_bark.BarkSelfAttention'>", + "BarkSelfFlashAttention2": "<'transformers.models.bark.modeling_bark.BarkSelfFlashAttention2'>", + "BartAttention": "<'transformers.models.bart.modeling_bart.BartAttention'>", + "BartClassificationHead": "<'transformers.models.bart.modeling_bart.BartClassificationHead'>", + "BartDecoder": "<'transformers.models.bart.modeling_bart.BartDecoder'>", + "BartDecoderLayer": "<'transformers.models.bart.modeling_bart.BartDecoderLayer'>", + "BartDecoderWrapper": "<'transformers.models.bart.modeling_bart.BartDecoderWrapper'>", + "BartEncoder": "<'transformers.models.bart.modeling_bart.BartEncoder'>", + "BartEncoderLayer": "<'transformers.models.bart.modeling_bart.BartEncoderLayer'>", + "BartLearnedPositionalEmbedding": "<'transformers.models.bart.modeling_bart.BartLearnedPositionalEmbedding'>", + "BartScaledWordEmbedding": "<'transformers.models.bart.modeling_bart.BartScaledWordEmbedding'>", + "BCEWithLogitsLoss": "<'torch.nn.modules.loss.BCEWithLogitsLoss'>", + "BeitAttention": "<'transformers.models.beit.modeling_beit.BeitAttention'>", + "BeitConvModule": "<'transformers.models.beit.modeling_beit.BeitConvModule'>", + "BeitDropPath": "<'transformers.models.beit.modeling_beit.BeitDropPath'>", + "BeitEmbeddings": "<'transformers.models.beit.modeling_beit.BeitEmbeddings'>", + "BeitEncoder": "<'transformers.models.beit.modeling_beit.BeitEncoder'>", + "BeitFCNHead": "<'transformers.models.beit.modeling_beit.BeitFCNHead'>", + "BeitIntermediate": "<'transformers.models.beit.modeling_beit.BeitIntermediate'>", + "BeitLayer": "<'transformers.models.beit.modeling_beit.BeitLayer'>", + "BeitOutput": "<'transformers.models.beit.modeling_beit.BeitOutput'>", + "BeitPatchEmbeddings": "<'transformers.models.beit.modeling_beit.BeitPatchEmbeddings'>", + "BeitPooler": "<'transformers.models.beit.modeling_beit.BeitPooler'>", + "BeitPyramidPoolingBlock": "<'transformers.models.beit.modeling_beit.BeitPyramidPoolingBlock'>", + "BeitPyramidPoolingModule": "<'transformers.models.beit.modeling_beit.BeitPyramidPoolingModule'>", + "BeitRelativePositionBias": "<'transformers.models.beit.modeling_beit.BeitRelativePositionBias'>", + "BeitSdpaSelfAttention": "<'transformers.models.beit.modeling_beit.BeitSdpaSelfAttention'>", + "BeitSelfAttention": "<'transformers.models.beit.modeling_beit.BeitSelfAttention'>", + "BeitSelfOutput": "<'transformers.models.beit.modeling_beit.BeitSelfOutput'>", + "BeitUperHead": "<'transformers.models.beit.modeling_beit.BeitUperHead'>", + "BertAttention": "<'transformers.models.bert.modeling_bert.BertAttention'>", + "BertEmbeddings": "<'transformers.models.bert.modeling_bert.BertEmbeddings'>", + "BertEncoder": "<'transformers.models.bert.modeling_bert.BertEncoder'>", + "BertGenerationAttention": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationAttention'>", + "BertGenerationEmbeddings": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationEmbeddings'>", + "BertGenerationIntermediate": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationIntermediate'>", + "BertGenerationLayer": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationLayer'>", + "BertGenerationOnlyLMHead": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationOnlyLMHead'>", + "BertGenerationOutput": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationOutput'>", + "BertGenerationSelfAttention": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationSelfAttention'>", + "BertGenerationSelfOutput": "<'transformers.models.bert_generation.modeling_bert_generation.BertGenerationSelfOutput'>", + "BertIntermediate": "<'transformers.models.bert.modeling_bert.BertIntermediate'>", + "BertLayer": "<'transformers.models.bert.modeling_bert.BertLayer'>", + "BertLMPredictionHead": "<'transformers.models.bert.modeling_bert.BertLMPredictionHead'>", + "BertOnlyMLMHead": "<'transformers.models.bert.modeling_bert.BertOnlyMLMHead'>", + "BertOnlyNSPHead": "<'transformers.models.bert.modeling_bert.BertOnlyNSPHead'>", + "BertOutput": "<'transformers.models.bert.modeling_bert.BertOutput'>", + "BertPooler": "<'transformers.models.bert.modeling_bert.BertPooler'>", + "BertPredictionHeadTransform": "<'transformers.models.bert.modeling_bert.BertPredictionHeadTransform'>", + "BertPreTrainingHeads": "<'transformers.models.bert.modeling_bert.BertPreTrainingHeads'>", + "BertSdpaSelfAttention": "<'transformers.models.bert.modeling_bert.BertSdpaSelfAttention'>", + "BertSelfAttention": "<'transformers.models.bert.modeling_bert.BertSelfAttention'>", + "BertSelfOutput": "<'transformers.models.bert.modeling_bert.BertSelfOutput'>", + "BigBirdAttention": "<'transformers.models.big_bird.modeling_big_bird.BigBirdAttention'>", + "BigBirdBlockSparseAttention": "<'transformers.models.big_bird.modeling_big_bird.BigBirdBlockSparseAttention'>", + "BigBirdClassificationHead": "<'transformers.models.big_bird.modeling_big_bird.BigBirdClassificationHead'>", + "BigBirdEmbeddings": "<'transformers.models.big_bird.modeling_big_bird.BigBirdEmbeddings'>", + "BigBirdEncoder": "<'transformers.models.big_bird.modeling_big_bird.BigBirdEncoder'>", + "BigBirdForQuestionAnsweringHead": "<'transformers.models.big_bird.modeling_big_bird.BigBirdForQuestionAnsweringHead'>", + "BigBirdIntermediate": "<'transformers.models.big_bird.modeling_big_bird.BigBirdIntermediate'>", + "BigBirdLayer": "<'transformers.models.big_bird.modeling_big_bird.BigBirdLayer'>", + "BigBirdLMPredictionHead": "<'transformers.models.big_bird.modeling_big_bird.BigBirdLMPredictionHead'>", + "BigBirdOnlyMLMHead": "<'transformers.models.big_bird.modeling_big_bird.BigBirdOnlyMLMHead'>", + "BigBirdOnlyNSPHead": "<'transformers.models.big_bird.modeling_big_bird.BigBirdOnlyNSPHead'>", + "BigBirdOutput": "<'transformers.models.big_bird.modeling_big_bird.BigBirdOutput'>", + "BigBirdPegasusBlockSparseAttention": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusBlockSparseAttention'>", + "BigBirdPegasusClassificationHead": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusClassificationHead'>", + "BigBirdPegasusDecoder": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusDecoder'>", + "BigBirdPegasusDecoderAttention": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusDecoderAttention'>", + "BigBirdPegasusDecoderLayer": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusDecoderLayer'>", + "BigBirdPegasusDecoderWrapper": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusDecoderWrapper'>", + "BigBirdPegasusEncoder": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusEncoder'>", + "BigBirdPegasusEncoderAttention": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusEncoderAttention'>", + "BigBirdPegasusEncoderLayer": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusEncoderLayer'>", + "BigBirdPegasusLearnedPositionalEmbedding": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusLearnedPositionalEmbedding'>", + "BigBirdPegasusScaledWordEmbedding": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusScaledWordEmbedding'>", + "BigBirdPegasusSelfAttention": "<'transformers.models.bigbird_pegasus.modeling_bigbird_pegasus.BigBirdPegasusSelfAttention'>", + "BigBirdPredictionHeadTransform": "<'transformers.models.big_bird.modeling_big_bird.BigBirdPredictionHeadTransform'>", + "BigBirdPreTrainingHeads": "<'transformers.models.big_bird.modeling_big_bird.BigBirdPreTrainingHeads'>", + "BigBirdSelfAttention": "<'transformers.models.big_bird.modeling_big_bird.BigBirdSelfAttention'>", + "BigBirdSelfOutput": "<'transformers.models.big_bird.modeling_big_bird.BigBirdSelfOutput'>", + "BioGptAttention": "<'transformers.models.biogpt.modeling_biogpt.BioGptAttention'>", + "BioGptDecoderLayer": "<'transformers.models.biogpt.modeling_biogpt.BioGptDecoderLayer'>", + "BioGptLearnedPositionalEmbedding": "<'transformers.models.biogpt.modeling_biogpt.BioGptLearnedPositionalEmbedding'>", + "BioGptScaledWordEmbedding": "<'transformers.models.biogpt.modeling_biogpt.BioGptScaledWordEmbedding'>", + "BitBottleneckLayer": "<'transformers.models.bit.modeling_bit.BitBottleneckLayer'>", + "BitDownsampleConv": "<'transformers.models.bit.modeling_bit.BitDownsampleConv'>", + "BitDropPath": "<'transformers.models.bit.modeling_bit.BitDropPath'>", + "BitEmbeddings": "<'transformers.models.bit.modeling_bit.BitEmbeddings'>", + "BitEncoder": "<'transformers.models.bit.modeling_bit.BitEncoder'>", + "BitGroupNormActivation": "<'transformers.models.bit.modeling_bit.BitGroupNormActivation'>", + "BitMaxPool2d": "<'transformers.models.bit.modeling_bit.BitMaxPool2d'>", + "BitNetAttention": "<'transformers.models.bitnet.modular_bitnet.BitNetAttention'>", + "BitNetDecoderLayer": "<'transformers.models.bitnet.modular_bitnet.BitNetDecoderLayer'>", + "BitNetMLP": "<'transformers.models.bitnet.modular_bitnet.BitNetMLP'>", + "BitNetRMSNorm": "<'transformers.models.bitnet.modular_bitnet.BitNetRMSNorm'>", + "BitNetRotaryEmbedding": "<'transformers.models.bitnet.modeling_bitnet.BitNetRotaryEmbedding'>", + "BitPreActivationBottleneckLayer": "<'transformers.models.bit.modeling_bit.BitPreActivationBottleneckLayer'>", + "BitStage": "<'transformers.models.bit.modeling_bit.BitStage'>", + "BlenderbotAttention": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotAttention'>", + "BlenderbotDecoder": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotDecoder'>", + "BlenderbotDecoderLayer": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotDecoderLayer'>", + "BlenderbotDecoderWrapper": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotDecoderWrapper'>", + "BlenderbotEncoder": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotEncoder'>", + "BlenderbotEncoderLayer": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotEncoderLayer'>", + "BlenderbotLearnedPositionalEmbedding": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotLearnedPositionalEmbedding'>", + "BlenderbotScaledWordEmbedding": "<'transformers.models.blenderbot.modeling_blenderbot.BlenderbotScaledWordEmbedding'>", + "BlenderbotSmallAttention": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallAttention'>", + "BlenderbotSmallDecoder": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallDecoder'>", + "BlenderbotSmallDecoderLayer": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallDecoderLayer'>", + "BlenderbotSmallDecoderWrapper": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallDecoderWrapper'>", + "BlenderbotSmallEncoder": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallEncoder'>", + "BlenderbotSmallEncoderLayer": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallEncoderLayer'>", + "BlenderbotSmallLearnedPositionalEmbedding": "<'transformers.models.blenderbot_small.modeling_blenderbot_small.BlenderbotSmallLearnedPositionalEmbedding'>", + "Blip2Attention": "<'transformers.models.blip_2.modeling_blip_2.Blip2Attention'>", + "Blip2Encoder": "<'transformers.models.blip_2.modeling_blip_2.Blip2Encoder'>", + "Blip2EncoderLayer": "<'transformers.models.blip_2.modeling_blip_2.Blip2EncoderLayer'>", + "Blip2MLP": "<'transformers.models.blip_2.modeling_blip_2.Blip2MLP'>", + "Blip2QFormerAttention": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerAttention'>", + "Blip2QFormerEncoder": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerEncoder'>", + "Blip2QFormerIntermediate": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerIntermediate'>", + "Blip2QFormerLayer": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerLayer'>", + "Blip2QFormerMultiHeadAttention": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerMultiHeadAttention'>", + "Blip2QFormerOutput": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerOutput'>", + "Blip2QFormerSelfOutput": "<'transformers.models.blip_2.modeling_blip_2.Blip2QFormerSelfOutput'>", + "Blip2TextEmbeddings": "<'transformers.models.blip_2.modeling_blip_2.Blip2TextEmbeddings'>", + "Blip2VisionEmbeddings": "<'transformers.models.blip_2.modeling_blip_2.Blip2VisionEmbeddings'>", + "BlipAttention": "<'transformers.models.blip.modeling_blip.BlipAttention'>", + "BlipEncoder": "<'transformers.models.blip.modeling_blip.BlipEncoder'>", + "BlipEncoderLayer": "<'transformers.models.blip.modeling_blip.BlipEncoderLayer'>", + "BlipMLP": "<'transformers.models.blip.modeling_blip.BlipMLP'>", + "BlipTextAttention": "<'transformers.models.blip.modeling_blip_text.BlipTextAttention'>", + "BlipTextEmbeddings": "<'transformers.models.blip.modeling_blip.BlipTextEmbeddings'>", + "BlipTextEncoder": "<'transformers.models.blip.modeling_blip_text.BlipTextEncoder'>", + "BlipTextIntermediate": "<'transformers.models.blip.modeling_blip_text.BlipTextIntermediate'>", + "BlipTextLayer": "<'transformers.models.blip.modeling_blip_text.BlipTextLayer'>", + "BlipTextLMPredictionHead": "<'transformers.models.blip.modeling_blip_text.BlipTextLMPredictionHead'>", + "BlipTextOnlyMLMHead": "<'transformers.models.blip.modeling_blip_text.BlipTextOnlyMLMHead'>", + "BlipTextOutput": "<'transformers.models.blip.modeling_blip_text.BlipTextOutput'>", + "BlipTextPooler": "<'transformers.models.blip.modeling_blip_text.BlipTextPooler'>", + "BlipTextPredictionHeadTransform": "<'transformers.models.blip.modeling_blip_text.BlipTextPredictionHeadTransform'>", + "BlipTextSelfAttention": "<'transformers.models.blip.modeling_blip_text.BlipTextSelfAttention'>", + "BlipTextSelfOutput": "<'transformers.models.blip.modeling_blip_text.BlipTextSelfOutput'>", + "BlipVisionEmbeddings": "<'transformers.models.blip.modeling_blip.BlipVisionEmbeddings'>", + "Block": "<'transformers.models.deprecated.trajectory_transformer.modeling_trajectory_transformer.Block'>", + "BloomAttention": "<'transformers.models.bloom.modeling_bloom.BloomAttention'>", + "BloomBlock": "<'transformers.models.bloom.modeling_bloom.BloomBlock'>", + "BloomGelu": "<'transformers.models.bloom.modeling_bloom.BloomGelu'>", + "BloomMLP": "<'transformers.models.bloom.modeling_bloom.BloomMLP'>", + "Bottleneck": "<'transformers.models.mobilebert.modeling_mobilebert.Bottleneck'>", + "BottleneckLayer": "<'transformers.models.mobilebert.modeling_mobilebert.BottleneckLayer'>", + "BridgeTowerAttention": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerAttention'>", + "BridgeTowerBertCrossLayer": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerBertCrossLayer'>", + "BridgeTowerContrastiveHead": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerContrastiveHead'>", + "BridgeTowerIntermediate": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerIntermediate'>", + "BridgeTowerITMHead": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerITMHead'>", + "BridgeTowerLinkTower": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerLinkTower'>", + "BridgeTowerMLMHead": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerMLMHead'>", + "BridgeTowerOutput": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerOutput'>", + "BridgeTowerPooler": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerPooler'>", + "BridgeTowerPredictionHeadTransform": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerPredictionHeadTransform'>", + "BridgeTowerResidualAttention": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerResidualAttention'>", + "BridgeTowerSelfAttention": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerSelfAttention'>", + "BridgeTowerSelfOutput": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerSelfOutput'>", + "BridgeTowerTextEmbeddings": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerTextEmbeddings'>", + "BridgeTowerTextEncoder": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerTextEncoder'>", + "BridgeTowerTextLayer": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerTextLayer'>", + "BridgeTowerTextModel": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerTextModel'>", + "BridgeTowerTransformer": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerTransformer'>", + "BridgeTowerVisionEmbeddings": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerVisionEmbeddings'>", + "BridgeTowerVisionModel": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerVisionModel'>", + "BridgeTowerVisionTransformer": "<'transformers.models.bridgetower.modeling_bridgetower.BridgeTowerVisionTransformer'>", + "BrosAttention": "<'transformers.models.bros.modeling_bros.BrosAttention'>", + "BrosBboxEmbeddings": "<'transformers.models.bros.modeling_bros.BrosBboxEmbeddings'>", + "BrosEncoder": "<'transformers.models.bros.modeling_bros.BrosEncoder'>", + "BrosIntermediate": "<'transformers.models.bros.modeling_bros.BrosIntermediate'>", + "BrosLayer": "<'transformers.models.bros.modeling_bros.BrosLayer'>", + "BrosOutput": "<'transformers.models.bros.modeling_bros.BrosOutput'>", + "BrosPooler": "<'transformers.models.bros.modeling_bros.BrosPooler'>", + "BrosPositionalEmbedding1D": "<'transformers.models.bros.modeling_bros.BrosPositionalEmbedding1D'>", + "BrosPositionalEmbedding2D": "<'transformers.models.bros.modeling_bros.BrosPositionalEmbedding2D'>", + "BrosRelationExtractor": "<'transformers.models.bros.modeling_bros.BrosRelationExtractor'>", + "BrosSelfAttention": "<'transformers.models.bros.modeling_bros.BrosSelfAttention'>", + "BrosSelfOutput": "<'transformers.models.bros.modeling_bros.BrosSelfOutput'>", + "BrosTextEmbeddings": "<'transformers.models.bros.modeling_bros.BrosTextEmbeddings'>", + "CamembertAttention": "<'transformers.models.camembert.modeling_camembert.CamembertAttention'>", + "CamembertClassificationHead": "<'transformers.models.camembert.modeling_camembert.CamembertClassificationHead'>", + "CamembertEmbeddings": "<'transformers.models.camembert.modeling_camembert.CamembertEmbeddings'>", + "CamembertEncoder": "<'transformers.models.camembert.modeling_camembert.CamembertEncoder'>", + "CamembertIntermediate": "<'transformers.models.camembert.modeling_camembert.CamembertIntermediate'>", + "CamembertLayer": "<'transformers.models.camembert.modeling_camembert.CamembertLayer'>", + "CamembertLMHead": "<'transformers.models.camembert.modeling_camembert.CamembertLMHead'>", + "CamembertOutput": "<'transformers.models.camembert.modeling_camembert.CamembertOutput'>", + "CamembertPooler": "<'transformers.models.camembert.modeling_camembert.CamembertPooler'>", + "CamembertSdpaSelfAttention": "<'transformers.models.camembert.modeling_camembert.CamembertSdpaSelfAttention'>", + "CamembertSelfAttention": "<'transformers.models.camembert.modeling_camembert.CamembertSelfAttention'>", + "CamembertSelfOutput": "<'transformers.models.camembert.modeling_camembert.CamembertSelfOutput'>", + "CanineAttention": "<'transformers.models.canine.modeling_canine.CanineAttention'>", + "CanineEmbeddings": "<'transformers.models.canine.modeling_canine.CanineEmbeddings'>", + "CanineEncoder": "<'transformers.models.canine.modeling_canine.CanineEncoder'>", + "CanineIntermediate": "<'transformers.models.canine.modeling_canine.CanineIntermediate'>", + "CanineLayer": "<'transformers.models.canine.modeling_canine.CanineLayer'>", + "CanineLMPredictionHead": "<'transformers.models.canine.modeling_canine.CanineLMPredictionHead'>", + "CanineOnlyMLMHead": "<'transformers.models.canine.modeling_canine.CanineOnlyMLMHead'>", + "CanineOutput": "<'transformers.models.canine.modeling_canine.CanineOutput'>", + "CaninePooler": "<'transformers.models.canine.modeling_canine.CaninePooler'>", + "CaninePredictionHeadTransform": "<'transformers.models.canine.modeling_canine.CaninePredictionHeadTransform'>", + "CanineSelfAttention": "<'transformers.models.canine.modeling_canine.CanineSelfAttention'>", + "CanineSelfOutput": "<'transformers.models.canine.modeling_canine.CanineSelfOutput'>", + "CausalSelfAttention": "<'transformers.models.deprecated.trajectory_transformer.modeling_trajectory_transformer.CausalSelfAttention'>", + "ChameleonAttention": "<'transformers.models.chameleon.modeling_chameleon.ChameleonAttention'>", + "ChameleonDecoderLayer": "<'transformers.models.chameleon.modeling_chameleon.ChameleonDecoderLayer'>", + "ChameleonDynamicNTKScalingRotaryEmbedding": "<'transformers.models.chameleon.modeling_chameleon.ChameleonDynamicNTKScalingRotaryEmbedding'>", + "ChameleonLayerNorm": "<'transformers.models.chameleon.modeling_chameleon.ChameleonLayerNorm'>", + "ChameleonLinearScalingRotaryEmbedding": "<'transformers.models.chameleon.modeling_chameleon.ChameleonLinearScalingRotaryEmbedding'>", + "ChameleonMLP": "<'transformers.models.chameleon.modeling_chameleon.ChameleonMLP'>", + "ChameleonRMSNorm": "<'transformers.models.chameleon.modeling_chameleon.ChameleonRMSNorm'>", + "ChameleonRotaryEmbedding": "<'transformers.models.chameleon.modeling_chameleon.ChameleonRotaryEmbedding'>", + "ChameleonSwinDecoderLayer": "<'transformers.models.chameleon.modeling_chameleon.ChameleonSwinDecoderLayer'>", + "ChameleonVQVAEEncoder": "<'transformers.models.chameleon.modeling_chameleon.ChameleonVQVAEEncoder'>", + "ChameleonVQVAEEncoderAttnBlock": "<'transformers.models.chameleon.modeling_chameleon.ChameleonVQVAEEncoderAttnBlock'>", + "ChameleonVQVAEEncoderConvDownsample": "<'transformers.models.chameleon.modeling_chameleon.ChameleonVQVAEEncoderConvDownsample'>", + "ChameleonVQVAEEncoderResnetBlock": "<'transformers.models.chameleon.modeling_chameleon.ChameleonVQVAEEncoderResnetBlock'>", + "ChameleonVQVAEVectorQuantizer": "<'transformers.models.chameleon.modeling_chameleon.ChameleonVQVAEVectorQuantizer'>", + "CharactersToMolecules": "<'transformers.models.canine.modeling_canine.CharactersToMolecules'>", + "ChineseCLIPTextAttention": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextAttention'>", + "ChineseCLIPTextEmbeddings": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextEmbeddings'>", + "ChineseCLIPTextEncoder": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextEncoder'>", + "ChineseCLIPTextIntermediate": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextIntermediate'>", + "ChineseCLIPTextLayer": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextLayer'>", + "ChineseCLIPTextOutput": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextOutput'>", + "ChineseCLIPTextPooler": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextPooler'>", + "ChineseCLIPTextSelfAttention": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextSelfAttention'>", + "ChineseCLIPTextSelfOutput": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPTextSelfOutput'>", + "ChineseCLIPVisionAttention": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionAttention'>", + "ChineseCLIPVisionEmbeddings": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionEmbeddings'>", + "ChineseCLIPVisionEncoder": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionEncoder'>", + "ChineseCLIPVisionLayer": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionLayer'>", + "ChineseCLIPVisionMLP": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionMLP'>", + "ChineseCLIPVisionTransformer": "<'transformers.models.chinese_clip.modeling_chinese_clip.ChineseCLIPVisionTransformer'>", + "ChunkReformerFeedForward": "<'transformers.models.reformer.modeling_reformer.ChunkReformerFeedForward'>", + "ClapAudioAFFBlock": "<'transformers.models.clap.modeling_clap.ClapAudioAFFBlock'>", + "ClapAudioAttention": "<'transformers.models.clap.modeling_clap.ClapAudioAttention'>", + "ClapAudioEncoder": "<'transformers.models.clap.modeling_clap.ClapAudioEncoder'>", + "ClapAudioIntermediate": "<'transformers.models.clap.modeling_clap.ClapAudioIntermediate'>", + "ClapAudioLayer": "<'transformers.models.clap.modeling_clap.ClapAudioLayer'>", + "ClapAudioOutput": "<'transformers.models.clap.modeling_clap.ClapAudioOutput'>", + "ClapAudioPatchEmbed": "<'transformers.models.clap.modeling_clap.ClapAudioPatchEmbed'>", + "ClapAudioPatchMerging": "<'transformers.models.clap.modeling_clap.ClapAudioPatchMerging'>", + "ClapAudioSelfAttention": "<'transformers.models.clap.modeling_clap.ClapAudioSelfAttention'>", + "ClapAudioSelfOutput": "<'transformers.models.clap.modeling_clap.ClapAudioSelfOutput'>", + "ClapAudioStage": "<'transformers.models.clap.modeling_clap.ClapAudioStage'>", + "ClapDropPath": "<'transformers.models.clap.modeling_clap.ClapDropPath'>", + "ClapProjectionLayer": "<'transformers.models.clap.modeling_clap.ClapProjectionLayer'>", + "ClapTextAttention": "<'transformers.models.clap.modeling_clap.ClapTextAttention'>", + "ClapTextEmbeddings": "<'transformers.models.clap.modeling_clap.ClapTextEmbeddings'>", + "ClapTextEncoder": "<'transformers.models.clap.modeling_clap.ClapTextEncoder'>", + "ClapTextIntermediate": "<'transformers.models.clap.modeling_clap.ClapTextIntermediate'>", + "ClapTextLayer": "<'transformers.models.clap.modeling_clap.ClapTextLayer'>", + "ClapTextOutput": "<'transformers.models.clap.modeling_clap.ClapTextOutput'>", + "ClapTextPooler": "<'transformers.models.clap.modeling_clap.ClapTextPooler'>", + "ClapTextSelfAttention": "<'transformers.models.clap.modeling_clap.ClapTextSelfAttention'>", + "ClapTextSelfOutput": "<'transformers.models.clap.modeling_clap.ClapTextSelfOutput'>", + "CLIPAttention": "<'transformers.models.clip.modeling_clip.CLIPAttention'>", + "CLIPEncoder": "<'transformers.models.clip.modeling_clip.CLIPEncoder'>", + "CLIPEncoderLayer": "<'transformers.models.clip.modeling_clip.CLIPEncoderLayer'>", + "CLIPMLP": "<'transformers.models.clip.modeling_clip.CLIPMLP'>", + "ClippedGELUActivation": "<'transformers.activations.ClippedGELUActivation'>", + "CLIPSegAttention": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegAttention'>", + "CLIPSegDecoder": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegDecoder'>", + "CLIPSegDecoderLayer": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegDecoderLayer'>", + "CLIPSegEncoder": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegEncoder'>", + "CLIPSegEncoderLayer": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegEncoderLayer'>", + "CLIPSegMLP": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegMLP'>", + "CLIPSegTextEmbeddings": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegTextEmbeddings'>", + "CLIPSegTextTransformer": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegTextTransformer'>", + "CLIPSegVisionEmbeddings": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegVisionEmbeddings'>", + "CLIPSegVisionTransformer": "<'transformers.models.clipseg.modeling_clipseg.CLIPSegVisionTransformer'>", + "CLIPTextEmbeddings": "<'transformers.models.clip.modeling_clip.CLIPTextEmbeddings'>", + "CLIPTextTransformer": "<'transformers.models.clip.modeling_clip.CLIPTextTransformer'>", + "CLIPVisionEmbeddings": "<'transformers.models.clip.modeling_clip.CLIPVisionEmbeddings'>", + "CLIPVisionTransformer": "<'transformers.models.clip.modeling_clip.CLIPVisionTransformer'>", + "ClvpConditioningEncoder": "<'transformers.models.clvp.modeling_clvp.ClvpConditioningEncoder'>", + "ClvpDecoderLayer": "<'transformers.models.clvp.modeling_clvp.ClvpDecoderLayer'>", + "ClvpDecoderMLP": "<'transformers.models.clvp.modeling_clvp.ClvpDecoderMLP'>", + "ClvpEncoderLayer": "<'transformers.models.clvp.modeling_clvp.ClvpEncoderLayer'>", + "ClvpEncoderMLP": "<'transformers.models.clvp.modeling_clvp.ClvpEncoderMLP'>", + "ClvpGatedLinearUnit": "<'transformers.models.clvp.modeling_clvp.ClvpGatedLinearUnit'>", + "ClvpRMSNorm": "<'transformers.models.clvp.modeling_clvp.ClvpRMSNorm'>", + "ClvpRotaryPositionalEmbedding": "<'transformers.models.clvp.modeling_clvp.ClvpRotaryPositionalEmbedding'>", + "ClvpSelfAttention": "<'transformers.models.clvp.modeling_clvp.ClvpSelfAttention'>", + "ClvpSequenceSummary": "<'transformers.models.clvp.modeling_clvp.ClvpSequenceSummary'>", + "CodeGenAttention": "<'transformers.models.codegen.modeling_codegen.CodeGenAttention'>", + "CodeGenBlock": "<'transformers.models.codegen.modeling_codegen.CodeGenBlock'>", + "CodeGenMLP": "<'transformers.models.codegen.modeling_codegen.CodeGenMLP'>", + "Cohere2Attention": "<'transformers.models.cohere2.modular_cohere2.Cohere2Attention'>", + "Cohere2DecoderLayer": "<'transformers.models.cohere2.modular_cohere2.Cohere2DecoderLayer'>", + "Cohere2LayerNorm": "<'transformers.models.cohere2.modular_cohere2.Cohere2LayerNorm'>", + "Cohere2MLP": "<'transformers.models.cohere2.modeling_cohere2.Cohere2MLP'>", + "Cohere2RotaryEmbedding": "<'transformers.models.cohere2.modular_cohere2.Cohere2RotaryEmbedding'>", + "Cohere2VisionMultiModalProjector": "<'transformers.models.cohere2_vision.modeling_cohere2_vision.Cohere2VisionMultiModalProjector'>", + "CohereAttention": "<'transformers.models.cohere.modeling_cohere.CohereAttention'>", + "CohereDecoderLayer": "<'transformers.models.cohere.modeling_cohere.CohereDecoderLayer'>", + "CohereLayerNorm": "<'transformers.models.cohere.modeling_cohere.CohereLayerNorm'>", + "CohereMLP": "<'transformers.models.cohere.modeling_cohere.CohereMLP'>", + "CohereRotaryEmbedding": "<'transformers.models.cohere.modeling_cohere.CohereRotaryEmbedding'>", + "ConditionalDetrAttention": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrAttention'>", + "ConditionalDetrConvEncoder": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrConvEncoder'>", + "ConditionalDetrConvModel": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrConvModel'>", + "ConditionalDetrDecoder": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrDecoder'>", + "ConditionalDetrDecoderLayer": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrDecoderLayer'>", + "ConditionalDetrEncoder": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrEncoder'>", + "ConditionalDetrEncoderLayer": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrEncoderLayer'>", + "ConditionalDetrFrozenBatchNorm2d": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrFrozenBatchNorm2d'>", + "ConditionalDetrLearnedPositionEmbedding": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrLearnedPositionEmbedding'>", + "ConditionalDetrMaskHeadSmallConv": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrMaskHeadSmallConv'>", + "ConditionalDetrMHAttentionMap": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrMHAttentionMap'>", + "ConditionalDetrMLPPredictionHead": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrMLPPredictionHead'>", + "ConditionalDetrSinePositionEmbedding": "<'transformers.models.conditional_detr.modeling_conditional_detr.ConditionalDetrSinePositionEmbedding'>", + "ContextPooler": "<'transformers.models.deberta_v2.modeling_deberta_v2.ContextPooler'>", + "Conv1dSubsampler": "<'transformers.models.speech_to_text.modeling_speech_to_text.Conv1dSubsampler'>", + "Conv2DDownsample": "<'transformers.models.perceiver.modeling_perceiver.Conv2DDownsample'>", + "Conv2dSamePadding": "<'transformers.models.perceiver.modeling_perceiver.Conv2dSamePadding'>", + "ConvActivation": "<'transformers.models.squeezebert.modeling_squeezebert.ConvActivation'>", + "ConvBertAttention": "<'transformers.models.convbert.modeling_convbert.ConvBertAttention'>", + "ConvBertClassificationHead": "<'transformers.models.convbert.modeling_convbert.ConvBertClassificationHead'>", + "ConvBertEmbeddings": "<'transformers.models.convbert.modeling_convbert.ConvBertEmbeddings'>", + "ConvBertEncoder": "<'transformers.models.convbert.modeling_convbert.ConvBertEncoder'>", + "ConvBertGeneratorPredictions": "<'transformers.models.convbert.modeling_convbert.ConvBertGeneratorPredictions'>", + "ConvBertIntermediate": "<'transformers.models.convbert.modeling_convbert.ConvBertIntermediate'>", + "ConvBertLayer": "<'transformers.models.convbert.modeling_convbert.ConvBertLayer'>", + "ConvBertOutput": "<'transformers.models.convbert.modeling_convbert.ConvBertOutput'>", + "ConvBertPredictionHeadTransform": "<'transformers.models.convbert.modeling_convbert.ConvBertPredictionHeadTransform'>", + "ConvBertSelfAttention": "<'transformers.models.convbert.modeling_convbert.ConvBertSelfAttention'>", + "ConvBertSelfOutput": "<'transformers.models.convbert.modeling_convbert.ConvBertSelfOutput'>", + "ConvBertSequenceSummary": "<'transformers.models.convbert.modeling_convbert.ConvBertSequenceSummary'>", + "ConvDropoutLayerNorm": "<'transformers.models.squeezebert.modeling_squeezebert.ConvDropoutLayerNorm'>", + "ConvLayer": "<'transformers.models.deberta_v2.modeling_deberta_v2.ConvLayer'>", + "ConvNextDropPath": "<'transformers.models.convnext.modeling_convnext.ConvNextDropPath'>", + "ConvNextEmbeddings": "<'transformers.models.convnext.modeling_convnext.ConvNextEmbeddings'>", + "ConvNextEncoder": "<'transformers.models.convnext.modeling_convnext.ConvNextEncoder'>", + "ConvNextLayer": "<'transformers.models.convnext.modeling_convnext.ConvNextLayer'>", + "ConvNextLayerNorm": "<'transformers.models.convnext.modeling_convnext.ConvNextLayerNorm'>", + "ConvNextStage": "<'transformers.models.convnext.modeling_convnext.ConvNextStage'>", + "ConvNextV2DropPath": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2DropPath'>", + "ConvNextV2Embeddings": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2Embeddings'>", + "ConvNextV2Encoder": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2Encoder'>", + "ConvNextV2GRN": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2GRN'>", + "ConvNextV2Layer": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2Layer'>", + "ConvNextV2LayerNorm": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2LayerNorm'>", + "ConvNextV2Stage": "<'transformers.models.convnextv2.modeling_convnextv2.ConvNextV2Stage'>", + "ConvProjection": "<'transformers.models.canine.modeling_canine.ConvProjection'>", + "CpmAntAttention": "<'transformers.models.cpmant.modeling_cpmant.CpmAntAttention'>", + "CpmAntDenseGatedACT": "<'transformers.models.cpmant.modeling_cpmant.CpmAntDenseGatedACT'>", + "CpmAntEncoder": "<'transformers.models.cpmant.modeling_cpmant.CpmAntEncoder'>", + "CpmAntFeedForward": "<'transformers.models.cpmant.modeling_cpmant.CpmAntFeedForward'>", + "CpmAntFFNBlock": "<'transformers.models.cpmant.modeling_cpmant.CpmAntFFNBlock'>", + "CpmAntIntermediate": "<'transformers.models.cpmant.modeling_cpmant.CpmAntIntermediate'>", + "CpmAntLayerNorm": "<'transformers.models.cpmant.modeling_cpmant.CpmAntLayerNorm'>", + "CpmAntOutput": "<'transformers.models.cpmant.modeling_cpmant.CpmAntOutput'>", + "CpmAntSegmentPositionEmbedding": "<'transformers.models.cpmant.modeling_cpmant.CpmAntSegmentPositionEmbedding'>", + "CpmAntSelfAttentionBlock": "<'transformers.models.cpmant.modeling_cpmant.CpmAntSelfAttentionBlock'>", + "CpmAntTransformerBlock": "<'transformers.models.cpmant.modeling_cpmant.CpmAntTransformerBlock'>", + "CrossEntropyLoss": "<'torch.nn.modules.loss.CrossEntropyLoss'>", + "CsmAttention": "<'transformers.models.csm.modeling_csm.CsmAttention'>", + "CsmBackboneModelEmbeddings": "<'transformers.models.csm.modeling_csm.CsmBackboneModelEmbeddings'>", + "CsmCodebooksHead": "<'transformers.models.csm.modeling_csm.CsmCodebooksHead'>", + "CsmDecoderLayer": "<'transformers.models.csm.modeling_csm.CsmDecoderLayer'>", + "CsmMLP": "<'transformers.models.csm.modeling_csm.CsmMLP'>", + "CsmRMSNorm": "<'transformers.models.csm.modeling_csm.CsmRMSNorm'>", + "CsmRotaryEmbedding": "<'transformers.models.csm.modeling_csm.CsmRotaryEmbedding'>", + "CvtAttention": "<'transformers.models.cvt.modeling_cvt.CvtAttention'>", + "CvtConvEmbeddings": "<'transformers.models.cvt.modeling_cvt.CvtConvEmbeddings'>", + "CvtDropPath": "<'transformers.models.cvt.modeling_cvt.CvtDropPath'>", + "CvtEmbeddings": "<'transformers.models.cvt.modeling_cvt.CvtEmbeddings'>", + "CvtEncoder": "<'transformers.models.cvt.modeling_cvt.CvtEncoder'>", + "CvtIntermediate": "<'transformers.models.cvt.modeling_cvt.CvtIntermediate'>", + "CvtLayer": "<'transformers.models.cvt.modeling_cvt.CvtLayer'>", + "CvtOutput": "<'transformers.models.cvt.modeling_cvt.CvtOutput'>", + "CvtSelfAttention": "<'transformers.models.cvt.modeling_cvt.CvtSelfAttention'>", + "CvtSelfAttentionConvProjection": "<'transformers.models.cvt.modeling_cvt.CvtSelfAttentionConvProjection'>", + "CvtSelfAttentionLinearProjection": "<'transformers.models.cvt.modeling_cvt.CvtSelfAttentionLinearProjection'>", + "CvtSelfAttentionProjection": "<'transformers.models.cvt.modeling_cvt.CvtSelfAttentionProjection'>", + "CvtSelfOutput": "<'transformers.models.cvt.modeling_cvt.CvtSelfOutput'>", + "CvtStage": "<'transformers.models.cvt.modeling_cvt.CvtStage'>", + "DabDetrAttention": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrAttention'>", + "DabDetrConvEncoder": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrConvEncoder'>", + "DabDetrConvModel": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrConvModel'>", + "DabDetrDecoder": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrDecoder'>", + "DabDetrDecoderLayer": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrDecoderLayer'>", + "DabDetrDecoderLayerCrossAttention": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrDecoderLayerCrossAttention'>", + "DabDetrDecoderLayerFFN": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrDecoderLayerFFN'>", + "DabDetrDecoderLayerSelfAttention": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrDecoderLayerSelfAttention'>", + "DabDetrEncoder": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrEncoder'>", + "DabDetrEncoderLayer": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrEncoderLayer'>", + "DabDetrFrozenBatchNorm2d": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrFrozenBatchNorm2d'>", + "DabDetrMHAttentionMap": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrMHAttentionMap'>", + "DabDetrMLP": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrMLP'>", + "DabDetrSinePositionEmbedding": "<'transformers.models.dab_detr.modeling_dab_detr.DabDetrSinePositionEmbedding'>", + "DacDecoder": "<'transformers.models.dac.modeling_dac.DacDecoder'>", + "DacDecoderBlock": "<'transformers.models.dac.modeling_dac.DacDecoderBlock'>", + "DacEncoder": "<'transformers.models.dac.modeling_dac.DacEncoder'>", + "DacEncoderBlock": "<'transformers.models.dac.modeling_dac.DacEncoderBlock'>", + "DacResidualUnit": "<'transformers.models.dac.modeling_dac.DacResidualUnit'>", + "DacResidualVectorQuantize": "<'transformers.models.dac.modeling_dac.DacResidualVectorQuantize'>", + "DacVectorQuantize": "<'transformers.models.dac.modeling_dac.DacVectorQuantize'>", + "Data2VecAudioAdapter": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioAdapter'>", + "Data2VecAudioAdapterLayer": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioAdapterLayer'>", + "Data2VecAudioAttention": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioAttention'>", + "Data2VecAudioConvLayer": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioConvLayer'>", + "Data2VecAudioEncoder": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioEncoder'>", + "Data2VecAudioEncoderLayer": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioEncoderLayer'>", + "Data2VecAudioFeatureEncoder": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioFeatureEncoder'>", + "Data2VecAudioFeatureProjection": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioFeatureProjection'>", + "Data2VecAudioFeedForward": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioFeedForward'>", + "Data2VecAudioPadLayer": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioPadLayer'>", + "Data2VecAudioPositionalConvEmbedding": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioPositionalConvEmbedding'>", + "Data2VecAudioPositionalConvLayer": "<'transformers.models.data2vec.modeling_data2vec_audio.Data2VecAudioPositionalConvLayer'>", + "Data2VecTextAttention": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextAttention'>", + "Data2VecTextClassificationHead": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextClassificationHead'>", + "Data2VecTextEncoder": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextEncoder'>", + "Data2VecTextForTextEmbeddings": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextForTextEmbeddings'>", + "Data2VecTextIntermediate": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextIntermediate'>", + "Data2VecTextLayer": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextLayer'>", + "Data2VecTextLMHead": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextLMHead'>", + "Data2VecTextOutput": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextOutput'>", + "Data2VecTextPooler": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextPooler'>", + "Data2VecTextSelfAttention": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextSelfAttention'>", + "Data2VecTextSelfOutput": "<'transformers.models.data2vec.modeling_data2vec_text.Data2VecTextSelfOutput'>", + "Data2VecVisionAttention": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionAttention'>", + "Data2VecVisionConvModule": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionConvModule'>", + "Data2VecVisionDropPath": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionDropPath'>", + "Data2VecVisionEmbeddings": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionEmbeddings'>", + "Data2VecVisionEncoder": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionEncoder'>", + "Data2VecVisionFCNHead": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionFCNHead'>", + "Data2VecVisionIntermediate": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionIntermediate'>", + "Data2VecVisionLayer": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionLayer'>", + "Data2VecVisionOutput": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionOutput'>", + "Data2VecVisionPatchEmbeddings": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionPatchEmbeddings'>", + "Data2VecVisionPooler": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionPooler'>", + "Data2VecVisionPyramidPoolingBlock": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionPyramidPoolingBlock'>", + "Data2VecVisionPyramidPoolingModule": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionPyramidPoolingModule'>", + "Data2VecVisionRelativePositionBias": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionRelativePositionBias'>", + "Data2VecVisionSdpaSelfAttention": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionSdpaSelfAttention'>", + "Data2VecVisionSelfAttention": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionSelfAttention'>", + "Data2VecVisionSelfOutput": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionSelfOutput'>", + "Data2VecVisionUperHead": "<'transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionUperHead'>", + "DbrxAttention": "<'transformers.models.dbrx.modeling_dbrx.DbrxAttention'>", + "DbrxBlock": "<'transformers.models.dbrx.modeling_dbrx.DbrxBlock'>", + "DbrxExpertGLU": "<'transformers.models.dbrx.modeling_dbrx.DbrxExpertGLU'>", + "DbrxExperts": "<'transformers.models.dbrx.modeling_dbrx.DbrxExperts'>", + "DbrxFFN": "<'transformers.models.dbrx.modeling_dbrx.DbrxFFN'>", + "DbrxFlashAttention2": "<'transformers.models.dbrx.modeling_dbrx.DbrxFlashAttention2'>", + "DbrxNormAttentionNorm": "<'transformers.models.dbrx.modeling_dbrx.DbrxNormAttentionNorm'>", + "DbrxRotaryEmbedding": "<'transformers.models.dbrx.modeling_dbrx.DbrxRotaryEmbedding'>", + "DbrxRouter": "<'transformers.models.dbrx.modeling_dbrx.DbrxRouter'>", + "DbrxSdpaAttention": "<'transformers.models.dbrx.modeling_dbrx.DbrxSdpaAttention'>", + "DebertaAttention": "<'transformers.models.deberta.modeling_deberta.DebertaAttention'>", + "DebertaEmbeddings": "<'transformers.models.deberta.modeling_deberta.DebertaEmbeddings'>", + "DebertaEncoder": "<'transformers.models.deberta.modeling_deberta.DebertaEncoder'>", + "DebertaIntermediate": "<'transformers.models.deberta.modeling_deberta.DebertaIntermediate'>", + "DebertaLayer": "<'transformers.models.deberta.modeling_deberta.DebertaLayer'>", + "DebertaLayerNorm": "<'transformers.models.deberta.modeling_deberta.DebertaLayerNorm'>", + "DebertaLMPredictionHead": "<'transformers.models.deberta.modeling_deberta.DebertaLMPredictionHead'>", + "DebertaOnlyMLMHead": "<'transformers.models.deberta.modeling_deberta.DebertaOnlyMLMHead'>", + "DebertaOutput": "<'transformers.models.deberta.modeling_deberta.DebertaOutput'>", + "DebertaSelfOutput": "<'transformers.models.deberta.modeling_deberta.DebertaSelfOutput'>", + "DebertaV2Attention": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Attention'>", + "DebertaV2Embeddings": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Embeddings'>", + "DebertaV2Encoder": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Encoder'>", + "DebertaV2Intermediate": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Intermediate'>", + "DebertaV2Layer": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Layer'>", + "DebertaV2LMPredictionHead": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2LMPredictionHead'>", + "DebertaV2OnlyMLMHead": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2OnlyMLMHead'>", + "DebertaV2Output": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2Output'>", + "DebertaV2SelfOutput": "<'transformers.models.deberta_v2.modeling_deberta_v2.DebertaV2SelfOutput'>", + "DecisionTransformerGPT2Attention": "<'transformers.models.decision_transformer.modeling_decision_transformer.DecisionTransformerGPT2Attention'>", + "DecisionTransformerGPT2Block": "<'transformers.models.decision_transformer.modeling_decision_transformer.DecisionTransformerGPT2Block'>", + "DecisionTransformerGPT2MLP": "<'transformers.models.decision_transformer.modeling_decision_transformer.DecisionTransformerGPT2MLP'>", + "DecoderLayer": "<'transformers.models.fsmt.modeling_fsmt.DecoderLayer'>", + "DeepseekV2Attention": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2Attention'>", + "DeepseekV2DecoderLayer": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2DecoderLayer'>", + "DeepseekV2MLP": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2MLP'>", + "DeepseekV2MoE": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2MoE'>", + "DeepseekV2MoEGate": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2MoEGate'>", + "DeepseekV2RMSNorm": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2RMSNorm'>", + "DeepseekV2RotaryEmbedding": "<'transformers.models.deepseek_v2.modular_deepseek_v2.DeepseekV2RotaryEmbedding'>", + "DeepseekV3Attention": "<'transformers.models.deepseek_v3.modular_deepseek_v3.DeepseekV3Attention'>", + "DeepseekV3DecoderLayer": "<'transformers.models.deepseek_v3.modeling_deepseek_v3.DeepseekV3DecoderLayer'>", + "DeepseekV3MLP": "<'transformers.models.deepseek_v3.modeling_deepseek_v3.DeepseekV3MLP'>", + "DeepseekV3MoE": "<'transformers.models.deepseek_v3.modular_deepseek_v3.DeepseekV3MoE'>", + "DeepseekV3RMSNorm": "<'transformers.models.deepseek_v3.modeling_deepseek_v3.DeepseekV3RMSNorm'>", + "DeepseekV3RotaryEmbedding": "<'transformers.models.deepseek_v3.modular_deepseek_v3.DeepseekV3RotaryEmbedding'>", + "DeepseekV3TopkRouter": "<'transformers.models.deepseek_v3.modeling_deepseek_v3.DeepseekV3TopkRouter'>", + "DeepseekVLAligner": "<'transformers.models.deepseek_vl.modular_deepseek_vl.DeepseekVLAligner'>", + "DeepseekVLHybridAligner": "<'transformers.models.deepseek_vl_hybrid.modular_deepseek_vl_hybrid.DeepseekVLHybridAligner'>", + "DeepseekVLHybridLayerNorm": "<'transformers.models.deepseek_vl_hybrid.modular_deepseek_vl_hybrid.DeepseekVLHybridLayerNorm'>", + "DeepseekVLSamVisionNeck": "<'transformers.models.deepseek_vl_hybrid.modular_deepseek_vl_hybrid.DeepseekVLSamVisionNeck'>", + "DeepseekVLSamVisionProj": "<'transformers.models.deepseek_vl_hybrid.modular_deepseek_vl_hybrid.DeepseekVLSamVisionProj'>", + "DeformableDetrConvEncoder": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrConvEncoder'>", + "DeformableDetrConvModel": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrConvModel'>", + "DeformableDetrDecoder": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrDecoder'>", + "DeformableDetrDecoderLayer": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrDecoderLayer'>", + "DeformableDetrEncoder": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrEncoder'>", + "DeformableDetrEncoderLayer": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrEncoderLayer'>", + "DeformableDetrFrozenBatchNorm2d": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrFrozenBatchNorm2d'>", + "DeformableDetrHungarianMatcher": "<'transformers.loss.loss_deformable_detr.DeformableDetrHungarianMatcher'>", + "DeformableDetrImageLoss": "<'transformers.loss.loss_deformable_detr.DeformableDetrImageLoss'>", + "DeformableDetrLearnedPositionEmbedding": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrLearnedPositionEmbedding'>", + "DeformableDetrMLPPredictionHead": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrMLPPredictionHead'>", + "DeformableDetrMultiheadAttention": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrMultiheadAttention'>", + "DeformableDetrMultiscaleDeformableAttention": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrMultiscaleDeformableAttention'>", + "DeformableDetrSinePositionEmbedding": "<'transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrSinePositionEmbedding'>", + "DeiTAttention": "<'transformers.models.deit.modeling_deit.DeiTAttention'>", + "DeiTEmbeddings": "<'transformers.models.deit.modeling_deit.DeiTEmbeddings'>", + "DeiTEncoder": "<'transformers.models.deit.modeling_deit.DeiTEncoder'>", + "DeiTIntermediate": "<'transformers.models.deit.modeling_deit.DeiTIntermediate'>", + "DeiTLayer": "<'transformers.models.deit.modeling_deit.DeiTLayer'>", + "DeiTOutput": "<'transformers.models.deit.modeling_deit.DeiTOutput'>", + "DeiTPatchEmbeddings": "<'transformers.models.deit.modeling_deit.DeiTPatchEmbeddings'>", + "DeiTPooler": "<'transformers.models.deit.modeling_deit.DeiTPooler'>", + "DeiTSelfAttention": "<'transformers.models.deit.modeling_deit.DeiTSelfAttention'>", + "DeiTSelfOutput": "<'transformers.models.deit.modeling_deit.DeiTSelfOutput'>", + "DepthAnythingDepthEstimationHead": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingDepthEstimationHead'>", + "DepthAnythingFeatureFusionLayer": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingFeatureFusionLayer'>", + "DepthAnythingFeatureFusionStage": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingFeatureFusionStage'>", + "DepthAnythingNeck": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingNeck'>", + "DepthAnythingPreActResidualLayer": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingPreActResidualLayer'>", + "DepthAnythingReassembleLayer": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingReassembleLayer'>", + "DepthAnythingReassembleStage": "<'transformers.models.depth_anything.modeling_depth_anything.DepthAnythingReassembleStage'>", + "DepthProDepthEstimationHead": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProDepthEstimationHead'>", + "DepthProEncoder": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProEncoder'>", + "DepthProFeatureFusionLayer": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFeatureFusionLayer'>", + "DepthProFeatureFusionStage": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFeatureFusionStage'>", + "DepthProFeatureProjection": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFeatureProjection'>", + "DepthProFeatureUpsample": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFeatureUpsample'>", + "DepthProFeatureUpsampleBlock": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFeatureUpsampleBlock'>", + "DepthProFovEncoder": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFovEncoder'>", + "DepthProFovHead": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFovHead'>", + "DepthProFovModel": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProFovModel'>", + "DepthProImageEncoder": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProImageEncoder'>", + "DepthProNeck": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProNeck'>", + "DepthProPatchEncoder": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProPatchEncoder'>", + "DepthProPreActResidualLayer": "<'transformers.models.depth_pro.modeling_depth_pro.DepthProPreActResidualLayer'>", + "DetaBackboneWithPositionalEncodings": "<'transformers.models.deprecated.deta.modeling_deta.DetaBackboneWithPositionalEncodings'>", + "DetaDecoder": "<'transformers.models.deprecated.deta.modeling_deta.DetaDecoder'>", + "DetaDecoderLayer": "<'transformers.models.deprecated.deta.modeling_deta.DetaDecoderLayer'>", + "DetaEncoder": "<'transformers.models.deprecated.deta.modeling_deta.DetaEncoder'>", + "DetaEncoderLayer": "<'transformers.models.deprecated.deta.modeling_deta.DetaEncoderLayer'>", + "DetaFrozenBatchNorm2d": "<'transformers.models.deprecated.deta.modeling_deta.DetaFrozenBatchNorm2d'>", + "DetaHungarianMatcher": "<'transformers.models.deprecated.deta.modeling_deta.DetaHungarianMatcher'>", + "DetaLearnedPositionEmbedding": "<'transformers.models.deprecated.deta.modeling_deta.DetaLearnedPositionEmbedding'>", + "DetaLoss": "<'transformers.models.deprecated.deta.modeling_deta.DetaLoss'>", + "DetaMLPPredictionHead": "<'transformers.models.deprecated.deta.modeling_deta.DetaMLPPredictionHead'>", + "DetaMultiheadAttention": "<'transformers.models.deprecated.deta.modeling_deta.DetaMultiheadAttention'>", + "DetaMultiscaleDeformableAttention": "<'transformers.models.deprecated.deta.modeling_deta.DetaMultiscaleDeformableAttention'>", + "DetaSinePositionEmbedding": "<'transformers.models.deprecated.deta.modeling_deta.DetaSinePositionEmbedding'>", + "DetaStage1Assigner": "<'transformers.models.deprecated.deta.modeling_deta.DetaStage1Assigner'>", + "DetaStage2Assigner": "<'transformers.models.deprecated.deta.modeling_deta.DetaStage2Assigner'>", + "DetrAttention": "<'transformers.models.detr.modeling_detr.DetrAttention'>", + "DetrConvEncoder": "<'transformers.models.detr.modeling_detr.DetrConvEncoder'>", + "DetrConvModel": "<'transformers.models.detr.modeling_detr.DetrConvModel'>", + "DetrDecoder": "<'transformers.models.detr.modeling_detr.DetrDecoder'>", + "DetrDecoderLayer": "<'transformers.models.detr.modeling_detr.DetrDecoderLayer'>", + "DetrEncoder": "<'transformers.models.detr.modeling_detr.DetrEncoder'>", + "DetrEncoderLayer": "<'transformers.models.detr.modeling_detr.DetrEncoderLayer'>", + "DetrFrozenBatchNorm2d": "<'transformers.models.detr.modeling_detr.DetrFrozenBatchNorm2d'>", + "DetrLearnedPositionEmbedding": "<'transformers.models.detr.modeling_detr.DetrLearnedPositionEmbedding'>", + "DetrMaskHeadSmallConv": "<'transformers.models.detr.modeling_detr.DetrMaskHeadSmallConv'>", + "DetrMHAttentionMap": "<'transformers.models.detr.modeling_detr.DetrMHAttentionMap'>", + "DetrMLPPredictionHead": "<'transformers.models.detr.modeling_detr.DetrMLPPredictionHead'>", + "DetrSinePositionEmbedding": "<'transformers.models.detr.modeling_detr.DetrSinePositionEmbedding'>", + "DFineConvEncoder": "<'transformers.models.d_fine.modeling_d_fine.DFineConvEncoder'>", + "DFineConvNormLayer": "<'transformers.models.d_fine.modeling_d_fine.DFineConvNormLayer'>", + "DFineCSPRepLayer": "<'transformers.models.d_fine.modeling_d_fine.DFineCSPRepLayer'>", + "DFineDecoder": "<'transformers.models.d_fine.modeling_d_fine.DFineDecoder'>", + "DFineDecoderLayer": "<'transformers.models.d_fine.modeling_d_fine.DFineDecoderLayer'>", + "DFineEncoder": "<'transformers.models.d_fine.modeling_d_fine.DFineEncoder'>", + "DFineEncoderLayer": "<'transformers.models.d_fine.modeling_d_fine.DFineEncoderLayer'>", + "DFineFrozenBatchNorm2d": "<'transformers.models.d_fine.modeling_d_fine.DFineFrozenBatchNorm2d'>", + "DFineGate": "<'transformers.models.d_fine.modeling_d_fine.DFineGate'>", + "DFineHybridEncoder": "<'transformers.models.d_fine.modeling_d_fine.DFineHybridEncoder'>", + "DFineIntegral": "<'transformers.models.d_fine.modeling_d_fine.DFineIntegral'>", + "DFineLoss": "<'transformers.loss.loss_d_fine.DFineLoss'>", + "DFineLQE": "<'transformers.models.d_fine.modeling_d_fine.DFineLQE'>", + "DFineMLP": "<'transformers.models.d_fine.modeling_d_fine.DFineMLP'>", + "DFineMLPPredictionHead": "<'transformers.models.d_fine.modeling_d_fine.DFineMLPPredictionHead'>", + "DFineMultiheadAttention": "<'transformers.models.d_fine.modeling_d_fine.DFineMultiheadAttention'>", + "DFineMultiscaleDeformableAttention": "<'transformers.models.d_fine.modeling_d_fine.DFineMultiscaleDeformableAttention'>", + "DFineRepNCSPELAN4": "<'transformers.models.d_fine.modeling_d_fine.DFineRepNCSPELAN4'>", + "DFineRepVggBlock": "<'transformers.models.d_fine.modeling_d_fine.DFineRepVggBlock'>", + "DFineSCDown": "<'transformers.models.d_fine.modeling_d_fine.DFineSCDown'>", + "DiaCrossAttention": "<'transformers.models.dia.modeling_dia.DiaCrossAttention'>", + "DiaDecoder": "<'transformers.models.dia.modeling_dia.DiaDecoder'>", + "DiaDecoderLayer": "<'transformers.models.dia.modeling_dia.DiaDecoderLayer'>", + "DiaEncoder": "<'transformers.models.dia.modeling_dia.DiaEncoder'>", + "DiaEncoderLayer": "<'transformers.models.dia.modeling_dia.DiaEncoderLayer'>", + "DiaMLP": "<'transformers.models.dia.modeling_dia.DiaMLP'>", + "DiaMultiChannelEmbedding": "<'transformers.models.dia.modeling_dia.DiaMultiChannelEmbedding'>", + "DiaRMSNorm": "<'transformers.models.dia.modeling_dia.DiaRMSNorm'>", + "DiaRotaryEmbedding": "<'transformers.models.dia.modeling_dia.DiaRotaryEmbedding'>", + "DiaSelfAttention": "<'transformers.models.dia.modeling_dia.DiaSelfAttention'>", + "DiffLlamaAttention": "<'transformers.models.diffllama.modular_diffllama.DiffLlamaAttention'>", + "DiffLlamaDecoderLayer": "<'transformers.models.diffllama.modular_diffllama.DiffLlamaDecoderLayer'>", + "DiffLlamaFlashAttention2": "<'transformers.models.diffllama.modular_diffllama.DiffLlamaFlashAttention2'>", + "DiffLlamaMLP": "<'transformers.models.diffllama.modular_diffllama.DiffLlamaMLP'>", + "DiffLlamaRMSNorm": "<'transformers.models.diffllama.modeling_diffllama.DiffLlamaRMSNorm'>", + "DiffLlamaRotaryEmbedding": "<'transformers.models.diffllama.modeling_diffllama.DiffLlamaRotaryEmbedding'>", + "DiffLlamaSdpaAttention": "<'transformers.models.diffllama.modular_diffllama.DiffLlamaSdpaAttention'>", + "DinatDownsampler": "<'transformers.models.dinat.modeling_dinat.DinatDownsampler'>", + "DinatDropPath": "<'transformers.models.dinat.modeling_dinat.DinatDropPath'>", + "DinatEmbeddings": "<'transformers.models.dinat.modeling_dinat.DinatEmbeddings'>", + "DinatEncoder": "<'transformers.models.dinat.modeling_dinat.DinatEncoder'>", + "DinatIntermediate": "<'transformers.models.dinat.modeling_dinat.DinatIntermediate'>", + "DinatLayer": "<'transformers.models.dinat.modeling_dinat.DinatLayer'>", + "DinatOutput": "<'transformers.models.dinat.modeling_dinat.DinatOutput'>", + "DinatPatchEmbeddings": "<'transformers.models.dinat.modeling_dinat.DinatPatchEmbeddings'>", + "DinatStage": "<'transformers.models.dinat.modeling_dinat.DinatStage'>", + "Dinov2Attention": "<'transformers.models.dinov2.modeling_dinov2.Dinov2Attention'>", + "Dinov2DropPath": "<'transformers.models.dinov2.modeling_dinov2.Dinov2DropPath'>", + "Dinov2Embeddings": "<'transformers.models.dinov2.modeling_dinov2.Dinov2Embeddings'>", + "Dinov2Encoder": "<'transformers.models.dinov2.modeling_dinov2.Dinov2Encoder'>", + "Dinov2Layer": "<'transformers.models.dinov2.modeling_dinov2.Dinov2Layer'>", + "Dinov2LayerScale": "<'transformers.models.dinov2.modeling_dinov2.Dinov2LayerScale'>", + "Dinov2MLP": "<'transformers.models.dinov2.modeling_dinov2.Dinov2MLP'>", + "Dinov2PatchEmbeddings": "<'transformers.models.dinov2.modeling_dinov2.Dinov2PatchEmbeddings'>", + "Dinov2SelfAttention": "<'transformers.models.dinov2.modeling_dinov2.Dinov2SelfAttention'>", + "Dinov2SelfOutput": "<'transformers.models.dinov2.modeling_dinov2.Dinov2SelfOutput'>", + "Dinov2SwiGLUFFN": "<'transformers.models.dinov2.modeling_dinov2.Dinov2SwiGLUFFN'>", + "Dinov2WithRegistersAttention": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersAttention'>", + "Dinov2WithRegistersDropPath": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersDropPath'>", + "Dinov2WithRegistersEmbeddings": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersEmbeddings'>", + "Dinov2WithRegistersEncoder": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersEncoder'>", + "Dinov2WithRegistersLayer": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersLayer'>", + "Dinov2WithRegistersLayerScale": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersLayerScale'>", + "Dinov2WithRegistersMLP": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersMLP'>", + "Dinov2WithRegistersPatchEmbeddings": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersPatchEmbeddings'>", + "Dinov2WithRegistersSelfAttention": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersSelfAttention'>", + "Dinov2WithRegistersSelfOutput": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersSelfOutput'>", + "Dinov2WithRegistersSwiGLUFFN": "<'transformers.models.dinov2_with_registers.modeling_dinov2_with_registers.Dinov2WithRegistersSwiGLUFFN'>", + "DisentangledSelfAttention": "<'transformers.models.deberta_v2.modeling_deberta_v2.DisentangledSelfAttention'>", + "DistilBertFlashAttention2": "<'transformers.models.distilbert.modeling_distilbert.DistilBertFlashAttention2'>", + "DistilBertSdpaAttention": "<'transformers.models.distilbert.modeling_distilbert.DistilBertSdpaAttention'>", + "DiTAttention": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTAttention'>", + "DiTCodecEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTCodecEmbedding'>", + "DiTDecoderLayer": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTDecoderLayer'>", + "DiTInputEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTInputEmbedding'>", + "DiTMLP": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTMLP'>", + "DiTTimestepEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DiTTimestepEmbedding'>", + "DogeAttention": "<'transformers.models.doge.modeling_doge.DogeAttention'>", + "DogeCDMoE": "<'transformers.models.doge.modeling_doge.DogeCDMoE'>", + "DogeDecoderLayer": "<'transformers.models.doge.modeling_doge.DogeDecoderLayer'>", + "DogeMLP": "<'transformers.models.doge.modeling_doge.DogeMLP'>", + "DogeRMSNorm": "<'transformers.models.doge.modeling_doge.DogeRMSNorm'>", + "DogeRotaryEmbedding": "<'transformers.models.doge.modeling_doge.DogeRotaryEmbedding'>", + "DonutSwinAttention": "<'transformers.models.donut.modeling_donut_swin.DonutSwinAttention'>", + "DonutSwinDropPath": "<'transformers.models.donut.modeling_donut_swin.DonutSwinDropPath'>", + "DonutSwinEmbeddings": "<'transformers.models.donut.modeling_donut_swin.DonutSwinEmbeddings'>", + "DonutSwinEncoder": "<'transformers.models.donut.modeling_donut_swin.DonutSwinEncoder'>", + "DonutSwinIntermediate": "<'transformers.models.donut.modeling_donut_swin.DonutSwinIntermediate'>", + "DonutSwinLayer": "<'transformers.models.donut.modeling_donut_swin.DonutSwinLayer'>", + "DonutSwinOutput": "<'transformers.models.donut.modeling_donut_swin.DonutSwinOutput'>", + "DonutSwinPatchEmbeddings": "<'transformers.models.donut.modeling_donut_swin.DonutSwinPatchEmbeddings'>", + "DonutSwinPatchMerging": "<'transformers.models.donut.modeling_donut_swin.DonutSwinPatchMerging'>", + "DonutSwinSelfAttention": "<'transformers.models.donut.modeling_donut_swin.DonutSwinSelfAttention'>", + "DonutSwinSelfOutput": "<'transformers.models.donut.modeling_donut_swin.DonutSwinSelfOutput'>", + "DonutSwinStage": "<'transformers.models.donut.modeling_donut_swin.DonutSwinStage'>", + "Dots1Attention": "<'transformers.models.dots1.modeling_dots1.Dots1Attention'>", + "Dots1DecoderLayer": "<'transformers.models.dots1.modeling_dots1.Dots1DecoderLayer'>", + "Dots1MLP": "<'transformers.models.dots1.modeling_dots1.Dots1MLP'>", + "Dots1MoE": "<'transformers.models.dots1.modeling_dots1.Dots1MoE'>", + "Dots1RMSNorm": "<'transformers.models.dots1.modeling_dots1.Dots1RMSNorm'>", + "Dots1RotaryEmbedding": "<'transformers.models.dots1.modeling_dots1.Dots1RotaryEmbedding'>", + "Dots1TopkRouter": "<'transformers.models.dots1.modeling_dots1.Dots1TopkRouter'>", + "DownSample1d": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.DownSample1d'>", + "DPREncoder": "<'transformers.models.dpr.modeling_dpr.DPREncoder'>", + "DPRSpanPredictor": "<'transformers.models.dpr.modeling_dpr.DPRSpanPredictor'>", + "DPTAuxiliaryHead": "<'transformers.models.dpt.modeling_dpt.DPTAuxiliaryHead'>", + "DPTDepthEstimationHead": "<'transformers.models.dpt.modeling_dpt.DPTDepthEstimationHead'>", + "DPTFeatureFusionLayer": "<'transformers.models.dpt.modeling_dpt.DPTFeatureFusionLayer'>", + "DPTFeatureFusionStage": "<'transformers.models.dpt.modeling_dpt.DPTFeatureFusionStage'>", + "DPTNeck": "<'transformers.models.dpt.modeling_dpt.DPTNeck'>", + "DPTPreActResidualLayer": "<'transformers.models.dpt.modeling_dpt.DPTPreActResidualLayer'>", + "DPTReassembleLayer": "<'transformers.models.dpt.modeling_dpt.DPTReassembleLayer'>", + "DPTReassembleStage": "<'transformers.models.dpt.modeling_dpt.DPTReassembleStage'>", + "DPTSelfAttention": "<'transformers.models.dpt.modeling_dpt.DPTSelfAttention'>", + "DPTSemanticSegmentationHead": "<'transformers.models.dpt.modeling_dpt.DPTSemanticSegmentationHead'>", + "DPTViTAttention": "<'transformers.models.dpt.modeling_dpt.DPTViTAttention'>", + "DPTViTEmbeddings": "<'transformers.models.dpt.modeling_dpt.DPTViTEmbeddings'>", + "DPTViTEncoder": "<'transformers.models.dpt.modeling_dpt.DPTViTEncoder'>", + "DPTViTHybridEmbeddings": "<'transformers.models.dpt.modeling_dpt.DPTViTHybridEmbeddings'>", + "DPTViTIntermediate": "<'transformers.models.dpt.modeling_dpt.DPTViTIntermediate'>", + "DPTViTLayer": "<'transformers.models.dpt.modeling_dpt.DPTViTLayer'>", + "DPTViTOutput": "<'transformers.models.dpt.modeling_dpt.DPTViTOutput'>", + "DPTViTPatchEmbeddings": "<'transformers.models.dpt.modeling_dpt.DPTViTPatchEmbeddings'>", + "DPTViTPooler": "<'transformers.models.dpt.modeling_dpt.DPTViTPooler'>", + "DPTViTSelfOutput": "<'transformers.models.dpt.modeling_dpt.DPTViTSelfOutput'>", + "DynamicPad2d": "<'transformers.models.bit.modeling_bit.DynamicPad2d'>", + "ECAPA_TimeDelayNet": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.ECAPA_TimeDelayNet'>", + "EfficientFormerConvMlp": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerConvMlp'>", + "EfficientFormerConvStem": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerConvStem'>", + "EfficientFormerDenseMlp": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerDenseMlp'>", + "EfficientFormerDropPath": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerDropPath'>", + "EfficientFormerEncoder": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerEncoder'>", + "EfficientFormerFlat": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerFlat'>", + "EfficientFormerIntermediateStage": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerIntermediateStage'>", + "EfficientFormerLastStage": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerLastStage'>", + "EfficientFormerMeta3D": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerMeta3D'>", + "EfficientFormerMeta3DLayers": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerMeta3DLayers'>", + "EfficientFormerMeta4D": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerMeta4D'>", + "EfficientFormerMeta4DLayers": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerMeta4DLayers'>", + "EfficientFormerPatchEmbeddings": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerPatchEmbeddings'>", + "EfficientFormerPooling": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerPooling'>", + "EfficientFormerSelfAttention": "<'transformers.models.deprecated.efficientformer.modeling_efficientformer.EfficientFormerSelfAttention'>", + "EfficientLoFTRAggregatedAttention": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRAggregatedAttention'>", + "EfficientLoFTRAggregationLayer": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRAggregationLayer'>", + "EfficientLoFTRAttention": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRAttention'>", + "EfficientLoFTRConvNormLayer": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRConvNormLayer'>", + "EfficientLoFTRepVGG": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRepVGG'>", + "EfficientLoFTRFineFusionLayer": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRFineFusionLayer'>", + "EfficientLoFTRLocalFeatureTransformer": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRLocalFeatureTransformer'>", + "EfficientLoFTRLocalFeatureTransformerLayer": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRLocalFeatureTransformerLayer'>", + "EfficientLoFTRMLP": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRMLP'>", + "EfficientLoFTROutConvBlock": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTROutConvBlock'>", + "EfficientLoFTRRepVGGBlock": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRRepVGGBlock'>", + "EfficientLoFTRRepVGGStage": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRRepVGGStage'>", + "EfficientLoFTRRotaryEmbedding": "<'transformers.models.efficientloftr.modeling_efficientloftr.EfficientLoFTRRotaryEmbedding'>", + "EfficientNetBlock": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetBlock'>", + "EfficientNetDepthwiseConv2d": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetDepthwiseConv2d'>", + "EfficientNetDepthwiseLayer": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetDepthwiseLayer'>", + "EfficientNetEmbeddings": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetEmbeddings'>", + "EfficientNetEncoder": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetEncoder'>", + "EfficientNetExpansionLayer": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetExpansionLayer'>", + "EfficientNetFinalBlockLayer": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetFinalBlockLayer'>", + "EfficientNetSqueezeExciteLayer": "<'transformers.models.efficientnet.modeling_efficientnet.EfficientNetSqueezeExciteLayer'>", + "EinLinear": "<'transformers.models.deprecated.trajectory_transformer.modeling_trajectory_transformer.EinLinear'>", + "ElectraAttention": "<'transformers.models.electra.modeling_electra.ElectraAttention'>", + "ElectraClassificationHead": "<'transformers.models.electra.modeling_electra.ElectraClassificationHead'>", + "ElectraDiscriminatorPredictions": "<'transformers.models.electra.modeling_electra.ElectraDiscriminatorPredictions'>", + "ElectraEmbeddings": "<'transformers.models.electra.modeling_electra.ElectraEmbeddings'>", + "ElectraEncoder": "<'transformers.models.electra.modeling_electra.ElectraEncoder'>", + "ElectraGeneratorPredictions": "<'transformers.models.electra.modeling_electra.ElectraGeneratorPredictions'>", + "ElectraIntermediate": "<'transformers.models.electra.modeling_electra.ElectraIntermediate'>", + "ElectraLayer": "<'transformers.models.electra.modeling_electra.ElectraLayer'>", + "ElectraOutput": "<'transformers.models.electra.modeling_electra.ElectraOutput'>", + "ElectraSelfAttention": "<'transformers.models.electra.modeling_electra.ElectraSelfAttention'>", + "ElectraSelfOutput": "<'transformers.models.electra.modeling_electra.ElectraSelfOutput'>", + "ElectraSequenceSummary": "<'transformers.models.electra.modeling_electra.ElectraSequenceSummary'>", + "Embeddings": "<'transformers.models.distilbert.modeling_distilbert.Embeddings'>", + "Emu3Attention": "<'transformers.models.emu3.modeling_emu3.Emu3Attention'>", + "Emu3DecoderLayer": "<'transformers.models.emu3.modeling_emu3.Emu3DecoderLayer'>", + "Emu3MLP": "<'transformers.models.emu3.modeling_emu3.Emu3MLP'>", + "Emu3RMSNorm": "<'transformers.models.emu3.modeling_emu3.Emu3RMSNorm'>", + "Emu3RotaryEmbedding": "<'transformers.models.emu3.modeling_emu3.Emu3RotaryEmbedding'>", + "Emu3VQVAEAttentionBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEAttentionBlock'>", + "Emu3VQVAEConv3d": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEConv3d'>", + "Emu3VQVAEDecoder": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEDecoder'>", + "Emu3VQVAEDownBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEDownBlock'>", + "Emu3VQVAEEncoder": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEEncoder'>", + "Emu3VQVAEEncoderConvDownsample": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEEncoderConvDownsample'>", + "Emu3VQVAEEncoderConvUpsample": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEEncoderConvUpsample'>", + "Emu3VQVAEGroupNorm": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEGroupNorm'>", + "Emu3VQVAEMiddleBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEMiddleBlock'>", + "Emu3VQVAEResnetBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEResnetBlock'>", + "Emu3VQVAESpatialNorm": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAESpatialNorm'>", + "Emu3VQVAETemporalDownsample": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAETemporalDownsample'>", + "Emu3VQVAETemporalResnetBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAETemporalResnetBlock'>", + "Emu3VQVAETemporalUpsample": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAETemporalUpsample'>", + "Emu3VQVAEUpBlock": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEUpBlock'>", + "Emu3VQVAEVectorQuantizer": "<'transformers.models.emu3.modeling_emu3.Emu3VQVAEVectorQuantizer'>", + "EncodecConv1d": "<'transformers.models.encodec.modeling_encodec.EncodecConv1d'>", + "EncodecConvTranspose1d": "<'transformers.models.encodec.modeling_encodec.EncodecConvTranspose1d'>", + "EncodecDecoder": "<'transformers.models.encodec.modeling_encodec.EncodecDecoder'>", + "EncodecEncoder": "<'transformers.models.encodec.modeling_encodec.EncodecEncoder'>", + "EncodecEuclideanCodebook": "<'transformers.models.encodec.modeling_encodec.EncodecEuclideanCodebook'>", + "EncodecLSTM": "<'transformers.models.encodec.modeling_encodec.EncodecLSTM'>", + "EncodecResidualVectorQuantizer": "<'transformers.models.encodec.modeling_encodec.EncodecResidualVectorQuantizer'>", + "EncodecResnetBlock": "<'transformers.models.encodec.modeling_encodec.EncodecResnetBlock'>", + "EncodecVectorQuantization": "<'transformers.models.encodec.modeling_encodec.EncodecVectorQuantization'>", + "EncoderLayer": "<'transformers.models.fsmt.modeling_fsmt.EncoderLayer'>", + "EntityPredictionHead": "<'transformers.models.luke.modeling_luke.EntityPredictionHead'>", + "EntityPredictionHeadTransform": "<'transformers.models.luke.modeling_luke.EntityPredictionHeadTransform'>", + "EomtAttention": "<'transformers.models.eomt.modeling_eomt.EomtAttention'>", + "EomtDropPath": "<'transformers.models.eomt.modeling_eomt.EomtDropPath'>", + "EomtEmbeddings": "<'transformers.models.eomt.modeling_eomt.EomtEmbeddings'>", + "EomtHungarianMatcher": "<'transformers.models.eomt.modeling_eomt.EomtHungarianMatcher'>", + "EomtLayer": "<'transformers.models.eomt.modeling_eomt.EomtLayer'>", + "EomtLayerNorm2d": "<'transformers.models.eomt.modeling_eomt.EomtLayerNorm2d'>", + "EomtLayerScale": "<'transformers.models.eomt.modeling_eomt.EomtLayerScale'>", + "EomtLoss": "<'transformers.models.eomt.modeling_eomt.EomtLoss'>", + "EomtMaskHead": "<'transformers.models.eomt.modeling_eomt.EomtMaskHead'>", + "EomtMLP": "<'transformers.models.eomt.modeling_eomt.EomtMLP'>", + "EomtPatchEmbeddings": "<'transformers.models.eomt.modeling_eomt.EomtPatchEmbeddings'>", + "EomtScaleBlock": "<'transformers.models.eomt.modeling_eomt.EomtScaleBlock'>", + "EomtScaleLayer": "<'transformers.models.eomt.modeling_eomt.EomtScaleLayer'>", + "EomtSwiGLUFFN": "<'transformers.models.eomt.modeling_eomt.EomtSwiGLUFFN'>", + "Ernie4_5_MoeAttention": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeAttention'>", + "Ernie4_5_MoeDecoderLayer": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeDecoderLayer'>", + "Ernie4_5_MoeMLP": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeMLP'>", + "Ernie4_5_MoeRMSNorm": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeRMSNorm'>", + "Ernie4_5_MoeRotaryEmbedding": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeRotaryEmbedding'>", + "Ernie4_5_MoeSparseMoeBlock": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeSparseMoeBlock'>", + "Ernie4_5_MoeStatics": "<'transformers.models.ernie4_5_moe.modular_ernie4_5_moe.Ernie4_5_MoeStatics'>", + "Ernie4_5Attention": "<'transformers.models.ernie4_5.modeling_ernie4_5.Ernie4_5Attention'>", + "Ernie4_5DecoderLayer": "<'transformers.models.ernie4_5.modeling_ernie4_5.Ernie4_5DecoderLayer'>", + "Ernie4_5MLP": "<'transformers.models.ernie4_5.modeling_ernie4_5.Ernie4_5MLP'>", + "Ernie4_5RMSNorm": "<'transformers.models.ernie4_5.modeling_ernie4_5.Ernie4_5RMSNorm'>", + "Ernie4_5RotaryEmbedding": "<'transformers.models.ernie4_5.modeling_ernie4_5.Ernie4_5RotaryEmbedding'>", + "ErnieAttention": "<'transformers.models.ernie.modeling_ernie.ErnieAttention'>", + "ErnieEmbeddings": "<'transformers.models.ernie.modeling_ernie.ErnieEmbeddings'>", + "ErnieEncoder": "<'transformers.models.ernie.modeling_ernie.ErnieEncoder'>", + "ErnieIntermediate": "<'transformers.models.ernie.modeling_ernie.ErnieIntermediate'>", + "ErnieLayer": "<'transformers.models.ernie.modeling_ernie.ErnieLayer'>", + "ErnieLMPredictionHead": "<'transformers.models.ernie.modeling_ernie.ErnieLMPredictionHead'>", + "ErnieMAttention": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMAttention'>", + "ErnieMEmbeddings": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMEmbeddings'>", + "ErnieMEncoder": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMEncoder'>", + "ErnieMEncoderLayer": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMEncoderLayer'>", + "ErnieMPooler": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMPooler'>", + "ErnieMSelfAttention": "<'transformers.models.deprecated.ernie_m.modeling_ernie_m.ErnieMSelfAttention'>", + "ErnieOnlyMLMHead": "<'transformers.models.ernie.modeling_ernie.ErnieOnlyMLMHead'>", + "ErnieOnlyNSPHead": "<'transformers.models.ernie.modeling_ernie.ErnieOnlyNSPHead'>", + "ErnieOutput": "<'transformers.models.ernie.modeling_ernie.ErnieOutput'>", + "ErniePooler": "<'transformers.models.ernie.modeling_ernie.ErniePooler'>", + "ErniePredictionHeadTransform": "<'transformers.models.ernie.modeling_ernie.ErniePredictionHeadTransform'>", + "ErniePreTrainingHeads": "<'transformers.models.ernie.modeling_ernie.ErniePreTrainingHeads'>", + "ErnieSelfAttention": "<'transformers.models.ernie.modeling_ernie.ErnieSelfAttention'>", + "ErnieSelfOutput": "<'transformers.models.ernie.modeling_ernie.ErnieSelfOutput'>", + "EsmAttention": "<'transformers.models.esm.modeling_esm.EsmAttention'>", + "EsmClassificationHead": "<'transformers.models.esm.modeling_esm.EsmClassificationHead'>", + "EsmContactPredictionHead": "<'transformers.models.esm.modeling_esm.EsmContactPredictionHead'>", + "EsmEmbeddings": "<'transformers.models.esm.modeling_esm.EsmEmbeddings'>", + "EsmEncoder": "<'transformers.models.esm.modeling_esm.EsmEncoder'>", + "EsmFlashAttention2": "<'transformers.models.esm.modeling_esm.EsmFlashAttention2'>", + "EsmFoldAngleResnet": "<'transformers.models.esm.modeling_esmfold.EsmFoldAngleResnet'>", + "EsmFoldAngleResnetBlock": "<'transformers.models.esm.modeling_esmfold.EsmFoldAngleResnetBlock'>", + "EsmFoldAttention": "<'transformers.models.esm.modeling_esmfold.EsmFoldAttention'>", + "EsmFoldBackboneUpdate": "<'transformers.models.esm.modeling_esmfold.EsmFoldBackboneUpdate'>", + "EsmFoldDropout": "<'transformers.models.esm.modeling_esmfold.EsmFoldDropout'>", + "EsmFoldingTrunk": "<'transformers.models.esm.modeling_esmfold.EsmFoldingTrunk'>", + "EsmFoldInvariantPointAttention": "<'transformers.models.esm.modeling_esmfold.EsmFoldInvariantPointAttention'>", + "EsmFoldLayerNorm": "<'transformers.models.esm.modeling_esmfold.EsmFoldLayerNorm'>", + "EsmFoldLinear": "<'transformers.models.esm.modeling_esmfold.EsmFoldLinear'>", + "EsmFoldPairToSequence": "<'transformers.models.esm.modeling_esmfold.EsmFoldPairToSequence'>", + "EsmFoldRelativePosition": "<'transformers.models.esm.modeling_esmfold.EsmFoldRelativePosition'>", + "EsmFoldResidueMLP": "<'transformers.models.esm.modeling_esmfold.EsmFoldResidueMLP'>", + "EsmFoldSelfAttention": "<'transformers.models.esm.modeling_esmfold.EsmFoldSelfAttention'>", + "EsmFoldSequenceToPair": "<'transformers.models.esm.modeling_esmfold.EsmFoldSequenceToPair'>", + "EsmFoldStructureModule": "<'transformers.models.esm.modeling_esmfold.EsmFoldStructureModule'>", + "EsmFoldStructureModuleTransition": "<'transformers.models.esm.modeling_esmfold.EsmFoldStructureModuleTransition'>", + "EsmFoldStructureModuleTransitionLayer": "<'transformers.models.esm.modeling_esmfold.EsmFoldStructureModuleTransitionLayer'>", + "EsmFoldTriangleAttention": "<'transformers.models.esm.modeling_esmfold.EsmFoldTriangleAttention'>", + "EsmFoldTriangleMultiplicativeUpdate": "<'transformers.models.esm.modeling_esmfold.EsmFoldTriangleMultiplicativeUpdate'>", + "EsmFoldTriangularSelfAttentionBlock": "<'transformers.models.esm.modeling_esmfold.EsmFoldTriangularSelfAttentionBlock'>", + "EsmIntermediate": "<'transformers.models.esm.modeling_esm.EsmIntermediate'>", + "EsmLayer": "<'transformers.models.esm.modeling_esm.EsmLayer'>", + "EsmLMHead": "<'transformers.models.esm.modeling_esm.EsmLMHead'>", + "EsmOutput": "<'transformers.models.esm.modeling_esm.EsmOutput'>", + "EsmPooler": "<'transformers.models.esm.modeling_esm.EsmPooler'>", + "EsmSelfAttention": "<'transformers.models.esm.modeling_esm.EsmSelfAttention'>", + "EsmSelfOutput": "<'transformers.models.esm.modeling_esm.EsmSelfOutput'>", + "EvollaAttention": "<'transformers.models.evolla.modeling_evolla.EvollaAttention'>", + "EvollaDecoderLayer": "<'transformers.models.evolla.modeling_evolla.EvollaDecoderLayer'>", + "EvollaFeedForward": "<'transformers.models.evolla.modeling_evolla.EvollaFeedForward'>", + "EvollaMLP": "<'transformers.models.evolla.modeling_evolla.EvollaMLP'>", + "EvollaProteinEncoder": "<'transformers.models.evolla.modeling_evolla.EvollaProteinEncoder'>", + "EvollaRMSNorm": "<'transformers.models.evolla.modeling_evolla.EvollaRMSNorm'>", + "EvollaRotaryEmbedding": "<'transformers.models.evolla.modeling_evolla.EvollaRotaryEmbedding'>", + "EvollaSaProtAttention": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtAttention'>", + "EvollaSaProtEmbeddings": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtEmbeddings'>", + "EvollaSaProtEncoder": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtEncoder'>", + "EvollaSaProtFlashAttention2": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtFlashAttention2'>", + "EvollaSaProtIntermediate": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtIntermediate'>", + "EvollaSaProtLayer": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtLayer'>", + "EvollaSaProtOutput": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtOutput'>", + "EvollaSaProtPooler": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtPooler'>", + "EvollaSaProtPreTrainedModel": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtPreTrainedModel'>", + "EvollaSaProtProteinEncoder": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtProteinEncoder'>", + "EvollaSaProtRotaryEmbedding": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtRotaryEmbedding'>", + "EvollaSaProtSelfAttention": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtSelfAttention'>", + "EvollaSaProtSelfOutput": "<'transformers.models.evolla.modeling_evolla.EvollaSaProtSelfOutput'>", + "EvollaSequenceAlignerCrossAttention": "<'transformers.models.evolla.modeling_evolla.EvollaSequenceAlignerCrossAttention'>", + "EvollaSequenceCompressorAttention": "<'transformers.models.evolla.modeling_evolla.EvollaSequenceCompressorAttention'>", + "EvollaSequenceCompressorResampler": "<'transformers.models.evolla.modeling_evolla.EvollaSequenceCompressorResampler'>", + "Exaone4Attention": "<'transformers.models.exaone4.modular_exaone4.Exaone4Attention'>", + "Exaone4DecoderLayer": "<'transformers.models.exaone4.modular_exaone4.Exaone4DecoderLayer'>", + "Exaone4MLP": "<'transformers.models.exaone4.modular_exaone4.Exaone4MLP'>", + "Exaone4RMSNorm": "<'transformers.models.exaone4.modular_exaone4.Exaone4RMSNorm'>", + "Exaone4RotaryEmbedding": "<'transformers.models.exaone4.modular_exaone4.Exaone4RotaryEmbedding'>", + "FalconAttention": "<'transformers.models.falcon.modeling_falcon.FalconAttention'>", + "FalconDecoderLayer": "<'transformers.models.falcon.modeling_falcon.FalconDecoderLayer'>", + "FalconFlashAttention2": "<'transformers.models.falcon.modeling_falcon.FalconFlashAttention2'>", + "FalconH1Attention": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1Attention'>", + "FalconH1DecoderLayer": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1DecoderLayer'>", + "FalconH1Mixer": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1Mixer'>", + "FalconH1MLP": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1MLP'>", + "FalconH1RMSNorm": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1RMSNorm'>", + "FalconH1RMSNormGated": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1RMSNormGated'>", + "FalconH1RotaryEmbedding": "<'transformers.models.falcon_h1.modeling_falcon_h1.FalconH1RotaryEmbedding'>", + "FalconLinear": "<'transformers.models.falcon.modeling_falcon.FalconLinear'>", + "FalconMambaBlock": "<'transformers.models.falcon_mamba.modeling_falcon_mamba.FalconMambaBlock'>", + "FalconMambaMixer": "<'transformers.models.falcon_mamba.modeling_falcon_mamba.FalconMambaMixer'>", + "FalconMambaRMSNorm": "<'transformers.models.falcon_mamba.modeling_falcon_mamba.FalconMambaRMSNorm'>", + "FalconMLP": "<'transformers.models.falcon.modeling_falcon.FalconMLP'>", + "FalconRotaryEmbedding": "<'transformers.models.falcon.modeling_falcon.FalconRotaryEmbedding'>", + "FastGELUActivation": "<'transformers.activations.FastGELUActivation'>", + "FastSpeech2ConformerAttention": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerAttention'>", + "FastSpeech2ConformerBatchNormConvLayer": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerBatchNormConvLayer'>", + "FastSpeech2ConformerConvolutionModule": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerConvolutionModule'>", + "FastSpeech2ConformerDurationPredictor": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerDurationPredictor'>", + "FastSpeech2ConformerEncoder": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerEncoder'>", + "FastSpeech2ConformerEncoderLayer": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerEncoderLayer'>", + "FastSpeech2ConformerLoss": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerLoss'>", + "FastSpeech2ConformerMultiLayeredConv1d": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerMultiLayeredConv1d'>", + "FastSpeech2ConformerPredictorLayer": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerPredictorLayer'>", + "FastSpeech2ConformerRelPositionalEncoding": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerRelPositionalEncoding'>", + "FastSpeech2ConformerSpeechDecoderPostnet": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerSpeechDecoderPostnet'>", + "FastSpeech2ConformerVarianceEmbedding": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerVarianceEmbedding'>", + "FastSpeech2ConformerVariancePredictor": "<'transformers.models.fastspeech2_conformer.modeling_fastspeech2_conformer.FastSpeech2ConformerVariancePredictor'>", + "FeatureMixerBlock": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.FeatureMixerBlock'>", + "FFN": "<'transformers.models.distilbert.modeling_distilbert.FFN'>", + "FFNLayer": "<'transformers.models.mobilebert.modeling_mobilebert.FFNLayer'>", + "FFNOutput": "<'transformers.models.mobilebert.modeling_mobilebert.FFNOutput'>", + "FlaubertPoolerAnswerClass": "<'transformers.models.flaubert.modeling_flaubert.FlaubertPoolerAnswerClass'>", + "FlaubertPoolerEndLogits": "<'transformers.models.flaubert.modeling_flaubert.FlaubertPoolerEndLogits'>", + "FlaubertPoolerStartLogits": "<'transformers.models.flaubert.modeling_flaubert.FlaubertPoolerStartLogits'>", + "FlaubertPredLayer": "<'transformers.models.flaubert.modeling_flaubert.FlaubertPredLayer'>", + "FlaubertSequenceSummary": "<'transformers.models.flaubert.modeling_flaubert.FlaubertSequenceSummary'>", + "FlaubertSQuADHead": "<'transformers.models.flaubert.modeling_flaubert.FlaubertSQuADHead'>", + "FlavaAttention": "<'transformers.models.flava.modeling_flava.FlavaAttention'>", + "FlavaEncoder": "<'transformers.models.flava.modeling_flava.FlavaEncoder'>", + "FlavaGlobalContrastiveHead": "<'transformers.models.flava.modeling_flava.FlavaGlobalContrastiveHead'>", + "FlavaImageCodebookBlock": "<'transformers.models.flava.modeling_flava.FlavaImageCodebookBlock'>", + "FlavaImageCodebookLayerGroup": "<'transformers.models.flava.modeling_flava.FlavaImageCodebookLayerGroup'>", + "FlavaImageCodebookResPath": "<'transformers.models.flava.modeling_flava.FlavaImageCodebookResPath'>", + "FlavaImageEmbeddings": "<'transformers.models.flava.modeling_flava.FlavaImageEmbeddings'>", + "FlavaIntermediate": "<'transformers.models.flava.modeling_flava.FlavaIntermediate'>", + "FlavaITMHead": "<'transformers.models.flava.modeling_flava.FlavaITMHead'>", + "FlavaLayer": "<'transformers.models.flava.modeling_flava.FlavaLayer'>", + "FlavaMaskedPredictionHead": "<'transformers.models.flava.modeling_flava.FlavaMaskedPredictionHead'>", + "FlavaOutput": "<'transformers.models.flava.modeling_flava.FlavaOutput'>", + "FlavaPooler": "<'transformers.models.flava.modeling_flava.FlavaPooler'>", + "FlavaPredictionHeadTransform": "<'transformers.models.flava.modeling_flava.FlavaPredictionHeadTransform'>", + "FlavaSelfAttention": "<'transformers.models.flava.modeling_flava.FlavaSelfAttention'>", + "FlavaSelfOutput": "<'transformers.models.flava.modeling_flava.FlavaSelfOutput'>", + "FlavaTextEmbeddings": "<'transformers.models.flava.modeling_flava.FlavaTextEmbeddings'>", + "FNetBasicFourierTransform": "<'transformers.models.fnet.modeling_fnet.FNetBasicFourierTransform'>", + "FNetBasicOutput": "<'transformers.models.fnet.modeling_fnet.FNetBasicOutput'>", + "FNetEmbeddings": "<'transformers.models.fnet.modeling_fnet.FNetEmbeddings'>", + "FNetEncoder": "<'transformers.models.fnet.modeling_fnet.FNetEncoder'>", + "FNetFourierTransform": "<'transformers.models.fnet.modeling_fnet.FNetFourierTransform'>", + "FNetIntermediate": "<'transformers.models.fnet.modeling_fnet.FNetIntermediate'>", + "FNetLayer": "<'transformers.models.fnet.modeling_fnet.FNetLayer'>", + "FNetLMPredictionHead": "<'transformers.models.fnet.modeling_fnet.FNetLMPredictionHead'>", + "FNetOnlyMLMHead": "<'transformers.models.fnet.modeling_fnet.FNetOnlyMLMHead'>", + "FNetOnlyNSPHead": "<'transformers.models.fnet.modeling_fnet.FNetOnlyNSPHead'>", + "FNetOutput": "<'transformers.models.fnet.modeling_fnet.FNetOutput'>", + "FNetPooler": "<'transformers.models.fnet.modeling_fnet.FNetPooler'>", + "FNetPredictionHeadTransform": "<'transformers.models.fnet.modeling_fnet.FNetPredictionHeadTransform'>", + "FNetPreTrainingHeads": "<'transformers.models.fnet.modeling_fnet.FNetPreTrainingHeads'>", + "FocalNetDropPath": "<'transformers.models.focalnet.modeling_focalnet.FocalNetDropPath'>", + "FocalNetEmbeddings": "<'transformers.models.focalnet.modeling_focalnet.FocalNetEmbeddings'>", + "FocalNetEncoder": "<'transformers.models.focalnet.modeling_focalnet.FocalNetEncoder'>", + "FocalNetLayer": "<'transformers.models.focalnet.modeling_focalnet.FocalNetLayer'>", + "FocalNetMlp": "<'transformers.models.focalnet.modeling_focalnet.FocalNetMlp'>", + "FocalNetModulation": "<'transformers.models.focalnet.modeling_focalnet.FocalNetModulation'>", + "FocalNetPatchEmbeddings": "<'transformers.models.focalnet.modeling_focalnet.FocalNetPatchEmbeddings'>", + "FocalNetStage": "<'transformers.models.focalnet.modeling_focalnet.FocalNetStage'>", + "FSMTDecoder": "<'transformers.models.fsmt.modeling_fsmt.FSMTDecoder'>", + "FSMTEncoder": "<'transformers.models.fsmt.modeling_fsmt.FSMTEncoder'>", + "FullyShardedDataParallel": "<'torch.distributed.fsdp.fully_sharded_data_parallel.FullyShardedDataParallel'>", + "FunnelAttentionStructure": "<'transformers.models.funnel.modeling_funnel.FunnelAttentionStructure'>", + "FunnelClassificationHead": "<'transformers.models.funnel.modeling_funnel.FunnelClassificationHead'>", + "FunnelDecoder": "<'transformers.models.funnel.modeling_funnel.FunnelDecoder'>", + "FunnelDiscriminatorPredictions": "<'transformers.models.funnel.modeling_funnel.FunnelDiscriminatorPredictions'>", + "FunnelEmbeddings": "<'transformers.models.funnel.modeling_funnel.FunnelEmbeddings'>", + "FunnelEncoder": "<'transformers.models.funnel.modeling_funnel.FunnelEncoder'>", + "FunnelLayer": "<'transformers.models.funnel.modeling_funnel.FunnelLayer'>", + "FunnelPositionwiseFFN": "<'transformers.models.funnel.modeling_funnel.FunnelPositionwiseFFN'>", + "FunnelRelMultiheadAttention": "<'transformers.models.funnel.modeling_funnel.FunnelRelMultiheadAttention'>", + "FusedLayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "GeLU": "<'transformers.models.lxmert.modeling_lxmert.GeLU'>", + "GELUActivation": "<'transformers.activations.GELUActivation'>", + "Gemma2Attention": "<'transformers.models.gemma2.modeling_gemma2.Gemma2Attention'>", + "Gemma2DecoderLayer": "<'transformers.models.gemma2.modular_gemma2.Gemma2DecoderLayer'>", + "Gemma2MLP": "<'transformers.models.gemma2.modeling_gemma2.Gemma2MLP'>", + "Gemma2RMSNorm": "<'transformers.models.gemma2.modeling_gemma2.Gemma2RMSNorm'>", + "Gemma2RotaryEmbedding": "<'transformers.models.gemma2.modeling_gemma2.Gemma2RotaryEmbedding'>", + "Gemma3Attention": "<'transformers.models.gemma3.modeling_gemma3.Gemma3Attention'>", + "Gemma3DecoderLayer": "<'transformers.models.gemma3.modeling_gemma3.Gemma3DecoderLayer'>", + "Gemma3MLP": "<'transformers.models.gemma3.modeling_gemma3.Gemma3MLP'>", + "Gemma3MultiModalProjector": "<'transformers.models.gemma3.modeling_gemma3.Gemma3MultiModalProjector'>", + "Gemma3nAudioAttention": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioAttention'>", + "Gemma3nAudioConformerAttention": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioConformerAttention'>", + "Gemma3nAudioConformerBlock": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioConformerBlock'>", + "Gemma3nAudioConformerFeedForward": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioConformerFeedForward'>", + "Gemma3nAudioConformerLightConv1d": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioConformerLightConv1d'>", + "Gemma3nAudioCumulativeGroupNorm": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioCumulativeGroupNorm'>", + "Gemma3nAudioRelativePositionEmbedding": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioRelativePositionEmbedding'>", + "Gemma3nAudioSSCPConvBlock": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioSSCPConvBlock'>", + "Gemma3nAudioSubSampleConvProjection": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nAudioSubSampleConvProjection'>", + "Gemma3nMultimodalEmbedder": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nMultimodalEmbedder'>", + "Gemma3nRMSNorm": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nRMSNorm'>", + "Gemma3nTextAltUp": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextAltUp'>", + "Gemma3nTextAttention": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextAttention'>", + "Gemma3nTextDecoderLayer": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextDecoderLayer'>", + "Gemma3nTextLaurelBlock": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextLaurelBlock'>", + "Gemma3nTextMLP": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextMLP'>", + "Gemma3nTextRotaryEmbedding": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextRotaryEmbedding'>", + "Gemma3nTextScaledWordEmbedding": "<'transformers.models.gemma3n.modeling_gemma3n.Gemma3nTextScaledWordEmbedding'>", + "Gemma3RMSNorm": "<'transformers.models.gemma3.modeling_gemma3.Gemma3RMSNorm'>", + "Gemma3RotaryEmbedding": "<'transformers.models.gemma3.modeling_gemma3.Gemma3RotaryEmbedding'>", + "Gemma3TextScaledWordEmbedding": "<'transformers.models.gemma3.modeling_gemma3.Gemma3TextScaledWordEmbedding'>", + "GemmaAttention": "<'transformers.models.gemma.modeling_gemma.GemmaAttention'>", + "GemmaDecoderLayer": "<'transformers.models.gemma.modeling_gemma.GemmaDecoderLayer'>", + "GemmaMLP": "<'transformers.models.gemma.modeling_gemma.GemmaMLP'>", + "GemmaRMSNorm": "<'transformers.models.gemma.modeling_gemma.GemmaRMSNorm'>", + "GemmaRotaryEmbedding": "<'transformers.models.gemma.modeling_gemma.GemmaRotaryEmbedding'>", + "GitAttention": "<'transformers.models.git.modeling_git.GitAttention'>", + "GitEmbeddings": "<'transformers.models.git.modeling_git.GitEmbeddings'>", + "GitEncoder": "<'transformers.models.git.modeling_git.GitEncoder'>", + "GitIntermediate": "<'transformers.models.git.modeling_git.GitIntermediate'>", + "GitLayer": "<'transformers.models.git.modeling_git.GitLayer'>", + "GitOutput": "<'transformers.models.git.modeling_git.GitOutput'>", + "GitProjection": "<'transformers.models.git.modeling_git.GitProjection'>", + "GitSelfAttention": "<'transformers.models.git.modeling_git.GitSelfAttention'>", + "GitSelfOutput": "<'transformers.models.git.modeling_git.GitSelfOutput'>", + "GitVisionAttention": "<'transformers.models.git.modeling_git.GitVisionAttention'>", + "GitVisionEmbeddings": "<'transformers.models.git.modeling_git.GitVisionEmbeddings'>", + "GitVisionEncoder": "<'transformers.models.git.modeling_git.GitVisionEncoder'>", + "GitVisionEncoderLayer": "<'transformers.models.git.modeling_git.GitVisionEncoderLayer'>", + "GitVisionMLP": "<'transformers.models.git.modeling_git.GitVisionMLP'>", + "GitVisionTransformer": "<'transformers.models.git.modeling_git.GitVisionTransformer'>", + "Glm4Attention": "<'transformers.models.glm4.modeling_glm4.Glm4Attention'>", + "Glm4DecoderLayer": "<'transformers.models.glm4.modeling_glm4.Glm4DecoderLayer'>", + "Glm4MLP": "<'transformers.models.glm4.modeling_glm4.Glm4MLP'>", + "Glm4MoeAttention": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeAttention'>", + "Glm4MoeDecoderLayer": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeDecoderLayer'>", + "Glm4MoeMLP": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeMLP'>", + "Glm4MoeMoE": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeMoE'>", + "Glm4MoeRMSNorm": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeRMSNorm'>", + "Glm4MoeRotaryEmbedding": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeRotaryEmbedding'>", + "Glm4MoeTopkRouter": "<'transformers.models.glm4_moe.modeling_glm4_moe.Glm4MoeTopkRouter'>", + "Glm4RMSNorm": "<'transformers.models.glm4.modeling_glm4.Glm4RMSNorm'>", + "Glm4RotaryEmbedding": "<'transformers.models.glm4.modeling_glm4.Glm4RotaryEmbedding'>", + "Glm4VisionMlp": "<'transformers.models.glm4v.modeling_glm4v.Glm4VisionMlp'>", + "Glm4vRMSNorm": "<'transformers.models.glm4v.modeling_glm4v.Glm4vRMSNorm'>", + "Glm4vTextAttention": "<'transformers.models.glm4v.modeling_glm4v.Glm4vTextAttention'>", + "Glm4vTextDecoderLayer": "<'transformers.models.glm4v.modeling_glm4v.Glm4vTextDecoderLayer'>", + "Glm4vTextMLP": "<'transformers.models.glm4v.modeling_glm4v.Glm4vTextMLP'>", + "Glm4vTextRotaryEmbedding": "<'transformers.models.glm4v.modeling_glm4v.Glm4vTextRotaryEmbedding'>", + "Glm4vVisionAttention": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionAttention'>", + "Glm4vVisionBlock": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionBlock'>", + "Glm4vVisionEmbeddings": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionEmbeddings'>", + "Glm4vVisionModel": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionModel'>", + "Glm4vVisionPatchEmbed": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionPatchEmbed'>", + "Glm4vVisionPatchMerger": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionPatchMerger'>", + "Glm4vVisionRotaryEmbedding": "<'transformers.models.glm4v.modeling_glm4v.Glm4vVisionRotaryEmbedding'>", + "GlmAttention": "<'transformers.models.glm.modeling_glm.GlmAttention'>", + "GlmDecoderLayer": "<'transformers.models.glm.modeling_glm.GlmDecoderLayer'>", + "GlmMLP": "<'transformers.models.glm.modeling_glm.GlmMLP'>", + "GlmRMSNorm": "<'transformers.models.glm.modeling_glm.GlmRMSNorm'>", + "GlmRotaryEmbedding": "<'transformers.models.glm.modeling_glm.GlmRotaryEmbedding'>", + "GLPNAttention": "<'transformers.models.glpn.modeling_glpn.GLPNAttention'>", + "GLPNDecoder": "<'transformers.models.glpn.modeling_glpn.GLPNDecoder'>", + "GLPNDecoderStage": "<'transformers.models.glpn.modeling_glpn.GLPNDecoderStage'>", + "GLPNDepthEstimationHead": "<'transformers.models.glpn.modeling_glpn.GLPNDepthEstimationHead'>", + "GLPNDropPath": "<'transformers.models.glpn.modeling_glpn.GLPNDropPath'>", + "GLPNDWConv": "<'transformers.models.glpn.modeling_glpn.GLPNDWConv'>", + "GLPNEfficientSelfAttention": "<'transformers.models.glpn.modeling_glpn.GLPNEfficientSelfAttention'>", + "GLPNEncoder": "<'transformers.models.glpn.modeling_glpn.GLPNEncoder'>", + "GLPNLayer": "<'transformers.models.glpn.modeling_glpn.GLPNLayer'>", + "GLPNMixFFN": "<'transformers.models.glpn.modeling_glpn.GLPNMixFFN'>", + "GLPNOverlapPatchEmbeddings": "<'transformers.models.glpn.modeling_glpn.GLPNOverlapPatchEmbeddings'>", + "GLPNSelectiveFeatureFusion": "<'transformers.models.glpn.modeling_glpn.GLPNSelectiveFeatureFusion'>", + "GLPNSelfOutput": "<'transformers.models.glpn.modeling_glpn.GLPNSelfOutput'>", + "GotOcr2LayerNorm": "<'transformers.models.got_ocr2.modeling_got_ocr2.GotOcr2LayerNorm'>", + "GotOcr2MLPBlock": "<'transformers.models.got_ocr2.modular_got_ocr2.GotOcr2MLPBlock'>", + "GotOcr2MultiModalProjector": "<'transformers.models.got_ocr2.modular_got_ocr2.GotOcr2MultiModalProjector'>", + "GotOcr2PatchEmbeddings": "<'transformers.models.got_ocr2.modeling_got_ocr2.GotOcr2PatchEmbeddings'>", + "GotOcr2VisionAttention": "<'transformers.models.got_ocr2.modular_got_ocr2.GotOcr2VisionAttention'>", + "GotOcr2VisionEncoder": "<'transformers.models.got_ocr2.modular_got_ocr2.GotOcr2VisionEncoder'>", + "GotOcr2VisionLayer": "<'transformers.models.got_ocr2.modular_got_ocr2.GotOcr2VisionLayer'>", + "GotOcr2VisionNeck": "<'transformers.models.got_ocr2.modeling_got_ocr2.GotOcr2VisionNeck'>", + "GPT2Attention": "<'transformers.models.gpt2.modeling_gpt2.GPT2Attention'>", + "GPT2Block": "<'transformers.models.gpt2.modeling_gpt2.GPT2Block'>", + "GPT2MLP": "<'transformers.models.gpt2.modeling_gpt2.GPT2MLP'>", + "GPT2SequenceSummary": "<'transformers.models.gpt2.modeling_gpt2.GPT2SequenceSummary'>", + "GPTBigCodeAttention": "<'transformers.models.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeAttention'>", + "GPTBigCodeBlock": "<'transformers.models.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeBlock'>", + "GPTBigCodeMLP": "<'transformers.models.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeMLP'>", + "GPTJAttention": "<'transformers.models.gptj.modeling_gptj.GPTJAttention'>", + "GPTJBlock": "<'transformers.models.gptj.modeling_gptj.GPTJBlock'>", + "GPTJFlashAttention2": "<'transformers.models.gptj.modeling_gptj.GPTJFlashAttention2'>", + "GPTJMLP": "<'transformers.models.gptj.modeling_gptj.GPTJMLP'>", + "GPTNeoAttention": "<'transformers.models.gpt_neo.modeling_gpt_neo.GPTNeoAttention'>", + "GPTNeoBlock": "<'transformers.models.gpt_neo.modeling_gpt_neo.GPTNeoBlock'>", + "GPTNeoFlashAttention2": "<'transformers.models.gpt_neo.modeling_gpt_neo.GPTNeoFlashAttention2'>", + "GPTNeoMLP": "<'transformers.models.gpt_neo.modeling_gpt_neo.GPTNeoMLP'>", + "GPTNeoSelfAttention": "<'transformers.models.gpt_neo.modeling_gpt_neo.GPTNeoSelfAttention'>", + "GPTNeoXAttention": "<'transformers.models.gpt_neox.modular_gpt_neox.GPTNeoXAttention'>", + "GPTNeoXDecoderLayer": "<'transformers.models.gpt_neox.modeling_gpt_neox.GPTNeoXDecoderLayer'>", + "GPTNeoXJapaneseAttention": "<'transformers.models.gpt_neox_japanese.modeling_gpt_neox_japanese.GPTNeoXJapaneseAttention'>", + "GPTNeoXJapaneseLayer": "<'transformers.models.gpt_neox_japanese.modeling_gpt_neox_japanese.GPTNeoXJapaneseLayer'>", + "GPTNeoXJapaneseMLP": "<'transformers.models.gpt_neox_japanese.modeling_gpt_neox_japanese.GPTNeoXJapaneseMLP'>", + "GPTNeoXJapaneseRotaryEmbedding": "<'transformers.models.gpt_neox_japanese.modeling_gpt_neox_japanese.GPTNeoXJapaneseRotaryEmbedding'>", + "GPTNeoXLayer": "<'transformers.models.gpt_neox.modular_gpt_neox.GPTNeoXLayer'>", + "GPTNeoXMLP": "<'transformers.models.gpt_neox.modular_gpt_neox.GPTNeoXMLP'>", + "GPTNeoXRMSNorm": "<'transformers.models.gpt_neox.modeling_gpt_neox.GPTNeoXRMSNorm'>", + "GPTNeoXRotaryEmbedding": "<'transformers.models.gpt_neox.modular_gpt_neox.GPTNeoXRotaryEmbedding'>", + "GptOssAttention": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssAttention'>", + "GptOssDecoderLayer": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssDecoderLayer'>", + "GptOssExperts": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssExperts'>", + "GptOssMLP": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssMLP'>", + "GptOssRMSNorm": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssRMSNorm'>", + "GptOssRotaryEmbedding": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssRotaryEmbedding'>", + "GptOssTopKRouter": "<'transformers.models.gpt_oss.modular_gpt_oss.GptOssTopKRouter'>", + "GPTSanJapaneseAttention": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseAttention'>", + "GPTSanJapaneseBlock": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseBlock'>", + "GPTSanJapaneseDenseActDense": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseDenseActDense'>", + "GPTSanJapaneseLayerDenseFF": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseLayerDenseFF'>", + "GPTSanJapaneseLayerSelfAttention": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseLayerSelfAttention'>", + "GPTSanJapaneseLayerSparseFF": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseLayerSparseFF'>", + "GPTSanJapaneseSparseMLP": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseSparseMLP'>", + "GPTSanJapaneseTop1Router": "<'transformers.models.deprecated.gptsan_japanese.modeling_gptsan_japanese.GPTSanJapaneseTop1Router'>", + "GradientCheckpointingLayer": "<'transformers.modeling_layers.GradientCheckpointingLayer'>", + "GraniteAttention": "<'transformers.models.granite.modeling_granite.GraniteAttention'>", + "GraniteDecoderLayer": "<'transformers.models.granite.modular_granite.GraniteDecoderLayer'>", + "GraniteMLP": "<'transformers.models.granite.modeling_granite.GraniteMLP'>", + "GraniteMoeAttention": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeAttention'>", + "GraniteMoeDecoderLayer": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeDecoderLayer'>", + "GraniteMoeHybridAttention": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridAttention'>", + "GraniteMoeHybridDecoderLayer": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridDecoderLayer'>", + "GraniteMoeHybridMambaLayer": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridMambaLayer'>", + "GraniteMoeHybridMLP": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridMLP'>", + "GraniteMoeHybridMoE": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridMoE'>", + "GraniteMoeHybridParallelExperts": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridParallelExperts'>", + "GraniteMoeHybridRMSNorm": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridRMSNorm'>", + "GraniteMoeHybridRMSNormGated": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridRMSNormGated'>", + "GraniteMoeHybridRotaryEmbedding": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridRotaryEmbedding'>", + "GraniteMoeHybridTopKGating": "<'transformers.models.granitemoehybrid.modeling_granitemoehybrid.GraniteMoeHybridTopKGating'>", + "GraniteMoeMoE": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeMoE'>", + "GraniteMoeParallelExperts": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeParallelExperts'>", + "GraniteMoeRMSNorm": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeRMSNorm'>", + "GraniteMoeRotaryEmbedding": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeRotaryEmbedding'>", + "GraniteMoeSharedAttention": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedAttention'>", + "GraniteMoeSharedDecoderLayer": "<'transformers.models.granitemoeshared.modular_granitemoeshared.GraniteMoeSharedDecoderLayer'>", + "GraniteMoeSharedMLP": "<'transformers.models.granitemoeshared.modular_granitemoeshared.GraniteMoeSharedMLP'>", + "GraniteMoeSharedMoE": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedMoE'>", + "GraniteMoeSharedParallelExperts": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedParallelExperts'>", + "GraniteMoeSharedRMSNorm": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedRMSNorm'>", + "GraniteMoeSharedRotaryEmbedding": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedRotaryEmbedding'>", + "GraniteMoeSharedTopKGating": "<'transformers.models.granitemoeshared.modeling_granitemoeshared.GraniteMoeSharedTopKGating'>", + "GraniteMoeTopKGating": "<'transformers.models.granitemoe.modeling_granitemoe.GraniteMoeTopKGating'>", + "GraniteRMSNorm": "<'transformers.models.granite.modeling_granite.GraniteRMSNorm'>", + "GraniteRotaryEmbedding": "<'transformers.models.granite.modeling_granite.GraniteRotaryEmbedding'>", + "GraniteSpeechConformerAttention": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechConformerAttention'>", + "GraniteSpeechConformerBlock": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechConformerBlock'>", + "GraniteSpeechConformerConvModule": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechConformerConvModule'>", + "GraniteSpeechConformerDepthWiseConv1d": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechConformerDepthWiseConv1d'>", + "GraniteSpeechConformerFeedForward": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechConformerFeedForward'>", + "GraniteSpeechEncoderProjector": "<'transformers.models.granite_speech.modeling_granite_speech.GraniteSpeechEncoderProjector'>", + "GraphModule": "<'torch.fx.graph_module.GraphModule'>", + "GraphormerDecoderHead": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerDecoderHead'>", + "GraphormerGraphAttnBias": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerGraphAttnBias'>", + "GraphormerGraphEncoder": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerGraphEncoder'>", + "GraphormerGraphEncoderLayer": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerGraphEncoderLayer'>", + "GraphormerGraphNodeFeature": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerGraphNodeFeature'>", + "GraphormerMultiheadAttention": "<'transformers.models.deprecated.graphormer.modeling_graphormer.GraphormerMultiheadAttention'>", + "GroundingDinoBiMultiHeadAttention": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoBiMultiHeadAttention'>", + "GroundingDinoContrastiveEmbedding": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoContrastiveEmbedding'>", + "GroundingDinoConvEncoder": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoConvEncoder'>", + "GroundingDinoConvModel": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoConvModel'>", + "GroundingDinoDecoder": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoDecoder'>", + "GroundingDinoDecoderLayer": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoDecoderLayer'>", + "GroundingDinoDeformableLayer": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoDeformableLayer'>", + "GroundingDinoDropPath": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoDropPath'>", + "GroundingDinoEncoder": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoEncoder'>", + "GroundingDinoEncoderLayer": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoEncoderLayer'>", + "GroundingDinoFrozenBatchNorm2d": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoFrozenBatchNorm2d'>", + "GroundingDinoFusionLayer": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoFusionLayer'>", + "GroundingDinoHungarianMatcher": "<'transformers.loss.loss_grounding_dino.GroundingDinoHungarianMatcher'>", + "GroundingDinoImageLoss": "<'transformers.loss.loss_grounding_dino.GroundingDinoImageLoss'>", + "GroundingDinoLearnedPositionEmbedding": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoLearnedPositionEmbedding'>", + "GroundingDinoMLPPredictionHead": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoMLPPredictionHead'>", + "GroundingDinoMultiheadAttention": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoMultiheadAttention'>", + "GroundingDinoMultiscaleDeformableAttention": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoMultiscaleDeformableAttention'>", + "GroundingDinoSinePositionEmbedding": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoSinePositionEmbedding'>", + "GroundingDinoTextEnhancerLayer": "<'transformers.models.grounding_dino.modeling_grounding_dino.GroundingDinoTextEnhancerLayer'>", + "GroupedLinearLayer": "<'transformers.models.convbert.modeling_convbert.GroupedLinearLayer'>", + "GroupViTAssignAttention": "<'transformers.models.groupvit.modeling_groupvit.GroupViTAssignAttention'>", + "GroupViTAttention": "<'transformers.models.groupvit.modeling_groupvit.GroupViTAttention'>", + "GroupViTCrossAttentionLayer": "<'transformers.models.groupvit.modeling_groupvit.GroupViTCrossAttentionLayer'>", + "GroupViTEncoderLayer": "<'transformers.models.groupvit.modeling_groupvit.GroupViTEncoderLayer'>", + "GroupViTMixerMLP": "<'transformers.models.groupvit.modeling_groupvit.GroupViTMixerMLP'>", + "GroupViTMLP": "<'transformers.models.groupvit.modeling_groupvit.GroupViTMLP'>", + "GroupViTPatchEmbeddings": "<'transformers.models.groupvit.modeling_groupvit.GroupViTPatchEmbeddings'>", + "GroupViTStage": "<'transformers.models.groupvit.modeling_groupvit.GroupViTStage'>", + "GroupViTTextEmbeddings": "<'transformers.models.groupvit.modeling_groupvit.GroupViTTextEmbeddings'>", + "GroupViTTextEncoder": "<'transformers.models.groupvit.modeling_groupvit.GroupViTTextEncoder'>", + "GroupViTTextTransformer": "<'transformers.models.groupvit.modeling_groupvit.GroupViTTextTransformer'>", + "GroupViTTokenAssign": "<'transformers.models.groupvit.modeling_groupvit.GroupViTTokenAssign'>", + "GroupViTVisionEmbeddings": "<'transformers.models.groupvit.modeling_groupvit.GroupViTVisionEmbeddings'>", + "GroupViTVisionEncoder": "<'transformers.models.groupvit.modeling_groupvit.GroupViTVisionEncoder'>", + "GroupViTVisionTransformer": "<'transformers.models.groupvit.modeling_groupvit.GroupViTVisionTransformer'>", + "HeliumAttention": "<'transformers.models.helium.modeling_helium.HeliumAttention'>", + "HeliumDecoderLayer": "<'transformers.models.helium.modeling_helium.HeliumDecoderLayer'>", + "HeliumMLP": "<'transformers.models.helium.modeling_helium.HeliumMLP'>", + "HeliumRMSNorm": "<'transformers.models.helium.modeling_helium.HeliumRMSNorm'>", + "HeliumRotaryEmbedding": "<'transformers.models.helium.modeling_helium.HeliumRotaryEmbedding'>", + "HGNetV2BasicLayer": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2BasicLayer'>", + "HGNetV2ConvLayer": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2ConvLayer'>", + "HGNetV2ConvLayerLight": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2ConvLayerLight'>", + "HGNetV2Embeddings": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2Embeddings'>", + "HGNetV2Encoder": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2Encoder'>", + "HGNetV2LearnableAffineBlock": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2LearnableAffineBlock'>", + "HGNetV2Stage": "<'transformers.models.hgnet_v2.modeling_hgnet_v2.HGNetV2Stage'>", + "HieraDecoder": "<'transformers.models.hiera.modeling_hiera.HieraDecoder'>", + "HieraDropPath": "<'transformers.models.hiera.modeling_hiera.HieraDropPath'>", + "HieraEmbeddings": "<'transformers.models.hiera.modeling_hiera.HieraEmbeddings'>", + "HieraEncoder": "<'transformers.models.hiera.modeling_hiera.HieraEncoder'>", + "HieraLayer": "<'transformers.models.hiera.modeling_hiera.HieraLayer'>", + "HieraMaskUnitAttention": "<'transformers.models.hiera.modeling_hiera.HieraMaskUnitAttention'>", + "HieraMlp": "<'transformers.models.hiera.modeling_hiera.HieraMlp'>", + "HieraMultiScaleHead": "<'transformers.models.hiera.modeling_hiera.HieraMultiScaleHead'>", + "HieraPatchEmbeddings": "<'transformers.models.hiera.modeling_hiera.HieraPatchEmbeddings'>", + "HieraPooler": "<'transformers.models.hiera.modeling_hiera.HieraPooler'>", + "HieraStage": "<'transformers.models.hiera.modeling_hiera.HieraStage'>", + "HifiGanResidualBlock": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.HifiGanResidualBlock'>", + "HubertAttention": "<'transformers.models.hubert.modeling_hubert.HubertAttention'>", + "HubertAttnAdapterLayer": "<'transformers.models.hubert.modeling_hubert.HubertAttnAdapterLayer'>", + "HubertEncoder": "<'transformers.models.hubert.modeling_hubert.HubertEncoder'>", + "HubertEncoderLayer": "<'transformers.models.hubert.modeling_hubert.HubertEncoderLayer'>", + "HubertEncoderLayerStableLayerNorm": "<'transformers.models.hubert.modeling_hubert.HubertEncoderLayerStableLayerNorm'>", + "HubertEncoderStableLayerNorm": "<'transformers.models.hubert.modeling_hubert.HubertEncoderStableLayerNorm'>", + "HubertFeatureEncoder": "<'transformers.models.hubert.modeling_hubert.HubertFeatureEncoder'>", + "HubertFeatureProjection": "<'transformers.models.hubert.modeling_hubert.HubertFeatureProjection'>", + "HubertFeedForward": "<'transformers.models.hubert.modeling_hubert.HubertFeedForward'>", + "HubertGroupNormConvLayer": "<'transformers.models.hubert.modeling_hubert.HubertGroupNormConvLayer'>", + "HubertLayerNormConvLayer": "<'transformers.models.hubert.modeling_hubert.HubertLayerNormConvLayer'>", + "HubertNoLayerNormConvLayer": "<'transformers.models.hubert.modeling_hubert.HubertNoLayerNormConvLayer'>", + "HubertPositionalConvEmbedding": "<'transformers.models.hubert.modeling_hubert.HubertPositionalConvEmbedding'>", + "HubertSamePadLayer": "<'transformers.models.hubert.modeling_hubert.HubertSamePadLayer'>", + "HungarianMatcher": "<'transformers.loss.loss_for_object_detection.HungarianMatcher'>", + "IBertAttention": "<'transformers.models.ibert.modeling_ibert.IBertAttention'>", + "IBertClassificationHead": "<'transformers.models.ibert.modeling_ibert.IBertClassificationHead'>", + "IBertEmbeddings": "<'transformers.models.ibert.modeling_ibert.IBertEmbeddings'>", + "IBertEncoder": "<'transformers.models.ibert.modeling_ibert.IBertEncoder'>", + "IBertIntermediate": "<'transformers.models.ibert.modeling_ibert.IBertIntermediate'>", + "IBertLayer": "<'transformers.models.ibert.modeling_ibert.IBertLayer'>", + "IBertLMHead": "<'transformers.models.ibert.modeling_ibert.IBertLMHead'>", + "IBertOutput": "<'transformers.models.ibert.modeling_ibert.IBertOutput'>", + "IBertPooler": "<'transformers.models.ibert.modeling_ibert.IBertPooler'>", + "IBertSelfAttention": "<'transformers.models.ibert.modeling_ibert.IBertSelfAttention'>", + "IBertSelfOutput": "<'transformers.models.ibert.modeling_ibert.IBertSelfOutput'>", + "Idefics2Connector": "<'transformers.models.idefics2.modeling_idefics2.Idefics2Connector'>", + "Idefics2Encoder": "<'transformers.models.idefics2.modeling_idefics2.Idefics2Encoder'>", + "Idefics2EncoderLayer": "<'transformers.models.idefics2.modeling_idefics2.Idefics2EncoderLayer'>", + "Idefics2MLP": "<'transformers.models.idefics2.modeling_idefics2.Idefics2MLP'>", + "Idefics2MultiheadAttentionPoolingHead": "<'transformers.models.idefics2.modeling_idefics2.Idefics2MultiheadAttentionPoolingHead'>", + "Idefics2PerceiverAttention": "<'transformers.models.idefics2.modeling_idefics2.Idefics2PerceiverAttention'>", + "Idefics2PerceiverLayer": "<'transformers.models.idefics2.modeling_idefics2.Idefics2PerceiverLayer'>", + "Idefics2PerceiverResampler": "<'transformers.models.idefics2.modeling_idefics2.Idefics2PerceiverResampler'>", + "Idefics2RMSNorm": "<'transformers.models.idefics2.modeling_idefics2.Idefics2RMSNorm'>", + "Idefics2VisionAttention": "<'transformers.models.idefics2.modeling_idefics2.Idefics2VisionAttention'>", + "Idefics2VisionEmbeddings": "<'transformers.models.idefics2.modeling_idefics2.Idefics2VisionEmbeddings'>", + "Idefics2VisionMLP": "<'transformers.models.idefics2.modeling_idefics2.Idefics2VisionMLP'>", + "Idefics2VisionTransformer": "<'transformers.models.idefics2.modeling_idefics2.Idefics2VisionTransformer'>", + "Idefics3Connector": "<'transformers.models.idefics3.modeling_idefics3.Idefics3Connector'>", + "Idefics3Encoder": "<'transformers.models.idefics3.modeling_idefics3.Idefics3Encoder'>", + "Idefics3EncoderLayer": "<'transformers.models.idefics3.modeling_idefics3.Idefics3EncoderLayer'>", + "Idefics3RMSNorm": "<'transformers.models.idefics3.modeling_idefics3.Idefics3RMSNorm'>", + "Idefics3SimpleMLP": "<'transformers.models.idefics3.modeling_idefics3.Idefics3SimpleMLP'>", + "Idefics3VisionAttention": "<'transformers.models.idefics3.modeling_idefics3.Idefics3VisionAttention'>", + "Idefics3VisionEmbeddings": "<'transformers.models.idefics3.modeling_idefics3.Idefics3VisionEmbeddings'>", + "Idefics3VisionMLP": "<'transformers.models.idefics3.modeling_idefics3.Idefics3VisionMLP'>", + "IdeficsAttention": "<'transformers.models.idefics.modeling_idefics.IdeficsAttention'>", + "IdeficsDecoderLayer": "<'transformers.models.idefics.modeling_idefics.IdeficsDecoderLayer'>", + "IdeficsDecoupledEmbedding": "<'transformers.models.idefics.modeling_idefics.IdeficsDecoupledEmbedding'>", + "IdeficsDecoupledLinear": "<'transformers.models.idefics.modeling_idefics.IdeficsDecoupledLinear'>", + "IdeficsEmbedding": "<'transformers.models.idefics.modeling_idefics.IdeficsEmbedding'>", + "IdeficsGatedCrossAttentionLayer": "<'transformers.models.idefics.modeling_idefics.IdeficsGatedCrossAttentionLayer'>", + "IdeficsMLP": "<'transformers.models.idefics.perceiver.IdeficsMLP'>", + "IdeficsPerceiverAttention": "<'transformers.models.idefics.perceiver.IdeficsPerceiverAttention'>", + "IdeficsPerceiverResampler": "<'transformers.models.idefics.perceiver.IdeficsPerceiverResampler'>", + "IdeficsRMSNorm": "<'transformers.models.idefics.modeling_idefics.IdeficsRMSNorm'>", + "IdeficsVisionAttention": "<'transformers.models.idefics.vision.IdeficsVisionAttention'>", + "IdeficsVisionEmbeddings": "<'transformers.models.idefics.vision.IdeficsVisionEmbeddings'>", + "IdeficsVisionEncoder": "<'transformers.models.idefics.vision.IdeficsVisionEncoder'>", + "IdeficsVisionEncoderLayer": "<'transformers.models.idefics.vision.IdeficsVisionEncoderLayer'>", + "IdeficsVisionMLP": "<'transformers.models.idefics.vision.IdeficsVisionMLP'>", + "IdeficsVisionTransformer": "<'transformers.models.idefics.vision.IdeficsVisionTransformer'>", + "IJepaAttention": "<'transformers.models.ijepa.modeling_ijepa.IJepaAttention'>", + "IJepaEmbeddings": "<'transformers.models.ijepa.modular_ijepa.IJepaEmbeddings'>", + "IJepaEncoder": "<'transformers.models.ijepa.modeling_ijepa.IJepaEncoder'>", + "IJepaIntermediate": "<'transformers.models.ijepa.modeling_ijepa.IJepaIntermediate'>", + "IJepaLayer": "<'transformers.models.ijepa.modeling_ijepa.IJepaLayer'>", + "IJepaOutput": "<'transformers.models.ijepa.modeling_ijepa.IJepaOutput'>", + "IJepaPatchEmbeddings": "<'transformers.models.ijepa.modeling_ijepa.IJepaPatchEmbeddings'>", + "IJepaPooler": "<'transformers.models.ijepa.modeling_ijepa.IJepaPooler'>", + "IJepaSelfAttention": "<'transformers.models.ijepa.modeling_ijepa.IJepaSelfAttention'>", + "IJepaSelfOutput": "<'transformers.models.ijepa.modeling_ijepa.IJepaSelfOutput'>", + "ImageGPTAttention": "<'transformers.models.imagegpt.modeling_imagegpt.ImageGPTAttention'>", + "ImageGPTBlock": "<'transformers.models.imagegpt.modeling_imagegpt.ImageGPTBlock'>", + "ImageGPTLayerNorm": "<'transformers.models.imagegpt.modeling_imagegpt.ImageGPTLayerNorm'>", + "ImageGPTMLP": "<'transformers.models.imagegpt.modeling_imagegpt.ImageGPTMLP'>", + "ImageLoss": "<'transformers.loss.loss_for_object_detection.ImageLoss'>", + "InformerAttention": "<'transformers.models.informer.modular_informer.InformerAttention'>", + "InformerConvLayer": "<'transformers.models.informer.modular_informer.InformerConvLayer'>", + "InformerDecoder": "<'transformers.models.informer.modular_informer.InformerDecoder'>", + "InformerDecoderLayer": "<'transformers.models.informer.modular_informer.InformerDecoderLayer'>", + "InformerEncoder": "<'transformers.models.informer.modular_informer.InformerEncoder'>", + "InformerEncoderLayer": "<'transformers.models.informer.modular_informer.InformerEncoderLayer'>", + "InformerFeatureEmbedder": "<'transformers.models.informer.modular_informer.InformerFeatureEmbedder'>", + "InformerMeanScaler": "<'transformers.models.informer.modular_informer.InformerMeanScaler'>", + "InformerNOPScaler": "<'transformers.models.informer.modular_informer.InformerNOPScaler'>", + "InformerProbSparseAttention": "<'transformers.models.informer.modular_informer.InformerProbSparseAttention'>", + "InformerSinusoidalPositionalEmbedding": "<'transformers.models.informer.modular_informer.InformerSinusoidalPositionalEmbedding'>", + "InformerStdScaler": "<'transformers.models.informer.modular_informer.InformerStdScaler'>", + "InformerValueEmbedding": "<'transformers.models.informer.modular_informer.InformerValueEmbedding'>", + "InjectScalerStatistics4D": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.InjectScalerStatistics4D'>", + "InstructBlipAttention": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipAttention'>", + "InstructBlipEncoder": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipEncoder'>", + "InstructBlipEncoderLayer": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipEncoderLayer'>", + "InstructBlipMLP": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipMLP'>", + "InstructBlipQFormerAttention": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerAttention'>", + "InstructBlipQFormerEmbeddings": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerEmbeddings'>", + "InstructBlipQFormerEncoder": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerEncoder'>", + "InstructBlipQFormerIntermediate": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerIntermediate'>", + "InstructBlipQFormerLayer": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerLayer'>", + "InstructBlipQFormerMultiHeadAttention": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerMultiHeadAttention'>", + "InstructBlipQFormerOutput": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerOutput'>", + "InstructBlipQFormerSelfOutput": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipQFormerSelfOutput'>", + "InstructBlipVideoAttention": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoAttention'>", + "InstructBlipVideoEncoder": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoEncoder'>", + "InstructBlipVideoEncoderLayer": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoEncoderLayer'>", + "InstructBlipVideoMLP": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoMLP'>", + "InstructBlipVideoQFormerAttention": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerAttention'>", + "InstructBlipVideoQFormerEmbeddings": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerEmbeddings'>", + "InstructBlipVideoQFormerEncoder": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerEncoder'>", + "InstructBlipVideoQFormerIntermediate": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerIntermediate'>", + "InstructBlipVideoQFormerLayer": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerLayer'>", + "InstructBlipVideoQFormerMultiHeadAttention": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerMultiHeadAttention'>", + "InstructBlipVideoQFormerOutput": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerOutput'>", + "InstructBlipVideoQFormerSelfOutput": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoQFormerSelfOutput'>", + "InstructBlipVideoVisionEmbeddings": "<'transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoVisionEmbeddings'>", + "InstructBlipVisionEmbeddings": "<'transformers.models.instructblip.modeling_instructblip.InstructBlipVisionEmbeddings'>", + "InternVLMultiModalProjector": "<'transformers.models.internvl.modular_internvl.InternVLMultiModalProjector'>", + "InternVLVisionAttention": "<'transformers.models.internvl.modular_internvl.InternVLVisionAttention'>", + "InternVLVisionEmbeddings": "<'transformers.models.internvl.modular_internvl.InternVLVisionEmbeddings'>", + "InternVLVisionEncoder": "<'transformers.models.internvl.modular_internvl.InternVLVisionEncoder'>", + "InternVLVisionLayer": "<'transformers.models.internvl.modular_internvl.InternVLVisionLayer'>", + "InternVLVisionMLP": "<'transformers.models.internvl.modular_internvl.InternVLVisionMLP'>", + "InternVLVisionPatchEmbeddings": "<'transformers.models.internvl.modular_internvl.InternVLVisionPatchEmbeddings'>", + "InternVLVisionRMSNorm": "<'transformers.models.internvl.modular_internvl.InternVLVisionRMSNorm'>", + "InterpolateInitialPositionEmbeddings": "<'transformers.models.yolos.modeling_yolos.InterpolateInitialPositionEmbeddings'>", + "InterpolateMidPositionEmbeddings": "<'transformers.models.yolos.modeling_yolos.InterpolateMidPositionEmbeddings'>", + "IntGELU": "<'transformers.models.ibert.quant_modules.IntGELU'>", + "IntLayerNorm": "<'transformers.models.ibert.quant_modules.IntLayerNorm'>", + "IntSoftmax": "<'transformers.models.ibert.quant_modules.IntSoftmax'>", + "JambaAttention": "<'transformers.models.jamba.modeling_jamba.JambaAttention'>", + "JambaAttentionDecoderLayer": "<'transformers.models.jamba.modeling_jamba.JambaAttentionDecoderLayer'>", + "JambaFlashAttention2": "<'transformers.models.jamba.modeling_jamba.JambaFlashAttention2'>", + "JambaMambaDecoderLayer": "<'transformers.models.jamba.modeling_jamba.JambaMambaDecoderLayer'>", + "JambaMambaMixer": "<'transformers.models.jamba.modeling_jamba.JambaMambaMixer'>", + "JambaMLP": "<'transformers.models.jamba.modeling_jamba.JambaMLP'>", + "JambaRMSNorm": "<'transformers.models.jamba.modeling_jamba.JambaRMSNorm'>", + "JambaSdpaAttention": "<'transformers.models.jamba.modeling_jamba.JambaSdpaAttention'>", + "JambaSparseMoeBlock": "<'transformers.models.jamba.modeling_jamba.JambaSparseMoeBlock'>", + "JanusVisionAlignerMLP": "<'transformers.models.janus.modular_janus.JanusVisionAlignerMLP'>", + "JanusVisionAttention": "<'transformers.models.janus.modeling_janus.JanusVisionAttention'>", + "JanusVisionEmbeddings": "<'transformers.models.janus.modular_janus.JanusVisionEmbeddings'>", + "JanusVisionEncoder": "<'transformers.models.janus.modular_janus.JanusVisionEncoder'>", + "JanusVisionEncoderLayer": "<'transformers.models.janus.modular_janus.JanusVisionEncoderLayer'>", + "JanusVisionMLP": "<'transformers.models.janus.modular_janus.JanusVisionMLP'>", + "JanusVQVAEAlignerMLP": "<'transformers.models.janus.modular_janus.JanusVQVAEAlignerMLP'>", + "JanusVQVAEAttnBlock": "<'transformers.models.janus.modular_janus.JanusVQVAEAttnBlock'>", + "JanusVQVAEConvDownsample": "<'transformers.models.janus.modular_janus.JanusVQVAEConvDownsample'>", + "JanusVQVAEConvUpsample": "<'transformers.models.janus.modular_janus.JanusVQVAEConvUpsample'>", + "JanusVQVAEDecoder": "<'transformers.models.janus.modular_janus.JanusVQVAEDecoder'>", + "JanusVQVAEEncoder": "<'transformers.models.janus.modular_janus.JanusVQVAEEncoder'>", + "JanusVQVAEHead": "<'transformers.models.janus.modular_janus.JanusVQVAEHead'>", + "JanusVQVAEMidBlock": "<'transformers.models.janus.modular_janus.JanusVQVAEMidBlock'>", + "JanusVQVAEResnetBlock": "<'transformers.models.janus.modular_janus.JanusVQVAEResnetBlock'>", + "JanusVQVAEVectorQuantizer": "<'transformers.models.janus.modular_janus.JanusVQVAEVectorQuantizer'>", + "JetMoeAttention": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeAttention'>", + "JetMoeBlock": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeBlock'>", + "JetMoeFlashAttention2": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeFlashAttention2'>", + "JetMoeMoA": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeMoA'>", + "JetMoeMoE": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeMoE'>", + "JetMoeParallelExperts": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeParallelExperts'>", + "JetMoeRMSNorm": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeRMSNorm'>", + "JetMoeRotaryEmbedding": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeRotaryEmbedding'>", + "JetMoeSdpaAttention": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeSdpaAttention'>", + "JetMoeTopKGating": "<'transformers.models.jetmoe.modeling_jetmoe.JetMoeTopKGating'>", + "JukeboxAttention": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxAttention'>", + "JukeboxBlock": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxBlock'>", + "JukeboxBottleneck": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxBottleneck'>", + "JukeboxBottleneckBlock": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxBottleneckBlock'>", + "JukeboxConditionalAutoregressive": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxConditionalAutoregressive'>", + "JukeboxConv1D": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxConv1D'>", + "JukeboxDecoder": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxDecoder'>", + "JukeboxDecoderConvBock": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxDecoderConvBock'>", + "JukeboxEncoder": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxEncoder'>", + "JukeboxEncoderConvBlock": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxEncoderConvBlock'>", + "JukeboxLabelConditioner": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxLabelConditioner'>", + "JukeboxLayerNorm": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxLayerNorm'>", + "JukeboxLayerStack": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxLayerStack'>", + "JukeboxMLP": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxMLP'>", + "JukeboxMusicTokenConditioner": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxMusicTokenConditioner'>", + "JukeboxPositionalEmbedding": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxPositionalEmbedding'>", + "JukeboxRangeEmbedding": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxRangeEmbedding'>", + "JukeboxResConv1DBlock": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxResConv1DBlock'>", + "JukeboxResnet1D": "<'transformers.models.deprecated.jukebox.modeling_jukebox.JukeboxResnet1D'>", + "KLDivLoss": "<'torch.nn.modules.loss.KLDivLoss'>", + "Kosmos2ImageToTextProjection": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2ImageToTextProjection'>", + "Kosmos2TextBlock": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextBlock'>", + "Kosmos2TextFFN": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextFFN'>", + "Kosmos2TextForCausalLM": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextForCausalLM'>", + "Kosmos2TextModel": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextModel'>", + "Kosmos2TextSinusoidalPositionalEmbedding": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextSinusoidalPositionalEmbedding'>", + "Kosmos2TextTransformer": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2TextTransformer'>", + "Kosmos2VisionAttention": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionAttention'>", + "Kosmos2VisionEmbeddings": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionEmbeddings'>", + "Kosmos2VisionEncoder": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionEncoder'>", + "Kosmos2VisionEncoderLayer": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionEncoderLayer'>", + "Kosmos2VisionMLP": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionMLP'>", + "Kosmos2VisionModel": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionModel'>", + "Kosmos2VisionTransformer": "<'transformers.models.kosmos2.modeling_kosmos2.Kosmos2VisionTransformer'>", + "KosmosTextAttention": "<'transformers.models.kosmos2.modeling_kosmos2.KosmosTextAttention'>", + "KyutaiSpeechToTextAttention": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextAttention'>", + "KyutaiSpeechToTextDecoderLayer": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextDecoderLayer'>", + "KyutaiSpeechToTextEmbeddings": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextEmbeddings'>", + "KyutaiSpeechToTextFlashAttention2": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextFlashAttention2'>", + "KyutaiSpeechToTextFlexibleLinear": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextFlexibleLinear'>", + "KyutaiSpeechToTextGatingMLP": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextGatingMLP'>", + "KyutaiSpeechToTextLinear": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextLinear'>", + "KyutaiSpeechToTextRMSNorm": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextRMSNorm'>", + "KyutaiSpeechToTextRotaryEmbedding": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextRotaryEmbedding'>", + "KyutaiSpeechToTextSdpaAttention": "<'transformers.models.kyutai_speech_to_text.modeling_kyutai_speech_to_text.KyutaiSpeechToTextSdpaAttention'>", + "L1Loss": "<'torch.nn.modules.loss.L1Loss'>", + "LambdaLayer": "<'transformers.time_series_utils.LambdaLayer'>", + "LaplaceActivation": "<'transformers.activations.LaplaceActivation'>", + "LayerDropModuleList": "<'transformers.models.deprecated.graphormer.modeling_graphormer.LayerDropModuleList'>", + "LayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "LayoutLMAttention": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMAttention'>", + "LayoutLMEmbeddings": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMEmbeddings'>", + "LayoutLMEncoder": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMEncoder'>", + "LayoutLMIntermediate": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMIntermediate'>", + "LayoutLMLayer": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMLayer'>", + "LayoutLMLayerNorm": "<'torch.nn.modules.normalization.LayerNorm'>", + "LayoutLMLMPredictionHead": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMLMPredictionHead'>", + "LayoutLMOnlyMLMHead": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMOnlyMLMHead'>", + "LayoutLMOutput": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMOutput'>", + "LayoutLMPooler": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMPooler'>", + "LayoutLMPredictionHeadTransform": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMPredictionHeadTransform'>", + "LayoutLMSelfAttention": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMSelfAttention'>", + "LayoutLMSelfOutput": "<'transformers.models.layoutlm.modeling_layoutlm.LayoutLMSelfOutput'>", + "LayoutLMv2Attention": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Attention'>", + "LayoutLMv2Embeddings": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Embeddings'>", + "LayoutLMv2Encoder": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Encoder'>", + "LayoutLMv2Intermediate": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Intermediate'>", + "LayoutLMv2Layer": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Layer'>", + "LayoutLMv2Output": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Output'>", + "LayoutLMv2Pooler": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2Pooler'>", + "LayoutLMv2SelfAttention": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2SelfAttention'>", + "LayoutLMv2SelfOutput": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2SelfOutput'>", + "LayoutLMv2VisualBackbone": "<'transformers.models.layoutlmv2.modeling_layoutlmv2.LayoutLMv2VisualBackbone'>", + "LayoutLMv3Attention": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3Attention'>", + "LayoutLMv3ClassificationHead": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3ClassificationHead'>", + "LayoutLMv3Encoder": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3Encoder'>", + "LayoutLMv3Intermediate": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3Intermediate'>", + "LayoutLMv3Layer": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3Layer'>", + "LayoutLMv3Output": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3Output'>", + "LayoutLMv3PatchEmbeddings": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3PatchEmbeddings'>", + "LayoutLMv3SelfAttention": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3SelfAttention'>", + "LayoutLMv3SelfOutput": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3SelfOutput'>", + "LayoutLMv3TextEmbeddings": "<'transformers.models.layoutlmv3.modeling_layoutlmv3.LayoutLMv3TextEmbeddings'>", + "LEDClassificationHead": "<'transformers.models.led.modeling_led.LEDClassificationHead'>", + "LEDDecoder": "<'transformers.models.led.modeling_led.LEDDecoder'>", + "LEDDecoderAttention": "<'transformers.models.led.modeling_led.LEDDecoderAttention'>", + "LEDDecoderLayer": "<'transformers.models.led.modeling_led.LEDDecoderLayer'>", + "LEDEncoder": "<'transformers.models.led.modeling_led.LEDEncoder'>", + "LEDEncoderAttention": "<'transformers.models.led.modeling_led.LEDEncoderAttention'>", + "LEDEncoderLayer": "<'transformers.models.led.modeling_led.LEDEncoderLayer'>", + "LEDEncoderSelfAttention": "<'transformers.models.led.modeling_led.LEDEncoderSelfAttention'>", + "LEDLearnedPositionalEmbedding": "<'transformers.models.led.modeling_led.LEDLearnedPositionalEmbedding'>", + "LegacyDebertaLMPredictionHead": "<'transformers.models.deberta.modeling_deberta.LegacyDebertaLMPredictionHead'>", + "LegacyDebertaOnlyMLMHead": "<'transformers.models.deberta.modeling_deberta.LegacyDebertaOnlyMLMHead'>", + "LegacyDebertaPredictionHeadTransform": "<'transformers.models.deberta.modeling_deberta.LegacyDebertaPredictionHeadTransform'>", + "LegacyDebertaV2LMPredictionHead": "<'transformers.models.deberta_v2.modeling_deberta_v2.LegacyDebertaV2LMPredictionHead'>", + "LegacyDebertaV2OnlyMLMHead": "<'transformers.models.deberta_v2.modeling_deberta_v2.LegacyDebertaV2OnlyMLMHead'>", + "LegacyDebertaV2PredictionHeadTransform": "<'transformers.models.deberta_v2.modeling_deberta_v2.LegacyDebertaV2PredictionHeadTransform'>", + "LevitAttention": "<'transformers.models.levit.modeling_levit.LevitAttention'>", + "LevitAttentionSubsample": "<'transformers.models.levit.modeling_levit.LevitAttentionSubsample'>", + "LevitClassificationLayer": "<'transformers.models.levit.modeling_levit.LevitClassificationLayer'>", + "LevitConvEmbeddings": "<'transformers.models.levit.modeling_levit.LevitConvEmbeddings'>", + "LevitEncoder": "<'transformers.models.levit.modeling_levit.LevitEncoder'>", + "LevitMLPLayer": "<'transformers.models.levit.modeling_levit.LevitMLPLayer'>", + "LevitPatchEmbeddings": "<'transformers.models.levit.modeling_levit.LevitPatchEmbeddings'>", + "LevitResidualLayer": "<'transformers.models.levit.modeling_levit.LevitResidualLayer'>", + "LevitStage": "<'transformers.models.levit.modeling_levit.LevitStage'>", + "LevitSubsample": "<'transformers.models.levit.modeling_levit.LevitSubsample'>", + "Lfm2Attention": "<'transformers.models.lfm2.modeling_lfm2.Lfm2Attention'>", + "Lfm2DecoderLayer": "<'transformers.models.lfm2.modeling_lfm2.Lfm2DecoderLayer'>", + "Lfm2MLP": "<'transformers.models.lfm2.modeling_lfm2.Lfm2MLP'>", + "Lfm2RMSNorm": "<'transformers.models.lfm2.modeling_lfm2.Lfm2RMSNorm'>", + "Lfm2RotaryEmbedding": "<'transformers.models.lfm2.modeling_lfm2.Lfm2RotaryEmbedding'>", + "Lfm2ShortConv": "<'transformers.models.lfm2.modeling_lfm2.Lfm2ShortConv'>", + "LightGlueAttention": "<'transformers.models.lightglue.modeling_lightglue.LightGlueAttention'>", + "LightGlueMatchAssignmentLayer": "<'transformers.models.lightglue.modeling_lightglue.LightGlueMatchAssignmentLayer'>", + "LightGlueMLP": "<'transformers.models.lightglue.modeling_lightglue.LightGlueMLP'>", + "LightGluePositionalEncoder": "<'transformers.models.lightglue.modeling_lightglue.LightGluePositionalEncoder'>", + "LightGlueTokenConfidenceLayer": "<'transformers.models.lightglue.modeling_lightglue.LightGlueTokenConfidenceLayer'>", + "LightGlueTransformerLayer": "<'transformers.models.lightglue.modeling_lightglue.LightGlueTransformerLayer'>", + "LiltAttention": "<'transformers.models.lilt.modeling_lilt.LiltAttention'>", + "LiltClassificationHead": "<'transformers.models.lilt.modeling_lilt.LiltClassificationHead'>", + "LiltEncoder": "<'transformers.models.lilt.modeling_lilt.LiltEncoder'>", + "LiltIntermediate": "<'transformers.models.lilt.modeling_lilt.LiltIntermediate'>", + "LiltLayer": "<'transformers.models.lilt.modeling_lilt.LiltLayer'>", + "LiltLayoutEmbeddings": "<'transformers.models.lilt.modeling_lilt.LiltLayoutEmbeddings'>", + "LiltOutput": "<'transformers.models.lilt.modeling_lilt.LiltOutput'>", + "LiltPooler": "<'transformers.models.lilt.modeling_lilt.LiltPooler'>", + "LiltSelfAttention": "<'transformers.models.lilt.modeling_lilt.LiltSelfAttention'>", + "LiltSelfOutput": "<'transformers.models.lilt.modeling_lilt.LiltSelfOutput'>", + "LiltTextEmbeddings": "<'transformers.models.lilt.modeling_lilt.LiltTextEmbeddings'>", + "LinearActivation": "<'transformers.activations.LinearActivation'>", + "Llama4MultiModalProjector": "<'transformers.models.llama4.modeling_llama4.Llama4MultiModalProjector'>", + "Llama4Router": "<'transformers.models.llama4.modeling_llama4.Llama4Router'>", + "Llama4TextAttention": "<'transformers.models.llama4.modeling_llama4.Llama4TextAttention'>", + "Llama4TextDecoderLayer": "<'transformers.models.llama4.modeling_llama4.Llama4TextDecoderLayer'>", + "Llama4TextExperts": "<'transformers.models.llama4.modeling_llama4.Llama4TextExperts'>", + "Llama4TextL2Norm": "<'transformers.models.llama4.modeling_llama4.Llama4TextL2Norm'>", + "Llama4TextMLP": "<'transformers.models.llama4.modeling_llama4.Llama4TextMLP'>", + "Llama4TextMoe": "<'transformers.models.llama4.modeling_llama4.Llama4TextMoe'>", + "Llama4TextRMSNorm": "<'transformers.models.llama4.modeling_llama4.Llama4TextRMSNorm'>", + "Llama4TextRotaryEmbedding": "<'transformers.models.llama4.modeling_llama4.Llama4TextRotaryEmbedding'>", + "Llama4UnfoldConvolution": "<'transformers.models.llama4.modeling_llama4.Llama4UnfoldConvolution'>", + "Llama4VisionAttention": "<'transformers.models.llama4.modeling_llama4.Llama4VisionAttention'>", + "Llama4VisionEncoder": "<'transformers.models.llama4.modeling_llama4.Llama4VisionEncoder'>", + "Llama4VisionEncoderLayer": "<'transformers.models.llama4.modeling_llama4.Llama4VisionEncoderLayer'>", + "Llama4VisionMLP": "<'transformers.models.llama4.modeling_llama4.Llama4VisionMLP'>", + "Llama4VisionMLP2": "<'transformers.models.llama4.modeling_llama4.Llama4VisionMLP2'>", + "Llama4VisionPixelShuffleMLP": "<'transformers.models.llama4.modeling_llama4.Llama4VisionPixelShuffleMLP'>", + "Llama4VisionRotaryEmbedding": "<'transformers.models.llama4.modeling_llama4.Llama4VisionRotaryEmbedding'>", + "LlamaAttention": "<'transformers.models.llama.modeling_llama.LlamaAttention'>", + "LlamaDecoderLayer": "<'transformers.models.llama.modeling_llama.LlamaDecoderLayer'>", + "LlamaMLP": "<'transformers.models.llama.modeling_llama.LlamaMLP'>", + "LlamaRMSNorm": "<'transformers.models.llama.modeling_llama.LlamaRMSNorm'>", + "LlamaRotaryEmbedding": "<'transformers.models.llama.modeling_llama.LlamaRotaryEmbedding'>", + "LlavaMultiModalProjector": "<'transformers.models.llava.modeling_llava.LlavaMultiModalProjector'>", + "LlavaNextMultiModalProjector": "<'transformers.models.llava_next.modeling_llava_next.LlavaNextMultiModalProjector'>", + "LlavaNextVideoMultiModalProjector": "<'transformers.models.llava_next_video.modeling_llava_next_video.LlavaNextVideoMultiModalProjector'>", + "LlavaNextVideoPooler": "<'transformers.models.llava_next_video.modeling_llava_next_video.LlavaNextVideoPooler'>", + "LlavaOnevisionMultiModalProjector": "<'transformers.models.llava_onevision.modeling_llava_onevision.LlavaOnevisionMultiModalProjector'>", + "LlavaOnevisionPooler": "<'transformers.models.llava_onevision.modeling_llava_onevision.LlavaOnevisionPooler'>", + "LocalSelfAttention": "<'transformers.models.reformer.modeling_reformer.LocalSelfAttention'>", + "LogBinomialSoftmax": "<'transformers.models.zoedepth.modeling_zoedepth.LogBinomialSoftmax'>", + "LogSoftmax": "<'torch.nn.modules.activation.LogSoftmax'>", + "LongformerAttention": "<'transformers.models.longformer.modeling_longformer.LongformerAttention'>", + "LongformerClassificationHead": "<'transformers.models.longformer.modeling_longformer.LongformerClassificationHead'>", + "LongformerEmbeddings": "<'transformers.models.longformer.modeling_longformer.LongformerEmbeddings'>", + "LongformerEncoder": "<'transformers.models.longformer.modeling_longformer.LongformerEncoder'>", + "LongformerIntermediate": "<'transformers.models.longformer.modeling_longformer.LongformerIntermediate'>", + "LongformerLayer": "<'transformers.models.longformer.modeling_longformer.LongformerLayer'>", + "LongformerLMHead": "<'transformers.models.longformer.modeling_longformer.LongformerLMHead'>", + "LongformerOutput": "<'transformers.models.longformer.modeling_longformer.LongformerOutput'>", + "LongformerPooler": "<'transformers.models.longformer.modeling_longformer.LongformerPooler'>", + "LongformerSelfAttention": "<'transformers.models.longformer.modeling_longformer.LongformerSelfAttention'>", + "LongformerSelfOutput": "<'transformers.models.longformer.modeling_longformer.LongformerSelfOutput'>", + "LongT5Attention": "<'transformers.models.longt5.modeling_longt5.LongT5Attention'>", + "LongT5Block": "<'transformers.models.longt5.modeling_longt5.LongT5Block'>", + "LongT5DenseActDense": "<'transformers.models.longt5.modeling_longt5.LongT5DenseActDense'>", + "LongT5DenseGatedActDense": "<'transformers.models.longt5.modeling_longt5.LongT5DenseGatedActDense'>", + "LongT5LayerCrossAttention": "<'transformers.models.longt5.modeling_longt5.LongT5LayerCrossAttention'>", + "LongT5LayerFF": "<'transformers.models.longt5.modeling_longt5.LongT5LayerFF'>", + "LongT5LayerLocalSelfAttention": "<'transformers.models.longt5.modeling_longt5.LongT5LayerLocalSelfAttention'>", + "LongT5LayerNorm": "<'transformers.models.longt5.modeling_longt5.LongT5LayerNorm'>", + "LongT5LayerSelfAttention": "<'transformers.models.longt5.modeling_longt5.LongT5LayerSelfAttention'>", + "LongT5LayerTransientGlobalSelfAttention": "<'transformers.models.longt5.modeling_longt5.LongT5LayerTransientGlobalSelfAttention'>", + "LongT5LocalAttention": "<'transformers.models.longt5.modeling_longt5.LongT5LocalAttention'>", + "LongT5Stack": "<'transformers.models.longt5.modeling_longt5.LongT5Stack'>", + "LongT5TransientGlobalAttention": "<'transformers.models.longt5.modeling_longt5.LongT5TransientGlobalAttention'>", + "LSHSelfAttention": "<'transformers.models.reformer.modeling_reformer.LSHSelfAttention'>", + "LukeAttention": "<'transformers.models.luke.modeling_luke.LukeAttention'>", + "LukeEmbeddings": "<'transformers.models.luke.modeling_luke.LukeEmbeddings'>", + "LukeEncoder": "<'transformers.models.luke.modeling_luke.LukeEncoder'>", + "LukeEntityEmbeddings": "<'transformers.models.luke.modeling_luke.LukeEntityEmbeddings'>", + "LukeIntermediate": "<'transformers.models.luke.modeling_luke.LukeIntermediate'>", + "LukeLayer": "<'transformers.models.luke.modeling_luke.LukeLayer'>", + "LukeLMHead": "<'transformers.models.luke.modeling_luke.LukeLMHead'>", + "LukeOutput": "<'transformers.models.luke.modeling_luke.LukeOutput'>", + "LukePooler": "<'transformers.models.luke.modeling_luke.LukePooler'>", + "LukeSelfAttention": "<'transformers.models.luke.modeling_luke.LukeSelfAttention'>", + "LukeSelfOutput": "<'transformers.models.luke.modeling_luke.LukeSelfOutput'>", + "LxmertAttention": "<'transformers.models.lxmert.modeling_lxmert.LxmertAttention'>", + "LxmertAttentionOutput": "<'transformers.models.lxmert.modeling_lxmert.LxmertAttentionOutput'>", + "LxmertCrossAttentionLayer": "<'transformers.models.lxmert.modeling_lxmert.LxmertCrossAttentionLayer'>", + "LxmertEmbeddings": "<'transformers.models.lxmert.modeling_lxmert.LxmertEmbeddings'>", + "LxmertIntermediate": "<'transformers.models.lxmert.modeling_lxmert.LxmertIntermediate'>", + "LxmertLayer": "<'transformers.models.lxmert.modeling_lxmert.LxmertLayer'>", + "LxmertLMPredictionHead": "<'transformers.models.lxmert.modeling_lxmert.LxmertLMPredictionHead'>", + "LxmertOutput": "<'transformers.models.lxmert.modeling_lxmert.LxmertOutput'>", + "LxmertPooler": "<'transformers.models.lxmert.modeling_lxmert.LxmertPooler'>", + "LxmertPredictionHeadTransform": "<'transformers.models.lxmert.modeling_lxmert.LxmertPredictionHeadTransform'>", + "LxmertPreTrainingHeads": "<'transformers.models.lxmert.modeling_lxmert.LxmertPreTrainingHeads'>", + "LxmertSelfAttentionLayer": "<'transformers.models.lxmert.modeling_lxmert.LxmertSelfAttentionLayer'>", + "LxmertVisualAnswerHead": "<'transformers.models.lxmert.modeling_lxmert.LxmertVisualAnswerHead'>", + "LxmertVisualObjHead": "<'transformers.models.lxmert.modeling_lxmert.LxmertVisualObjHead'>", + "LxmertXLayer": "<'transformers.models.lxmert.modeling_lxmert.LxmertXLayer'>", + "M2M100Attention": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100Attention'>", + "M2M100Decoder": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100Decoder'>", + "M2M100DecoderLayer": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100DecoderLayer'>", + "M2M100Encoder": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100Encoder'>", + "M2M100EncoderLayer": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100EncoderLayer'>", + "M2M100ScaledWordEmbedding": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100ScaledWordEmbedding'>", + "M2M100SinusoidalPositionalEmbedding": "<'transformers.models.m2m_100.modeling_m2m_100.M2M100SinusoidalPositionalEmbedding'>", + "Mamba2Block": "<'transformers.models.mamba2.modeling_mamba2.Mamba2Block'>", + "Mamba2Mixer": "<'transformers.models.mamba2.modeling_mamba2.Mamba2Mixer'>", + "Mamba2RMSNorm": "<'transformers.models.mamba2.modeling_mamba2.Mamba2RMSNorm'>", + "MambaBlock": "<'transformers.models.mamba.modeling_mamba.MambaBlock'>", + "MambaMixer": "<'transformers.models.mamba.modeling_mamba.MambaMixer'>", + "MambaRMSNorm": "<'transformers.models.mamba.modeling_mamba.MambaRMSNorm'>", + "MambaRMSNormGated": "<'transformers.models.mamba2.modeling_mamba2.MambaRMSNormGated'>", + "MarianAttention": "<'transformers.models.marian.modeling_marian.MarianAttention'>", + "MarianDecoder": "<'transformers.models.marian.modeling_marian.MarianDecoder'>", + "MarianDecoderLayer": "<'transformers.models.marian.modeling_marian.MarianDecoderLayer'>", + "MarianDecoderWrapper": "<'transformers.models.marian.modeling_marian.MarianDecoderWrapper'>", + "MarianEncoder": "<'transformers.models.marian.modeling_marian.MarianEncoder'>", + "MarianEncoderLayer": "<'transformers.models.marian.modeling_marian.MarianEncoderLayer'>", + "MarianSinusoidalPositionalEmbedding": "<'transformers.models.marian.modeling_marian.MarianSinusoidalPositionalEmbedding'>", + "MarkupLMAttention": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMAttention'>", + "MarkupLMEmbeddings": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMEmbeddings'>", + "MarkupLMEncoder": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMEncoder'>", + "MarkupLMIntermediate": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMIntermediate'>", + "MarkupLMLayer": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMLayer'>", + "MarkupLMLMPredictionHead": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMLMPredictionHead'>", + "MarkupLMOnlyMLMHead": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMOnlyMLMHead'>", + "MarkupLMOutput": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMOutput'>", + "MarkupLMPooler": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMPooler'>", + "MarkupLMPredictionHeadTransform": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMPredictionHeadTransform'>", + "MarkupLMSelfAttention": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMSelfAttention'>", + "MarkupLMSelfOutput": "<'transformers.models.markuplm.modeling_markuplm.MarkupLMSelfOutput'>", + "Mask2FormerAttention": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerAttention'>", + "Mask2FormerHungarianMatcher": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerHungarianMatcher'>", + "Mask2FormerLoss": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerLoss'>", + "Mask2FormerMaskedAttentionDecoder": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerMaskedAttentionDecoder'>", + "Mask2FormerMaskedAttentionDecoderLayer": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerMaskedAttentionDecoderLayer'>", + "Mask2FormerMaskPredictor": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerMaskPredictor'>", + "Mask2FormerMLPPredictionHead": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerMLPPredictionHead'>", + "Mask2FormerPixelDecoder": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPixelDecoder'>", + "Mask2FormerPixelDecoderEncoderLayer": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPixelDecoderEncoderLayer'>", + "Mask2FormerPixelDecoderEncoderMultiscaleDeformableAttention": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPixelDecoderEncoderMultiscaleDeformableAttention'>", + "Mask2FormerPixelDecoderEncoderOnly": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPixelDecoderEncoderOnly'>", + "Mask2FormerPixelLevelModule": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPixelLevelModule'>", + "Mask2FormerPredictionBlock": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerPredictionBlock'>", + "Mask2FormerSinePositionEmbedding": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerSinePositionEmbedding'>", + "Mask2FormerTransformerModule": "<'transformers.models.mask2former.modeling_mask2former.Mask2FormerTransformerModule'>", + "MaskFormerFPNConvLayer": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerFPNConvLayer'>", + "MaskFormerFPNLayer": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerFPNLayer'>", + "MaskFormerFPNModel": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerFPNModel'>", + "MaskFormerHungarianMatcher": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerHungarianMatcher'>", + "MaskFormerLoss": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerLoss'>", + "MaskformerMLPPredictionHead": "<'transformers.models.maskformer.modeling_maskformer.MaskformerMLPPredictionHead'>", + "MaskFormerPixelDecoder": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerPixelDecoder'>", + "MaskFormerPixelLevelModule": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerPixelLevelModule'>", + "MaskFormerSinePositionEmbedding": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerSinePositionEmbedding'>", + "MaskFormerSwinAttention": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinAttention'>", + "MaskFormerSwinDropPath": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinDropPath'>", + "MaskFormerSwinEmbeddings": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinEmbeddings'>", + "MaskFormerSwinEncoder": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinEncoder'>", + "MaskFormerSwinIntermediate": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinIntermediate'>", + "MaskFormerSwinLayer": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinLayer'>", + "MaskFormerSwinOutput": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinOutput'>", + "MaskFormerSwinPatchEmbeddings": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinPatchEmbeddings'>", + "MaskFormerSwinPatchMerging": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinPatchMerging'>", + "MaskFormerSwinSelfAttention": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinSelfAttention'>", + "MaskFormerSwinSelfOutput": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinSelfOutput'>", + "MaskFormerSwinStage": "<'transformers.models.maskformer.modeling_maskformer_swin.MaskFormerSwinStage'>", + "MaskFormerTransformerModule": "<'transformers.models.maskformer.modeling_maskformer.MaskFormerTransformerModule'>", + "MatMulWrapper": "<'transformers.models.squeezebert.modeling_squeezebert.MatMulWrapper'>", + "MBartAttention": "<'transformers.models.mbart.modeling_mbart.MBartAttention'>", + "MBartClassificationHead": "<'transformers.models.mbart.modeling_mbart.MBartClassificationHead'>", + "MBartDecoder": "<'transformers.models.mbart.modeling_mbart.MBartDecoder'>", + "MBartDecoderLayer": "<'transformers.models.mbart.modeling_mbart.MBartDecoderLayer'>", + "MBartDecoderWrapper": "<'transformers.models.mbart.modeling_mbart.MBartDecoderWrapper'>", + "MBartEncoder": "<'transformers.models.mbart.modeling_mbart.MBartEncoder'>", + "MBartEncoderLayer": "<'transformers.models.mbart.modeling_mbart.MBartEncoderLayer'>", + "MBartLearnedPositionalEmbedding": "<'transformers.models.mbart.modeling_mbart.MBartLearnedPositionalEmbedding'>", + "MBartScaledWordEmbedding": "<'transformers.models.mbart.modeling_mbart.MBartScaledWordEmbedding'>", + "MCTCTAttention": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTAttention'>", + "MCTCTConv1dSubsampler": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTConv1dSubsampler'>", + "MCTCTEmbeddings": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTEmbeddings'>", + "MCTCTEncoder": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTEncoder'>", + "MCTCTIntermediate": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTIntermediate'>", + "MCTCTLayer": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTLayer'>", + "MCTCTLayerNorm": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTLayerNorm'>", + "MCTCTOutput": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTOutput'>", + "MCTCTSelfAttention": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTSelfAttention'>", + "MCTCTSelfOutput": "<'transformers.models.deprecated.mctct.modeling_mctct.MCTCTSelfOutput'>", + "MegaBlock": "<'transformers.models.deprecated.mega.modeling_mega.MegaBlock'>", + "MegaClassificationHead": "<'transformers.models.deprecated.mega.modeling_mega.MegaClassificationHead'>", + "MegaDropout": "<'transformers.models.deprecated.mega.modeling_mega.MegaDropout'>", + "MegaEmbeddings": "<'transformers.models.deprecated.mega.modeling_mega.MegaEmbeddings'>", + "MegaGatedCrossAttention": "<'transformers.models.deprecated.mega.modeling_mega.MegaGatedCrossAttention'>", + "MegaMovingAverageGatedAttention": "<'transformers.models.deprecated.mega.modeling_mega.MegaMovingAverageGatedAttention'>", + "MegaMultiDimensionDampedEma": "<'transformers.models.deprecated.mega.modeling_mega.MegaMultiDimensionDampedEma'>", + "MegaNormalizedFeedForwardNetwork": "<'transformers.models.deprecated.mega.modeling_mega.MegaNormalizedFeedForwardNetwork'>", + "MegaPooler": "<'transformers.models.deprecated.mega.modeling_mega.MegaPooler'>", + "MegaRMSNorm": "<'transformers.models.deprecated.mega.modeling_mega.MegaRMSNorm'>", + "MegaRotaryRelativePositionalBias": "<'transformers.models.deprecated.mega.modeling_mega.MegaRotaryRelativePositionalBias'>", + "MegaScaleNorm": "<'transformers.models.deprecated.mega.modeling_mega.MegaScaleNorm'>", + "MegaSequenceNorm": "<'transformers.models.deprecated.mega.modeling_mega.MegaSequenceNorm'>", + "MegaSimpleRelativePositionalBias": "<'transformers.models.deprecated.mega.modeling_mega.MegaSimpleRelativePositionalBias'>", + "MegatronBertAttention": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertAttention'>", + "MegatronBertEmbeddings": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertEmbeddings'>", + "MegatronBertEncoder": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertEncoder'>", + "MegatronBertIntermediate": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertIntermediate'>", + "MegatronBertLayer": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertLayer'>", + "MegatronBertLMPredictionHead": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertLMPredictionHead'>", + "MegatronBertOnlyMLMHead": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertOnlyMLMHead'>", + "MegatronBertOnlyNSPHead": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertOnlyNSPHead'>", + "MegatronBertOutput": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertOutput'>", + "MegatronBertPooler": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertPooler'>", + "MegatronBertPredictionHeadTransform": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertPredictionHeadTransform'>", + "MegatronBertPreTrainingHeads": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertPreTrainingHeads'>", + "MegatronBertSelfAttention": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertSelfAttention'>", + "MegatronBertSelfOutput": "<'transformers.models.megatron_bert.modeling_megatron_bert.MegatronBertSelfOutput'>", + "MgpstrA3Module": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrA3Module'>", + "MgpstrAttention": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrAttention'>", + "MgpstrDropPath": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrDropPath'>", + "MgpstrEmbeddings": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrEmbeddings'>", + "MgpstrEncoder": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrEncoder'>", + "MgpstrLayer": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrLayer'>", + "MgpstrMlp": "<'transformers.models.mgp_str.modeling_mgp_str.MgpstrMlp'>", + "MimiAttention": "<'transformers.models.mimi.modeling_mimi.MimiAttention'>", + "MimiConv1d": "<'transformers.models.mimi.modeling_mimi.MimiConv1d'>", + "MimiConvTranspose1d": "<'transformers.models.mimi.modeling_mimi.MimiConvTranspose1d'>", + "MimiDecoder": "<'transformers.models.mimi.modeling_mimi.MimiDecoder'>", + "MimiEncoder": "<'transformers.models.mimi.modeling_mimi.MimiEncoder'>", + "MimiEuclideanCodebook": "<'transformers.models.mimi.modeling_mimi.MimiEuclideanCodebook'>", + "MimiFlashAttention2": "<'transformers.models.mimi.modeling_mimi.MimiFlashAttention2'>", + "MimiLayerScale": "<'transformers.models.mimi.modeling_mimi.MimiLayerScale'>", + "MimiMLP": "<'transformers.models.mimi.modeling_mimi.MimiMLP'>", + "MimiResidualVectorQuantizer": "<'transformers.models.mimi.modeling_mimi.MimiResidualVectorQuantizer'>", + "MimiResnetBlock": "<'transformers.models.mimi.modeling_mimi.MimiResnetBlock'>", + "MimiRotaryEmbedding": "<'transformers.models.mimi.modeling_mimi.MimiRotaryEmbedding'>", + "MimiSdpaAttention": "<'transformers.models.mimi.modeling_mimi.MimiSdpaAttention'>", + "MimiSplitResidualVectorQuantizer": "<'transformers.models.mimi.modeling_mimi.MimiSplitResidualVectorQuantizer'>", + "MimiTransformerLayer": "<'transformers.models.mimi.modeling_mimi.MimiTransformerLayer'>", + "MimiTransformerModel": "<'transformers.models.mimi.modeling_mimi.MimiTransformerModel'>", + "MimiVectorQuantization": "<'transformers.models.mimi.modeling_mimi.MimiVectorQuantization'>", + "MiniMaxAttention": "<'transformers.models.minimax.modeling_minimax.MiniMaxAttention'>", + "MiniMaxBlockSparseTop2MLP": "<'transformers.models.minimax.modeling_minimax.MiniMaxBlockSparseTop2MLP'>", + "MiniMaxDecoderLayer": "<'transformers.models.minimax.modeling_minimax.MiniMaxDecoderLayer'>", + "MiniMaxLightningAttention": "<'transformers.models.minimax.modeling_minimax.MiniMaxLightningAttention'>", + "MiniMaxRMSNorm": "<'transformers.models.minimax.modeling_minimax.MiniMaxRMSNorm'>", + "MiniMaxRotaryEmbedding": "<'transformers.models.minimax.modeling_minimax.MiniMaxRotaryEmbedding'>", + "MiniMaxSparseMoeBlock": "<'transformers.models.minimax.modeling_minimax.MiniMaxSparseMoeBlock'>", + "MishActivation": "<'transformers.activations.MishActivation'>", + "Mistral3MultiModalProjector": "<'transformers.models.mistral3.modeling_mistral3.Mistral3MultiModalProjector'>", + "Mistral3PatchMerger": "<'transformers.models.mistral3.modeling_mistral3.Mistral3PatchMerger'>", + "Mistral3RMSNorm": "<'transformers.models.mistral3.modeling_mistral3.Mistral3RMSNorm'>", + "MistralAttention": "<'transformers.models.mistral.modeling_mistral.MistralAttention'>", + "MistralDecoderLayer": "<'transformers.models.mistral.modeling_mistral.MistralDecoderLayer'>", + "MistralMLP": "<'transformers.models.mistral.modeling_mistral.MistralMLP'>", + "MistralRMSNorm": "<'transformers.models.mistral.modeling_mistral.MistralRMSNorm'>", + "MistralRotaryEmbedding": "<'transformers.models.mistral.modeling_mistral.MistralRotaryEmbedding'>", + "MixtralAttention": "<'transformers.models.mixtral.modeling_mixtral.MixtralAttention'>", + "MixtralBlockSparseTop2MLP": "<'transformers.models.mixtral.modular_mixtral.MixtralBlockSparseTop2MLP'>", + "MixtralDecoderLayer": "<'transformers.models.mixtral.modeling_mixtral.MixtralDecoderLayer'>", + "MixtralRMSNorm": "<'transformers.models.mixtral.modeling_mixtral.MixtralRMSNorm'>", + "MixtralRotaryEmbedding": "<'transformers.models.mixtral.modular_mixtral.MixtralRotaryEmbedding'>", + "MixtralSparseMoeBlock": "<'transformers.models.mixtral.modeling_mixtral.MixtralSparseMoeBlock'>", + "MLCDAttention": "<'transformers.models.mlcd.modular_mlcd.MLCDAttention'>", + "MLCDEncoder": "<'transformers.models.mlcd.modular_mlcd.MLCDEncoder'>", + "MLCDEncoderLayer": "<'transformers.models.mlcd.modular_mlcd.MLCDEncoderLayer'>", + "MLCDMLP": "<'transformers.models.mlcd.modular_mlcd.MLCDMLP'>", + "MLCDRotaryEmbedding": "<'transformers.models.mlcd.modular_mlcd.MLCDRotaryEmbedding'>", + "MLCDVisionEmbeddings": "<'transformers.models.mlcd.modular_mlcd.MLCDVisionEmbeddings'>", + "MLCDVisionTransformer": "<'transformers.models.mlcd.modular_mlcd.MLCDVisionTransformer'>", + "MllamaCrossAttentionDecoderLayer": "<'transformers.models.mllama.modeling_mllama.MllamaCrossAttentionDecoderLayer'>", + "MllamaPrecomputedAspectRatioEmbedding": "<'transformers.models.mllama.modeling_mllama.MllamaPrecomputedAspectRatioEmbedding'>", + "MllamaPrecomputedPositionEmbedding": "<'transformers.models.mllama.modeling_mllama.MllamaPrecomputedPositionEmbedding'>", + "MllamaRotaryEmbedding": "<'transformers.models.mllama.modeling_mllama.MllamaRotaryEmbedding'>", + "MllamaSelfAttentionDecoderLayer": "<'transformers.models.mllama.modeling_mllama.MllamaSelfAttentionDecoderLayer'>", + "MllamaTextCrossAttention": "<'transformers.models.mllama.modeling_mllama.MllamaTextCrossAttention'>", + "MllamaTextMLP": "<'transformers.models.mllama.modeling_mllama.MllamaTextMLP'>", + "MllamaTextRMSNorm": "<'transformers.models.mllama.modeling_mllama.MllamaTextRMSNorm'>", + "MllamaTextSelfAttention": "<'transformers.models.mllama.modeling_mllama.MllamaTextSelfAttention'>", + "MllamaVisionAttention": "<'transformers.models.mllama.modeling_mllama.MllamaVisionAttention'>", + "MllamaVisionEncoder": "<'transformers.models.mllama.modeling_mllama.MllamaVisionEncoder'>", + "MllamaVisionEncoderLayer": "<'transformers.models.mllama.modeling_mllama.MllamaVisionEncoderLayer'>", + "MllamaVisionMLP": "<'transformers.models.mllama.modeling_mllama.MllamaVisionMLP'>", + "MLP": "<'transformers.models.openai.modeling_openai.MLP'>", + "MLPLayerWithBN": "<'transformers.models.levit.modeling_levit.MLPLayerWithBN'>", + "MMGroundingDinoBiMultiHeadAttention": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoBiMultiHeadAttention'>", + "MMGroundingDinoContrastiveEmbedding": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoContrastiveEmbedding'>", + "MMGroundingDinoConvEncoder": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoConvEncoder'>", + "MMGroundingDinoConvModel": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoConvModel'>", + "MMGroundingDinoDecoder": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoDecoder'>", + "MMGroundingDinoDecoderLayer": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoDecoderLayer'>", + "MMGroundingDinoDeformableLayer": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoDeformableLayer'>", + "MMGroundingDinoDropPath": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoDropPath'>", + "MMGroundingDinoEncoder": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoEncoder'>", + "MMGroundingDinoEncoderLayer": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoEncoderLayer'>", + "MMGroundingDinoFrozenBatchNorm2d": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoFrozenBatchNorm2d'>", + "MMGroundingDinoFusionLayer": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoFusionLayer'>", + "MMGroundingDinoLearnedPositionEmbedding": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoLearnedPositionEmbedding'>", + "MMGroundingDinoMLPPredictionHead": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoMLPPredictionHead'>", + "MMGroundingDinoMultiheadAttention": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoMultiheadAttention'>", + "MMGroundingDinoMultiscaleDeformableAttention": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoMultiscaleDeformableAttention'>", + "MMGroundingDinoSinePositionEmbedding": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoSinePositionEmbedding'>", + "MMGroundingDinoTextEnhancerLayer": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MMGroundingDinoTextEnhancerLayer'>", + "MobileBertAttention": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertAttention'>", + "MobileBertEmbeddings": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertEmbeddings'>", + "MobileBertEncoder": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertEncoder'>", + "MobileBertIntermediate": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertIntermediate'>", + "MobileBertLayer": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertLayer'>", + "MobileBertLMPredictionHead": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertLMPredictionHead'>", + "MobileBertOnlyMLMHead": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertOnlyMLMHead'>", + "MobileBertOnlyNSPHead": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertOnlyNSPHead'>", + "MobileBertOutput": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertOutput'>", + "MobileBertPooler": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertPooler'>", + "MobileBertPredictionHeadTransform": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertPredictionHeadTransform'>", + "MobileBertPreTrainingHeads": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertPreTrainingHeads'>", + "MobileBertSelfAttention": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertSelfAttention'>", + "MobileBertSelfOutput": "<'transformers.models.mobilebert.modeling_mobilebert.MobileBertSelfOutput'>", + "MobileNetV1ConvLayer": "<'transformers.models.mobilenet_v1.modeling_mobilenet_v1.MobileNetV1ConvLayer'>", + "MobileNetV2ConvLayer": "<'transformers.models.mobilenet_v2.modeling_mobilenet_v2.MobileNetV2ConvLayer'>", + "MobileNetV2DeepLabV3Plus": "<'transformers.models.mobilenet_v2.modeling_mobilenet_v2.MobileNetV2DeepLabV3Plus'>", + "MobileNetV2InvertedResidual": "<'transformers.models.mobilenet_v2.modeling_mobilenet_v2.MobileNetV2InvertedResidual'>", + "MobileNetV2Stem": "<'transformers.models.mobilenet_v2.modeling_mobilenet_v2.MobileNetV2Stem'>", + "MobileViTASPP": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTASPP'>", + "MobileViTASPPPooling": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTASPPPooling'>", + "MobileViTAttention": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTAttention'>", + "MobileViTConvLayer": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTConvLayer'>", + "MobileViTDeepLabV3": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTDeepLabV3'>", + "MobileViTEncoder": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTEncoder'>", + "MobileViTIntermediate": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTIntermediate'>", + "MobileViTInvertedResidual": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTInvertedResidual'>", + "MobileViTLayer": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTLayer'>", + "MobileViTMobileNetLayer": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTMobileNetLayer'>", + "MobileViTOutput": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTOutput'>", + "MobileViTSelfAttention": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTSelfAttention'>", + "MobileViTSelfOutput": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTSelfOutput'>", + "MobileViTTransformer": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTTransformer'>", + "MobileViTTransformerLayer": "<'transformers.models.mobilevit.modeling_mobilevit.MobileViTTransformerLayer'>", + "MobileViTV2ASPP": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2ASPP'>", + "MobileViTV2ASPPPooling": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2ASPPPooling'>", + "MobileViTV2ConvLayer": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2ConvLayer'>", + "MobileViTV2DeepLabV3": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2DeepLabV3'>", + "MobileViTV2Encoder": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2Encoder'>", + "MobileViTV2FFN": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2FFN'>", + "MobileViTV2InvertedResidual": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2InvertedResidual'>", + "MobileViTV2Layer": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2Layer'>", + "MobileViTV2LinearSelfAttention": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2LinearSelfAttention'>", + "MobileViTV2MobileNetLayer": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2MobileNetLayer'>", + "MobileViTV2Transformer": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2Transformer'>", + "MobileViTV2TransformerLayer": "<'transformers.models.mobilevitv2.modeling_mobilevitv2.MobileViTV2TransformerLayer'>", + "ModalEmbeddings": "<'transformers.models.deprecated.mmbt.modeling_mmbt.ModalEmbeddings'>", + "ModernBertAttention": "<'transformers.models.modernbert.modular_modernbert.ModernBertAttention'>", + "ModernBertDecoderAttention": "<'transformers.models.modernbert_decoder.modular_modernbert_decoder.ModernBertDecoderAttention'>", + "ModernBertDecoderLayer": "<'transformers.models.modernbert_decoder.modular_modernbert_decoder.ModernBertDecoderLayer'>", + "ModernBertEmbeddings": "<'transformers.models.modernbert.modeling_modernbert.ModernBertEmbeddings'>", + "ModernBertEncoderLayer": "<'transformers.models.modernbert.modular_modernbert.ModernBertEncoderLayer'>", + "ModernBertMLP": "<'transformers.models.modernbert.modeling_modernbert.ModernBertMLP'>", + "ModernBertPredictionHead": "<'transformers.models.modernbert.modeling_modernbert.ModernBertPredictionHead'>", + "ModernBertRotaryEmbedding": "<'transformers.models.modernbert.modeling_modernbert.ModernBertRotaryEmbedding'>", + "ModuleList": "<'torch.nn.modules.container.ModuleList'>", + "MoonshineAttention": "<'transformers.models.moonshine.modular_moonshine.MoonshineAttention'>", + "MoonshineDecoder": "<'transformers.models.moonshine.modular_moonshine.MoonshineDecoder'>", + "MoonshineDecoderLayer": "<'transformers.models.moonshine.modular_moonshine.MoonshineDecoderLayer'>", + "MoonshineDecoderMLP": "<'transformers.models.moonshine.modular_moonshine.MoonshineDecoderMLP'>", + "MoonshineEncoder": "<'transformers.models.moonshine.modular_moonshine.MoonshineEncoder'>", + "MoonshineEncoderLayer": "<'transformers.models.moonshine.modular_moonshine.MoonshineEncoderLayer'>", + "MoonshineEncoderMLP": "<'transformers.models.moonshine.modular_moonshine.MoonshineEncoderMLP'>", + "MoonshineRotaryEmbedding": "<'transformers.models.moonshine.modular_moonshine.MoonshineRotaryEmbedding'>", + "MoshiAttention": "<'transformers.models.moshi.modeling_moshi.MoshiAttention'>", + "MoshiDecoderLayer": "<'transformers.models.moshi.modeling_moshi.MoshiDecoderLayer'>", + "MoshiDepthDecoder": "<'transformers.models.moshi.modeling_moshi.MoshiDepthDecoder'>", + "MoshiFlashAttention2": "<'transformers.models.moshi.modeling_moshi.MoshiFlashAttention2'>", + "MoshiFlexibleLinear": "<'transformers.models.moshi.modeling_moshi.MoshiFlexibleLinear'>", + "MoshiGatingMLP": "<'transformers.models.moshi.modeling_moshi.MoshiGatingMLP'>", + "MoshiLinear": "<'transformers.models.moshi.modeling_moshi.MoshiLinear'>", + "MoshiRMSNorm": "<'transformers.models.moshi.modeling_moshi.MoshiRMSNorm'>", + "MoshiRotaryEmbedding": "<'transformers.models.moshi.modeling_moshi.MoshiRotaryEmbedding'>", + "MoshiSdpaAttention": "<'transformers.models.moshi.modeling_moshi.MoshiSdpaAttention'>", + "MPNetAttention": "<'transformers.models.mpnet.modeling_mpnet.MPNetAttention'>", + "MPNetClassificationHead": "<'transformers.models.mpnet.modeling_mpnet.MPNetClassificationHead'>", + "MPNetEmbeddings": "<'transformers.models.mpnet.modeling_mpnet.MPNetEmbeddings'>", + "MPNetEncoder": "<'transformers.models.mpnet.modeling_mpnet.MPNetEncoder'>", + "MPNetIntermediate": "<'transformers.models.mpnet.modeling_mpnet.MPNetIntermediate'>", + "MPNetLayer": "<'transformers.models.mpnet.modeling_mpnet.MPNetLayer'>", + "MPNetLMHead": "<'transformers.models.mpnet.modeling_mpnet.MPNetLMHead'>", + "MPNetOutput": "<'transformers.models.mpnet.modeling_mpnet.MPNetOutput'>", + "MPNetPooler": "<'transformers.models.mpnet.modeling_mpnet.MPNetPooler'>", + "MPNetSelfAttention": "<'transformers.models.mpnet.modeling_mpnet.MPNetSelfAttention'>", + "MptAttention": "<'transformers.models.mpt.modeling_mpt.MptAttention'>", + "MptBlock": "<'transformers.models.mpt.modeling_mpt.MptBlock'>", + "MptMLP": "<'transformers.models.mpt.modeling_mpt.MptMLP'>", + "MraAttention": "<'transformers.models.mra.modeling_mra.MraAttention'>", + "MraClassificationHead": "<'transformers.models.mra.modeling_mra.MraClassificationHead'>", + "MraEmbeddings": "<'transformers.models.mra.modeling_mra.MraEmbeddings'>", + "MraEncoder": "<'transformers.models.mra.modeling_mra.MraEncoder'>", + "MraIntermediate": "<'transformers.models.mra.modeling_mra.MraIntermediate'>", + "MraLayer": "<'transformers.models.mra.modeling_mra.MraLayer'>", + "MraLMPredictionHead": "<'transformers.models.mra.modeling_mra.MraLMPredictionHead'>", + "MraOnlyMLMHead": "<'transformers.models.mra.modeling_mra.MraOnlyMLMHead'>", + "MraOutput": "<'transformers.models.mra.modeling_mra.MraOutput'>", + "MraPredictionHeadTransform": "<'transformers.models.mra.modeling_mra.MraPredictionHeadTransform'>", + "MraSelfAttention": "<'transformers.models.mra.modeling_mra.MraSelfAttention'>", + "MraSelfOutput": "<'transformers.models.mra.modeling_mra.MraSelfOutput'>", + "MSELoss": "<'torch.nn.modules.loss.MSELoss'>", + "MT5Attention": "<'transformers.models.mt5.modeling_mt5.MT5Attention'>", + "MT5Block": "<'transformers.models.mt5.modeling_mt5.MT5Block'>", + "MT5ClassificationHead": "<'transformers.models.mt5.modeling_mt5.MT5ClassificationHead'>", + "MT5DenseActDense": "<'transformers.models.mt5.modeling_mt5.MT5DenseActDense'>", + "MT5DenseGatedActDense": "<'transformers.models.mt5.modeling_mt5.MT5DenseGatedActDense'>", + "MT5LayerCrossAttention": "<'transformers.models.mt5.modeling_mt5.MT5LayerCrossAttention'>", + "MT5LayerFF": "<'transformers.models.mt5.modeling_mt5.MT5LayerFF'>", + "MT5LayerNorm": "<'transformers.models.mt5.modeling_mt5.MT5LayerNorm'>", + "MT5LayerSelfAttention": "<'transformers.models.mt5.modeling_mt5.MT5LayerSelfAttention'>", + "MT5Stack": "<'transformers.models.mt5.modeling_mt5.MT5Stack'>", + "MultiHeadAttention": "<'transformers.models.flaubert.modeling_flaubert.MultiHeadAttention'>", + "MultiHeadSelfAttention": "<'transformers.models.distilbert.modeling_distilbert.MultiHeadSelfAttention'>", + "MultiScaleDeformableAttention": "<'transformers.models.mm_grounding_dino.modeling_mm_grounding_dino.MultiScaleDeformableAttention'>", + "MusicgenAttention": "<'transformers.models.musicgen.modeling_musicgen.MusicgenAttention'>", + "MusicgenDecoder": "<'transformers.models.musicgen.modeling_musicgen.MusicgenDecoder'>", + "MusicgenDecoderLayer": "<'transformers.models.musicgen.modeling_musicgen.MusicgenDecoderLayer'>", + "MusicgenMelodyAttention": "<'transformers.models.musicgen_melody.modeling_musicgen_melody.MusicgenMelodyAttention'>", + "MusicgenMelodyDecoder": "<'transformers.models.musicgen_melody.modeling_musicgen_melody.MusicgenMelodyDecoder'>", + "MusicgenMelodyDecoderLayer": "<'transformers.models.musicgen_melody.modeling_musicgen_melody.MusicgenMelodyDecoderLayer'>", + "MusicgenMelodySinusoidalPositionalEmbedding": "<'transformers.models.musicgen_melody.modeling_musicgen_melody.MusicgenMelodySinusoidalPositionalEmbedding'>", + "MusicgenSinusoidalPositionalEmbedding": "<'transformers.models.musicgen.modeling_musicgen.MusicgenSinusoidalPositionalEmbedding'>", + "MvpAttention": "<'transformers.models.mvp.modeling_mvp.MvpAttention'>", + "MvpClassificationHead": "<'transformers.models.mvp.modeling_mvp.MvpClassificationHead'>", + "MvpDecoder": "<'transformers.models.mvp.modeling_mvp.MvpDecoder'>", + "MvpDecoderLayer": "<'transformers.models.mvp.modeling_mvp.MvpDecoderLayer'>", + "MvpDecoderWrapper": "<'transformers.models.mvp.modeling_mvp.MvpDecoderWrapper'>", + "MvpEncoder": "<'transformers.models.mvp.modeling_mvp.MvpEncoder'>", + "MvpEncoderLayer": "<'transformers.models.mvp.modeling_mvp.MvpEncoderLayer'>", + "MvpLearnedPositionalEmbedding": "<'transformers.models.mvp.modeling_mvp.MvpLearnedPositionalEmbedding'>", + "MvpPrompt": "<'transformers.models.mvp.modeling_mvp.MvpPrompt'>", + "NatDownsampler": "<'transformers.models.deprecated.nat.modeling_nat.NatDownsampler'>", + "NatDropPath": "<'transformers.models.deprecated.nat.modeling_nat.NatDropPath'>", + "NatEmbeddings": "<'transformers.models.deprecated.nat.modeling_nat.NatEmbeddings'>", + "NatEncoder": "<'transformers.models.deprecated.nat.modeling_nat.NatEncoder'>", + "NatIntermediate": "<'transformers.models.deprecated.nat.modeling_nat.NatIntermediate'>", + "NatLayer": "<'transformers.models.deprecated.nat.modeling_nat.NatLayer'>", + "NatOutput": "<'transformers.models.deprecated.nat.modeling_nat.NatOutput'>", + "NatPatchEmbeddings": "<'transformers.models.deprecated.nat.modeling_nat.NatPatchEmbeddings'>", + "NatStage": "<'transformers.models.deprecated.nat.modeling_nat.NatStage'>", + "NearestConvUpsampler": "<'transformers.models.swin2sr.modeling_swin2sr.NearestConvUpsampler'>", + "NeighborhoodAttention": "<'transformers.models.deprecated.nat.modeling_nat.NeighborhoodAttention'>", + "NeighborhoodAttentionModule": "<'transformers.models.deprecated.nat.modeling_nat.NeighborhoodAttentionModule'>", + "NeighborhoodAttentionOutput": "<'transformers.models.deprecated.nat.modeling_nat.NeighborhoodAttentionOutput'>", + "NemotronAttention": "<'transformers.models.nemotron.modeling_nemotron.NemotronAttention'>", + "NemotronDecoderLayer": "<'transformers.models.nemotron.modeling_nemotron.NemotronDecoderLayer'>", + "NemotronFlashAttention2": "<'transformers.models.nemotron.modeling_nemotron.NemotronFlashAttention2'>", + "NemotronLayerNorm1P": "<'transformers.models.nemotron.modeling_nemotron.NemotronLayerNorm1P'>", + "NemotronMLP": "<'transformers.models.nemotron.modeling_nemotron.NemotronMLP'>", + "NemotronRotaryEmbedding": "<'transformers.models.nemotron.modeling_nemotron.NemotronRotaryEmbedding'>", + "NemotronSdpaAttention": "<'transformers.models.nemotron.modeling_nemotron.NemotronSdpaAttention'>", + "NewGELUActivation": "<'transformers.activations.NewGELUActivation'>", + "NezhaAttention": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaAttention'>", + "NezhaEmbeddings": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaEmbeddings'>", + "NezhaEncoder": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaEncoder'>", + "NezhaIntermediate": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaIntermediate'>", + "NezhaLayer": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaLayer'>", + "NezhaLMPredictionHead": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaLMPredictionHead'>", + "NezhaOnlyMLMHead": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaOnlyMLMHead'>", + "NezhaOnlyNSPHead": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaOnlyNSPHead'>", + "NezhaOutput": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaOutput'>", + "NezhaPooler": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaPooler'>", + "NezhaPredictionHeadTransform": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaPredictionHeadTransform'>", + "NezhaPreTrainingHeads": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaPreTrainingHeads'>", + "NezhaRelativePositionsEncoding": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaRelativePositionsEncoding'>", + "NezhaSelfAttention": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaSelfAttention'>", + "NezhaSelfOutput": "<'transformers.models.deprecated.nezha.modeling_nezha.NezhaSelfOutput'>", + "NllbMoeAttention": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeAttention'>", + "NllbMoeDecoder": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeDecoder'>", + "NllbMoeDecoderLayer": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeDecoderLayer'>", + "NllbMoeDenseActDense": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeDenseActDense'>", + "NllbMoeEncoder": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeEncoder'>", + "NllbMoeEncoderLayer": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeEncoderLayer'>", + "NllbMoeScaledWordEmbedding": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeScaledWordEmbedding'>", + "NllbMoeSinusoidalPositionalEmbedding": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeSinusoidalPositionalEmbedding'>", + "NllbMoeSparseMLP": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeSparseMLP'>", + "NllbMoeTop2Router": "<'transformers.models.nllb_moe.modeling_nllb_moe.NllbMoeTop2Router'>", + "NoNorm": "<'transformers.models.mobilebert.modeling_mobilebert.NoNorm'>", + "NystromformerAttention": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerAttention'>", + "NystromformerClassificationHead": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerClassificationHead'>", + "NystromformerEmbeddings": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerEmbeddings'>", + "NystromformerEncoder": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerEncoder'>", + "NystromformerIntermediate": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerIntermediate'>", + "NystromformerLayer": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerLayer'>", + "NystromformerLMPredictionHead": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerLMPredictionHead'>", + "NystromformerOnlyMLMHead": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerOnlyMLMHead'>", + "NystromformerOutput": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerOutput'>", + "NystromformerPredictionHeadTransform": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerPredictionHeadTransform'>", + "NystromformerSelfAttention": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerSelfAttention'>", + "NystromformerSelfOutput": "<'transformers.models.nystromformer.modeling_nystromformer.NystromformerSelfOutput'>", + "Olmo2Attention": "<'transformers.models.olmo2.modular_olmo2.Olmo2Attention'>", + "Olmo2DecoderLayer": "<'transformers.models.olmo2.modeling_olmo2.Olmo2DecoderLayer'>", + "Olmo2MLP": "<'transformers.models.olmo2.modeling_olmo2.Olmo2MLP'>", + "Olmo2RMSNorm": "<'transformers.models.olmo2.modular_olmo2.Olmo2RMSNorm'>", + "Olmo2RotaryEmbedding": "<'transformers.models.olmo2.modular_olmo2.Olmo2RotaryEmbedding'>", + "OlmoAttention": "<'transformers.models.olmo.modular_olmo.OlmoAttention'>", + "OlmoDecoderLayer": "<'transformers.models.olmo.modular_olmo.OlmoDecoderLayer'>", + "OlmoeAttention": "<'transformers.models.olmoe.modeling_olmoe.OlmoeAttention'>", + "OlmoeDecoderLayer": "<'transformers.models.olmoe.modeling_olmoe.OlmoeDecoderLayer'>", + "OlmoeFlashAttention2": "<'transformers.models.olmoe.modeling_olmoe.OlmoeFlashAttention2'>", + "OlmoeMLP": "<'transformers.models.olmoe.modeling_olmoe.OlmoeMLP'>", + "OlmoeRMSNorm": "<'transformers.models.olmoe.modeling_olmoe.OlmoeRMSNorm'>", + "OlmoeRotaryEmbedding": "<'transformers.models.olmoe.modeling_olmoe.OlmoeRotaryEmbedding'>", + "OlmoeSdpaAttention": "<'transformers.models.olmoe.modeling_olmoe.OlmoeSdpaAttention'>", + "OlmoeSparseMoeBlock": "<'transformers.models.olmoe.modeling_olmoe.OlmoeSparseMoeBlock'>", + "OlmoLayerNorm": "<'transformers.models.olmo.modular_olmo.OlmoLayerNorm'>", + "OlmoMLP": "<'transformers.models.olmo.modular_olmo.OlmoMLP'>", + "OlmoRotaryEmbedding": "<'transformers.models.olmo.modular_olmo.OlmoRotaryEmbedding'>", + "OmDetTurboConvNormLayer": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboConvNormLayer'>", + "OmDetTurboCSPRepLayer": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboCSPRepLayer'>", + "OmDetTurboDecoder": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboDecoder'>", + "OmDetTurboDeformableTransformerDecoderLayer": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboDeformableTransformerDecoderLayer'>", + "OmDetTurboEncoder": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboEncoder'>", + "OmDetTurboEncoderLayer": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboEncoderLayer'>", + "OmDetTurboHybridEncoder": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboHybridEncoder'>", + "OmDetTurboLanguageBackbone": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboLanguageBackbone'>", + "OmDetTurboMLP": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboMLP'>", + "OmDetTurboMLPWithDropout": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboMLPWithDropout'>", + "OmDetTurboMultiheadAttention": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboMultiheadAttention'>", + "OmDetTurboMultiscaleDeformableAttention": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboMultiscaleDeformableAttention'>", + "OmDetTurboRepVggBlock": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboRepVggBlock'>", + "OmDetTurboResidualLayer": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboResidualLayer'>", + "OmDetTurboTaskEncoder": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboTaskEncoder'>", + "OmDetTurboVisionBackbone": "<'transformers.models.omdet_turbo.modeling_omdet_turbo.OmDetTurboVisionBackbone'>", + "OneFormerAttention": "<'transformers.models.oneformer.modeling_oneformer.OneFormerAttention'>", + "OneFormerHungarianMatcher": "<'transformers.models.oneformer.modeling_oneformer.OneFormerHungarianMatcher'>", + "OneFormerLoss": "<'transformers.models.oneformer.modeling_oneformer.OneFormerLoss'>", + "OneFormerMLPPredictionHead": "<'transformers.models.oneformer.modeling_oneformer.OneFormerMLPPredictionHead'>", + "OneFormerPixelDecoder": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelDecoder'>", + "OneFormerPixelDecoderEncoderLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelDecoderEncoderLayer'>", + "OneFormerPixelDecoderEncoderMultiscaleDeformableAttention": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelDecoderEncoderMultiscaleDeformableAttention'>", + "OneFormerPixelDecoderEncoderOnly": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelDecoderEncoderOnly'>", + "OneFormerPixelDecoderFrozenBatchNorm2d": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelDecoderFrozenBatchNorm2d'>", + "OneFormerPixelLevelModule": "<'transformers.models.oneformer.modeling_oneformer.OneFormerPixelLevelModule'>", + "OneFormerSinePositionEmbedding": "<'transformers.models.oneformer.modeling_oneformer.OneFormerSinePositionEmbedding'>", + "OneFormerTaskModel": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTaskModel'>", + "OneFormerTextContextDecoder": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextContextDecoder'>", + "OneFormerTextEncoder": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextEncoder'>", + "OneFormerTextMapper": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextMapper'>", + "OneFormerTextMapperAttention": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextMapperAttention'>", + "OneFormerTextMLP": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextMLP'>", + "OneFormerTextTransformer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextTransformer'>", + "OneFormerTextTransformerDecoderLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextTransformerDecoderLayer'>", + "OneFormerTextTransformerLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTextTransformerLayer'>", + "OneFormerTransformerDecoder": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoder'>", + "OneFormerTransformerDecoderCrossAttentionLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderCrossAttentionLayer'>", + "OneFormerTransformerDecoderFFNLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderFFNLayer'>", + "OneFormerTransformerDecoderLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderLayer'>", + "OneFormerTransformerDecoderQueryTransformer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderQueryTransformer'>", + "OneFormerTransformerDecoderQueryTransformerDecoder": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderQueryTransformerDecoder'>", + "OneFormerTransformerDecoderQueryTransformerDecoderLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderQueryTransformerDecoderLayer'>", + "OneFormerTransformerDecoderSelfAttentionLayer": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerDecoderSelfAttentionLayer'>", + "OneFormerTransformerModule": "<'transformers.models.oneformer.modeling_oneformer.OneFormerTransformerModule'>", + "OpenAIGPTSequenceSummary": "<'transformers.models.openai.modeling_openai.OpenAIGPTSequenceSummary'>", + "OpenLlamaAttention": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaAttention'>", + "OpenLlamaDecoderLayer": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaDecoderLayer'>", + "OpenLlamaDynamicNTKScalingRotaryEmbedding": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaDynamicNTKScalingRotaryEmbedding'>", + "OpenLlamaLinearScalingRotaryEmbedding": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaLinearScalingRotaryEmbedding'>", + "OpenLlamaMLP": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaMLP'>", + "OpenLlamaRMSNorm": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaRMSNorm'>", + "OpenLlamaRotaryEmbedding": "<'transformers.models.deprecated.open_llama.modeling_open_llama.OpenLlamaRotaryEmbedding'>", + "OPTAttention": "<'transformers.models.opt.modeling_opt.OPTAttention'>", + "OPTDecoder": "<'transformers.models.opt.modeling_opt.OPTDecoder'>", + "OPTDecoderLayer": "<'transformers.models.opt.modeling_opt.OPTDecoderLayer'>", + "OPTLearnedPositionalEmbedding": "<'transformers.models.opt.modeling_opt.OPTLearnedPositionalEmbedding'>", + "OutputBottleneck": "<'transformers.models.mobilebert.modeling_mobilebert.OutputBottleneck'>", + "Owlv2Attention": "<'transformers.models.owlv2.modeling_owlv2.Owlv2Attention'>", + "Owlv2BoxPredictionHead": "<'transformers.models.owlv2.modeling_owlv2.Owlv2BoxPredictionHead'>", + "Owlv2ClassPredictionHead": "<'transformers.models.owlv2.modeling_owlv2.Owlv2ClassPredictionHead'>", + "Owlv2Encoder": "<'transformers.models.owlv2.modeling_owlv2.Owlv2Encoder'>", + "Owlv2EncoderLayer": "<'transformers.models.owlv2.modeling_owlv2.Owlv2EncoderLayer'>", + "Owlv2MLP": "<'transformers.models.owlv2.modeling_owlv2.Owlv2MLP'>", + "Owlv2TextEmbeddings": "<'transformers.models.owlv2.modeling_owlv2.Owlv2TextEmbeddings'>", + "Owlv2TextTransformer": "<'transformers.models.owlv2.modeling_owlv2.Owlv2TextTransformer'>", + "Owlv2VisionEmbeddings": "<'transformers.models.owlv2.modeling_owlv2.Owlv2VisionEmbeddings'>", + "Owlv2VisionTransformer": "<'transformers.models.owlv2.modeling_owlv2.Owlv2VisionTransformer'>", + "OwlViTAttention": "<'transformers.models.owlvit.modeling_owlvit.OwlViTAttention'>", + "OwlViTBoxPredictionHead": "<'transformers.models.owlvit.modeling_owlvit.OwlViTBoxPredictionHead'>", + "OwlViTClassPredictionHead": "<'transformers.models.owlvit.modeling_owlvit.OwlViTClassPredictionHead'>", + "OwlViTEncoder": "<'transformers.models.owlvit.modeling_owlvit.OwlViTEncoder'>", + "OwlViTEncoderLayer": "<'transformers.models.owlvit.modeling_owlvit.OwlViTEncoderLayer'>", + "OwlViTMLP": "<'transformers.models.owlvit.modeling_owlvit.OwlViTMLP'>", + "OwlViTTextEmbeddings": "<'transformers.models.owlvit.modeling_owlvit.OwlViTTextEmbeddings'>", + "OwlViTTextTransformer": "<'transformers.models.owlvit.modeling_owlvit.OwlViTTextTransformer'>", + "OwlViTVisionEmbeddings": "<'transformers.models.owlvit.modeling_owlvit.OwlViTVisionEmbeddings'>", + "OwlViTVisionTransformer": "<'transformers.models.owlvit.modeling_owlvit.OwlViTVisionTransformer'>", + "PaliGemmaMultiModalProjector": "<'transformers.models.paligemma.modeling_paligemma.PaliGemmaMultiModalProjector'>", + "ParameterProjection": "<'transformers.time_series_utils.ParameterProjection'>", + "PatchEmbed": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.PatchEmbed'>", + "PatchEmbeddings": "<'transformers.models.flava.modeling_flava.PatchEmbeddings'>", + "PatchMerger": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.PatchMerger'>", + "PatchMixerBlock": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchMixerBlock'>", + "PatchTSMixerAttention": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerAttention'>", + "PatchTSMixerBatchNorm": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerBatchNorm'>", + "PatchTSMixerBlock": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerBlock'>", + "PatchTSMixerChannelFeatureMixerBlock": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerChannelFeatureMixerBlock'>", + "PatchTSMixerEncoder": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerEncoder'>", + "PatchTSMixerForPredictionHead": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerForPredictionHead'>", + "PatchTSMixerGatedAttention": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerGatedAttention'>", + "PatchTSMixerLayer": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerLayer'>", + "PatchTSMixerLinearHead": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerLinearHead'>", + "PatchTSMixerMasking": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerMasking'>", + "PatchTSMixerMeanScaler": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerMeanScaler'>", + "PatchTSMixerMLP": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerMLP'>", + "PatchTSMixerNOPScaler": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerNOPScaler'>", + "PatchTSMixerNormLayer": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerNormLayer'>", + "PatchTSMixerPatchify": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerPatchify'>", + "PatchTSMixerPositionalEncoding": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerPositionalEncoding'>", + "PatchTSMixerPretrainHead": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerPretrainHead'>", + "PatchTSMixerStdScaler": "<'transformers.models.patchtsmixer.modeling_patchtsmixer.PatchTSMixerStdScaler'>", + "PatchTSTAttention": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTAttention'>", + "PatchTSTBatchNorm": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTBatchNorm'>", + "PatchTSTClassificationHead": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTClassificationHead'>", + "PatchTSTEmbedding": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTEmbedding'>", + "PatchTSTEncoder": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTEncoder'>", + "PatchTSTEncoderLayer": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTEncoderLayer'>", + "PatchTSTMasking": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTMasking'>", + "PatchTSTMaskPretrainHead": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTMaskPretrainHead'>", + "PatchTSTMeanScaler": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTMeanScaler'>", + "PatchTSTNOPScaler": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTNOPScaler'>", + "PatchTSTPatchify": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTPatchify'>", + "PatchTSTPositionalEncoding": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTPositionalEncoding'>", + "PatchTSTPredictionHead": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTPredictionHead'>", + "PatchTSTRegressionHead": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTRegressionHead'>", + "PatchTSTScaler": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTScaler'>", + "PatchTSTStdScaler": "<'transformers.models.patchtst.modeling_patchtst.PatchTSTStdScaler'>", + "PeftModel": "<'peft.peft_model.PeftModel'>", + "PegasusAttention": "<'transformers.models.pegasus.modeling_pegasus.PegasusAttention'>", + "PegasusDecoder": "<'transformers.models.pegasus.modeling_pegasus.PegasusDecoder'>", + "PegasusDecoderLayer": "<'transformers.models.pegasus.modeling_pegasus.PegasusDecoderLayer'>", + "PegasusDecoderWrapper": "<'transformers.models.pegasus.modeling_pegasus.PegasusDecoderWrapper'>", + "PegasusEncoder": "<'transformers.models.pegasus.modeling_pegasus.PegasusEncoder'>", + "PegasusEncoderLayer": "<'transformers.models.pegasus.modeling_pegasus.PegasusEncoderLayer'>", + "PegasusSinusoidalPositionalEmbedding": "<'transformers.models.pegasus.modeling_pegasus.PegasusSinusoidalPositionalEmbedding'>", + "PegasusXAttention": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXAttention'>", + "PegasusXDecoder": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXDecoder'>", + "PegasusXDecoderLayer": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXDecoderLayer'>", + "PegasusXDecoderWrapper": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXDecoderWrapper'>", + "PegasusXEncoder": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXEncoder'>", + "PegasusXEncoderLayer": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXEncoderLayer'>", + "PegasusXGlobalLocalAttention": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXGlobalLocalAttention'>", + "PegasusXScaledWordEmbedding": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXScaledWordEmbedding'>", + "PegasusXSinusoidalPositionalEmbedding": "<'transformers.models.pegasus_x.modeling_pegasus_x.PegasusXSinusoidalPositionalEmbedding'>", + "PerceiverAbstractDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverAbstractDecoder'>", + "PerceiverAbstractPositionEncoding": "<'transformers.models.perceiver.modeling_perceiver.PerceiverAbstractPositionEncoding'>", + "PerceiverAttention": "<'transformers.models.perceiver.modeling_perceiver.PerceiverAttention'>", + "PerceiverAudioPostprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverAudioPostprocessor'>", + "PerceiverAudioPreprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverAudioPreprocessor'>", + "PerceiverBasicDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverBasicDecoder'>", + "PerceiverBasicVideoAutoencodingDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverBasicVideoAutoencodingDecoder'>", + "PerceiverClassificationDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverClassificationDecoder'>", + "PerceiverClassificationPostprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverClassificationPostprocessor'>", + "PerceiverEmbeddingDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverEmbeddingDecoder'>", + "PerceiverEmbeddings": "<'transformers.models.perceiver.modeling_perceiver.PerceiverEmbeddings'>", + "PerceiverEncoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverEncoder'>", + "PerceiverFourierPositionEncoding": "<'transformers.models.perceiver.modeling_perceiver.PerceiverFourierPositionEncoding'>", + "PerceiverImagePreprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverImagePreprocessor'>", + "PerceiverLayer": "<'transformers.models.perceiver.modeling_perceiver.PerceiverLayer'>", + "PerceiverMLP": "<'transformers.models.perceiver.modeling_perceiver.PerceiverMLP'>", + "PerceiverMultimodalDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverMultimodalDecoder'>", + "PerceiverMultimodalPostprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverMultimodalPostprocessor'>", + "PerceiverMultimodalPreprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverMultimodalPreprocessor'>", + "PerceiverOneHotPreprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverOneHotPreprocessor'>", + "PerceiverOpticalFlowDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverOpticalFlowDecoder'>", + "PerceiverProjectionDecoder": "<'transformers.models.perceiver.modeling_perceiver.PerceiverProjectionDecoder'>", + "PerceiverProjectionPostprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverProjectionPostprocessor'>", + "PerceiverSelfAttention": "<'transformers.models.perceiver.modeling_perceiver.PerceiverSelfAttention'>", + "PerceiverSelfOutput": "<'transformers.models.perceiver.modeling_perceiver.PerceiverSelfOutput'>", + "PerceiverTextPreprocessor": "<'transformers.models.perceiver.modeling_perceiver.PerceiverTextPreprocessor'>", + "PerceiverTrainablePositionEncoding": "<'transformers.models.perceiver.modeling_perceiver.PerceiverTrainablePositionEncoding'>", + "PerceptionLMAdaptiveAvgPooling": "<'transformers.models.perception_lm.modeling_perception_lm.PerceptionLMAdaptiveAvgPooling'>", + "PerceptionLMMultiModalProjector": "<'transformers.models.perception_lm.modeling_perception_lm.PerceptionLMMultiModalProjector'>", + "PersimmonAttention": "<'transformers.models.persimmon.modeling_persimmon.PersimmonAttention'>", + "PersimmonDecoderLayer": "<'transformers.models.persimmon.modeling_persimmon.PersimmonDecoderLayer'>", + "PersimmonMLP": "<'transformers.models.persimmon.modeling_persimmon.PersimmonMLP'>", + "PersimmonRotaryEmbedding": "<'transformers.models.persimmon.modeling_persimmon.PersimmonRotaryEmbedding'>", + "Phi3Attention": "<'transformers.models.phi3.modeling_phi3.Phi3Attention'>", + "Phi3DecoderLayer": "<'transformers.models.phi3.modeling_phi3.Phi3DecoderLayer'>", + "Phi3MLP": "<'transformers.models.phi3.modeling_phi3.Phi3MLP'>", + "Phi3RMSNorm": "<'transformers.models.phi3.modeling_phi3.Phi3RMSNorm'>", + "Phi3RotaryEmbedding": "<'transformers.models.phi3.modeling_phi3.Phi3RotaryEmbedding'>", + "Phi4MultimodalAttention": "<'transformers.models.phi4_multimodal.modeling_phi4_multimodal.Phi4MultimodalAttention'>", + "Phi4MultimodalAudioAttention": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioAttention'>", + "Phi4MultimodalAudioConformerEncoderLayer": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioConformerEncoderLayer'>", + "Phi4MultimodalAudioConvModule": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioConvModule'>", + "Phi4MultimodalAudioDepthWiseSeperableConv1d": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioDepthWiseSeperableConv1d'>", + "Phi4MultimodalAudioEmbedding": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioEmbedding'>", + "Phi4MultimodalAudioGluPointWiseConv": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioGluPointWiseConv'>", + "Phi4MultimodalAudioMeanVarianceNormLayer": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioMeanVarianceNormLayer'>", + "Phi4MultimodalAudioMLP": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioMLP'>", + "Phi4MultimodalAudioNemoConvSubsampling": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioNemoConvSubsampling'>", + "Phi4MultimodalAudioRelativeAttentionBias": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalAudioRelativeAttentionBias'>", + "Phi4MultimodalDecoderLayer": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalDecoderLayer'>", + "Phi4MultimodalFeatureEmbedding": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalFeatureEmbedding'>", + "Phi4MultimodalImageEmbedding": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalImageEmbedding'>", + "Phi4MultimodalMLP": "<'transformers.models.phi4_multimodal.modeling_phi4_multimodal.Phi4MultimodalMLP'>", + "Phi4MultimodalRMSNorm": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalRMSNorm'>", + "Phi4MultimodalRotaryEmbedding": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalRotaryEmbedding'>", + "Phi4MultimodalVisionAttention": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionAttention'>", + "Phi4MultimodalVisionEmbeddings": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionEmbeddings'>", + "Phi4MultimodalVisionEncoder": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionEncoder'>", + "Phi4MultimodalVisionEncoderLayer": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionEncoderLayer'>", + "Phi4MultimodalVisionMLP": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionMLP'>", + "Phi4MultimodalVisionMultiheadAttentionPoolingHead": "<'transformers.models.phi4_multimodal.modular_phi4_multimodal.Phi4MultimodalVisionMultiheadAttentionPoolingHead'>", + "PhiAttention": "<'transformers.models.phi.modular_phi.PhiAttention'>", + "PhiDecoderLayer": "<'transformers.models.phi.modular_phi.PhiDecoderLayer'>", + "PhiMLP": "<'transformers.models.phi.modular_phi.PhiMLP'>", + "PhimoeAttention": "<'transformers.models.phimoe.modeling_phimoe.PhimoeAttention'>", + "PhimoeBlockSparseTop2MLP": "<'transformers.models.phimoe.modeling_phimoe.PhimoeBlockSparseTop2MLP'>", + "PhimoeDecoderLayer": "<'transformers.models.phimoe.modeling_phimoe.PhimoeDecoderLayer'>", + "PhimoeFlashAttention2": "<'transformers.models.phimoe.modeling_phimoe.PhimoeFlashAttention2'>", + "PhimoeRotaryEmbedding": "<'transformers.models.phimoe.modeling_phimoe.PhimoeRotaryEmbedding'>", + "PhimoeSdpaAttention": "<'transformers.models.phimoe.modeling_phimoe.PhimoeSdpaAttention'>", + "PhimoeSparseMoeBlock": "<'transformers.models.phimoe.modeling_phimoe.PhimoeSparseMoeBlock'>", + "PhiRotaryEmbedding": "<'transformers.models.phi.modular_phi.PhiRotaryEmbedding'>", + "Pix2StructLayerNorm": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructLayerNorm'>", + "Pix2StructTextAttention": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextAttention'>", + "Pix2StructTextBlock": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextBlock'>", + "Pix2StructTextDenseGatedActDense": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextDenseGatedActDense'>", + "Pix2StructTextLayerCrossAttention": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextLayerCrossAttention'>", + "Pix2StructTextLayerFF": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextLayerFF'>", + "Pix2StructTextLayerSelfAttention": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructTextLayerSelfAttention'>", + "Pix2StructVisionAttention": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructVisionAttention'>", + "Pix2StructVisionEmbeddings": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructVisionEmbeddings'>", + "Pix2StructVisionEncoder": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructVisionEncoder'>", + "Pix2StructVisionLayer": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructVisionLayer'>", + "Pix2StructVisionMlp": "<'transformers.models.pix2struct.modeling_pix2struct.Pix2StructVisionMlp'>", + "PixelShuffleAuxUpsampler": "<'transformers.models.swin2sr.modeling_swin2sr.PixelShuffleAuxUpsampler'>", + "PixelShuffleUpsampler": "<'transformers.models.swin2sr.modeling_swin2sr.PixelShuffleUpsampler'>", + "PixtralAttention": "<'transformers.models.pixtral.modeling_pixtral.PixtralAttention'>", + "PixtralAttentionLayer": "<'transformers.models.pixtral.modeling_pixtral.PixtralAttentionLayer'>", + "PixtralMLP": "<'transformers.models.pixtral.modeling_pixtral.PixtralMLP'>", + "PixtralRMSNorm": "<'transformers.models.pixtral.modeling_pixtral.PixtralRMSNorm'>", + "PixtralRotaryEmbedding": "<'transformers.models.pixtral.modeling_pixtral.PixtralRotaryEmbedding'>", + "PixtralTransformer": "<'transformers.models.pixtral.modeling_pixtral.PixtralTransformer'>", + "PLBartAttention": "<'transformers.models.plbart.modeling_plbart.PLBartAttention'>", + "PLBartClassificationHead": "<'transformers.models.plbart.modular_plbart.PLBartClassificationHead'>", + "PLBartDecoder": "<'transformers.models.plbart.modular_plbart.PLBartDecoder'>", + "PLBartDecoderLayer": "<'transformers.models.plbart.modeling_plbart.PLBartDecoderLayer'>", + "PLBartDecoderWrapper": "<'transformers.models.plbart.modeling_plbart.PLBartDecoderWrapper'>", + "PLBartEncoder": "<'transformers.models.plbart.modular_plbart.PLBartEncoder'>", + "PLBartEncoderLayer": "<'transformers.models.plbart.modeling_plbart.PLBartEncoderLayer'>", + "PLBartLearnedPositionalEmbedding": "<'transformers.models.plbart.modeling_plbart.PLBartLearnedPositionalEmbedding'>", + "PLBartScaledWordEmbedding": "<'transformers.models.plbart.modular_plbart.PLBartScaledWordEmbedding'>", + "PoolFormerDropPath": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerDropPath'>", + "PoolFormerEmbeddings": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerEmbeddings'>", + "PoolFormerEncoder": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerEncoder'>", + "PoolFormerFinalPooler": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerFinalPooler'>", + "PoolFormerGroupNorm": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerGroupNorm'>", + "PoolFormerLayer": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerLayer'>", + "PoolFormerOutput": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerOutput'>", + "PoolFormerPooling": "<'transformers.models.poolformer.modeling_poolformer.PoolFormerPooling'>", + "Pop2PianoAttention": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoAttention'>", + "Pop2PianoBlock": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoBlock'>", + "Pop2PianoConcatEmbeddingToMel": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoConcatEmbeddingToMel'>", + "Pop2PianoDenseActDense": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoDenseActDense'>", + "Pop2PianoDenseGatedActDense": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoDenseGatedActDense'>", + "Pop2PianoLayerCrossAttention": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoLayerCrossAttention'>", + "Pop2PianoLayerFF": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoLayerFF'>", + "Pop2PianoLayerNorm": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoLayerNorm'>", + "Pop2PianoLayerSelfAttention": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoLayerSelfAttention'>", + "Pop2PianoStack": "<'transformers.models.pop2piano.modeling_pop2piano.Pop2PianoStack'>", + "PositionalEmbedding": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl.PositionalEmbedding'>", + "PositionEmbeddings": "<'transformers.models.reformer.modeling_reformer.PositionEmbeddings'>", + "PositionwiseFF": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl.PositionwiseFF'>", + "PredictionBlock": "<'transformers.models.oneformer.modeling_oneformer.PredictionBlock'>", + "PreTrainedAudioTokenizerBase": "<'transformers.modeling_utils.PreTrainedAudioTokenizerBase'>", + "ProjectedAdaptiveLogSoftmax": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl_utilities.ProjectedAdaptiveLogSoftmax'>", + "PromptDepthAnythingDepthEstimationHead": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingDepthEstimationHead'>", + "PromptDepthAnythingFeatureFusionLayer": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingFeatureFusionLayer'>", + "PromptDepthAnythingFeatureFusionStage": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingFeatureFusionStage'>", + "PromptDepthAnythingLayer": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingLayer'>", + "PromptDepthAnythingNeck": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingNeck'>", + "PromptDepthAnythingPreActResidualLayer": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingPreActResidualLayer'>", + "PromptDepthAnythingReassembleLayer": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingReassembleLayer'>", + "PromptDepthAnythingReassembleStage": "<'transformers.models.prompt_depth_anything.modeling_prompt_depth_anything.PromptDepthAnythingReassembleStage'>", + "PromptGeneratorLayer": "<'transformers.models.x_clip.modeling_x_clip.PromptGeneratorLayer'>", + "ProphetNetAttention": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetAttention'>", + "ProphetNetDecoderLayer": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderLayer'>", + "ProphetNetDecoderWrapper": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetDecoderWrapper'>", + "ProphetNetEncoderLayer": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetEncoderLayer'>", + "ProphetNetFeedForward": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetFeedForward'>", + "ProphetNetNgramSelfAttention": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetNgramSelfAttention'>", + "ProphetNetPositionalEmbeddings": "<'transformers.models.prophetnet.modeling_prophetnet.ProphetNetPositionalEmbeddings'>", + "PvtAttention": "<'transformers.models.pvt.modeling_pvt.PvtAttention'>", + "PvtDropPath": "<'transformers.models.pvt.modeling_pvt.PvtDropPath'>", + "PvtEfficientSelfAttention": "<'transformers.models.pvt.modeling_pvt.PvtEfficientSelfAttention'>", + "PvtEncoder": "<'transformers.models.pvt.modeling_pvt.PvtEncoder'>", + "PvtFFN": "<'transformers.models.pvt.modeling_pvt.PvtFFN'>", + "PvtLayer": "<'transformers.models.pvt.modeling_pvt.PvtLayer'>", + "PvtPatchEmbeddings": "<'transformers.models.pvt.modeling_pvt.PvtPatchEmbeddings'>", + "PvtSelfOutput": "<'transformers.models.pvt.modeling_pvt.PvtSelfOutput'>", + "PvtV2BlockLayer": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2BlockLayer'>", + "PvtV2ConvFeedForwardNetwork": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2ConvFeedForwardNetwork'>", + "PvtV2DepthWiseConv": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2DepthWiseConv'>", + "PvtV2DropPath": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2DropPath'>", + "PvtV2Encoder": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2Encoder'>", + "PvtV2EncoderLayer": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2EncoderLayer'>", + "PvtV2OverlapPatchEmbeddings": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2OverlapPatchEmbeddings'>", + "PvtV2SelfAttention": "<'transformers.models.pvt_v2.modeling_pvt_v2.PvtV2SelfAttention'>", + "PytorchGELUTanh": "<'transformers.activations.PytorchGELUTanh'>", + "QDQBertAttention": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertAttention'>", + "QDQBertEmbeddings": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertEmbeddings'>", + "QDQBertEncoder": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertEncoder'>", + "QDQBertIntermediate": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertIntermediate'>", + "QDQBertLayer": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertLayer'>", + "QDQBertLMPredictionHead": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertLMPredictionHead'>", + "QDQBertOnlyMLMHead": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertOnlyMLMHead'>", + "QDQBertOnlyNSPHead": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertOnlyNSPHead'>", + "QDQBertOutput": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertOutput'>", + "QDQBertPooler": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertPooler'>", + "QDQBertPredictionHeadTransform": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertPredictionHeadTransform'>", + "QDQBertPreTrainingHeads": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertPreTrainingHeads'>", + "QDQBertSelfAttention": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertSelfAttention'>", + "QDQBertSelfOutput": "<'transformers.models.deprecated.qdqbert.modeling_qdqbert.QDQBertSelfOutput'>", + "QuantAct": "<'transformers.models.ibert.quant_modules.QuantAct'>", + "QuantEmbedding": "<'transformers.models.ibert.quant_modules.QuantEmbedding'>", + "QuantLinear": "<'transformers.models.ibert.quant_modules.QuantLinear'>", + "QuestionAwareSpanSelectionHead": "<'transformers.models.splinter.modeling_splinter.QuestionAwareSpanSelectionHead'>", + "QuickGELUActivation": "<'transformers.activations.QuickGELUActivation'>", + "Qwen2_5_OmniAdaLayerNormZero_Final": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5_OmniAdaLayerNormZero_Final'>", + "Qwen2_5_OmniAdaLayerNormZero": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5_OmniAdaLayerNormZero'>", + "Qwen2_5_VisionPatchEmbed": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VisionPatchEmbed'>", + "Qwen2_5_VisionRotaryEmbedding": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VisionRotaryEmbedding'>", + "Qwen2_5_VisionTransformerPretrainedModel": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VisionTransformerPretrainedModel'>", + "Qwen2_5_VLAttention": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLAttention'>", + "Qwen2_5_VLDecoderLayer": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLDecoderLayer'>", + "Qwen2_5_VLMLP": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLMLP'>", + "Qwen2_5_VLPatchMerger": "<'transformers.models.qwen2_5_vl.modular_qwen2_5_vl.Qwen2_5_VLPatchMerger'>", + "Qwen2_5_VLRotaryEmbedding": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLRotaryEmbedding'>", + "Qwen2_5_VLVisionAttention": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLVisionAttention'>", + "Qwen2_5_VLVisionBlock": "<'transformers.models.qwen2_5_vl.modeling_qwen2_5_vl.Qwen2_5_VLVisionBlock'>", + "Qwen2_5OmniAttention": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniAttention'>", + "Qwen2_5OmniAudioAttention": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniAudioAttention'>", + "Qwen2_5OmniAudioEncoder": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniAudioEncoder'>", + "Qwen2_5OmniAudioEncoderLayer": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniAudioEncoderLayer'>", + "Qwen2_5OmniDecoderLayer": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniDecoderLayer'>", + "Qwen2_5OmniDiTRotaryEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniDiTRotaryEmbedding'>", + "Qwen2_5OmniMLP": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniMLP'>", + "Qwen2_5OmniPatchMerger": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniPatchMerger'>", + "Qwen2_5OmniRotaryEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniRotaryEmbedding'>", + "Qwen2_5OmniVisionAttention": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniVisionAttention'>", + "Qwen2_5OmniVisionBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniVisionBlock'>", + "Qwen2_5OmniVisionEncoder": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2_5OmniVisionEncoder'>", + "Qwen2Attention": "<'transformers.models.qwen2.modeling_qwen2.Qwen2Attention'>", + "Qwen2AudioAttention": "<'transformers.models.qwen2_audio.modeling_qwen2_audio.Qwen2AudioAttention'>", + "Qwen2AudioEncoderLayer": "<'transformers.models.qwen2_audio.modeling_qwen2_audio.Qwen2AudioEncoderLayer'>", + "Qwen2AudioMultiModalProjector": "<'transformers.models.qwen2_audio.modeling_qwen2_audio.Qwen2AudioMultiModalProjector'>", + "Qwen2DecoderLayer": "<'transformers.models.qwen2.modeling_qwen2.Qwen2DecoderLayer'>", + "Qwen2MLP": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2MLP'>", + "Qwen2MoeAttention": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeAttention'>", + "Qwen2MoeDecoderLayer": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeDecoderLayer'>", + "Qwen2MoeFlashAttention2": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeFlashAttention2'>", + "Qwen2MoeMLP": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeMLP'>", + "Qwen2MoeRMSNorm": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeRMSNorm'>", + "Qwen2MoeRotaryEmbedding": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding'>", + "Qwen2MoeSdpaAttention": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeSdpaAttention'>", + "Qwen2MoeSparseMoeBlock": "<'transformers.models.qwen2_moe.modeling_qwen2_moe.Qwen2MoeSparseMoeBlock'>", + "Qwen2RMSNorm": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Qwen2RMSNorm'>", + "Qwen2RotaryEmbedding": "<'transformers.models.qwen2.modeling_qwen2.Qwen2RotaryEmbedding'>", + "Qwen2VisionTransformerPretrainedModel": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VisionTransformerPretrainedModel'>", + "Qwen2VLAttention": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLAttention'>", + "Qwen2VLDecoderLayer": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLDecoderLayer'>", + "Qwen2VLRotaryEmbedding": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLRotaryEmbedding'>", + "Qwen2VLVisionBlock": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.Qwen2VLVisionBlock'>", + "Qwen3Attention": "<'transformers.models.qwen3.modeling_qwen3.Qwen3Attention'>", + "Qwen3DecoderLayer": "<'transformers.models.qwen3.modeling_qwen3.Qwen3DecoderLayer'>", + "Qwen3MLP": "<'transformers.models.qwen3.modeling_qwen3.Qwen3MLP'>", + "Qwen3MoeAttention": "<'transformers.models.qwen3_moe.modular_qwen3_moe.Qwen3MoeAttention'>", + "Qwen3MoeDecoderLayer": "<'transformers.models.qwen3_moe.modular_qwen3_moe.Qwen3MoeDecoderLayer'>", + "Qwen3MoeMLP": "<'transformers.models.qwen3_moe.modular_qwen3_moe.Qwen3MoeMLP'>", + "Qwen3MoeRMSNorm": "<'transformers.models.qwen3_moe.modular_qwen3_moe.Qwen3MoeRMSNorm'>", + "Qwen3MoeRotaryEmbedding": "<'transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeRotaryEmbedding'>", + "Qwen3MoeSparseMoeBlock": "<'transformers.models.qwen3_moe.modular_qwen3_moe.Qwen3MoeSparseMoeBlock'>", + "Qwen3RMSNorm": "<'transformers.models.qwen3.modeling_qwen3.Qwen3RMSNorm'>", + "Qwen3RotaryEmbedding": "<'transformers.models.qwen3.modeling_qwen3.Qwen3RotaryEmbedding'>", + "RealmAttention": "<'transformers.models.deprecated.realm.modeling_realm.RealmAttention'>", + "RealmBertModel": "<'transformers.models.deprecated.realm.modeling_realm.RealmBertModel'>", + "RealmEmbeddings": "<'transformers.models.deprecated.realm.modeling_realm.RealmEmbeddings'>", + "RealmEncoder": "<'transformers.models.deprecated.realm.modeling_realm.RealmEncoder'>", + "RealmIntermediate": "<'transformers.models.deprecated.realm.modeling_realm.RealmIntermediate'>", + "RealmLayer": "<'transformers.models.deprecated.realm.modeling_realm.RealmLayer'>", + "RealmLMPredictionHead": "<'transformers.models.deprecated.realm.modeling_realm.RealmLMPredictionHead'>", + "RealmOnlyMLMHead": "<'transformers.models.deprecated.realm.modeling_realm.RealmOnlyMLMHead'>", + "RealmOutput": "<'transformers.models.deprecated.realm.modeling_realm.RealmOutput'>", + "RealmPooler": "<'transformers.models.deprecated.realm.modeling_realm.RealmPooler'>", + "RealmPredictionHeadTransform": "<'transformers.models.deprecated.realm.modeling_realm.RealmPredictionHeadTransform'>", + "RealmReaderProjection": "<'transformers.models.deprecated.realm.modeling_realm.RealmReaderProjection'>", + "RealmScorerProjection": "<'transformers.models.deprecated.realm.modeling_realm.RealmScorerProjection'>", + "RealmSelfAttention": "<'transformers.models.deprecated.realm.modeling_realm.RealmSelfAttention'>", + "RealmSelfOutput": "<'transformers.models.deprecated.realm.modeling_realm.RealmSelfOutput'>", + "RecurrentGemmaDecoderLayer": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaDecoderLayer'>", + "RecurrentGemmaMlp": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaMlp'>", + "RecurrentGemmaRecurrentBlock": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRecurrentBlock'>", + "RecurrentGemmaRglru": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRglru'>", + "RecurrentGemmaRMSNorm": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRMSNorm'>", + "RecurrentGemmaRotaryEmbedding": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRotaryEmbedding'>", + "RecurrentGemmaSdpaAttention": "<'transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaSdpaAttention'>", + "ReformerAttention": "<'transformers.models.reformer.modeling_reformer.ReformerAttention'>", + "ReformerClassificationHead": "<'transformers.models.reformer.modeling_reformer.ReformerClassificationHead'>", + "ReformerEmbeddings": "<'transformers.models.reformer.modeling_reformer.ReformerEmbeddings'>", + "ReformerEncoder": "<'transformers.models.reformer.modeling_reformer.ReformerEncoder'>", + "ReformerFeedForwardDense": "<'transformers.models.reformer.modeling_reformer.ReformerFeedForwardDense'>", + "ReformerFeedForwardOutput": "<'transformers.models.reformer.modeling_reformer.ReformerFeedForwardOutput'>", + "ReformerLayer": "<'transformers.models.reformer.modeling_reformer.ReformerLayer'>", + "ReformerOnlyLMHead": "<'transformers.models.reformer.modeling_reformer.ReformerOnlyLMHead'>", + "ReformerSelfOutput": "<'transformers.models.reformer.modeling_reformer.ReformerSelfOutput'>", + "RegNetConvLayer": "<'transformers.models.regnet.modeling_regnet.RegNetConvLayer'>", + "RegNetEmbeddings": "<'transformers.models.regnet.modeling_regnet.RegNetEmbeddings'>", + "RegNetEncoder": "<'transformers.models.regnet.modeling_regnet.RegNetEncoder'>", + "RegNetSELayer": "<'transformers.models.regnet.modeling_regnet.RegNetSELayer'>", + "RegNetShortCut": "<'transformers.models.regnet.modeling_regnet.RegNetShortCut'>", + "RegNetStage": "<'transformers.models.regnet.modeling_regnet.RegNetStage'>", + "RegNetXLayer": "<'transformers.models.regnet.modeling_regnet.RegNetXLayer'>", + "RegNetYLayer": "<'transformers.models.regnet.modeling_regnet.RegNetYLayer'>", + "RelativePositionBias1D": "<'transformers.models.udop.modeling_udop.RelativePositionBias1D'>", + "RelativePositionBiasAggregated": "<'transformers.models.udop.modeling_udop.RelativePositionBiasAggregated'>", + "RelativePositionBiasBase": "<'transformers.models.udop.modeling_udop.RelativePositionBiasBase'>", + "RelativePositionBiasHorizontal": "<'transformers.models.udop.modeling_udop.RelativePositionBiasHorizontal'>", + "RelativePositionBiasVertical": "<'transformers.models.udop.modeling_udop.RelativePositionBiasVertical'>", + "RelPartialLearnableDecoderLayer": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl.RelPartialLearnableDecoderLayer'>", + "RelPartialLearnableMultiHeadAttn": "<'transformers.models.deprecated.transfo_xl.modeling_transfo_xl.RelPartialLearnableMultiHeadAttn'>", + "ReLUSquaredActivation": "<'transformers.activations.ReLUSquaredActivation'>", + "RemBertAttention": "<'transformers.models.rembert.modeling_rembert.RemBertAttention'>", + "RemBertEmbeddings": "<'transformers.models.rembert.modeling_rembert.RemBertEmbeddings'>", + "RemBertEncoder": "<'transformers.models.rembert.modeling_rembert.RemBertEncoder'>", + "RemBertIntermediate": "<'transformers.models.rembert.modeling_rembert.RemBertIntermediate'>", + "RemBertLayer": "<'transformers.models.rembert.modeling_rembert.RemBertLayer'>", + "RemBertLMPredictionHead": "<'transformers.models.rembert.modeling_rembert.RemBertLMPredictionHead'>", + "RemBertOnlyMLMHead": "<'transformers.models.rembert.modeling_rembert.RemBertOnlyMLMHead'>", + "RemBertOutput": "<'transformers.models.rembert.modeling_rembert.RemBertOutput'>", + "RemBertPooler": "<'transformers.models.rembert.modeling_rembert.RemBertPooler'>", + "RemBertPredictionHeadTransform": "<'transformers.models.rembert.modeling_rembert.RemBertPredictionHeadTransform'>", + "RemBertSelfAttention": "<'transformers.models.rembert.modeling_rembert.RemBertSelfAttention'>", + "RemBertSelfOutput": "<'transformers.models.rembert.modeling_rembert.RemBertSelfOutput'>", + "Res2NetBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.Res2NetBlock'>", + "ResNetBasicLayer": "<'transformers.models.resnet.modeling_resnet.ResNetBasicLayer'>", + "ResNetBottleNeckLayer": "<'transformers.models.resnet.modeling_resnet.ResNetBottleNeckLayer'>", + "ResNetConvLayer": "<'transformers.models.resnet.modeling_resnet.ResNetConvLayer'>", + "ResNetEmbeddings": "<'transformers.models.resnet.modeling_resnet.ResNetEmbeddings'>", + "ResNetEncoder": "<'transformers.models.resnet.modeling_resnet.ResNetEncoder'>", + "ResNetShortCut": "<'transformers.models.resnet.modeling_resnet.ResNetShortCut'>", + "ResNetStage": "<'transformers.models.resnet.modeling_resnet.ResNetStage'>", + "RobertaAttention": "<'transformers.models.roberta.modeling_roberta.RobertaAttention'>", + "RobertaClassificationHead": "<'transformers.models.roberta.modeling_roberta.RobertaClassificationHead'>", + "RobertaEmbeddings": "<'transformers.models.roberta.modeling_roberta.RobertaEmbeddings'>", + "RobertaEncoder": "<'transformers.models.roberta.modeling_roberta.RobertaEncoder'>", + "RobertaIntermediate": "<'transformers.models.roberta.modeling_roberta.RobertaIntermediate'>", + "RobertaLayer": "<'transformers.models.roberta.modeling_roberta.RobertaLayer'>", + "RobertaLMHead": "<'transformers.models.roberta.modeling_roberta.RobertaLMHead'>", + "RobertaOutput": "<'transformers.models.roberta.modeling_roberta.RobertaOutput'>", + "RobertaPooler": "<'transformers.models.roberta.modeling_roberta.RobertaPooler'>", + "RobertaPreLayerNormAttention": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormAttention'>", + "RobertaPreLayerNormClassificationHead": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormClassificationHead'>", + "RobertaPreLayerNormEmbeddings": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormEmbeddings'>", + "RobertaPreLayerNormEncoder": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormEncoder'>", + "RobertaPreLayerNormIntermediate": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormIntermediate'>", + "RobertaPreLayerNormLayer": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormLayer'>", + "RobertaPreLayerNormLMHead": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormLMHead'>", + "RobertaPreLayerNormOutput": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormOutput'>", + "RobertaPreLayerNormPooler": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormPooler'>", + "RobertaPreLayerNormSelfAttention": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormSelfAttention'>", + "RobertaPreLayerNormSelfOutput": "<'transformers.models.roberta_prelayernorm.modeling_roberta_prelayernorm.RobertaPreLayerNormSelfOutput'>", + "RobertaSdpaSelfAttention": "<'transformers.models.roberta.modeling_roberta.RobertaSdpaSelfAttention'>", + "RobertaSelfAttention": "<'transformers.models.roberta.modeling_roberta.RobertaSelfAttention'>", + "RobertaSelfOutput": "<'transformers.models.roberta.modeling_roberta.RobertaSelfOutput'>", + "RoCBertAttention": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertAttention'>", + "RoCBertEmbeddings": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertEmbeddings'>", + "RoCBertEncoder": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertEncoder'>", + "RoCBertIntermediate": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertIntermediate'>", + "RoCBertLayer": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertLayer'>", + "RoCBertLMPredictionHead": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertLMPredictionHead'>", + "RoCBertOnlyMLMHead": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertOnlyMLMHead'>", + "RoCBertOutput": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertOutput'>", + "RoCBertPooler": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertPooler'>", + "RoCBertPredictionHeadTransform": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertPredictionHeadTransform'>", + "RoCBertSelfAttention": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertSelfAttention'>", + "RoCBertSelfOutput": "<'transformers.models.roc_bert.modeling_roc_bert.RoCBertSelfOutput'>", + "RoFormerAttention": "<'transformers.models.roformer.modeling_roformer.RoFormerAttention'>", + "RoFormerClassificationHead": "<'transformers.models.roformer.modeling_roformer.RoFormerClassificationHead'>", + "RoFormerEmbeddings": "<'transformers.models.roformer.modeling_roformer.RoFormerEmbeddings'>", + "RoFormerEncoder": "<'transformers.models.roformer.modeling_roformer.RoFormerEncoder'>", + "RoFormerIntermediate": "<'transformers.models.roformer.modeling_roformer.RoFormerIntermediate'>", + "RoFormerLayer": "<'transformers.models.roformer.modeling_roformer.RoFormerLayer'>", + "RoFormerLMPredictionHead": "<'transformers.models.roformer.modeling_roformer.RoFormerLMPredictionHead'>", + "RoFormerOnlyMLMHead": "<'transformers.models.roformer.modeling_roformer.RoFormerOnlyMLMHead'>", + "RoFormerOutput": "<'transformers.models.roformer.modeling_roformer.RoFormerOutput'>", + "RoFormerPredictionHeadTransform": "<'transformers.models.roformer.modeling_roformer.RoFormerPredictionHeadTransform'>", + "RoFormerSelfAttention": "<'transformers.models.roformer.modeling_roformer.RoFormerSelfAttention'>", + "RoFormerSelfOutput": "<'transformers.models.roformer.modeling_roformer.RoFormerSelfOutput'>", + "RoFormerSequenceSummary": "<'transformers.models.roformer.modeling_roformer.RoFormerSequenceSummary'>", + "RoFormerSinusoidalPositionalEmbedding": "<'transformers.models.roformer.modeling_roformer.RoFormerSinusoidalPositionalEmbedding'>", + "RotaryEmbedding": "<'transformers.models.esm.modeling_esm.RotaryEmbedding'>", + "RTDetrConvEncoder": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrConvEncoder'>", + "RTDetrConvNormLayer": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrConvNormLayer'>", + "RTDetrCSPRepLayer": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrCSPRepLayer'>", + "RTDetrDecoder": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrDecoder'>", + "RTDetrDecoderLayer": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrDecoderLayer'>", + "RTDetrEncoder": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrEncoder'>", + "RTDetrEncoderLayer": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrEncoderLayer'>", + "RTDetrFrozenBatchNorm2d": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrFrozenBatchNorm2d'>", + "RTDetrHungarianMatcher": "<'transformers.loss.loss_rt_detr.RTDetrHungarianMatcher'>", + "RTDetrHybridEncoder": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrHybridEncoder'>", + "RTDetrLoss": "<'transformers.loss.loss_rt_detr.RTDetrLoss'>", + "RTDetrMLPPredictionHead": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrMLPPredictionHead'>", + "RTDetrMultiheadAttention": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrMultiheadAttention'>", + "RTDetrMultiscaleDeformableAttention": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrMultiscaleDeformableAttention'>", + "RTDetrRepVggBlock": "<'transformers.models.rt_detr.modeling_rt_detr.RTDetrRepVggBlock'>", + "RTDetrResNetBasicLayer": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetBasicLayer'>", + "RTDetrResNetBottleNeckLayer": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetBottleNeckLayer'>", + "RTDetrResNetConvLayer": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetConvLayer'>", + "RTDetrResNetEmbeddings": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetEmbeddings'>", + "RTDetrResNetEncoder": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetEncoder'>", + "RTDetrResNetShortCut": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetShortCut'>", + "RTDetrResNetStage": "<'transformers.models.rt_detr.modeling_rt_detr_resnet.RTDetrResNetStage'>", + "RTDetrV2ConvEncoder": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2ConvEncoder'>", + "RTDetrV2ConvNormLayer": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2ConvNormLayer'>", + "RTDetrV2CSPRepLayer": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2CSPRepLayer'>", + "RTDetrV2Decoder": "<'transformers.models.rt_detr_v2.modular_rt_detr_v2.RTDetrV2Decoder'>", + "RTDetrV2DecoderLayer": "<'transformers.models.rt_detr_v2.modular_rt_detr_v2.RTDetrV2DecoderLayer'>", + "RTDetrV2Encoder": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2Encoder'>", + "RTDetrV2EncoderLayer": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2EncoderLayer'>", + "RTDetrV2FrozenBatchNorm2d": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2FrozenBatchNorm2d'>", + "RTDetrV2HybridEncoder": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2HybridEncoder'>", + "RTDetrV2MLPPredictionHead": "<'transformers.models.rt_detr_v2.modular_rt_detr_v2.RTDetrV2MLPPredictionHead'>", + "RTDetrV2MultiheadAttention": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2MultiheadAttention'>", + "RTDetrV2MultiscaleDeformableAttention": "<'transformers.models.rt_detr_v2.modular_rt_detr_v2.RTDetrV2MultiscaleDeformableAttention'>", + "RTDetrV2RepVggBlock": "<'transformers.models.rt_detr_v2.modeling_rt_detr_v2.RTDetrV2RepVggBlock'>", + "RwkvBlock": "<'transformers.models.rwkv.modeling_rwkv.RwkvBlock'>", + "RwkvFeedForward": "<'transformers.models.rwkv.modeling_rwkv.RwkvFeedForward'>", + "RwkvSelfAttention": "<'transformers.models.rwkv.modeling_rwkv.RwkvSelfAttention'>", + "SamAttention": "<'transformers.models.sam.modeling_sam.SamAttention'>", + "SamFeedForward": "<'transformers.models.sam.modeling_sam.SamFeedForward'>", + "SamHQAttention": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQAttention'>", + "SamHQFeedForward": "<'transformers.models.sam_hq.modular_sam_hq.SamHQFeedForward'>", + "SamHQLayerNorm": "<'transformers.models.sam_hq.modular_sam_hq.SamHQLayerNorm'>", + "SamHQMaskDecoder": "<'transformers.models.sam_hq.modular_sam_hq.SamHQMaskDecoder'>", + "SamHQMaskEmbedding": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQMaskEmbedding'>", + "SamHQMLPBlock": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQMLPBlock'>", + "SamHQPatchEmbeddings": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQPatchEmbeddings'>", + "SamHQPositionalEmbedding": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQPositionalEmbedding'>", + "SamHQPromptEncoder": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQPromptEncoder'>", + "SamHQTwoWayAttentionBlock": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQTwoWayAttentionBlock'>", + "SamHQTwoWayTransformer": "<'transformers.models.sam_hq.modular_sam_hq.SamHQTwoWayTransformer'>", + "SamHQVisionAttention": "<'transformers.models.sam_hq.modular_sam_hq.SamHQVisionAttention'>", + "SamHQVisionEncoder": "<'transformers.models.sam_hq.modular_sam_hq.SamHQVisionEncoder'>", + "SamHQVisionLayer": "<'transformers.models.sam_hq.modular_sam_hq.SamHQVisionLayer'>", + "SamHQVisionNeck": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQVisionNeck'>", + "SamHQVisionSdpaAttention": "<'transformers.models.sam_hq.modeling_sam_hq.SamHQVisionSdpaAttention'>", + "SamLayerNorm": "<'transformers.models.sam.modeling_sam.SamLayerNorm'>", + "SamMaskDecoder": "<'transformers.models.sam.modeling_sam.SamMaskDecoder'>", + "SamMaskEmbedding": "<'transformers.models.sam.modeling_sam.SamMaskEmbedding'>", + "SamMLPBlock": "<'transformers.models.sam.modeling_sam.SamMLPBlock'>", + "SamPatchEmbeddings": "<'transformers.models.sam.modeling_sam.SamPatchEmbeddings'>", + "SamPositionalEmbedding": "<'transformers.models.sam.modeling_sam.SamPositionalEmbedding'>", + "SamPromptEncoder": "<'transformers.models.sam.modeling_sam.SamPromptEncoder'>", + "SamTwoWayAttentionBlock": "<'transformers.models.sam.modeling_sam.SamTwoWayAttentionBlock'>", + "SamTwoWayTransformer": "<'transformers.models.sam.modeling_sam.SamTwoWayTransformer'>", + "SamVisionAttention": "<'transformers.models.sam.modeling_sam.SamVisionAttention'>", + "SamVisionEncoder": "<'transformers.models.sam.modeling_sam.SamVisionEncoder'>", + "SamVisionLayer": "<'transformers.models.sam.modeling_sam.SamVisionLayer'>", + "SamVisionNeck": "<'transformers.models.sam.modeling_sam.SamVisionNeck'>", + "SamVisionSdpaAttention": "<'transformers.models.sam.modeling_sam.SamVisionSdpaAttention'>", + "SeamlessM4TAttention": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TAttention'>", + "SeamlessM4TConformerAdapter": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerAdapter'>", + "SeamlessM4TConformerAdapterLayer": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerAdapterLayer'>", + "SeamlessM4TConformerConvolutionModule": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerConvolutionModule'>", + "SeamlessM4TConformerEncoder": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerEncoder'>", + "SeamlessM4TConformerEncoderLayer": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerEncoderLayer'>", + "SeamlessM4TConformerFeatureProjection": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerFeatureProjection'>", + "SeamlessM4TConformerFeedForward": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerFeedForward'>", + "SeamlessM4TConformerPositionalConvEmbedding": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerPositionalConvEmbedding'>", + "SeamlessM4TConformerRelPositionalEmbedding": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerRelPositionalEmbedding'>", + "SeamlessM4TConformerRotaryPositionalEmbedding": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerRotaryPositionalEmbedding'>", + "SeamlessM4TConformerSamePadLayer": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerSamePadLayer'>", + "SeamlessM4TConformerSelfAttention": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TConformerSelfAttention'>", + "SeamlessM4TDecoder": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TDecoder'>", + "SeamlessM4TDecoderLayer": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TDecoderLayer'>", + "SeamlessM4TEncoder": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TEncoder'>", + "SeamlessM4TEncoderLayer": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TEncoderLayer'>", + "SeamlessM4TFeedForwardNetwork": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TFeedForwardNetwork'>", + "SeamlessM4TScaledWordEmbedding": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TScaledWordEmbedding'>", + "SeamlessM4TSinusoidalPositionalEmbedding": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TSinusoidalPositionalEmbedding'>", + "SeamlessM4TSpeechEncoder": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TSpeechEncoder'>", + "SeamlessM4Tv2Attention": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2Attention'>", + "SeamlessM4Tv2CodeHifiGan": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2CodeHifiGan'>", + "SeamlessM4Tv2ConformerAdapter": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerAdapter'>", + "SeamlessM4Tv2ConformerAdapterLayer": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerAdapterLayer'>", + "SeamlessM4Tv2ConformerConvolutionModule": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerConvolutionModule'>", + "SeamlessM4Tv2ConformerEncoder": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerEncoder'>", + "SeamlessM4Tv2ConformerEncoderLayer": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerEncoderLayer'>", + "SeamlessM4Tv2ConformerFeatureProjection": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerFeatureProjection'>", + "SeamlessM4Tv2ConformerFeedForward": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerFeedForward'>", + "SeamlessM4Tv2ConformerSelfAttention": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ConformerSelfAttention'>", + "SeamlessM4Tv2Decoder": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2Decoder'>", + "SeamlessM4Tv2DecoderLayer": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2DecoderLayer'>", + "SeamlessM4Tv2Encoder": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2Encoder'>", + "SeamlessM4Tv2EncoderLayer": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2EncoderLayer'>", + "SeamlessM4Tv2FeedForwardNetwork": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2FeedForwardNetwork'>", + "SeamlessM4Tv2HifiGan": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2HifiGan'>", + "SeamlessM4Tv2ScaledWordEmbedding": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2ScaledWordEmbedding'>", + "SeamlessM4Tv2SinusoidalPositionalEmbedding": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2SinusoidalPositionalEmbedding'>", + "SeamlessM4Tv2SpeechEncoder": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2SpeechEncoder'>", + "SeamlessM4Tv2TextToUnitDecoder": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2TextToUnitDecoder'>", + "SeamlessM4Tv2TextToUnitDecoderLayer": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2TextToUnitDecoderLayer'>", + "SeamlessM4Tv2TextToUnitForConditionalGeneration": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2TextToUnitForConditionalGeneration'>", + "SeamlessM4Tv2TextToUnitModel": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2TextToUnitModel'>", + "SeamlessM4Tv2VariancePredictor": "<'transformers.models.seamless_m4t_v2.modeling_seamless_m4t_v2.SeamlessM4Tv2VariancePredictor'>", + "SeamlessM4TVariancePredictor": "<'transformers.models.seamless_m4t.modeling_seamless_m4t.SeamlessM4TVariancePredictor'>", + "SegformerAttention": "<'transformers.models.segformer.modeling_segformer.SegformerAttention'>", + "SegformerDropPath": "<'transformers.models.segformer.modeling_segformer.SegformerDropPath'>", + "SegformerDWConv": "<'transformers.models.segformer.modeling_segformer.SegformerDWConv'>", + "SegformerEfficientSelfAttention": "<'transformers.models.segformer.modeling_segformer.SegformerEfficientSelfAttention'>", + "SegformerEncoder": "<'transformers.models.segformer.modeling_segformer.SegformerEncoder'>", + "SegformerLayer": "<'transformers.models.segformer.modeling_segformer.SegformerLayer'>", + "SegformerMixFFN": "<'transformers.models.segformer.modeling_segformer.SegformerMixFFN'>", + "SegformerMLP": "<'transformers.models.segformer.modeling_segformer.SegformerMLP'>", + "SegformerOverlapPatchEmbeddings": "<'transformers.models.segformer.modeling_segformer.SegformerOverlapPatchEmbeddings'>", + "SegformerSelfOutput": "<'transformers.models.segformer.modeling_segformer.SegformerSelfOutput'>", + "SegGptAttention": "<'transformers.models.seggpt.modeling_seggpt.SegGptAttention'>", + "SegGptDecoder": "<'transformers.models.seggpt.modeling_seggpt.SegGptDecoder'>", + "SegGptDecoderHead": "<'transformers.models.seggpt.modeling_seggpt.SegGptDecoderHead'>", + "SegGptDropPath": "<'transformers.models.seggpt.modeling_seggpt.SegGptDropPath'>", + "SegGptEmbeddings": "<'transformers.models.seggpt.modeling_seggpt.SegGptEmbeddings'>", + "SegGptEncoder": "<'transformers.models.seggpt.modeling_seggpt.SegGptEncoder'>", + "SegGptLayer": "<'transformers.models.seggpt.modeling_seggpt.SegGptLayer'>", + "SegGptLayerNorm": "<'transformers.models.seggpt.modeling_seggpt.SegGptLayerNorm'>", + "SegGptLoss": "<'transformers.models.seggpt.modeling_seggpt.SegGptLoss'>", + "SegGptMlp": "<'transformers.models.seggpt.modeling_seggpt.SegGptMlp'>", + "SegGptPatchEmbeddings": "<'transformers.models.seggpt.modeling_seggpt.SegGptPatchEmbeddings'>", + "SeparableConv1D": "<'transformers.models.convbert.modeling_convbert.SeparableConv1D'>", + "SequentialLlama4TextExperts": "<'transformers.quantizers.base.SequentialLlama4TextExperts'>", + "SEWAttention": "<'transformers.models.sew.modeling_sew.SEWAttention'>", + "SEWDAttention": "<'transformers.models.sew_d.modeling_sew_d.SEWDAttention'>", + "SEWDEncoder": "<'transformers.models.sew_d.modeling_sew_d.SEWDEncoder'>", + "SEWDFeatureEncoder": "<'transformers.models.sew_d.modeling_sew_d.SEWDFeatureEncoder'>", + "SEWDFeatureExtractor": "<'transformers.models.sew_d.modeling_sew_d.SEWDFeatureExtractor'>", + "SEWDGroupNormConvLayer": "<'transformers.models.sew_d.modeling_sew_d.SEWDGroupNormConvLayer'>", + "SEWDIntermediate": "<'transformers.models.sew_d.modeling_sew_d.SEWDIntermediate'>", + "SEWDLayer": "<'transformers.models.sew_d.modeling_sew_d.SEWDLayer'>", + "SEWDLayerNormConvLayer": "<'transformers.models.sew_d.modeling_sew_d.SEWDLayerNormConvLayer'>", + "SEWDNoLayerNormConvLayer": "<'transformers.models.sew_d.modeling_sew_d.SEWDNoLayerNormConvLayer'>", + "SEWDOutput": "<'transformers.models.sew_d.modeling_sew_d.SEWDOutput'>", + "SEWDPositionalConvEmbedding": "<'transformers.models.sew_d.modeling_sew_d.SEWDPositionalConvEmbedding'>", + "SEWDSamePadLayer": "<'transformers.models.sew_d.modeling_sew_d.SEWDSamePadLayer'>", + "SEWDSelfOutput": "<'transformers.models.sew_d.modeling_sew_d.SEWDSelfOutput'>", + "SEWDTransformerEncoder": "<'transformers.models.sew_d.modeling_sew_d.SEWDTransformerEncoder'>", + "SEWDUpsampling": "<'transformers.models.sew_d.modeling_sew_d.SEWDUpsampling'>", + "SEWEncoder": "<'transformers.models.sew.modeling_sew.SEWEncoder'>", + "SEWEncoderLayer": "<'transformers.models.sew.modeling_sew.SEWEncoderLayer'>", + "SEWFeatureEncoder": "<'transformers.models.sew.modeling_sew.SEWFeatureEncoder'>", + "SEWFeatureExtractor": "<'transformers.models.sew.feature_extraction_sew.SEWFeatureExtractor'>", + "SEWFeedForward": "<'transformers.models.sew.modeling_sew.SEWFeedForward'>", + "SEWGroupNormConvLayer": "<'transformers.models.sew.modeling_sew.SEWGroupNormConvLayer'>", + "SEWLayerNormConvLayer": "<'transformers.models.sew.modeling_sew.SEWLayerNormConvLayer'>", + "SEWNoLayerNormConvLayer": "<'transformers.models.sew.modeling_sew.SEWNoLayerNormConvLayer'>", + "SEWPositionalConvEmbedding": "<'transformers.models.sew.modeling_sew.SEWPositionalConvEmbedding'>", + "SEWSamePadLayer": "<'transformers.models.sew.modeling_sew.SEWSamePadLayer'>", + "SEWUpsampling": "<'transformers.models.sew.modeling_sew.SEWUpsampling'>", + "Siglip2Attention": "<'transformers.models.siglip2.modeling_siglip2.Siglip2Attention'>", + "Siglip2Encoder": "<'transformers.models.siglip2.modeling_siglip2.Siglip2Encoder'>", + "Siglip2EncoderLayer": "<'transformers.models.siglip2.modeling_siglip2.Siglip2EncoderLayer'>", + "Siglip2MLP": "<'transformers.models.siglip2.modeling_siglip2.Siglip2MLP'>", + "Siglip2MultiheadAttentionPoolingHead": "<'transformers.models.siglip2.modeling_siglip2.Siglip2MultiheadAttentionPoolingHead'>", + "Siglip2TextEmbeddings": "<'transformers.models.siglip2.modeling_siglip2.Siglip2TextEmbeddings'>", + "Siglip2TextTransformer": "<'transformers.models.siglip2.modeling_siglip2.Siglip2TextTransformer'>", + "Siglip2VisionEmbeddings": "<'transformers.models.siglip2.modeling_siglip2.Siglip2VisionEmbeddings'>", + "Siglip2VisionTransformer": "<'transformers.models.siglip2.modeling_siglip2.Siglip2VisionTransformer'>", + "SiglipAttention": "<'transformers.models.siglip.modeling_siglip.SiglipAttention'>", + "SiglipEncoder": "<'transformers.models.siglip.modeling_siglip.SiglipEncoder'>", + "SiglipEncoderLayer": "<'transformers.models.siglip.modeling_siglip.SiglipEncoderLayer'>", + "SiglipMLP": "<'transformers.models.siglip.modeling_siglip.SiglipMLP'>", + "SiglipMultiheadAttentionPoolingHead": "<'transformers.models.siglip.modeling_siglip.SiglipMultiheadAttentionPoolingHead'>", + "SiglipTextEmbeddings": "<'transformers.models.siglip.modeling_siglip.SiglipTextEmbeddings'>", + "SiglipTextTransformer": "<'transformers.models.siglip.modeling_siglip.SiglipTextTransformer'>", + "SiglipVisionEmbeddings": "<'transformers.models.siglip.modeling_siglip.SiglipVisionEmbeddings'>", + "SiglipVisionTransformer": "<'transformers.models.siglip.modeling_siglip.SiglipVisionTransformer'>", + "SiLogLoss": "<'transformers.models.glpn.modeling_glpn.SiLogLoss'>", + "SinusoidalPositionalEmbedding": "<'transformers.models.fsmt.modeling_fsmt.SinusoidalPositionalEmbedding'>", + "SinusoidsPositionEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.SinusoidsPositionEmbedding'>", + "SinusPositionEmbedding": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.SinusPositionEmbedding'>", + "SmolLM3Attention": "<'transformers.models.smollm3.modular_smollm3.SmolLM3Attention'>", + "SmolLM3DecoderLayer": "<'transformers.models.smollm3.modular_smollm3.SmolLM3DecoderLayer'>", + "SmolLM3MLP": "<'transformers.models.smollm3.modeling_smollm3.SmolLM3MLP'>", + "SmolLM3RMSNorm": "<'transformers.models.smollm3.modeling_smollm3.SmolLM3RMSNorm'>", + "SmolLM3RotaryEmbedding": "<'transformers.models.smollm3.modeling_smollm3.SmolLM3RotaryEmbedding'>", + "SmolVLMConnector": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMConnector'>", + "SmolVLMEncoder": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMEncoder'>", + "SmolVLMEncoderLayer": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMEncoderLayer'>", + "SmolVLMRMSNorm": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMRMSNorm'>", + "SmolVLMSimpleMLP": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMSimpleMLP'>", + "SmolVLMVisionAttention": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMVisionAttention'>", + "SmolVLMVisionEmbeddings": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMVisionEmbeddings'>", + "SmolVLMVisionMLP": "<'transformers.models.smolvlm.modeling_smolvlm.SmolVLMVisionMLP'>", + "SmoothL1Loss": "<'torch.nn.modules.loss.SmoothL1Loss'>", + "Snake1d": "<'transformers.models.dac.modeling_dac.Snake1d'>", + "SnakeBeta": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.SnakeBeta'>", + "Speech2Text2Attention": "<'transformers.models.deprecated.speech_to_text_2.modeling_speech_to_text_2.Speech2Text2Attention'>", + "Speech2Text2Decoder": "<'transformers.models.deprecated.speech_to_text_2.modeling_speech_to_text_2.Speech2Text2Decoder'>", + "Speech2Text2DecoderLayer": "<'transformers.models.deprecated.speech_to_text_2.modeling_speech_to_text_2.Speech2Text2DecoderLayer'>", + "Speech2Text2DecoderWrapper": "<'transformers.models.deprecated.speech_to_text_2.modeling_speech_to_text_2.Speech2Text2DecoderWrapper'>", + "Speech2Text2SinusoidalPositionalEmbedding": "<'transformers.models.deprecated.speech_to_text_2.modeling_speech_to_text_2.Speech2Text2SinusoidalPositionalEmbedding'>", + "Speech2TextAttention": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextAttention'>", + "Speech2TextDecoder": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoder'>", + "Speech2TextDecoderLayer": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoderLayer'>", + "Speech2TextEncoder": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoder'>", + "Speech2TextEncoderLayer": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoderLayer'>", + "Speech2TextSinusoidalPositionalEmbedding": "<'transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextSinusoidalPositionalEmbedding'>", + "SpeechT5Attention": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5Attention'>", + "SpeechT5BatchNormConvLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5BatchNormConvLayer'>", + "SpeechT5Decoder": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5Decoder'>", + "SpeechT5DecoderLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5DecoderLayer'>", + "SpeechT5DecoderWithoutPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5DecoderWithoutPrenet'>", + "SpeechT5DecoderWithSpeechPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5DecoderWithSpeechPrenet'>", + "SpeechT5DecoderWithTextPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5DecoderWithTextPrenet'>", + "SpeechT5Encoder": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5Encoder'>", + "SpeechT5EncoderLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5EncoderLayer'>", + "SpeechT5EncoderWithoutPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5EncoderWithoutPrenet'>", + "SpeechT5EncoderWithSpeechPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5EncoderWithSpeechPrenet'>", + "SpeechT5EncoderWithTextPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5EncoderWithTextPrenet'>", + "SpeechT5FeatureEncoder": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5FeatureEncoder'>", + "SpeechT5FeatureProjection": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5FeatureProjection'>", + "SpeechT5FeedForward": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5FeedForward'>", + "SpeechT5GroupNormConvLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5GroupNormConvLayer'>", + "SpeechT5GuidedMultiheadAttentionLoss": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5GuidedMultiheadAttentionLoss'>", + "SpeechT5LayerNormConvLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5LayerNormConvLayer'>", + "SpeechT5NoLayerNormConvLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5NoLayerNormConvLayer'>", + "SpeechT5PositionalConvEmbedding": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5PositionalConvEmbedding'>", + "SpeechT5RelativePositionalEncoding": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5RelativePositionalEncoding'>", + "SpeechT5SamePadLayer": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SamePadLayer'>", + "SpeechT5ScaledPositionalEncoding": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5ScaledPositionalEncoding'>", + "SpeechT5SinusoidalPositionalEmbedding": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SinusoidalPositionalEmbedding'>", + "SpeechT5SpectrogramLoss": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SpectrogramLoss'>", + "SpeechT5SpeechDecoderPostnet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SpeechDecoderPostnet'>", + "SpeechT5SpeechDecoderPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SpeechDecoderPrenet'>", + "SpeechT5SpeechEncoderPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5SpeechEncoderPrenet'>", + "SpeechT5TextDecoderPostnet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5TextDecoderPostnet'>", + "SpeechT5TextDecoderPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5TextDecoderPrenet'>", + "SpeechT5TextEncoderPrenet": "<'transformers.models.speecht5.modeling_speecht5.SpeechT5TextEncoderPrenet'>", + "SplinterAttention": "<'transformers.models.splinter.modeling_splinter.SplinterAttention'>", + "SplinterEmbeddings": "<'transformers.models.splinter.modeling_splinter.SplinterEmbeddings'>", + "SplinterEncoder": "<'transformers.models.splinter.modeling_splinter.SplinterEncoder'>", + "SplinterFullyConnectedLayer": "<'transformers.models.splinter.modeling_splinter.SplinterFullyConnectedLayer'>", + "SplinterIntermediate": "<'transformers.models.splinter.modeling_splinter.SplinterIntermediate'>", + "SplinterLayer": "<'transformers.models.splinter.modeling_splinter.SplinterLayer'>", + "SplinterOutput": "<'transformers.models.splinter.modeling_splinter.SplinterOutput'>", + "SplinterSelfAttention": "<'transformers.models.splinter.modeling_splinter.SplinterSelfAttention'>", + "SplinterSelfOutput": "<'transformers.models.splinter.modeling_splinter.SplinterSelfOutput'>", + "SqueezeBertEmbeddings": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertEmbeddings'>", + "SqueezeBertEncoder": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertEncoder'>", + "SqueezeBertLayerNorm": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertLayerNorm'>", + "SqueezeBertLMPredictionHead": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertLMPredictionHead'>", + "SqueezeBertOnlyMLMHead": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertOnlyMLMHead'>", + "SqueezeBertPooler": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertPooler'>", + "SqueezeBertPredictionHeadTransform": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertPredictionHeadTransform'>", + "SqueezeBertSelfAttention": "<'transformers.models.squeezebert.modeling_squeezebert.SqueezeBertSelfAttention'>", + "SqueezeExcitationBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.SqueezeExcitationBlock'>", + "SqueezeExcitationRes2NetBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.SqueezeExcitationRes2NetBlock'>", + "StableDropout": "<'transformers.models.sew_d.modeling_sew_d.StableDropout'>", + "StableLmAttention": "<'transformers.models.stablelm.modeling_stablelm.StableLmAttention'>", + "StableLmDecoderLayer": "<'transformers.models.stablelm.modeling_stablelm.StableLmDecoderLayer'>", + "StableLmFlashAttention2": "<'transformers.models.stablelm.modeling_stablelm.StableLmFlashAttention2'>", + "StableLmLayerNormPerHead": "<'transformers.models.stablelm.modeling_stablelm.StableLmLayerNormPerHead'>", + "StableLmMLP": "<'transformers.models.stablelm.modeling_stablelm.StableLmMLP'>", + "StableLmRotaryEmbedding": "<'transformers.models.stablelm.modeling_stablelm.StableLmRotaryEmbedding'>", + "StableLmSdpaAttention": "<'transformers.models.stablelm.modeling_stablelm.StableLmSdpaAttention'>", + "Starcoder2Attention": "<'transformers.models.starcoder2.modular_starcoder2.Starcoder2Attention'>", + "Starcoder2DecoderLayer": "<'transformers.models.starcoder2.modular_starcoder2.Starcoder2DecoderLayer'>", + "Starcoder2MLP": "<'transformers.models.starcoder2.modular_starcoder2.Starcoder2MLP'>", + "Starcoder2RotaryEmbedding": "<'transformers.models.starcoder2.modular_starcoder2.Starcoder2RotaryEmbedding'>", + "SuperGlueAttention": "<'transformers.models.superglue.modeling_superglue.SuperGlueAttention'>", + "SuperGlueAttentionalGNN": "<'transformers.models.superglue.modeling_superglue.SuperGlueAttentionalGNN'>", + "SuperGlueAttentionalPropagation": "<'transformers.models.superglue.modeling_superglue.SuperGlueAttentionalPropagation'>", + "SuperGlueFinalProjection": "<'transformers.models.superglue.modeling_superglue.SuperGlueFinalProjection'>", + "SuperGlueKeypointEncoder": "<'transformers.models.superglue.modeling_superglue.SuperGlueKeypointEncoder'>", + "SuperGlueMultiLayerPerceptron": "<'transformers.models.superglue.modeling_superglue.SuperGlueMultiLayerPerceptron'>", + "SuperGlueSelfAttention": "<'transformers.models.superglue.modeling_superglue.SuperGlueSelfAttention'>", + "SuperGlueSelfOutput": "<'transformers.models.superglue.modeling_superglue.SuperGlueSelfOutput'>", + "SuperPointConvBlock": "<'transformers.models.superpoint.modeling_superpoint.SuperPointConvBlock'>", + "SuperPointDescriptorDecoder": "<'transformers.models.superpoint.modeling_superpoint.SuperPointDescriptorDecoder'>", + "SuperPointEncoder": "<'transformers.models.superpoint.modeling_superpoint.SuperPointEncoder'>", + "SuperPointInterestPointDecoder": "<'transformers.models.superpoint.modeling_superpoint.SuperPointInterestPointDecoder'>", + "SwiftFormerConvEncoder": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerConvEncoder'>", + "SwiftFormerDropPath": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerDropPath'>", + "SwiftFormerEfficientAdditiveAttention": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerEfficientAdditiveAttention'>", + "SwiftFormerEmbeddings": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerEmbeddings'>", + "SwiftFormerEncoder": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerEncoder'>", + "SwiftFormerEncoderBlock": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerEncoderBlock'>", + "SwiftFormerLocalRepresentation": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerLocalRepresentation'>", + "SwiftFormerMlp": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerMlp'>", + "SwiftFormerPatchEmbedding": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerPatchEmbedding'>", + "SwiftFormerStage": "<'transformers.models.swiftformer.modeling_swiftformer.SwiftFormerStage'>", + "Swin2SRAttention": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRAttention'>", + "Swin2SRDropPath": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRDropPath'>", + "Swin2SREmbeddings": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SREmbeddings'>", + "Swin2SREncoder": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SREncoder'>", + "Swin2SRIntermediate": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRIntermediate'>", + "Swin2SRLayer": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRLayer'>", + "Swin2SROutput": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SROutput'>", + "Swin2SRPatchEmbeddings": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRPatchEmbeddings'>", + "Swin2SRPatchMerging": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRPatchMerging'>", + "Swin2SRPatchUnEmbeddings": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRPatchUnEmbeddings'>", + "Swin2SRSelfAttention": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRSelfAttention'>", + "Swin2SRSelfOutput": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRSelfOutput'>", + "Swin2SRStage": "<'transformers.models.swin2sr.modeling_swin2sr.Swin2SRStage'>", + "SwinAttention": "<'transformers.models.swin.modeling_swin.SwinAttention'>", + "SwinDropPath": "<'transformers.models.swin.modeling_swin.SwinDropPath'>", + "SwinEmbeddings": "<'transformers.models.swin.modeling_swin.SwinEmbeddings'>", + "SwinEncoder": "<'transformers.models.swin.modeling_swin.SwinEncoder'>", + "SwinIntermediate": "<'transformers.models.swin.modeling_swin.SwinIntermediate'>", + "SwinLayer": "<'transformers.models.swin.modeling_swin.SwinLayer'>", + "SwinOutput": "<'transformers.models.swin.modeling_swin.SwinOutput'>", + "SwinPatchEmbeddings": "<'transformers.models.swin.modeling_swin.SwinPatchEmbeddings'>", + "SwinPatchMerging": "<'transformers.models.swin.modeling_swin.SwinPatchMerging'>", + "SwinSelfAttention": "<'transformers.models.swin.modeling_swin.SwinSelfAttention'>", + "SwinSelfOutput": "<'transformers.models.swin.modeling_swin.SwinSelfOutput'>", + "SwinStage": "<'transformers.models.swin.modeling_swin.SwinStage'>", + "Swinv2Attention": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Attention'>", + "Swinv2DropPath": "<'transformers.models.swinv2.modeling_swinv2.Swinv2DropPath'>", + "Swinv2Embeddings": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Embeddings'>", + "Swinv2Encoder": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Encoder'>", + "Swinv2Intermediate": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Intermediate'>", + "Swinv2Layer": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Layer'>", + "Swinv2Output": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Output'>", + "Swinv2PatchEmbeddings": "<'transformers.models.swinv2.modeling_swinv2.Swinv2PatchEmbeddings'>", + "Swinv2PatchMerging": "<'transformers.models.swinv2.modeling_swinv2.Swinv2PatchMerging'>", + "Swinv2SelfAttention": "<'transformers.models.swinv2.modeling_swinv2.Swinv2SelfAttention'>", + "Swinv2SelfOutput": "<'transformers.models.swinv2.modeling_swinv2.Swinv2SelfOutput'>", + "Swinv2Stage": "<'transformers.models.swinv2.modeling_swinv2.Swinv2Stage'>", + "SwitchTransformersAttention": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersAttention'>", + "SwitchTransformersBlock": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersBlock'>", + "SwitchTransformersDenseActDense": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersDenseActDense'>", + "SwitchTransformersLayerCrossAttention": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersLayerCrossAttention'>", + "SwitchTransformersLayerFF": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersLayerFF'>", + "SwitchTransformersLayerNorm": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersLayerNorm'>", + "SwitchTransformersLayerSelfAttention": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersLayerSelfAttention'>", + "SwitchTransformersSparseMLP": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersSparseMLP'>", + "SwitchTransformersStack": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersStack'>", + "SwitchTransformersTop1Router": "<'transformers.models.switch_transformers.modeling_switch_transformers.SwitchTransformersTop1Router'>", + "T5Attention": "<'transformers.models.t5.modeling_t5.T5Attention'>", + "T5Block": "<'transformers.models.t5.modeling_t5.T5Block'>", + "T5ClassificationHead": "<'transformers.models.t5.modeling_t5.T5ClassificationHead'>", + "T5DenseActDense": "<'transformers.models.t5.modeling_t5.T5DenseActDense'>", + "T5DenseGatedActDense": "<'transformers.models.t5.modeling_t5.T5DenseGatedActDense'>", + "T5GemmaAttention": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaAttention'>", + "T5GemmaClassificationHead": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaClassificationHead'>", + "T5GemmaCrossAttention": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaCrossAttention'>", + "T5GemmaDecoder": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaDecoder'>", + "T5GemmaDecoderLayer": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaDecoderLayer'>", + "T5GemmaEncoder": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaEncoder'>", + "T5GemmaEncoderLayer": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaEncoderLayer'>", + "T5GemmaLMHead": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaLMHead'>", + "T5GemmaMLP": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaMLP'>", + "T5GemmaRMSNorm": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaRMSNorm'>", + "T5GemmaRotaryEmbedding": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaRotaryEmbedding'>", + "T5GemmaSelfAttention": "<'transformers.models.t5gemma.modeling_t5gemma.T5GemmaSelfAttention'>", + "T5LayerCrossAttention": "<'transformers.models.t5.modeling_t5.T5LayerCrossAttention'>", + "T5LayerFF": "<'transformers.models.t5.modeling_t5.T5LayerFF'>", + "T5LayerNorm": "<'transformers.models.t5.modeling_t5.T5LayerNorm'>", + "T5LayerSelfAttention": "<'transformers.models.t5.modeling_t5.T5LayerSelfAttention'>", + "T5Stack": "<'transformers.models.t5.modeling_t5.T5Stack'>", + "TableTransformerAttention": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerAttention'>", + "TableTransformerConvEncoder": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerConvEncoder'>", + "TableTransformerConvModel": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerConvModel'>", + "TableTransformerDecoder": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerDecoder'>", + "TableTransformerDecoderLayer": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerDecoderLayer'>", + "TableTransformerEncoder": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerEncoder'>", + "TableTransformerEncoderLayer": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerEncoderLayer'>", + "TableTransformerFrozenBatchNorm2d": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerFrozenBatchNorm2d'>", + "TableTransformerLearnedPositionEmbedding": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerLearnedPositionEmbedding'>", + "TableTransformerMLPPredictionHead": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerMLPPredictionHead'>", + "TableTransformerSinePositionEmbedding": "<'transformers.models.table_transformer.modeling_table_transformer.TableTransformerSinePositionEmbedding'>", + "TapasAttention": "<'transformers.models.tapas.modeling_tapas.TapasAttention'>", + "TapasEmbeddings": "<'transformers.models.tapas.modeling_tapas.TapasEmbeddings'>", + "TapasEncoder": "<'transformers.models.tapas.modeling_tapas.TapasEncoder'>", + "TapasIntermediate": "<'transformers.models.tapas.modeling_tapas.TapasIntermediate'>", + "TapasLayer": "<'transformers.models.tapas.modeling_tapas.TapasLayer'>", + "TapasLMPredictionHead": "<'transformers.models.tapas.modeling_tapas.TapasLMPredictionHead'>", + "TapasOnlyMLMHead": "<'transformers.models.tapas.modeling_tapas.TapasOnlyMLMHead'>", + "TapasOutput": "<'transformers.models.tapas.modeling_tapas.TapasOutput'>", + "TapasPooler": "<'transformers.models.tapas.modeling_tapas.TapasPooler'>", + "TapasPredictionHeadTransform": "<'transformers.models.tapas.modeling_tapas.TapasPredictionHeadTransform'>", + "TapasSelfAttention": "<'transformers.models.tapas.modeling_tapas.TapasSelfAttention'>", + "TapasSelfOutput": "<'transformers.models.tapas.modeling_tapas.TapasSelfOutput'>", + "TDNNLayer": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.TDNNLayer'>", + "TextEmbeddings": "<'transformers.models.vilt.modeling_vilt.TextEmbeddings'>", + "TextNetConvLayer": "<'transformers.models.textnet.modeling_textnet.TextNetConvLayer'>", + "TextNetEncoder": "<'transformers.models.textnet.modeling_textnet.TextNetEncoder'>", + "TextNetRepConvLayer": "<'transformers.models.textnet.modeling_textnet.TextNetRepConvLayer'>", + "TextNetStage": "<'transformers.models.textnet.modeling_textnet.TextNetStage'>", + "TimeDelayNetBlock": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.TimeDelayNetBlock'>", + "TimeSeriesFeatureEmbedder": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesFeatureEmbedder'>", + "TimeSeriesMeanScaler": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesMeanScaler'>", + "TimeSeriesNOPScaler": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesNOPScaler'>", + "TimeSeriesSinusoidalPositionalEmbedding": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesSinusoidalPositionalEmbedding'>", + "TimeSeriesStdScaler": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesStdScaler'>", + "TimeSeriesTransformerAttention": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesTransformerAttention'>", + "TimeSeriesTransformerDecoder": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesTransformerDecoder'>", + "TimeSeriesTransformerDecoderLayer": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesTransformerDecoderLayer'>", + "TimeSeriesTransformerEncoder": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesTransformerEncoder'>", + "TimeSeriesTransformerEncoderLayer": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesTransformerEncoderLayer'>", + "TimeSeriesValueEmbedding": "<'transformers.models.time_series_transformer.modeling_time_series_transformer.TimeSeriesValueEmbedding'>", + "TimesFmAttention": "<'transformers.models.timesfm.modular_timesfm.TimesFmAttention'>", + "TimesFmDecoderLayer": "<'transformers.models.timesfm.modular_timesfm.TimesFmDecoderLayer'>", + "TimesFmMLP": "<'transformers.models.timesfm.modular_timesfm.TimesFmMLP'>", + "TimesFmPositionalEmbedding": "<'transformers.models.timesfm.modular_timesfm.TimesFmPositionalEmbedding'>", + "TimesFmResidualBlock": "<'transformers.models.timesfm.modular_timesfm.TimesFmResidualBlock'>", + "TimesFmRMSNorm": "<'transformers.models.timesfm.modular_timesfm.TimesFmRMSNorm'>", + "TimeSformerAttention": "<'transformers.models.timesformer.modeling_timesformer.TimeSformerAttention'>", + "TimeSformerDropPath": "<'transformers.models.timesformer.modeling_timesformer.TimeSformerDropPath'>", + "TimesformerEmbeddings": "<'transformers.models.timesformer.modeling_timesformer.TimesformerEmbeddings'>", + "TimesformerEncoder": "<'transformers.models.timesformer.modeling_timesformer.TimesformerEncoder'>", + "TimesformerIntermediate": "<'transformers.models.timesformer.modeling_timesformer.TimesformerIntermediate'>", + "TimesformerLayer": "<'transformers.models.timesformer.modeling_timesformer.TimesformerLayer'>", + "TimesformerOutput": "<'transformers.models.timesformer.modeling_timesformer.TimesformerOutput'>", + "TimesformerPatchEmbeddings": "<'transformers.models.timesformer.modeling_timesformer.TimesformerPatchEmbeddings'>", + "TimesformerSelfAttention": "<'transformers.models.timesformer.modeling_timesformer.TimesformerSelfAttention'>", + "TimesformerSelfOutput": "<'transformers.models.timesformer.modeling_timesformer.TimesformerSelfOutput'>", + "TorchActivation1d": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.TorchActivation1d'>", + "Transformer": "<'transformers.models.distilbert.modeling_distilbert.Transformer'>", + "TransformerBlock": "<'transformers.models.distilbert.modeling_distilbert.TransformerBlock'>", + "TransformerFFN": "<'transformers.models.flaubert.modeling_flaubert.TransformerFFN'>", + "TrOCRAttention": "<'transformers.models.trocr.modeling_trocr.TrOCRAttention'>", + "TrOCRDecoder": "<'transformers.models.trocr.modeling_trocr.TrOCRDecoder'>", + "TrOCRDecoderLayer": "<'transformers.models.trocr.modeling_trocr.TrOCRDecoderLayer'>", + "TrOCRDecoderWrapper": "<'transformers.models.trocr.modeling_trocr.TrOCRDecoderWrapper'>", + "TrOCRLearnedPositionalEmbedding": "<'transformers.models.trocr.modeling_trocr.TrOCRLearnedPositionalEmbedding'>", + "TrOCRScaledWordEmbedding": "<'transformers.models.trocr.modeling_trocr.TrOCRScaledWordEmbedding'>", + "TrOCRSinusoidalPositionalEmbedding": "<'transformers.models.trocr.modeling_trocr.TrOCRSinusoidalPositionalEmbedding'>", + "TvltAttention": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltAttention'>", + "TvltAudioEmbeddings": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltAudioEmbeddings'>", + "TvltAudioPatchEmbeddings": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltAudioPatchEmbeddings'>", + "TvltDecoder": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltDecoder'>", + "TvltEncoder": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltEncoder'>", + "TvltIntermediate": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltIntermediate'>", + "TvltLayer": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltLayer'>", + "TvltMAEHead": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltMAEHead'>", + "TvltMatchingHead": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltMatchingHead'>", + "TvltOutput": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltOutput'>", + "TvltPixelEmbeddings": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltPixelEmbeddings'>", + "TvltPixelPatchEmbeddings": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltPixelPatchEmbeddings'>", + "TvltPooler": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltPooler'>", + "TvltSelfAttention": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltSelfAttention'>", + "TvltSelfOutput": "<'transformers.models.deprecated.tvlt.modeling_tvlt.TvltSelfOutput'>", + "TvpAttention": "<'transformers.models.tvp.modeling_tvp.TvpAttention'>", + "TvpEncodeLayer": "<'transformers.models.tvp.modeling_tvp.TvpEncodeLayer'>", + "TvpEncoder": "<'transformers.models.tvp.modeling_tvp.TvpEncoder'>", + "TvpFrameDownPadPrompter": "<'transformers.models.tvp.modeling_tvp.TvpFrameDownPadPrompter'>", + "TvpFramePadPrompter": "<'transformers.models.tvp.modeling_tvp.TvpFramePadPrompter'>", + "TvpIntermediate": "<'transformers.models.tvp.modeling_tvp.TvpIntermediate'>", + "TvpLoss": "<'transformers.models.tvp.modeling_tvp.TvpLoss'>", + "TvpOutputLayer": "<'transformers.models.tvp.modeling_tvp.TvpOutputLayer'>", + "TvpPooler": "<'transformers.models.tvp.modeling_tvp.TvpPooler'>", + "TvpTextInputEmbeddings": "<'transformers.models.tvp.modeling_tvp.TvpTextInputEmbeddings'>", + "TvpVideoGroundingHead": "<'transformers.models.tvp.modeling_tvp.TvpVideoGroundingHead'>", + "TvpVisionModel": "<'transformers.models.tvp.modeling_tvp.TvpVisionModel'>", + "TvpVisualInputEmbedding": "<'transformers.models.tvp.modeling_tvp.TvpVisualInputEmbedding'>", + "UdopAttention": "<'transformers.models.udop.modeling_udop.UdopAttention'>", + "UdopBlock": "<'transformers.models.udop.modeling_udop.UdopBlock'>", + "UdopCellEmbeddings": "<'transformers.models.udop.modeling_udop.UdopCellEmbeddings'>", + "UdopDenseActDense": "<'transformers.models.udop.modeling_udop.UdopDenseActDense'>", + "UdopDenseGatedActDense": "<'transformers.models.udop.modeling_udop.UdopDenseGatedActDense'>", + "UdopLayerCrossAttention": "<'transformers.models.udop.modeling_udop.UdopLayerCrossAttention'>", + "UdopLayerFF": "<'transformers.models.udop.modeling_udop.UdopLayerFF'>", + "UdopLayerNorm": "<'transformers.models.udop.modeling_udop.UdopLayerNorm'>", + "UdopLayerSelfAttention": "<'transformers.models.udop.modeling_udop.UdopLayerSelfAttention'>", + "UdopPatchEmbeddings": "<'transformers.models.udop.modeling_udop.UdopPatchEmbeddings'>", + "UdopStack": "<'transformers.models.udop.modeling_udop.UdopStack'>", + "UMT5Attention": "<'transformers.models.umt5.modeling_umt5.UMT5Attention'>", + "UMT5Block": "<'transformers.models.umt5.modeling_umt5.UMT5Block'>", + "UMT5ClassificationHead": "<'transformers.models.umt5.modeling_umt5.UMT5ClassificationHead'>", + "UMT5DenseActDense": "<'transformers.models.umt5.modeling_umt5.UMT5DenseActDense'>", + "UMT5DenseGatedActDense": "<'transformers.models.umt5.modeling_umt5.UMT5DenseGatedActDense'>", + "UMT5LayerCrossAttention": "<'transformers.models.umt5.modeling_umt5.UMT5LayerCrossAttention'>", + "UMT5LayerFF": "<'transformers.models.umt5.modeling_umt5.UMT5LayerFF'>", + "UMT5LayerNorm": "<'transformers.models.umt5.modeling_umt5.UMT5LayerNorm'>", + "UMT5LayerSelfAttention": "<'transformers.models.umt5.modeling_umt5.UMT5LayerSelfAttention'>", + "UMT5Stack": "<'transformers.models.umt5.modeling_umt5.UMT5Stack'>", + "UniSpeechAttention": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechAttention'>", + "UniSpeechAttnAdapterLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechAttnAdapterLayer'>", + "UniSpeechEncoder": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechEncoder'>", + "UniSpeechEncoderLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechEncoderLayer'>", + "UniSpeechEncoderLayerStableLayerNorm": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechEncoderLayerStableLayerNorm'>", + "UniSpeechEncoderStableLayerNorm": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechEncoderStableLayerNorm'>", + "UniSpeechFeatureEncoder": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechFeatureEncoder'>", + "UniSpeechFeatureProjection": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechFeatureProjection'>", + "UniSpeechFeedForward": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechFeedForward'>", + "UniSpeechGroupNormConvLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechGroupNormConvLayer'>", + "UniSpeechGumbelVectorQuantizer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechGumbelVectorQuantizer'>", + "UniSpeechLayerNormConvLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechLayerNormConvLayer'>", + "UniSpeechNoLayerNormConvLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechNoLayerNormConvLayer'>", + "UniSpeechPositionalConvEmbedding": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechPositionalConvEmbedding'>", + "UniSpeechSamePadLayer": "<'transformers.models.unispeech.modeling_unispeech.UniSpeechSamePadLayer'>", + "UniSpeechSatAttention": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatAttention'>", + "UniSpeechSatAttnAdapterLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatAttnAdapterLayer'>", + "UniSpeechSatEncoder": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatEncoder'>", + "UniSpeechSatEncoderLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatEncoderLayer'>", + "UniSpeechSatEncoderLayerStableLayerNorm": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatEncoderLayerStableLayerNorm'>", + "UniSpeechSatEncoderStableLayerNorm": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatEncoderStableLayerNorm'>", + "UniSpeechSatFeatureEncoder": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatFeatureEncoder'>", + "UniSpeechSatFeatureProjection": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatFeatureProjection'>", + "UniSpeechSatFeedForward": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatFeedForward'>", + "UniSpeechSatGroupNormConvLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatGroupNormConvLayer'>", + "UniSpeechSatGumbelVectorQuantizer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatGumbelVectorQuantizer'>", + "UniSpeechSatLayerNormConvLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatLayerNormConvLayer'>", + "UniSpeechSatNoLayerNormConvLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatNoLayerNormConvLayer'>", + "UniSpeechSatPositionalConvEmbedding": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatPositionalConvEmbedding'>", + "UniSpeechSatSamePadLayer": "<'transformers.models.unispeech_sat.modeling_unispeech_sat.UniSpeechSatSamePadLayer'>", + "UnivNetKernelPredictor": "<'transformers.models.univnet.modeling_univnet.UnivNetKernelPredictor'>", + "UnivNetKernelPredictorResidualBlock": "<'transformers.models.univnet.modeling_univnet.UnivNetKernelPredictorResidualBlock'>", + "UnivNetLvcBlock": "<'transformers.models.univnet.modeling_univnet.UnivNetLvcBlock'>", + "UnivNetLvcResidualBlock": "<'transformers.models.univnet.modeling_univnet.UnivNetLvcResidualBlock'>", + "UperNetConvModule": "<'transformers.models.upernet.modeling_upernet.UperNetConvModule'>", + "UperNetFCNHead": "<'transformers.models.upernet.modeling_upernet.UperNetFCNHead'>", + "UperNetHead": "<'transformers.models.upernet.modeling_upernet.UperNetHead'>", + "UperNetPyramidPoolingBlock": "<'transformers.models.upernet.modeling_upernet.UperNetPyramidPoolingBlock'>", + "UperNetPyramidPoolingModule": "<'transformers.models.upernet.modeling_upernet.UperNetPyramidPoolingModule'>", + "Upsample": "<'transformers.models.swin2sr.modeling_swin2sr.Upsample'>", + "UpSample1d": "<'transformers.models.qwen2_5_omni.modeling_qwen2_5_omni.UpSample1d'>", + "UpsampleOneStep": "<'transformers.models.swin2sr.modeling_swin2sr.UpsampleOneStep'>", + "VanDropPath": "<'transformers.models.deprecated.van.modeling_van.VanDropPath'>", + "VanEncoder": "<'transformers.models.deprecated.van.modeling_van.VanEncoder'>", + "VanLargeKernelAttention": "<'transformers.models.deprecated.van.modeling_van.VanLargeKernelAttention'>", + "VanLargeKernelAttentionLayer": "<'transformers.models.deprecated.van.modeling_van.VanLargeKernelAttentionLayer'>", + "VanLayer": "<'transformers.models.deprecated.van.modeling_van.VanLayer'>", + "VanLayerScaling": "<'transformers.models.deprecated.van.modeling_van.VanLayerScaling'>", + "VanMlpLayer": "<'transformers.models.deprecated.van.modeling_van.VanMlpLayer'>", + "VanOverlappingPatchEmbedder": "<'transformers.models.deprecated.van.modeling_van.VanOverlappingPatchEmbedder'>", + "VanSpatialAttentionLayer": "<'transformers.models.deprecated.van.modeling_van.VanSpatialAttentionLayer'>", + "VanStage": "<'transformers.models.deprecated.van.modeling_van.VanStage'>", + "VideoLlavaMultiModalProjector": "<'transformers.models.video_llava.modeling_video_llava.VideoLlavaMultiModalProjector'>", + "VideoMAEAttention": "<'transformers.models.videomae.modeling_videomae.VideoMAEAttention'>", + "VideoMAEDecoder": "<'transformers.models.videomae.modeling_videomae.VideoMAEDecoder'>", + "VideoMAEEmbeddings": "<'transformers.models.videomae.modeling_videomae.VideoMAEEmbeddings'>", + "VideoMAEEncoder": "<'transformers.models.videomae.modeling_videomae.VideoMAEEncoder'>", + "VideoMAEIntermediate": "<'transformers.models.videomae.modeling_videomae.VideoMAEIntermediate'>", + "VideoMAELayer": "<'transformers.models.videomae.modeling_videomae.VideoMAELayer'>", + "VideoMAEOutput": "<'transformers.models.videomae.modeling_videomae.VideoMAEOutput'>", + "VideoMAEPatchEmbeddings": "<'transformers.models.videomae.modeling_videomae.VideoMAEPatchEmbeddings'>", + "VideoMAESelfAttention": "<'transformers.models.videomae.modeling_videomae.VideoMAESelfAttention'>", + "VideoMAESelfOutput": "<'transformers.models.videomae.modeling_videomae.VideoMAESelfOutput'>", + "ViltAttention": "<'transformers.models.vilt.modeling_vilt.ViltAttention'>", + "ViltEmbeddings": "<'transformers.models.vilt.modeling_vilt.ViltEmbeddings'>", + "ViltEncoder": "<'transformers.models.vilt.modeling_vilt.ViltEncoder'>", + "ViltIntermediate": "<'transformers.models.vilt.modeling_vilt.ViltIntermediate'>", + "ViltMLMHead": "<'transformers.models.vilt.modeling_vilt.ViltMLMHead'>", + "ViltOutput": "<'transformers.models.vilt.modeling_vilt.ViltOutput'>", + "ViltPatchEmbeddings": "<'transformers.models.vilt.modeling_vilt.ViltPatchEmbeddings'>", + "ViltPooler": "<'transformers.models.vilt.modeling_vilt.ViltPooler'>", + "ViltPredictionHeadTransform": "<'transformers.models.vilt.modeling_vilt.ViltPredictionHeadTransform'>", + "ViltSelfAttention": "<'transformers.models.vilt.modeling_vilt.ViltSelfAttention'>", + "ViltSelfOutput": "<'transformers.models.vilt.modeling_vilt.ViltSelfOutput'>", + "VipLlavaMultiModalProjector": "<'transformers.models.vipllava.modular_vipllava.VipLlavaMultiModalProjector'>", + "VisionAttention": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.VisionAttention'>", + "VisionMlp": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.VisionMlp'>", + "VisionRotaryEmbedding": "<'transformers.models.qwen2_vl.modeling_qwen2_vl.VisionRotaryEmbedding'>", + "VisualBertAttention": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertAttention'>", + "VisualBertEmbeddings": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertEmbeddings'>", + "VisualBertEncoder": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertEncoder'>", + "VisualBertIntermediate": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertIntermediate'>", + "VisualBertLMPredictionHead": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertLMPredictionHead'>", + "VisualBertOutput": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertOutput'>", + "VisualBertPooler": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertPooler'>", + "VisualBertPredictionHeadTransform": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertPredictionHeadTransform'>", + "VisualBertPreTrainingHeads": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertPreTrainingHeads'>", + "VisualBertRegionToPhraseAttention": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertRegionToPhraseAttention'>", + "VisualBertSelfAttention": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertSelfAttention'>", + "VisualBertSelfOutput": "<'transformers.models.visual_bert.modeling_visual_bert.VisualBertSelfOutput'>", + "ViTAttention": "<'transformers.models.vit.modeling_vit.ViTAttention'>", + "VitDetAttention": "<'transformers.models.vitdet.modeling_vitdet.VitDetAttention'>", + "VitDetDropPath": "<'transformers.models.vitdet.modeling_vitdet.VitDetDropPath'>", + "VitDetEmbeddings": "<'transformers.models.vitdet.modeling_vitdet.VitDetEmbeddings'>", + "VitDetEncoder": "<'transformers.models.vitdet.modeling_vitdet.VitDetEncoder'>", + "VitDetLayer": "<'transformers.models.vitdet.modeling_vitdet.VitDetLayer'>", + "VitDetLayerNorm": "<'transformers.models.vitdet.modeling_vitdet.VitDetLayerNorm'>", + "VitDetMlp": "<'transformers.models.vitdet.modeling_vitdet.VitDetMlp'>", + "VitDetResBottleneckBlock": "<'transformers.models.vitdet.modeling_vitdet.VitDetResBottleneckBlock'>", + "ViTEmbeddings": "<'transformers.models.vit.modeling_vit.ViTEmbeddings'>", + "ViTEncoder": "<'transformers.models.vit.modeling_vit.ViTEncoder'>", + "ViTHybridAttention": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridAttention'>", + "ViTHybridEmbeddings": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridEmbeddings'>", + "ViTHybridEncoder": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridEncoder'>", + "ViTHybridIntermediate": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridIntermediate'>", + "ViTHybridLayer": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridLayer'>", + "ViTHybridOutput": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridOutput'>", + "ViTHybridPatchEmbeddings": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridPatchEmbeddings'>", + "ViTHybridPooler": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridPooler'>", + "ViTHybridSdpaAttention": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridSdpaAttention'>", + "ViTHybridSdpaSelfAttention": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridSdpaSelfAttention'>", + "ViTHybridSelfAttention": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridSelfAttention'>", + "ViTHybridSelfOutput": "<'transformers.models.deprecated.vit_hybrid.modeling_vit_hybrid.ViTHybridSelfOutput'>", + "ViTIntermediate": "<'transformers.models.vit.modeling_vit.ViTIntermediate'>", + "ViTLayer": "<'transformers.models.vit.modeling_vit.ViTLayer'>", + "ViTMAEAttention": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEAttention'>", + "ViTMAEDecoder": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEDecoder'>", + "ViTMAEEmbeddings": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEEmbeddings'>", + "ViTMAEEncoder": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEEncoder'>", + "ViTMAEIntermediate": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEIntermediate'>", + "ViTMAEOutput": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEOutput'>", + "ViTMAEPatchEmbeddings": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAEPatchEmbeddings'>", + "ViTMAESelfAttention": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAESelfAttention'>", + "ViTMAESelfOutput": "<'transformers.models.vit_mae.modeling_vit_mae.ViTMAESelfOutput'>", + "VitMatteBasicConv3x3": "<'transformers.models.vitmatte.modeling_vitmatte.VitMatteBasicConv3x3'>", + "VitMatteConvStream": "<'transformers.models.vitmatte.modeling_vitmatte.VitMatteConvStream'>", + "VitMatteDetailCaptureModule": "<'transformers.models.vitmatte.modeling_vitmatte.VitMatteDetailCaptureModule'>", + "VitMatteFusionBlock": "<'transformers.models.vitmatte.modeling_vitmatte.VitMatteFusionBlock'>", + "VitMatteHead": "<'transformers.models.vitmatte.modeling_vitmatte.VitMatteHead'>", + "ViTMSNAttention": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNAttention'>", + "ViTMSNEmbeddings": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNEmbeddings'>", + "ViTMSNEncoder": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNEncoder'>", + "ViTMSNIntermediate": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNIntermediate'>", + "ViTMSNLayer": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNLayer'>", + "ViTMSNOutput": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNOutput'>", + "ViTMSNPatchEmbeddings": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNPatchEmbeddings'>", + "ViTMSNSelfAttention": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNSelfAttention'>", + "ViTMSNSelfOutput": "<'transformers.models.vit_msn.modeling_vit_msn.ViTMSNSelfOutput'>", + "ViTOutput": "<'transformers.models.vit.modeling_vit.ViTOutput'>", + "ViTPatchEmbeddings": "<'transformers.models.vit.modeling_vit.ViTPatchEmbeddings'>", + "ViTPooler": "<'transformers.models.vit.modeling_vit.ViTPooler'>", + "VitPoseBackboneAttention": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneAttention'>", + "VitPoseBackboneEmbeddings": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneEmbeddings'>", + "VitPoseBackboneEncoder": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneEncoder'>", + "VitPoseBackboneLayer": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneLayer'>", + "VitPoseBackboneMLP": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneMLP'>", + "VitPoseBackboneMoeMLP": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneMoeMLP'>", + "VitPoseBackbonePatchEmbeddings": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackbonePatchEmbeddings'>", + "VitPoseBackboneSelfAttention": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneSelfAttention'>", + "VitPoseBackboneSelfOutput": "<'transformers.models.vitpose_backbone.modeling_vitpose_backbone.VitPoseBackboneSelfOutput'>", + "VitPoseClassicDecoder": "<'transformers.models.vitpose.modeling_vitpose.VitPoseClassicDecoder'>", + "VitPoseSimpleDecoder": "<'transformers.models.vitpose.modeling_vitpose.VitPoseSimpleDecoder'>", + "VitsAttention": "<'transformers.models.vits.modeling_vits.VitsAttention'>", + "VitsConvFlow": "<'transformers.models.vits.modeling_vits.VitsConvFlow'>", + "VitsDilatedDepthSeparableConv": "<'transformers.models.vits.modeling_vits.VitsDilatedDepthSeparableConv'>", + "VitsDurationPredictor": "<'transformers.models.vits.modeling_vits.VitsDurationPredictor'>", + "VitsElementwiseAffine": "<'transformers.models.vits.modeling_vits.VitsElementwiseAffine'>", + "ViTSelfAttention": "<'transformers.models.vit.modeling_vit.ViTSelfAttention'>", + "ViTSelfOutput": "<'transformers.models.vit.modeling_vit.ViTSelfOutput'>", + "VitsEncoder": "<'transformers.models.vits.modeling_vits.VitsEncoder'>", + "VitsEncoderLayer": "<'transformers.models.vits.modeling_vits.VitsEncoderLayer'>", + "VitsFeedForward": "<'transformers.models.vits.modeling_vits.VitsFeedForward'>", + "VitsHifiGan": "<'transformers.models.vits.modeling_vits.VitsHifiGan'>", + "VitsPosteriorEncoder": "<'transformers.models.vits.modeling_vits.VitsPosteriorEncoder'>", + "VitsResidualCouplingBlock": "<'transformers.models.vits.modeling_vits.VitsResidualCouplingBlock'>", + "VitsResidualCouplingLayer": "<'transformers.models.vits.modeling_vits.VitsResidualCouplingLayer'>", + "VitsStochasticDurationPredictor": "<'transformers.models.vits.modeling_vits.VitsStochasticDurationPredictor'>", + "VitsTextEncoder": "<'transformers.models.vits.modeling_vits.VitsTextEncoder'>", + "VitsWaveNet": "<'transformers.models.vits.modeling_vits.VitsWaveNet'>", + "VivitAttention": "<'transformers.models.vivit.modeling_vivit.VivitAttention'>", + "VivitEmbeddings": "<'transformers.models.vivit.modeling_vivit.VivitEmbeddings'>", + "VivitEncoder": "<'transformers.models.vivit.modeling_vivit.VivitEncoder'>", + "VivitIntermediate": "<'transformers.models.vivit.modeling_vivit.VivitIntermediate'>", + "VivitLayer": "<'transformers.models.vivit.modeling_vivit.VivitLayer'>", + "VivitOutput": "<'transformers.models.vivit.modeling_vivit.VivitOutput'>", + "VivitPooler": "<'transformers.models.vivit.modeling_vivit.VivitPooler'>", + "VivitSelfAttention": "<'transformers.models.vivit.modeling_vivit.VivitSelfAttention'>", + "VivitSelfOutput": "<'transformers.models.vivit.modeling_vivit.VivitSelfOutput'>", + "VivitTubeletEmbeddings": "<'transformers.models.vivit.modeling_vivit.VivitTubeletEmbeddings'>", + "VJEPA2AttentivePooler": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2AttentivePooler'>", + "VJEPA2DropPath": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2DropPath'>", + "VJEPA2Embeddings": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2Embeddings'>", + "VJEPA2Encoder": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2Encoder'>", + "VJEPA2Layer": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2Layer'>", + "VJEPA2MLP": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2MLP'>", + "VJEPA2PatchEmbeddings3D": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PatchEmbeddings3D'>", + "VJEPA2PoolerCrossAttention": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PoolerCrossAttention'>", + "VJEPA2PoolerCrossAttentionLayer": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PoolerCrossAttentionLayer'>", + "VJEPA2PoolerSelfAttention": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PoolerSelfAttention'>", + "VJEPA2PoolerSelfAttentionLayer": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PoolerSelfAttentionLayer'>", + "VJEPA2Predictor": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2Predictor'>", + "VJEPA2PredictorEmbeddings": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2PredictorEmbeddings'>", + "VJEPA2RopeAttention": "<'transformers.models.vjepa2.modeling_vjepa2.VJEPA2RopeAttention'>", + "VoxtralAttention": "<'transformers.models.voxtral.modular_voxtral.VoxtralAttention'>", + "VoxtralEncoderLayer": "<'transformers.models.voxtral.modular_voxtral.VoxtralEncoderLayer'>", + "VoxtralMultiModalProjector": "<'transformers.models.voxtral.modular_voxtral.VoxtralMultiModalProjector'>", + "Wav2Vec2Adapter": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2Adapter'>", + "Wav2Vec2AdapterLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2AdapterLayer'>", + "Wav2Vec2Attention": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2Attention'>", + "Wav2Vec2AttnAdapterLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2AttnAdapterLayer'>", + "Wav2Vec2BertAdapter": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertAdapter'>", + "Wav2Vec2BertAdapterLayer": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertAdapterLayer'>", + "Wav2Vec2BertConvolutionModule": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertConvolutionModule'>", + "Wav2Vec2BertEncoder": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertEncoder'>", + "Wav2Vec2BertEncoderLayer": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertEncoderLayer'>", + "Wav2Vec2BertFeatureProjection": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertFeatureProjection'>", + "Wav2Vec2BertFeedForward": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertFeedForward'>", + "Wav2Vec2BertRelPositionalEmbedding": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertRelPositionalEmbedding'>", + "Wav2Vec2BertRotaryPositionalEmbedding": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertRotaryPositionalEmbedding'>", + "Wav2Vec2BertSelfAttention": "<'transformers.models.wav2vec2_bert.modeling_wav2vec2_bert.Wav2Vec2BertSelfAttention'>", + "Wav2Vec2ConformerAdapter": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerAdapter'>", + "Wav2Vec2ConformerAdapterLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerAdapterLayer'>", + "Wav2Vec2ConformerConvolutionModule": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerConvolutionModule'>", + "Wav2Vec2ConformerEncoder": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerEncoder'>", + "Wav2Vec2ConformerEncoderLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerEncoderLayer'>", + "Wav2Vec2ConformerFeatureEncoder": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerFeatureEncoder'>", + "Wav2Vec2ConformerFeatureProjection": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerFeatureProjection'>", + "Wav2Vec2ConformerFeedForward": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerFeedForward'>", + "Wav2Vec2ConformerGroupNormConvLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerGroupNormConvLayer'>", + "Wav2Vec2ConformerGumbelVectorQuantizer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerGumbelVectorQuantizer'>", + "Wav2Vec2ConformerLayerNormConvLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerLayerNormConvLayer'>", + "Wav2Vec2ConformerNoLayerNormConvLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerNoLayerNormConvLayer'>", + "Wav2Vec2ConformerPositionalConvEmbedding": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerPositionalConvEmbedding'>", + "Wav2Vec2ConformerRelPositionalEmbedding": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerRelPositionalEmbedding'>", + "Wav2Vec2ConformerRotaryPositionalEmbedding": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerRotaryPositionalEmbedding'>", + "Wav2Vec2ConformerSamePadLayer": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerSamePadLayer'>", + "Wav2Vec2ConformerSelfAttention": "<'transformers.models.wav2vec2_conformer.modeling_wav2vec2_conformer.Wav2Vec2ConformerSelfAttention'>", + "Wav2Vec2Encoder": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2Encoder'>", + "Wav2Vec2EncoderLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2EncoderLayer'>", + "Wav2Vec2EncoderLayerStableLayerNorm": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2EncoderLayerStableLayerNorm'>", + "Wav2Vec2EncoderStableLayerNorm": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2EncoderStableLayerNorm'>", + "Wav2Vec2FeatureEncoder": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2FeatureEncoder'>", + "Wav2Vec2FeatureExtractor": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2FeatureExtractor'>", + "Wav2Vec2FeatureProjection": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2FeatureProjection'>", + "Wav2Vec2FeedForward": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2FeedForward'>", + "Wav2Vec2GroupNormConvLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2GroupNormConvLayer'>", + "Wav2Vec2GumbelVectorQuantizer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2GumbelVectorQuantizer'>", + "Wav2Vec2LayerNormConvLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2LayerNormConvLayer'>", + "Wav2Vec2NoLayerNormConvLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2NoLayerNormConvLayer'>", + "Wav2Vec2PositionalConvEmbedding": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2PositionalConvEmbedding'>", + "Wav2Vec2SamePadLayer": "<'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2SamePadLayer'>", + "WavLMAdapter": "<'transformers.models.wavlm.modeling_wavlm.WavLMAdapter'>", + "WavLMAdapterLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMAdapterLayer'>", + "WavLMAttention": "<'transformers.models.wavlm.modeling_wavlm.WavLMAttention'>", + "WavLMEncoder": "<'transformers.models.wavlm.modeling_wavlm.WavLMEncoder'>", + "WavLMEncoderLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMEncoderLayer'>", + "WavLMEncoderLayerStableLayerNorm": "<'transformers.models.wavlm.modeling_wavlm.WavLMEncoderLayerStableLayerNorm'>", + "WavLMEncoderStableLayerNorm": "<'transformers.models.wavlm.modeling_wavlm.WavLMEncoderStableLayerNorm'>", + "WavLMFeatureEncoder": "<'transformers.models.wavlm.modeling_wavlm.WavLMFeatureEncoder'>", + "WavLMFeatureProjection": "<'transformers.models.wavlm.modeling_wavlm.WavLMFeatureProjection'>", + "WavLMFeedForward": "<'transformers.models.wavlm.modeling_wavlm.WavLMFeedForward'>", + "WavLMGroupNormConvLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMGroupNormConvLayer'>", + "WavLMGumbelVectorQuantizer": "<'transformers.models.wavlm.modeling_wavlm.WavLMGumbelVectorQuantizer'>", + "WavLMLayerNormConvLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMLayerNormConvLayer'>", + "WavLMNoLayerNormConvLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMNoLayerNormConvLayer'>", + "WavLMPositionalConvEmbedding": "<'transformers.models.wavlm.modeling_wavlm.WavLMPositionalConvEmbedding'>", + "WavLMSamePadLayer": "<'transformers.models.wavlm.modeling_wavlm.WavLMSamePadLayer'>", + "WeightStandardizedConv2d": "<'transformers.models.bit.modeling_bit.WeightStandardizedConv2d'>", + "WhisperAttention": "<'transformers.models.whisper.modeling_whisper.WhisperAttention'>", + "WhisperDecoder": "<'transformers.models.whisper.modeling_whisper.WhisperDecoder'>", + "WhisperDecoderLayer": "<'transformers.models.whisper.modeling_whisper.WhisperDecoderLayer'>", + "WhisperDecoderWrapper": "<'transformers.models.whisper.modeling_whisper.WhisperDecoderWrapper'>", + "WhisperEncoder": "<'transformers.models.whisper.modeling_whisper.WhisperEncoder'>", + "WhisperEncoderLayer": "<'transformers.models.whisper.modeling_whisper.WhisperEncoderLayer'>", + "WhisperPositionalEmbedding": "<'transformers.models.whisper.modeling_whisper.WhisperPositionalEmbedding'>", + "XCLIPAttention": "<'transformers.models.x_clip.modeling_x_clip.XCLIPAttention'>", + "XCLIPCrossAttention": "<'transformers.models.x_clip.modeling_x_clip.XCLIPCrossAttention'>", + "XCLIPDropPath": "<'transformers.models.x_clip.modeling_x_clip.XCLIPDropPath'>", + "XCLIPEncoder": "<'transformers.models.x_clip.modeling_x_clip.XCLIPEncoder'>", + "XCLIPEncoderLayer": "<'transformers.models.x_clip.modeling_x_clip.XCLIPEncoderLayer'>", + "XCLIPMLP": "<'transformers.models.x_clip.modeling_x_clip.XCLIPMLP'>", + "XCLIPMultiframeIntegrationTransformer": "<'transformers.models.x_clip.modeling_x_clip.XCLIPMultiframeIntegrationTransformer'>", + "XCLIPPromptGenerator": "<'transformers.models.x_clip.modeling_x_clip.XCLIPPromptGenerator'>", + "XCLIPTextEmbeddings": "<'transformers.models.x_clip.modeling_x_clip.XCLIPTextEmbeddings'>", + "XCLIPTextTransformer": "<'transformers.models.x_clip.modeling_x_clip.XCLIPTextTransformer'>", + "XCLIPVisionEmbeddings": "<'transformers.models.x_clip.modeling_x_clip.XCLIPVisionEmbeddings'>", + "XCLIPVisionEncoder": "<'transformers.models.x_clip.modeling_x_clip.XCLIPVisionEncoder'>", + "XCLIPVisionEncoderLayer": "<'transformers.models.x_clip.modeling_x_clip.XCLIPVisionEncoderLayer'>", + "XCLIPVisionTransformer": "<'transformers.models.x_clip.modeling_x_clip.XCLIPVisionTransformer'>", + "XGLMAttention": "<'transformers.models.xglm.modeling_xglm.XGLMAttention'>", + "XGLMDecoderLayer": "<'transformers.models.xglm.modeling_xglm.XGLMDecoderLayer'>", + "XGLMScaledWordEmbedding": "<'transformers.models.xglm.modeling_xglm.XGLMScaledWordEmbedding'>", + "XGLMSinusoidalPositionalEmbedding": "<'transformers.models.xglm.modeling_xglm.XGLMSinusoidalPositionalEmbedding'>", + "XLMPoolerAnswerClass": "<'transformers.models.xlm.modeling_xlm.XLMPoolerAnswerClass'>", + "XLMPoolerEndLogits": "<'transformers.models.xlm.modeling_xlm.XLMPoolerEndLogits'>", + "XLMPoolerStartLogits": "<'transformers.models.xlm.modeling_xlm.XLMPoolerStartLogits'>", + "XLMPredLayer": "<'transformers.models.xlm.modeling_xlm.XLMPredLayer'>", + "XLMProphetNetAttention": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetAttention'>", + "XLMProphetNetDecoderLayer": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetDecoderLayer'>", + "XLMProphetNetDecoderWrapper": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetDecoderWrapper'>", + "XLMProphetNetEncoderLayer": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetEncoderLayer'>", + "XLMProphetNetFeedForward": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetFeedForward'>", + "XLMProphetNetNgramSelfAttention": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetNgramSelfAttention'>", + "XLMProphetNetPositionalEmbeddings": "<'transformers.models.deprecated.xlm_prophetnet.modeling_xlm_prophetnet.XLMProphetNetPositionalEmbeddings'>", + "XLMRobertaAttention": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaAttention'>", + "XLMRobertaClassificationHead": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaClassificationHead'>", + "XLMRobertaEmbeddings": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaEmbeddings'>", + "XLMRobertaEncoder": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaEncoder'>", + "XLMRobertaIntermediate": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaIntermediate'>", + "XLMRobertaLayer": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaLayer'>", + "XLMRobertaLMHead": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaLMHead'>", + "XLMRobertaOutput": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaOutput'>", + "XLMRobertaPooler": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaPooler'>", + "XLMRobertaSdpaSelfAttention": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaSdpaSelfAttention'>", + "XLMRobertaSelfAttention": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaSelfAttention'>", + "XLMRobertaSelfOutput": "<'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaSelfOutput'>", + "XLMRobertaXLAttention": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLAttention'>", + "XLMRobertaXLClassificationHead": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLClassificationHead'>", + "XLMRobertaXLEmbeddings": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLEmbeddings'>", + "XLMRobertaXLEncoder": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLEncoder'>", + "XLMRobertaXLIntermediate": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLIntermediate'>", + "XLMRobertaXLLayer": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLLayer'>", + "XLMRobertaXLLMHead": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLLMHead'>", + "XLMRobertaXLOutput": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLOutput'>", + "XLMRobertaXLPooler": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLPooler'>", + "XLMRobertaXLSdpaSelfAttention": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLSdpaSelfAttention'>", + "XLMRobertaXLSelfAttention": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLSelfAttention'>", + "XLMRobertaXLSelfOutput": "<'transformers.models.xlm_roberta_xl.modeling_xlm_roberta_xl.XLMRobertaXLSelfOutput'>", + "XLMSequenceSummary": "<'transformers.models.xlm.modeling_xlm.XLMSequenceSummary'>", + "XLMSQuADHead": "<'transformers.models.xlm.modeling_xlm.XLMSQuADHead'>", + "XLNetFeedForward": "<'transformers.models.xlnet.modeling_xlnet.XLNetFeedForward'>", + "XLNetLayer": "<'transformers.models.xlnet.modeling_xlnet.XLNetLayer'>", + "XLNetPoolerAnswerClass": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerAnswerClass'>", + "XLNetPoolerEndLogits": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerEndLogits'>", + "XLNetPoolerStartLogits": "<'transformers.models.xlnet.modeling_xlnet.XLNetPoolerStartLogits'>", + "XLNetRelativeAttention": "<'transformers.models.xlnet.modeling_xlnet.XLNetRelativeAttention'>", + "XLNetSequenceSummary": "<'transformers.models.xlnet.modeling_xlnet.XLNetSequenceSummary'>", + "xLSTMBackend": "<'transformers.models.xlstm.modeling_xlstm.xLSTMBackend'>", + "xLSTMBlock": "<'transformers.models.xlstm.modeling_xlstm.xLSTMBlock'>", + "xLSTMFeedForward": "<'transformers.models.xlstm.modeling_xlstm.xLSTMFeedForward'>", + "xLSTMLayer": "<'transformers.models.xlstm.modeling_xlstm.xLSTMLayer'>", + "xLSTMMultiHeadLayerNorm": "<'transformers.models.xlstm.modeling_xlstm.xLSTMMultiHeadLayerNorm'>", + "xLSTMRMSNorm": "<'transformers.models.xlstm.modeling_xlstm.xLSTMRMSNorm'>", + "XmodAdapter": "<'transformers.models.xmod.modeling_xmod.XmodAdapter'>", + "XmodAttention": "<'transformers.models.xmod.modeling_xmod.XmodAttention'>", + "XmodClassificationHead": "<'transformers.models.xmod.modeling_xmod.XmodClassificationHead'>", + "XmodEmbeddings": "<'transformers.models.xmod.modeling_xmod.XmodEmbeddings'>", + "XmodEncoder": "<'transformers.models.xmod.modeling_xmod.XmodEncoder'>", + "XmodIntermediate": "<'transformers.models.xmod.modeling_xmod.XmodIntermediate'>", + "XmodLayer": "<'transformers.models.xmod.modeling_xmod.XmodLayer'>", + "XmodLMHead": "<'transformers.models.xmod.modeling_xmod.XmodLMHead'>", + "XmodOutput": "<'transformers.models.xmod.modeling_xmod.XmodOutput'>", + "XmodPooler": "<'transformers.models.xmod.modeling_xmod.XmodPooler'>", + "XmodSelfAttention": "<'transformers.models.xmod.modeling_xmod.XmodSelfAttention'>", + "XmodSelfOutput": "<'transformers.models.xmod.modeling_xmod.XmodSelfOutput'>", + "XPathEmbeddings": "<'transformers.models.markuplm.modeling_markuplm.XPathEmbeddings'>", + "YolosAttention": "<'transformers.models.yolos.modeling_yolos.YolosAttention'>", + "YolosEmbeddings": "<'transformers.models.yolos.modeling_yolos.YolosEmbeddings'>", + "YolosEncoder": "<'transformers.models.yolos.modeling_yolos.YolosEncoder'>", + "YolosIntermediate": "<'transformers.models.yolos.modeling_yolos.YolosIntermediate'>", + "YolosLayer": "<'transformers.models.yolos.modeling_yolos.YolosLayer'>", + "YolosMLPPredictionHead": "<'transformers.models.yolos.modeling_yolos.YolosMLPPredictionHead'>", + "YolosOutput": "<'transformers.models.yolos.modeling_yolos.YolosOutput'>", + "YolosPatchEmbeddings": "<'transformers.models.yolos.modeling_yolos.YolosPatchEmbeddings'>", + "YolosPooler": "<'transformers.models.yolos.modeling_yolos.YolosPooler'>", + "YolosSelfAttention": "<'transformers.models.yolos.modeling_yolos.YolosSelfAttention'>", + "YolosSelfOutput": "<'transformers.models.yolos.modeling_yolos.YolosSelfOutput'>", + "YosoAttention": "<'transformers.models.yoso.modeling_yoso.YosoAttention'>", + "YosoClassificationHead": "<'transformers.models.yoso.modeling_yoso.YosoClassificationHead'>", + "YosoEmbeddings": "<'transformers.models.yoso.modeling_yoso.YosoEmbeddings'>", + "YosoEncoder": "<'transformers.models.yoso.modeling_yoso.YosoEncoder'>", + "YosoIntermediate": "<'transformers.models.yoso.modeling_yoso.YosoIntermediate'>", + "YosoLayer": "<'transformers.models.yoso.modeling_yoso.YosoLayer'>", + "YosoLMPredictionHead": "<'transformers.models.yoso.modeling_yoso.YosoLMPredictionHead'>", + "YosoOnlyMLMHead": "<'transformers.models.yoso.modeling_yoso.YosoOnlyMLMHead'>", + "YosoOutput": "<'transformers.models.yoso.modeling_yoso.YosoOutput'>", + "YosoPredictionHeadTransform": "<'transformers.models.yoso.modeling_yoso.YosoPredictionHeadTransform'>", + "YosoSelfAttention": "<'transformers.models.yoso.modeling_yoso.YosoSelfAttention'>", + "YosoSelfOutput": "<'transformers.models.yoso.modeling_yoso.YosoSelfOutput'>", + "Zamba2Attention": "<'transformers.models.zamba2.modular_zamba2.Zamba2Attention'>", + "Zamba2AttentionDecoderLayer": "<'transformers.models.zamba2.modular_zamba2.Zamba2AttentionDecoderLayer'>", + "Zamba2HybridLayer": "<'transformers.models.zamba2.modular_zamba2.Zamba2HybridLayer'>", + "Zamba2MambaDecoderLayer": "<'transformers.models.zamba2.modular_zamba2.Zamba2MambaDecoderLayer'>", + "Zamba2MambaMixer": "<'transformers.models.zamba2.modular_zamba2.Zamba2MambaMixer'>", + "Zamba2MLP": "<'transformers.models.zamba2.modular_zamba2.Zamba2MLP'>", + "Zamba2RMSNorm": "<'transformers.models.zamba2.modular_zamba2.Zamba2RMSNorm'>", + "Zamba2RMSNormGated": "<'transformers.models.zamba2.modular_zamba2.Zamba2RMSNormGated'>", + "Zamba2RotaryEmbedding": "<'transformers.models.zamba2.modular_zamba2.Zamba2RotaryEmbedding'>", + "ZambaAttention": "<'transformers.models.zamba.modeling_zamba.ZambaAttention'>", + "ZambaAttentionDecoderLayer": "<'transformers.models.zamba.modeling_zamba.ZambaAttentionDecoderLayer'>", + "ZambaHybridLayer": "<'transformers.models.zamba.modeling_zamba.ZambaHybridLayer'>", + "ZambaMambaDecoderLayer": "<'transformers.models.zamba.modeling_zamba.ZambaMambaDecoderLayer'>", + "ZambaMambaMixer": "<'transformers.models.zamba.modeling_zamba.ZambaMambaMixer'>", + "ZambaMLP": "<'transformers.models.zamba.modeling_zamba.ZambaMLP'>", + "ZambaRMSNorm": "<'transformers.models.zamba.modeling_zamba.ZambaRMSNorm'>", + "ZoeDepthAttractorLayer": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthAttractorLayer'>", + "ZoeDepthAttractorLayerUnnormed": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthAttractorLayerUnnormed'>", + "ZoeDepthConditionalLogBinomialSoftmax": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthConditionalLogBinomialSoftmax'>", + "ZoeDepthFeatureFusionLayer": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthFeatureFusionLayer'>", + "ZoeDepthFeatureFusionStage": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthFeatureFusionStage'>", + "ZoeDepthMetricDepthEstimationHead": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthMetricDepthEstimationHead'>", + "ZoeDepthMLPClassifier": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthMLPClassifier'>", + "ZoeDepthMultiheadAttention": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthMultiheadAttention'>", + "ZoeDepthMultipleMetricDepthEstimationHeads": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthMultipleMetricDepthEstimationHeads'>", + "ZoeDepthNeck": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthNeck'>", + "ZoeDepthPatchTransformerEncoder": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthPatchTransformerEncoder'>", + "ZoeDepthPreActResidualLayer": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthPreActResidualLayer'>", + "ZoeDepthProjector": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthProjector'>", + "ZoeDepthReassembleLayer": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthReassembleLayer'>", + "ZoeDepthReassembleStage": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthReassembleStage'>", + "ZoeDepthRelativeDepthEstimationHead": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthRelativeDepthEstimationHead'>", + "ZoeDepthSeedBinRegressor": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthSeedBinRegressor'>", + "ZoeDepthTransformerEncoderLayer": "<'transformers.models.zoedepth.modeling_zoedepth.ZoeDepthTransformerEncoderLayer'>" +} \ No newline at end of file diff --git a/tests/subclasses_test.py b/tests/subclasses_test.py index 131601c..20c1eb5 100644 --- a/tests/subclasses_test.py +++ b/tests/subclasses_test.py @@ -1,10 +1,10 @@ # SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 # + from mir.gatherers.transformers import GatherLoop from mir.json_io import write_json_file - transformers_packages = GatherLoop() from mir.gatherers.diffusers import GatherLoop @@ -13,4 +13,18 @@ packages = {"transformers": transformers_packages.model_db, "diffusers": diffusers_packages.model_db} -write_json_file(folder_path_named="tests", file_name="test.json", data=packages) +write_json_file(folder_path_named="tests", file_name=".test.json", data=packages) + + +# def test_two(): +# from transformers import AltCLIPModel +# from torch import nn +# from mir.lookups import find_nn_modules + +# modules = find_nn_modules(AltCLIPModel) +# for name, module in modules.items(): +# nn.ModuleList(module) + + +# if __name__ == "__main__": +# test_two() diff --git a/tests/test_nn_lookup.py b/tests/test_nn_lookup.py new file mode 100644 index 0000000..d311784 --- /dev/null +++ b/tests/test_nn_lookup.py @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: MPL-2.0 AND LicenseRef-Commons-Clause-License-Condition-1.0 +# + +from typing import Callable +from mir.lookups import get_source_of, nn_source_tree, get_import_chain +from mir.gatherers.transformers import AUTO_MAP +import torch +from torch import nn +from transformers import Aimv2TextConfig +from mir.json_io import write_json_file + + +@torch.no_grad +def test_lookups(): + lookups = [] + for config, model in AUTO_MAP.items(): + if isinstance(model, tuple): + model: Callable = model[0] # type: ignore + try: + model_source = get_source_of(model) + except AttributeError as _: + print(model.__name__) + continue + try: + if call_data := nn_source_tree(model_source): + print(call_data) + model_path = model.__module__ + try: + module_obj: Callable = get_import_chain(f"{model_path}.{call_data['class_name']}") + except AttributeError as _: + print(model.__name__) + continue + try: + config_obj = config() + except (TypeError, ImportError) as _: + print(model.__name__) + continue + if hasattr(config_obj, call_data["config_attribute"]): + config_attribute = getattr(config_obj, call_data["config_attribute"]) + elif call_data["class_name"] == "Aimv2EncoderLayer": + config_obj = Aimv2TextConfig() + config_attribute = getattr(config_obj, call_data["config_attribute"]) + try: + lookups.append(nn.ModuleList(module_obj(config_obj) for _ in range(config_attribute))) + except TypeError as _: + print(f"error with {call_data['class_name']}") + except AttributeError as _: + print(f"no attribute for with {call_data['class_name']} config.{config_attribute}") + except KeyError as _: + print(f"no attribute for with {call_data['class_name']} config.{config_attribute}") + print(model.__name__) + except IndexError as _: + print(model.__name__) + with open("somesuch.txt", mode="w", encoding="utf-8") as i: + i.write(str(lookups)) + + +test_lookups() diff --git a/uv.lock b/uv.lock index 3616533..048c475 100644 --- a/uv.lock +++ b/uv.lock @@ -2,8 +2,15 @@ version = 1 revision = 3 requires-python = ">=3.11" resolution-markers = [ - "python_full_version >= '3.12'", - "python_full_version < '3.12'", + "python_full_version >= '3.14' and sys_platform == 'win32'", + "python_full_version >= '3.14' and sys_platform == 'emscripten'", + "python_full_version >= '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'", + "python_full_version >= '3.12' and python_full_version < '3.14' and sys_platform == 'win32'", + "python_full_version < '3.12' and sys_platform == 'win32'", + "python_full_version >= '3.12' and python_full_version < '3.14' and sys_platform == 'emscripten'", + "python_full_version < '3.12' and sys_platform == 'emscripten'", + "python_full_version >= '3.12' and python_full_version < '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'", + "python_full_version < '3.12' and sys_platform != 'emscripten' and sys_platform != 'win32'", ] [[package]] @@ -17,15 +24,15 @@ wheels = [ [[package]] name = "anyio" -version = "4.12.0" +version = "4.12.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "idna" }, { name = "typing-extensions", marker = "python_full_version < '3.13'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/16/ce/8a777047513153587e5434fd752e89334ac33e379aa3497db860eeb60377/anyio-4.12.0.tar.gz", hash = "sha256:73c693b567b0c55130c104d0b43a9baf3aa6a31fc6110116509f27bf75e21ec0", size = 228266, upload-time = "2025-11-28T23:37:38.911Z" } +sdist = { url = "https://files.pythonhosted.org/packages/96/f0/5eb65b2bb0d09ac6776f2eb54adee6abe8228ea05b20a5ad0e4945de8aac/anyio-4.12.1.tar.gz", hash = "sha256:41cfcc3a4c85d3f05c932da7c26d0201ac36f72abd4435ba90d0464a3ffed703", size = 228685, upload-time = "2026-01-06T11:45:21.246Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/7f/9c/36c5c37947ebfb8c7f22e0eb6e4d188ee2d53aa3880f3f2744fb894f0cb1/anyio-4.12.0-py3-none-any.whl", hash = "sha256:dad2376a628f98eeca4881fc56cd06affd18f659b17a747d3ff0307ced94b1bb", size = 113362, upload-time = "2025-11-28T23:36:57.897Z" }, + { url = "https://files.pythonhosted.org/packages/38/0e/27be9fdef66e72d64c0cdc3cc2823101b80585f8119b5c112c2e8f5f7dab/anyio-4.12.1-py3-none-any.whl", hash = "sha256:d405828884fc140aa80a3c667b8beed277f1dfedec42ba031bd6ac3db606ab6c", size = 113592, upload-time = "2026-01-06T11:45:19.497Z" }, ] [[package]] @@ -145,10 +152,34 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" }, ] +[[package]] +name = "cuda-bindings" +version = "12.9.4" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "cuda-pathfinder", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/45/e7/b47792cc2d01c7e1d37c32402182524774dadd2d26339bd224e0e913832e/cuda_bindings-12.9.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c912a3d9e6b6651853eed8eed96d6800d69c08e94052c292fec3f282c5a817c9", size = 12210593, upload-time = "2025-10-21T14:51:36.574Z" }, + { url = "https://files.pythonhosted.org/packages/a9/c1/dabe88f52c3e3760d861401bb994df08f672ec893b8f7592dc91626adcf3/cuda_bindings-12.9.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fda147a344e8eaeca0c6ff113d2851ffca8f7dfc0a6c932374ee5c47caa649c8", size = 12151019, upload-time = "2025-10-21T14:51:43.167Z" }, + { url = "https://files.pythonhosted.org/packages/63/56/e465c31dc9111be3441a9ba7df1941fe98f4aa6e71e8788a3fb4534ce24d/cuda_bindings-12.9.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:32bdc5a76906be4c61eb98f546a6786c5773a881f3b166486449b5d141e4a39f", size = 11906628, upload-time = "2025-10-21T14:51:49.905Z" }, + { url = "https://files.pythonhosted.org/packages/a3/84/1e6be415e37478070aeeee5884c2022713c1ecc735e6d82d744de0252eee/cuda_bindings-12.9.4-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:56e0043c457a99ac473ddc926fe0dc4046694d99caef633e92601ab52cbe17eb", size = 11925991, upload-time = "2025-10-21T14:51:56.535Z" }, + { url = "https://files.pythonhosted.org/packages/d1/af/6dfd8f2ed90b1d4719bc053ff8940e494640fe4212dc3dd72f383e4992da/cuda_bindings-12.9.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8b72ee72a9cc1b531db31eebaaee5c69a8ec3500e32c6933f2d3b15297b53686", size = 11922703, upload-time = "2025-10-21T14:52:03.585Z" }, + { url = "https://files.pythonhosted.org/packages/6c/19/90ac264acc00f6df8a49378eedec9fd2db3061bf9263bf9f39fd3d8377c3/cuda_bindings-12.9.4-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d80bffc357df9988dca279734bc9674c3934a654cab10cadeed27ce17d8635ee", size = 11924658, upload-time = "2025-10-21T14:52:10.411Z" }, +] + +[[package]] +name = "cuda-pathfinder" +version = "1.3.3" +source = { registry = "https://pypi.org/simple" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0b/02/4dbe7568a42e46582248942f54dc64ad094769532adbe21e525e4edf7bc4/cuda_pathfinder-1.3.3-py3-none-any.whl", hash = "sha256:9984b664e404f7c134954a771be8775dfd6180ea1e1aef4a5a37d4be05d9bbb1", size = 27154, upload-time = "2025-12-04T22:35:08.996Z" }, +] + [[package]] name = "diffusers" version = "0.37.0.dev0" -source = { git = "https://github.com/huggingface/diffusers#5ffb65803d0ddc5e3298c35df638ceed5e580922" } +source = { git = "https://github.com/huggingface/diffusers#e8e88ff2ce3c8706883f4a90b5b2c023d213625a" } dependencies = [ { name = "filelock" }, { name = "httpx" }, @@ -163,20 +194,20 @@ dependencies = [ [[package]] name = "filelock" -version = "3.20.2" +version = "3.20.3" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/c1/e0/a75dbe4bca1e7d41307323dad5ea2efdd95408f74ab2de8bd7dba9b51a1a/filelock-3.20.2.tar.gz", hash = "sha256:a2241ff4ddde2a7cebddf78e39832509cb045d18ec1a09d7248d6bfc6bfbbe64", size = 19510, upload-time = "2026-01-02T15:33:32.582Z" } +sdist = { url = "https://files.pythonhosted.org/packages/1d/65/ce7f1b70157833bf3cb851b556a37d4547ceafc158aa9b34b36782f23696/filelock-3.20.3.tar.gz", hash = "sha256:18c57ee915c7ec61cff0ecf7f0f869936c7c30191bb0cf406f1341778d0834e1", size = 19485, upload-time = "2026-01-09T17:55:05.421Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/9a/30/ab407e2ec752aa541704ed8f93c11e2a5d92c168b8a755d818b74a3c5c2d/filelock-3.20.2-py3-none-any.whl", hash = "sha256:fbba7237d6ea277175a32c54bb71ef814a8546d8601269e1bfc388de333974e8", size = 16697, upload-time = "2026-01-02T15:33:31.133Z" }, + { url = "https://files.pythonhosted.org/packages/b5/36/7fb70f04bf00bc646cd5bb45aa9eddb15e19437a28b8fb2b4a5249fac770/filelock-3.20.3-py3-none-any.whl", hash = "sha256:4b0dda527ee31078689fc205ec4f1c1bf7d56cf88b6dc9426c4f230e46c2dce1", size = 16701, upload-time = "2026-01-09T17:55:04.334Z" }, ] [[package]] name = "fsspec" -version = "2025.12.0" +version = "2026.1.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/b6/27/954057b0d1f53f086f681755207dda6de6c660ce133c829158e8e8fe7895/fsspec-2025.12.0.tar.gz", hash = "sha256:c505de011584597b1060ff778bb664c1bc022e87921b0e4f10cc9c44f9635973", size = 309748, upload-time = "2025-12-03T15:23:42.687Z" } +sdist = { url = "https://files.pythonhosted.org/packages/d5/7d/5df2650c57d47c57232af5ef4b4fdbff182070421e405e0d62c6cdbfaa87/fsspec-2026.1.0.tar.gz", hash = "sha256:e987cb0496a0d81bba3a9d1cee62922fb395e7d4c3b575e57f547953334fe07b", size = 310496, upload-time = "2026-01-09T15:21:35.562Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/51/c7/b64cae5dba3a1b138d7123ec36bb5ccd39d39939f18454407e5468f4763f/fsspec-2025.12.0-py3-none-any.whl", hash = "sha256:8bf1fe301b7d8acfa6e8571e3b1c3d158f909666642431cc78a1b7b4dbc5ec5b", size = 201422, upload-time = "2025-12-03T15:23:41.434Z" }, + { url = "https://files.pythonhosted.org/packages/01/c9/97cc5aae1648dcb851958a3ddf73ccd7dbe5650d95203ecb4d7720b4cdbf/fsspec-2026.1.0-py3-none-any.whl", hash = "sha256:cb76aa913c2285a3b49bdd5fc55b1d7c708d7208126b60f2eb8194fe1b4cbdcc", size = 201838, upload-time = "2026-01-09T15:21:34.041Z" }, ] [[package]] @@ -259,7 +290,7 @@ wheels = [ [[package]] name = "huggingface-hub" -version = "1.2.3" +version = "1.3.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "filelock" }, @@ -273,9 +304,9 @@ dependencies = [ { name = "typer-slim" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/a7/c8/9cd2fcb670ba0e708bfdf95a1177b34ca62de2d3821df0773bc30559af80/huggingface_hub-1.2.3.tar.gz", hash = "sha256:4ba57f17004fd27bb176a6b7107df579865d4cde015112db59184c51f5602ba7", size = 614605, upload-time = "2025-12-12T15:31:42.161Z" } +sdist = { url = "https://files.pythonhosted.org/packages/02/c3/544cd4cdd4b3c6de8591b56bb69efc3682e9ac81e36135c02e909dd98c5b/huggingface_hub-1.3.3.tar.gz", hash = "sha256:f8be6f468da4470db48351e8c77d6d8115dff9b3daeb30276e568767b1ff7574", size = 627649, upload-time = "2026-01-22T13:59:46.931Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/df/8d/7ca723a884d55751b70479b8710f06a317296b1fa1c1dec01d0420d13e43/huggingface_hub-1.2.3-py3-none-any.whl", hash = "sha256:c9b7a91a9eedaa2149cdc12bdd8f5a11780e10de1f1024718becf9e41e5a4642", size = 520953, upload-time = "2025-12-12T15:31:40.339Z" }, + { url = "https://files.pythonhosted.org/packages/48/e8/0d032698916b9773b710c46e3b8e0154fc34cd017b151cc316c84c6c34fe/huggingface_hub-1.3.3-py3-none-any.whl", hash = "sha256:44af7b62380efc87c1c3bde7e1bf0661899b5bdfca1fc60975c61ee68410e10e", size = 536604, upload-time = "2026-01-22T13:59:45.391Z" }, ] [package.optional-dependencies] @@ -426,6 +457,7 @@ dependencies = [ { name = "diffusers" }, { name = "ftfy" }, { name = "huggingface-hub", extra = ["hf-xet"] }, + { name = "numpy" }, { name = "pydantic" }, { name = "sentencepiece" }, { name = "tokenizers" }, @@ -450,6 +482,7 @@ requires-dist = [ { name = "diffusers", git = "https://github.com/huggingface/diffusers" }, { name = "ftfy", specifier = ">=6.3.1" }, { name = "huggingface-hub", extras = ["hf-xet"], specifier = ">=1.1.7" }, + { name = "numpy", specifier = ">=2.4.1" }, { name = "pydantic", specifier = ">=2.12.5" }, { name = "sentencepiece", specifier = ">=0.2.1" }, { name = "tokenizers", specifier = ">=0.22.1" }, @@ -497,81 +530,81 @@ wheels = [ [[package]] name = "numpy" -version = "2.4.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/a4/7a/6a3d14e205d292b738db449d0de649b373a59edb0d0b4493821d0a3e8718/numpy-2.4.0.tar.gz", hash = "sha256:6e504f7b16118198f138ef31ba24d985b124c2c469fe8467007cf30fd992f934", size = 20685720, upload-time = "2025-12-20T16:18:19.023Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/26/7e/7bae7cbcc2f8132271967aa03e03954fc1e48aa1f3bf32b29ca95fbef352/numpy-2.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:316b2f2584682318539f0bcaca5a496ce9ca78c88066579ebd11fd06f8e4741e", size = 16940166, upload-time = "2025-12-20T16:15:43.434Z" }, - { url = "https://files.pythonhosted.org/packages/0f/27/6c13f5b46776d6246ec884ac5817452672156a506d08a1f2abb39961930a/numpy-2.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a2718c1de8504121714234b6f8241d0019450353276c88b9453c9c3d92e101db", size = 12641781, upload-time = "2025-12-20T16:15:45.701Z" }, - { url = "https://files.pythonhosted.org/packages/14/1c/83b4998d4860d15283241d9e5215f28b40ac31f497c04b12fa7f428ff370/numpy-2.4.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:21555da4ec4a0c942520ead42c3b0dc9477441e085c42b0fbdd6a084869a6f6b", size = 5470247, upload-time = "2025-12-20T16:15:47.943Z" }, - { url = "https://files.pythonhosted.org/packages/54/08/cbce72c835d937795571b0464b52069f869c9e78b0c076d416c5269d2718/numpy-2.4.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:413aa561266a4be2d06cd2b9665e89d9f54c543f418773076a76adcf2af08bc7", size = 6799807, upload-time = "2025-12-20T16:15:49.795Z" }, - { url = "https://files.pythonhosted.org/packages/ff/be/2e647961cd8c980591d75cdcd9e8f647d69fbe05e2a25613dc0a2ea5fb1a/numpy-2.4.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0feafc9e03128074689183031181fac0897ff169692d8492066e949041096548", size = 14701992, upload-time = "2025-12-20T16:15:51.615Z" }, - { url = "https://files.pythonhosted.org/packages/a2/fb/e1652fb8b6fd91ce6ed429143fe2e01ce714711e03e5b762615e7b36172c/numpy-2.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a8fdfed3deaf1928fb7667d96e0567cdf58c2b370ea2ee7e586aa383ec2cb346", size = 16646871, upload-time = "2025-12-20T16:15:54.129Z" }, - { url = "https://files.pythonhosted.org/packages/62/23/d841207e63c4322842f7cd042ae981cffe715c73376dcad8235fb31debf1/numpy-2.4.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:e06a922a469cae9a57100864caf4f8a97a1026513793969f8ba5b63137a35d25", size = 16487190, upload-time = "2025-12-20T16:15:56.147Z" }, - { url = "https://files.pythonhosted.org/packages/bc/a0/6a842c8421ebfdec0a230e65f61e0dabda6edbef443d999d79b87c273965/numpy-2.4.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:927ccf5cd17c48f801f4ed43a7e5673a2724bd2171460be3e3894e6e332ef83a", size = 18580762, upload-time = "2025-12-20T16:15:58.524Z" }, - { url = "https://files.pythonhosted.org/packages/0a/d1/c79e0046641186f2134dde05e6181825b911f8bdcef31b19ddd16e232847/numpy-2.4.0-cp311-cp311-win32.whl", hash = "sha256:882567b7ae57c1b1a0250208cc21a7976d8cbcc49d5a322e607e6f09c9e0bd53", size = 6233359, upload-time = "2025-12-20T16:16:00.938Z" }, - { url = "https://files.pythonhosted.org/packages/fc/f0/74965001d231f28184d6305b8cdc1b6fcd4bf23033f6cb039cfe76c9fca7/numpy-2.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:8b986403023c8f3bf8f487c2e6186afda156174d31c175f747d8934dfddf3479", size = 12601132, upload-time = "2025-12-20T16:16:02.484Z" }, - { url = "https://files.pythonhosted.org/packages/65/32/55408d0f46dfebce38017f5bd931affa7256ad6beac1a92a012e1fbc67a7/numpy-2.4.0-cp311-cp311-win_arm64.whl", hash = "sha256:3f3096405acc48887458bbf9f6814d43785ac7ba2a57ea6442b581dedbc60ce6", size = 10573977, upload-time = "2025-12-20T16:16:04.77Z" }, - { url = "https://files.pythonhosted.org/packages/8b/ff/f6400ffec95de41c74b8e73df32e3fff1830633193a7b1e409be7fb1bb8c/numpy-2.4.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2a8b6bb8369abefb8bd1801b054ad50e02b3275c8614dc6e5b0373c305291037", size = 16653117, upload-time = "2025-12-20T16:16:06.709Z" }, - { url = "https://files.pythonhosted.org/packages/fd/28/6c23e97450035072e8d830a3c411bf1abd1f42c611ff9d29e3d8f55c6252/numpy-2.4.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2e284ca13d5a8367e43734148622caf0b261b275673823593e3e3634a6490f83", size = 12369711, upload-time = "2025-12-20T16:16:08.758Z" }, - { url = "https://files.pythonhosted.org/packages/bc/af/acbef97b630ab1bb45e6a7d01d1452e4251aa88ce680ac36e56c272120ec/numpy-2.4.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:49ff32b09f5aa0cd30a20c2b39db3e669c845589f2b7fc910365210887e39344", size = 5198355, upload-time = "2025-12-20T16:16:10.902Z" }, - { url = "https://files.pythonhosted.org/packages/c1/c8/4e0d436b66b826f2e53330adaa6311f5cac9871a5b5c31ad773b27f25a74/numpy-2.4.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:36cbfb13c152b1c7c184ddac43765db8ad672567e7bafff2cc755a09917ed2e6", size = 6545298, upload-time = "2025-12-20T16:16:12.607Z" }, - { url = "https://files.pythonhosted.org/packages/ef/27/e1f5d144ab54eac34875e79037011d511ac57b21b220063310cb96c80fbc/numpy-2.4.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:35ddc8f4914466e6fc954c76527aa91aa763682a4f6d73249ef20b418fe6effb", size = 14398387, upload-time = "2025-12-20T16:16:14.257Z" }, - { url = "https://files.pythonhosted.org/packages/67/64/4cb909dd5ab09a9a5d086eff9586e69e827b88a5585517386879474f4cf7/numpy-2.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dc578891de1db95b2a35001b695451767b580bb45753717498213c5ff3c41d63", size = 16363091, upload-time = "2025-12-20T16:16:17.32Z" }, - { url = "https://files.pythonhosted.org/packages/9d/9c/8efe24577523ec6809261859737cf117b0eb6fdb655abdfdc81b2e468ce4/numpy-2.4.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:98e81648e0b36e325ab67e46b5400a7a6d4a22b8a7c8e8bbfe20e7db7906bf95", size = 16176394, upload-time = "2025-12-20T16:16:19.524Z" }, - { url = "https://files.pythonhosted.org/packages/61/f0/1687441ece7b47a62e45a1f82015352c240765c707928edd8aef875d5951/numpy-2.4.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d57b5046c120561ba8fa8e4030fbb8b822f3063910fa901ffadf16e2b7128ad6", size = 18287378, upload-time = "2025-12-20T16:16:22.866Z" }, - { url = "https://files.pythonhosted.org/packages/d3/6f/f868765d44e6fc466467ed810ba9d8d6db1add7d4a748abfa2a4c99a3194/numpy-2.4.0-cp312-cp312-win32.whl", hash = "sha256:92190db305a6f48734d3982f2c60fa30d6b5ee9bff10f2887b930d7b40119f4c", size = 5955432, upload-time = "2025-12-20T16:16:25.06Z" }, - { url = "https://files.pythonhosted.org/packages/d4/b5/94c1e79fcbab38d1ca15e13777477b2914dd2d559b410f96949d6637b085/numpy-2.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:680060061adb2d74ce352628cb798cfdec399068aa7f07ba9fb818b2b3305f98", size = 12306201, upload-time = "2025-12-20T16:16:26.979Z" }, - { url = "https://files.pythonhosted.org/packages/70/09/c39dadf0b13bb0768cd29d6a3aaff1fb7c6905ac40e9aaeca26b1c086e06/numpy-2.4.0-cp312-cp312-win_arm64.whl", hash = "sha256:39699233bc72dd482da1415dcb06076e32f60eddc796a796c5fb6c5efce94667", size = 10308234, upload-time = "2025-12-20T16:16:29.417Z" }, - { url = "https://files.pythonhosted.org/packages/a7/0d/853fd96372eda07c824d24adf02e8bc92bb3731b43a9b2a39161c3667cc4/numpy-2.4.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a152d86a3ae00ba5f47b3acf3b827509fd0b6cb7d3259665e63dafbad22a75ea", size = 16649088, upload-time = "2025-12-20T16:16:31.421Z" }, - { url = "https://files.pythonhosted.org/packages/e3/37/cc636f1f2a9f585434e20a3e6e63422f70bfe4f7f6698e941db52ea1ac9a/numpy-2.4.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:39b19251dec4de8ff8496cd0806cbe27bf0684f765abb1f4809554de93785f2d", size = 12364065, upload-time = "2025-12-20T16:16:33.491Z" }, - { url = "https://files.pythonhosted.org/packages/ed/69/0b78f37ca3690969beee54103ce5f6021709134e8020767e93ba691a72f1/numpy-2.4.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:009bd0ea12d3c784b6639a8457537016ce5172109e585338e11334f6a7bb88ee", size = 5192640, upload-time = "2025-12-20T16:16:35.636Z" }, - { url = "https://files.pythonhosted.org/packages/1d/2a/08569f8252abf590294dbb09a430543ec8f8cc710383abfb3e75cc73aeda/numpy-2.4.0-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:5fe44e277225fd3dff6882d86d3d447205d43532c3627313d17e754fb3905a0e", size = 6541556, upload-time = "2025-12-20T16:16:37.276Z" }, - { url = "https://files.pythonhosted.org/packages/93/e9/a949885a4e177493d61519377952186b6cbfdf1d6002764c664ba28349b5/numpy-2.4.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f935c4493eda9069851058fa0d9e39dbf6286be690066509305e52912714dbb2", size = 14396562, upload-time = "2025-12-20T16:16:38.953Z" }, - { url = "https://files.pythonhosted.org/packages/99/98/9d4ad53b0e9ef901c2ef1d550d2136f5ac42d3fd2988390a6def32e23e48/numpy-2.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8cfa5f29a695cb7438965e6c3e8d06e0416060cf0d709c1b1c1653a939bf5c2a", size = 16351719, upload-time = "2025-12-20T16:16:41.503Z" }, - { url = "https://files.pythonhosted.org/packages/28/de/5f3711a38341d6e8dd619f6353251a0cdd07f3d6d101a8fd46f4ef87f895/numpy-2.4.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ba0cb30acd3ef11c94dc27fbfba68940652492bc107075e7ffe23057f9425681", size = 16176053, upload-time = "2025-12-20T16:16:44.552Z" }, - { url = "https://files.pythonhosted.org/packages/2a/5b/2a3753dc43916501b4183532e7ace862e13211042bceafa253afb5c71272/numpy-2.4.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:60e8c196cd82cbbd4f130b5290007e13e6de3eca79f0d4d38014769d96a7c475", size = 18277859, upload-time = "2025-12-20T16:16:47.174Z" }, - { url = "https://files.pythonhosted.org/packages/2c/c5/a18bcdd07a941db3076ef489d036ab16d2bfc2eae0cf27e5a26e29189434/numpy-2.4.0-cp313-cp313-win32.whl", hash = "sha256:5f48cb3e88fbc294dc90e215d86fbaf1c852c63dbdb6c3a3e63f45c4b57f7344", size = 5953849, upload-time = "2025-12-20T16:16:49.554Z" }, - { url = "https://files.pythonhosted.org/packages/4f/f1/719010ff8061da6e8a26e1980cf090412d4f5f8060b31f0c45d77dd67a01/numpy-2.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:a899699294f28f7be8992853c0c60741f16ff199205e2e6cdca155762cbaa59d", size = 12302840, upload-time = "2025-12-20T16:16:51.227Z" }, - { url = "https://files.pythonhosted.org/packages/f5/5a/b3d259083ed8b4d335270c76966cb6cf14a5d1b69e1a608994ac57a659e6/numpy-2.4.0-cp313-cp313-win_arm64.whl", hash = "sha256:9198f447e1dc5647d07c9a6bbe2063cc0132728cc7175b39dbc796da5b54920d", size = 10308509, upload-time = "2025-12-20T16:16:53.313Z" }, - { url = "https://files.pythonhosted.org/packages/31/01/95edcffd1bb6c0633df4e808130545c4f07383ab629ac7e316fb44fff677/numpy-2.4.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:74623f2ab5cc3f7c886add4f735d1031a1d2be4a4ae63c0546cfd74e7a31ddf6", size = 12491815, upload-time = "2025-12-20T16:16:55.496Z" }, - { url = "https://files.pythonhosted.org/packages/59/ea/5644b8baa92cc1c7163b4b4458c8679852733fa74ca49c942cfa82ded4e0/numpy-2.4.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:0804a8e4ab070d1d35496e65ffd3cf8114c136a2b81f61dfab0de4b218aacfd5", size = 5320321, upload-time = "2025-12-20T16:16:57.468Z" }, - { url = "https://files.pythonhosted.org/packages/26/4e/e10938106d70bc21319bd6a86ae726da37edc802ce35a3a71ecdf1fdfe7f/numpy-2.4.0-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:02a2038eb27f9443a8b266a66911e926566b5a6ffd1a689b588f7f35b81e7dc3", size = 6641635, upload-time = "2025-12-20T16:16:59.379Z" }, - { url = "https://files.pythonhosted.org/packages/b3/8d/a8828e3eaf5c0b4ab116924df82f24ce3416fa38d0674d8f708ddc6c8aac/numpy-2.4.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1889b3a3f47a7b5bee16bc25a2145bd7cb91897f815ce3499db64c7458b6d91d", size = 14456053, upload-time = "2025-12-20T16:17:01.768Z" }, - { url = "https://files.pythonhosted.org/packages/68/a1/17d97609d87d4520aa5ae2dcfb32305654550ac6a35effb946d303e594ce/numpy-2.4.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:85eef4cb5625c47ee6425c58a3502555e10f45ee973da878ac8248ad58c136f3", size = 16401702, upload-time = "2025-12-20T16:17:04.235Z" }, - { url = "https://files.pythonhosted.org/packages/18/32/0f13c1b2d22bea1118356b8b963195446f3af124ed7a5adfa8fdecb1b6ca/numpy-2.4.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:6dc8b7e2f4eb184b37655195f421836cfae6f58197b67e3ffc501f1333d993fa", size = 16242493, upload-time = "2025-12-20T16:17:06.856Z" }, - { url = "https://files.pythonhosted.org/packages/ae/23/48f21e3d309fbc137c068a1475358cbd3a901b3987dcfc97a029ab3068e2/numpy-2.4.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:44aba2f0cafd287871a495fb3163408b0bd25bbce135c6f621534a07f4f7875c", size = 18324222, upload-time = "2025-12-20T16:17:09.392Z" }, - { url = "https://files.pythonhosted.org/packages/ac/52/41f3d71296a3dcaa4f456aaa3c6fc8e745b43d0552b6bde56571bb4b4a0f/numpy-2.4.0-cp313-cp313t-win32.whl", hash = "sha256:20c115517513831860c573996e395707aa9fb691eb179200125c250e895fcd93", size = 6076216, upload-time = "2025-12-20T16:17:11.437Z" }, - { url = "https://files.pythonhosted.org/packages/35/ff/46fbfe60ab0710d2a2b16995f708750307d30eccbb4c38371ea9e986866e/numpy-2.4.0-cp313-cp313t-win_amd64.whl", hash = "sha256:b48e35f4ab6f6a7597c46e301126ceba4c44cd3280e3750f85db48b082624fa4", size = 12444263, upload-time = "2025-12-20T16:17:13.182Z" }, - { url = "https://files.pythonhosted.org/packages/a3/e3/9189ab319c01d2ed556c932ccf55064c5d75bb5850d1df7a482ce0badead/numpy-2.4.0-cp313-cp313t-win_arm64.whl", hash = "sha256:4d1cfce39e511069b11e67cd0bd78ceff31443b7c9e5c04db73c7a19f572967c", size = 10378265, upload-time = "2025-12-20T16:17:15.211Z" }, - { url = "https://files.pythonhosted.org/packages/ab/ed/52eac27de39d5e5a6c9aadabe672bc06f55e24a3d9010cd1183948055d76/numpy-2.4.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c95eb6db2884917d86cde0b4d4cf31adf485c8ec36bf8696dd66fa70de96f36b", size = 16647476, upload-time = "2025-12-20T16:17:17.671Z" }, - { url = "https://files.pythonhosted.org/packages/77/c0/990ce1b7fcd4e09aeaa574e2a0a839589e4b08b2ca68070f1acb1fea6736/numpy-2.4.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:65167da969cd1ec3a1df31cb221ca3a19a8aaa25370ecb17d428415e93c1935e", size = 12374563, upload-time = "2025-12-20T16:17:20.216Z" }, - { url = "https://files.pythonhosted.org/packages/37/7c/8c5e389c6ae8f5fd2277a988600d79e9625db3fff011a2d87ac80b881a4c/numpy-2.4.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:3de19cfecd1465d0dcf8a5b5ea8b3155b42ed0b639dba4b71e323d74f2a3be5e", size = 5203107, upload-time = "2025-12-20T16:17:22.47Z" }, - { url = "https://files.pythonhosted.org/packages/e6/94/ca5b3bd6a8a70a5eec9a0b8dd7f980c1eff4b8a54970a9a7fef248ef564f/numpy-2.4.0-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:6c05483c3136ac4c91b4e81903cb53a8707d316f488124d0398499a4f8e8ef51", size = 6538067, upload-time = "2025-12-20T16:17:24.001Z" }, - { url = "https://files.pythonhosted.org/packages/79/43/993eb7bb5be6761dde2b3a3a594d689cec83398e3f58f4758010f3b85727/numpy-2.4.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:36667db4d6c1cea79c8930ab72fadfb4060feb4bfe724141cd4bd064d2e5f8ce", size = 14411926, upload-time = "2025-12-20T16:17:25.822Z" }, - { url = "https://files.pythonhosted.org/packages/03/75/d4c43b61de473912496317a854dac54f1efec3eeb158438da6884b70bb90/numpy-2.4.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9a818668b674047fd88c4cddada7ab8f1c298812783e8328e956b78dc4807f9f", size = 16354295, upload-time = "2025-12-20T16:17:28.308Z" }, - { url = "https://files.pythonhosted.org/packages/b8/0a/b54615b47ee8736a6461a4bb6749128dd3435c5a759d5663f11f0e9af4ac/numpy-2.4.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:1ee32359fb7543b7b7bd0b2f46294db27e29e7bbdf70541e81b190836cd83ded", size = 16190242, upload-time = "2025-12-20T16:17:30.993Z" }, - { url = "https://files.pythonhosted.org/packages/98/ce/ea207769aacad6246525ec6c6bbd66a2bf56c72443dc10e2f90feed29290/numpy-2.4.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:e493962256a38f58283de033d8af176c5c91c084ea30f15834f7545451c42059", size = 18280875, upload-time = "2025-12-20T16:17:33.327Z" }, - { url = "https://files.pythonhosted.org/packages/17/ef/ec409437aa962ea372ed601c519a2b141701683ff028f894b7466f0ab42b/numpy-2.4.0-cp314-cp314-win32.whl", hash = "sha256:6bbaebf0d11567fa8926215ae731e1d58e6ec28a8a25235b8a47405d301332db", size = 6002530, upload-time = "2025-12-20T16:17:35.729Z" }, - { url = "https://files.pythonhosted.org/packages/5f/4a/5cb94c787a3ed1ac65e1271b968686521169a7b3ec0b6544bb3ca32960b0/numpy-2.4.0-cp314-cp314-win_amd64.whl", hash = "sha256:3d857f55e7fdf7c38ab96c4558c95b97d1c685be6b05c249f5fdafcbd6f9899e", size = 12435890, upload-time = "2025-12-20T16:17:37.599Z" }, - { url = "https://files.pythonhosted.org/packages/48/a0/04b89db963af9de1104975e2544f30de89adbf75b9e75f7dd2599be12c79/numpy-2.4.0-cp314-cp314-win_arm64.whl", hash = "sha256:bb50ce5fb202a26fd5404620e7ef820ad1ab3558b444cb0b55beb7ef66cd2d63", size = 10591892, upload-time = "2025-12-20T16:17:39.649Z" }, - { url = "https://files.pythonhosted.org/packages/53/e5/d74b5ccf6712c06c7a545025a6a71bfa03bdc7e0568b405b0d655232fd92/numpy-2.4.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:355354388cba60f2132df297e2d53053d4063f79077b67b481d21276d61fc4df", size = 12494312, upload-time = "2025-12-20T16:17:41.714Z" }, - { url = "https://files.pythonhosted.org/packages/c2/08/3ca9cc2ddf54dfee7ae9a6479c071092a228c68aef08252aa08dac2af002/numpy-2.4.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:1d8f9fde5f6dc1b6fc34df8162f3b3079365468703fee7f31d4e0cc8c63baed9", size = 5322862, upload-time = "2025-12-20T16:17:44.145Z" }, - { url = "https://files.pythonhosted.org/packages/87/74/0bb63a68394c0c1e52670cfff2e309afa41edbe11b3327d9af29e4383f34/numpy-2.4.0-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:e0434aa22c821f44eeb4c650b81c7fbdd8c0122c6c4b5a576a76d5a35625ecd9", size = 6644986, upload-time = "2025-12-20T16:17:46.203Z" }, - { url = "https://files.pythonhosted.org/packages/06/8f/9264d9bdbcf8236af2823623fe2f3981d740fc3461e2787e231d97c38c28/numpy-2.4.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:40483b2f2d3ba7aad426443767ff5632ec3156ef09742b96913787d13c336471", size = 14457958, upload-time = "2025-12-20T16:17:48.017Z" }, - { url = "https://files.pythonhosted.org/packages/8c/d9/f9a69ae564bbc7236a35aa883319364ef5fd41f72aa320cc1cbe66148fe2/numpy-2.4.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d9e6a7664ddd9746e20b7325351fe1a8408d0a2bf9c63b5e898290ddc8f09544", size = 16398394, upload-time = "2025-12-20T16:17:50.409Z" }, - { url = "https://files.pythonhosted.org/packages/34/c7/39241501408dde7f885d241a98caba5421061a2c6d2b2197ac5e3aa842d8/numpy-2.4.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:ecb0019d44f4cdb50b676c5d0cb4b1eae8e15d1ed3d3e6639f986fc92b2ec52c", size = 16241044, upload-time = "2025-12-20T16:17:52.661Z" }, - { url = "https://files.pythonhosted.org/packages/7c/95/cae7effd90e065a95e59fe710eeee05d7328ed169776dfdd9f789e032125/numpy-2.4.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:d0ffd9e2e4441c96a9c91ec1783285d80bf835b677853fc2770a89d50c1e48ac", size = 18321772, upload-time = "2025-12-20T16:17:54.947Z" }, - { url = "https://files.pythonhosted.org/packages/96/df/3c6c279accd2bfb968a76298e5b276310bd55d243df4fa8ac5816d79347d/numpy-2.4.0-cp314-cp314t-win32.whl", hash = "sha256:77f0d13fa87036d7553bf81f0e1fe3ce68d14c9976c9851744e4d3e91127e95f", size = 6148320, upload-time = "2025-12-20T16:17:57.249Z" }, - { url = "https://files.pythonhosted.org/packages/92/8d/f23033cce252e7a75cae853d17f582e86534c46404dea1c8ee094a9d6d84/numpy-2.4.0-cp314-cp314t-win_amd64.whl", hash = "sha256:b1f5b45829ac1848893f0ddf5cb326110604d6df96cdc255b0bf9edd154104d4", size = 12623460, upload-time = "2025-12-20T16:17:58.963Z" }, - { url = "https://files.pythonhosted.org/packages/a4/4f/1f8475907d1a7c4ef9020edf7f39ea2422ec896849245f00688e4b268a71/numpy-2.4.0-cp314-cp314t-win_arm64.whl", hash = "sha256:23a3e9d1a6f360267e8fbb38ba5db355a6a7e9be71d7fce7ab3125e88bb646c8", size = 10661799, upload-time = "2025-12-20T16:18:01.078Z" }, - { url = "https://files.pythonhosted.org/packages/4b/ef/088e7c7342f300aaf3ee5f2c821c4b9996a1bef2aaf6a49cc8ab4883758e/numpy-2.4.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:b54c83f1c0c0f1d748dca0af516062b8829d53d1f0c402be24b4257a9c48ada6", size = 16819003, upload-time = "2025-12-20T16:18:03.41Z" }, - { url = "https://files.pythonhosted.org/packages/ff/ce/a53017b5443b4b84517182d463fc7bcc2adb4faa8b20813f8e5f5aeb5faa/numpy-2.4.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:aabb081ca0ec5d39591fc33018cd4b3f96e1a2dd6756282029986d00a785fba4", size = 12567105, upload-time = "2025-12-20T16:18:05.594Z" }, - { url = "https://files.pythonhosted.org/packages/77/58/5ff91b161f2ec650c88a626c3905d938c89aaadabd0431e6d9c1330c83e2/numpy-2.4.0-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:8eafe7c36c8430b7794edeab3087dec7bf31d634d92f2af9949434b9d1964cba", size = 5395590, upload-time = "2025-12-20T16:18:08.031Z" }, - { url = "https://files.pythonhosted.org/packages/1d/4e/f1a084106df8c2df8132fc437e56987308e0524836aa7733721c8429d4fe/numpy-2.4.0-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:2f585f52b2baf07ff3356158d9268ea095e221371f1074fadea2f42544d58b4d", size = 6709947, upload-time = "2025-12-20T16:18:09.836Z" }, - { url = "https://files.pythonhosted.org/packages/63/09/3d8aeb809c0332c3f642da812ac2e3d74fc9252b3021f8c30c82e99e3f3d/numpy-2.4.0-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:32ed06d0fe9cae27d8fb5f400c63ccee72370599c75e683a6358dd3a4fb50aaf", size = 14535119, upload-time = "2025-12-20T16:18:12.105Z" }, - { url = "https://files.pythonhosted.org/packages/fd/7f/68f0fc43a2cbdc6bb239160c754d87c922f60fbaa0fa3cd3d312b8a7f5ee/numpy-2.4.0-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:57c540ed8fb1f05cb997c6761cd56db72395b0d6985e90571ff660452ade4f98", size = 16475815, upload-time = "2025-12-20T16:18:14.433Z" }, - { url = "https://files.pythonhosted.org/packages/11/73/edeacba3167b1ca66d51b1a5a14697c2c40098b5ffa01811c67b1785a5ab/numpy-2.4.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:a39fb973a726e63223287adc6dafe444ce75af952d711e400f3bf2b36ef55a7b", size = 12489376, upload-time = "2025-12-20T16:18:16.524Z" }, +version = "2.4.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/24/62/ae72ff66c0f1fd959925b4c11f8c2dea61f47f6acaea75a08512cdfe3fed/numpy-2.4.1.tar.gz", hash = "sha256:a1ceafc5042451a858231588a104093474c6a5c57dcc724841f5c888d237d690", size = 20721320, upload-time = "2026-01-10T06:44:59.619Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a5/34/2b1bc18424f3ad9af577f6ce23600319968a70575bd7db31ce66731bbef9/numpy-2.4.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0cce2a669e3c8ba02ee563c7835f92c153cf02edff1ae05e1823f1dde21b16a5", size = 16944563, upload-time = "2026-01-10T06:42:14.615Z" }, + { url = "https://files.pythonhosted.org/packages/2c/57/26e5f97d075aef3794045a6ca9eada6a4ed70eb9a40e7a4a93f9ac80d704/numpy-2.4.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:899d2c18024984814ac7e83f8f49d8e8180e2fbe1b2e252f2e7f1d06bea92425", size = 12645658, upload-time = "2026-01-10T06:42:17.298Z" }, + { url = "https://files.pythonhosted.org/packages/8e/ba/80fc0b1e3cb2fd5c6143f00f42eb67762aa043eaa05ca924ecc3222a7849/numpy-2.4.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:09aa8a87e45b55a1c2c205d42e2808849ece5c484b2aab11fecabec3841cafba", size = 5474132, upload-time = "2026-01-10T06:42:19.637Z" }, + { url = "https://files.pythonhosted.org/packages/40/ae/0a5b9a397f0e865ec171187c78d9b57e5588afc439a04ba9cab1ebb2c945/numpy-2.4.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:edee228f76ee2dab4579fad6f51f6a305de09d444280109e0f75df247ff21501", size = 6804159, upload-time = "2026-01-10T06:42:21.44Z" }, + { url = "https://files.pythonhosted.org/packages/86/9c/841c15e691c7085caa6fd162f063eff494099c8327aeccd509d1ab1e36ab/numpy-2.4.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a92f227dbcdc9e4c3e193add1a189a9909947d4f8504c576f4a732fd0b54240a", size = 14708058, upload-time = "2026-01-10T06:42:23.546Z" }, + { url = "https://files.pythonhosted.org/packages/5d/9d/7862db06743f489e6a502a3b93136d73aea27d97b2cf91504f70a27501d6/numpy-2.4.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:538bf4ec353709c765ff75ae616c34d3c3dca1a68312727e8f2676ea644f8509", size = 16651501, upload-time = "2026-01-10T06:42:25.909Z" }, + { url = "https://files.pythonhosted.org/packages/a6/9c/6fc34ebcbd4015c6e5f0c0ce38264010ce8a546cb6beacb457b84a75dfc8/numpy-2.4.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:ac08c63cb7779b85e9d5318e6c3518b424bc1f364ac4cb2c6136f12e5ff2dccc", size = 16492627, upload-time = "2026-01-10T06:42:28.938Z" }, + { url = "https://files.pythonhosted.org/packages/aa/63/2494a8597502dacda439f61b3c0db4da59928150e62be0e99395c3ad23c5/numpy-2.4.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4f9c360ecef085e5841c539a9a12b883dff005fbd7ce46722f5e9cef52634d82", size = 18585052, upload-time = "2026-01-10T06:42:31.312Z" }, + { url = "https://files.pythonhosted.org/packages/6a/93/098e1162ae7522fc9b618d6272b77404c4656c72432ecee3abc029aa3de0/numpy-2.4.1-cp311-cp311-win32.whl", hash = "sha256:0f118ce6b972080ba0758c6087c3617b5ba243d806268623dc34216d69099ba0", size = 6236575, upload-time = "2026-01-10T06:42:33.872Z" }, + { url = "https://files.pythonhosted.org/packages/8c/de/f5e79650d23d9e12f38a7bc6b03ea0835b9575494f8ec94c11c6e773b1b1/numpy-2.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:18e14c4d09d55eef39a6ab5b08406e84bc6869c1e34eef45564804f90b7e0574", size = 12604479, upload-time = "2026-01-10T06:42:35.778Z" }, + { url = "https://files.pythonhosted.org/packages/dd/65/e1097a7047cff12ce3369bd003811516b20ba1078dbdec135e1cd7c16c56/numpy-2.4.1-cp311-cp311-win_arm64.whl", hash = "sha256:6461de5113088b399d655d45c3897fa188766415d0f568f175ab071c8873bd73", size = 10578325, upload-time = "2026-01-10T06:42:38.518Z" }, + { url = "https://files.pythonhosted.org/packages/78/7f/ec53e32bf10c813604edf07a3682616bd931d026fcde7b6d13195dfb684a/numpy-2.4.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d3703409aac693fa82c0aee023a1ae06a6e9d065dba10f5e8e80f642f1e9d0a2", size = 16656888, upload-time = "2026-01-10T06:42:40.913Z" }, + { url = "https://files.pythonhosted.org/packages/b8/e0/1f9585d7dae8f14864e948fd7fa86c6cb72dee2676ca2748e63b1c5acfe0/numpy-2.4.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7211b95ca365519d3596a1d8688a95874cc94219d417504d9ecb2df99fa7bfa8", size = 12373956, upload-time = "2026-01-10T06:42:43.091Z" }, + { url = "https://files.pythonhosted.org/packages/8e/43/9762e88909ff2326f5e7536fa8cb3c49fb03a7d92705f23e6e7f553d9cb3/numpy-2.4.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:5adf01965456a664fc727ed69cc71848f28d063217c63e1a0e200a118d5eec9a", size = 5202567, upload-time = "2026-01-10T06:42:45.107Z" }, + { url = "https://files.pythonhosted.org/packages/4b/ee/34b7930eb61e79feb4478800a4b95b46566969d837546aa7c034c742ef98/numpy-2.4.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:26f0bcd9c79a00e339565b303badc74d3ea2bd6d52191eeca5f95936cad107d0", size = 6549459, upload-time = "2026-01-10T06:42:48.152Z" }, + { url = "https://files.pythonhosted.org/packages/79/e3/5f115fae982565771be994867c89bcd8d7208dbfe9469185497d70de5ddf/numpy-2.4.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0093e85df2960d7e4049664b26afc58b03236e967fb942354deef3208857a04c", size = 14404859, upload-time = "2026-01-10T06:42:49.947Z" }, + { url = "https://files.pythonhosted.org/packages/d9/7d/9c8a781c88933725445a859cac5d01b5871588a15969ee6aeb618ba99eee/numpy-2.4.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7ad270f438cbdd402c364980317fb6b117d9ec5e226fff5b4148dd9aa9fc6e02", size = 16371419, upload-time = "2026-01-10T06:42:52.409Z" }, + { url = "https://files.pythonhosted.org/packages/a6/d2/8aa084818554543f17cf4162c42f162acbd3bb42688aefdba6628a859f77/numpy-2.4.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:297c72b1b98100c2e8f873d5d35fb551fce7040ade83d67dd51d38c8d42a2162", size = 16182131, upload-time = "2026-01-10T06:42:54.694Z" }, + { url = "https://files.pythonhosted.org/packages/60/db/0425216684297c58a8df35f3284ef56ec4a043e6d283f8a59c53562caf1b/numpy-2.4.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:cf6470d91d34bf669f61d515499859fa7a4c2f7c36434afb70e82df7217933f9", size = 18295342, upload-time = "2026-01-10T06:42:56.991Z" }, + { url = "https://files.pythonhosted.org/packages/31/4c/14cb9d86240bd8c386c881bafbe43f001284b7cce3bc01623ac9475da163/numpy-2.4.1-cp312-cp312-win32.whl", hash = "sha256:b6bcf39112e956594b3331316d90c90c90fb961e39696bda97b89462f5f3943f", size = 5959015, upload-time = "2026-01-10T06:42:59.631Z" }, + { url = "https://files.pythonhosted.org/packages/51/cf/52a703dbeb0c65807540d29699fef5fda073434ff61846a564d5c296420f/numpy-2.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:e1a27bb1b2dee45a2a53f5ca6ff2d1a7f135287883a1689e930d44d1ff296c87", size = 12310730, upload-time = "2026-01-10T06:43:01.627Z" }, + { url = "https://files.pythonhosted.org/packages/69/80/a828b2d0ade5e74a9fe0f4e0a17c30fdc26232ad2bc8c9f8b3197cf7cf18/numpy-2.4.1-cp312-cp312-win_arm64.whl", hash = "sha256:0e6e8f9d9ecf95399982019c01223dc130542960a12edfa8edd1122dfa66a8a8", size = 10312166, upload-time = "2026-01-10T06:43:03.673Z" }, + { url = "https://files.pythonhosted.org/packages/04/68/732d4b7811c00775f3bd522a21e8dd5a23f77eb11acdeb663e4a4ebf0ef4/numpy-2.4.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d797454e37570cfd61143b73b8debd623c3c0952959adb817dd310a483d58a1b", size = 16652495, upload-time = "2026-01-10T06:43:06.283Z" }, + { url = "https://files.pythonhosted.org/packages/20/ca/857722353421a27f1465652b2c66813eeeccea9d76d5f7b74b99f298e60e/numpy-2.4.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:82c55962006156aeef1629b953fd359064aa47e4d82cfc8e67f0918f7da3344f", size = 12368657, upload-time = "2026-01-10T06:43:09.094Z" }, + { url = "https://files.pythonhosted.org/packages/81/0d/2377c917513449cc6240031a79d30eb9a163d32a91e79e0da47c43f2c0c8/numpy-2.4.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:71abbea030f2cfc3092a0ff9f8c8fdefdc5e0bf7d9d9c99663538bb0ecdac0b9", size = 5197256, upload-time = "2026-01-10T06:43:13.634Z" }, + { url = "https://files.pythonhosted.org/packages/17/39/569452228de3f5de9064ac75137082c6214be1f5c532016549a7923ab4b5/numpy-2.4.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:5b55aa56165b17aaf15520beb9cbd33c9039810e0d9643dd4379e44294c7303e", size = 6545212, upload-time = "2026-01-10T06:43:15.661Z" }, + { url = "https://files.pythonhosted.org/packages/8c/a4/77333f4d1e4dac4395385482557aeecf4826e6ff517e32ca48e1dafbe42a/numpy-2.4.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c0faba4a331195bfa96f93dd9dfaa10b2c7aa8cda3a02b7fd635e588fe821bf5", size = 14402871, upload-time = "2026-01-10T06:43:17.324Z" }, + { url = "https://files.pythonhosted.org/packages/ba/87/d341e519956273b39d8d47969dd1eaa1af740615394fe67d06f1efa68773/numpy-2.4.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d3e3087f53e2b4428766b54932644d148613c5a595150533ae7f00dab2f319a8", size = 16359305, upload-time = "2026-01-10T06:43:19.376Z" }, + { url = "https://files.pythonhosted.org/packages/32/91/789132c6666288eaa20ae8066bb99eba1939362e8f1a534949a215246e97/numpy-2.4.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:49e792ec351315e16da54b543db06ca8a86985ab682602d90c60ef4ff4db2a9c", size = 16181909, upload-time = "2026-01-10T06:43:21.808Z" }, + { url = "https://files.pythonhosted.org/packages/cf/b8/090b8bd27b82a844bb22ff8fdf7935cb1980b48d6e439ae116f53cdc2143/numpy-2.4.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:79e9e06c4c2379db47f3f6fc7a8652e7498251789bf8ff5bd43bf478ef314ca2", size = 18284380, upload-time = "2026-01-10T06:43:23.957Z" }, + { url = "https://files.pythonhosted.org/packages/67/78/722b62bd31842ff029412271556a1a27a98f45359dea78b1548a3a9996aa/numpy-2.4.1-cp313-cp313-win32.whl", hash = "sha256:3d1a100e48cb266090a031397863ff8a30050ceefd798f686ff92c67a486753d", size = 5957089, upload-time = "2026-01-10T06:43:27.535Z" }, + { url = "https://files.pythonhosted.org/packages/da/a6/cf32198b0b6e18d4fbfa9a21a992a7fca535b9bb2b0cdd217d4a3445b5ca/numpy-2.4.1-cp313-cp313-win_amd64.whl", hash = "sha256:92a0e65272fd60bfa0d9278e0484c2f52fe03b97aedc02b357f33fe752c52ffb", size = 12307230, upload-time = "2026-01-10T06:43:29.298Z" }, + { url = "https://files.pythonhosted.org/packages/44/6c/534d692bfb7d0afe30611320c5fb713659dcb5104d7cc182aff2aea092f5/numpy-2.4.1-cp313-cp313-win_arm64.whl", hash = "sha256:20d4649c773f66cc2fc36f663e091f57c3b7655f936a4c681b4250855d1da8f5", size = 10313125, upload-time = "2026-01-10T06:43:31.782Z" }, + { url = "https://files.pythonhosted.org/packages/da/a1/354583ac5c4caa566de6ddfbc42744409b515039e085fab6e0ff942e0df5/numpy-2.4.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:f93bc6892fe7b0663e5ffa83b61aab510aacffd58c16e012bb9352d489d90cb7", size = 12496156, upload-time = "2026-01-10T06:43:34.237Z" }, + { url = "https://files.pythonhosted.org/packages/51/b0/42807c6e8cce58c00127b1dc24d365305189991f2a7917aa694a109c8d7d/numpy-2.4.1-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:178de8f87948163d98a4c9ab5bee4ce6519ca918926ec8df195af582de28544d", size = 5324663, upload-time = "2026-01-10T06:43:36.211Z" }, + { url = "https://files.pythonhosted.org/packages/fe/55/7a621694010d92375ed82f312b2f28017694ed784775269115323e37f5e2/numpy-2.4.1-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:98b35775e03ab7f868908b524fc0a84d38932d8daf7b7e1c3c3a1b6c7a2c9f15", size = 6645224, upload-time = "2026-01-10T06:43:37.884Z" }, + { url = "https://files.pythonhosted.org/packages/50/96/9fa8635ed9d7c847d87e30c834f7109fac5e88549d79ef3324ab5c20919f/numpy-2.4.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:941c2a93313d030f219f3a71fd3d91a728b82979a5e8034eb2e60d394a2b83f9", size = 14462352, upload-time = "2026-01-10T06:43:39.479Z" }, + { url = "https://files.pythonhosted.org/packages/03/d1/8cf62d8bb2062da4fb82dd5d49e47c923f9c0738032f054e0a75342faba7/numpy-2.4.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:529050522e983e00a6c1c6b67411083630de8b57f65e853d7b03d9281b8694d2", size = 16407279, upload-time = "2026-01-10T06:43:41.93Z" }, + { url = "https://files.pythonhosted.org/packages/86/1c/95c86e17c6b0b31ce6ef219da00f71113b220bcb14938c8d9a05cee0ff53/numpy-2.4.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:2302dc0224c1cbc49bb94f7064f3f923a971bfae45c33870dcbff63a2a550505", size = 16248316, upload-time = "2026-01-10T06:43:44.121Z" }, + { url = "https://files.pythonhosted.org/packages/30/b4/e7f5ff8697274c9d0fa82398b6a372a27e5cef069b37df6355ccb1f1db1a/numpy-2.4.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:9171a42fcad32dcf3fa86f0a4faa5e9f8facefdb276f54b8b390d90447cff4e2", size = 18329884, upload-time = "2026-01-10T06:43:46.613Z" }, + { url = "https://files.pythonhosted.org/packages/37/a4/b073f3e9d77f9aec8debe8ca7f9f6a09e888ad1ba7488f0c3b36a94c03ac/numpy-2.4.1-cp313-cp313t-win32.whl", hash = "sha256:382ad67d99ef49024f11d1ce5dcb5ad8432446e4246a4b014418ba3a1175a1f4", size = 6081138, upload-time = "2026-01-10T06:43:48.854Z" }, + { url = "https://files.pythonhosted.org/packages/16/16/af42337b53844e67752a092481ab869c0523bc95c4e5c98e4dac4e9581ac/numpy-2.4.1-cp313-cp313t-win_amd64.whl", hash = "sha256:62fea415f83ad8fdb6c20840578e5fbaf5ddd65e0ec6c3c47eda0f69da172510", size = 12447478, upload-time = "2026-01-10T06:43:50.476Z" }, + { url = "https://files.pythonhosted.org/packages/6c/f8/fa85b2eac68ec631d0b631abc448552cb17d39afd17ec53dcbcc3537681a/numpy-2.4.1-cp313-cp313t-win_arm64.whl", hash = "sha256:a7870e8c5fc11aef57d6fea4b4085e537a3a60ad2cdd14322ed531fdca68d261", size = 10382981, upload-time = "2026-01-10T06:43:52.575Z" }, + { url = "https://files.pythonhosted.org/packages/1b/a7/ef08d25698e0e4b4efbad8d55251d20fe2a15f6d9aa7c9b30cd03c165e6f/numpy-2.4.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:3869ea1ee1a1edc16c29bbe3a2f2a4e515cc3a44d43903ad41e0cacdbaf733dc", size = 16652046, upload-time = "2026-01-10T06:43:54.797Z" }, + { url = "https://files.pythonhosted.org/packages/8f/39/e378b3e3ca13477e5ac70293ec027c438d1927f18637e396fe90b1addd72/numpy-2.4.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:e867df947d427cdd7a60e3e271729090b0f0df80f5f10ab7dd436f40811699c3", size = 12378858, upload-time = "2026-01-10T06:43:57.099Z" }, + { url = "https://files.pythonhosted.org/packages/c3/74/7ec6154f0006910ed1fdbb7591cf4432307033102b8a22041599935f8969/numpy-2.4.1-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:e3bd2cb07841166420d2fa7146c96ce00cb3410664cbc1a6be028e456c4ee220", size = 5207417, upload-time = "2026-01-10T06:43:59.037Z" }, + { url = "https://files.pythonhosted.org/packages/f7/b7/053ac11820d84e42f8feea5cb81cc4fcd1091499b45b1ed8c7415b1bf831/numpy-2.4.1-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:f0a90aba7d521e6954670550e561a4cb925713bd944445dbe9e729b71f6cabee", size = 6542643, upload-time = "2026-01-10T06:44:01.852Z" }, + { url = "https://files.pythonhosted.org/packages/c0/c4/2e7908915c0e32ca636b92e4e4a3bdec4cb1e7eb0f8aedf1ed3c68a0d8cd/numpy-2.4.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d558123217a83b2d1ba316b986e9248a1ed1971ad495963d555ccd75dcb1556", size = 14418963, upload-time = "2026-01-10T06:44:04.047Z" }, + { url = "https://files.pythonhosted.org/packages/eb/c0/3ed5083d94e7ffd7c404e54619c088e11f2e1939a9544f5397f4adb1b8ba/numpy-2.4.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2f44de05659b67d20499cbc96d49f2650769afcb398b79b324bb6e297bfe3844", size = 16363811, upload-time = "2026-01-10T06:44:06.207Z" }, + { url = "https://files.pythonhosted.org/packages/0e/68/42b66f1852bf525050a67315a4fb94586ab7e9eaa541b1bef530fab0c5dd/numpy-2.4.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:69e7419c9012c4aaf695109564e3387f1259f001b4326dfa55907b098af082d3", size = 16197643, upload-time = "2026-01-10T06:44:08.33Z" }, + { url = "https://files.pythonhosted.org/packages/d2/40/e8714fc933d85f82c6bfc7b998a0649ad9769a32f3494ba86598aaf18a48/numpy-2.4.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2ffd257026eb1b34352e749d7cc1678b5eeec3e329ad8c9965a797e08ccba205", size = 18289601, upload-time = "2026-01-10T06:44:10.841Z" }, + { url = "https://files.pythonhosted.org/packages/80/9a/0d44b468cad50315127e884802351723daca7cf1c98d102929468c81d439/numpy-2.4.1-cp314-cp314-win32.whl", hash = "sha256:727c6c3275ddefa0dc078524a85e064c057b4f4e71ca5ca29a19163c607be745", size = 6005722, upload-time = "2026-01-10T06:44:13.332Z" }, + { url = "https://files.pythonhosted.org/packages/7e/bb/c6513edcce5a831810e2dddc0d3452ce84d208af92405a0c2e58fd8e7881/numpy-2.4.1-cp314-cp314-win_amd64.whl", hash = "sha256:7d5d7999df434a038d75a748275cd6c0094b0ecdb0837342b332a82defc4dc4d", size = 12438590, upload-time = "2026-01-10T06:44:15.006Z" }, + { url = "https://files.pythonhosted.org/packages/e9/da/a598d5cb260780cf4d255102deba35c1d072dc028c4547832f45dd3323a8/numpy-2.4.1-cp314-cp314-win_arm64.whl", hash = "sha256:ce9ce141a505053b3c7bce3216071f3bf5c182b8b28930f14cd24d43932cd2df", size = 10596180, upload-time = "2026-01-10T06:44:17.386Z" }, + { url = "https://files.pythonhosted.org/packages/de/bc/ea3f2c96fcb382311827231f911723aeff596364eb6e1b6d1d91128aa29b/numpy-2.4.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:4e53170557d37ae404bf8d542ca5b7c629d6efa1117dac6a83e394142ea0a43f", size = 12498774, upload-time = "2026-01-10T06:44:19.467Z" }, + { url = "https://files.pythonhosted.org/packages/aa/ab/ef9d939fe4a812648c7a712610b2ca6140b0853c5efea361301006c02ae5/numpy-2.4.1-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:a73044b752f5d34d4232f25f18160a1cc418ea4507f5f11e299d8ac36875f8a0", size = 5327274, upload-time = "2026-01-10T06:44:23.189Z" }, + { url = "https://files.pythonhosted.org/packages/bd/31/d381368e2a95c3b08b8cf7faac6004849e960f4a042d920337f71cef0cae/numpy-2.4.1-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:fb1461c99de4d040666ca0444057b06541e5642f800b71c56e6ea92d6a853a0c", size = 6648306, upload-time = "2026-01-10T06:44:25.012Z" }, + { url = "https://files.pythonhosted.org/packages/c8/e5/0989b44ade47430be6323d05c23207636d67d7362a1796ccbccac6773dd2/numpy-2.4.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:423797bdab2eeefbe608d7c1ec7b2b4fd3c58d51460f1ee26c7500a1d9c9ee93", size = 14464653, upload-time = "2026-01-10T06:44:26.706Z" }, + { url = "https://files.pythonhosted.org/packages/10/a7/cfbe475c35371cae1358e61f20c5f075badc18c4797ab4354140e1d283cf/numpy-2.4.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:52b5f61bdb323b566b528899cc7db2ba5d1015bda7ea811a8bcf3c89c331fa42", size = 16405144, upload-time = "2026-01-10T06:44:29.378Z" }, + { url = "https://files.pythonhosted.org/packages/f8/a3/0c63fe66b534888fa5177cc7cef061541064dbe2b4b60dcc60ffaf0d2157/numpy-2.4.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:42d7dd5fa36d16d52a84f821eb96031836fd405ee6955dd732f2023724d0aa01", size = 16247425, upload-time = "2026-01-10T06:44:31.721Z" }, + { url = "https://files.pythonhosted.org/packages/6b/2b/55d980cfa2c93bd40ff4c290bf824d792bd41d2fe3487b07707559071760/numpy-2.4.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:e7b6b5e28bbd47b7532698e5db2fe1db693d84b58c254e4389d99a27bb9b8f6b", size = 18330053, upload-time = "2026-01-10T06:44:34.617Z" }, + { url = "https://files.pythonhosted.org/packages/23/12/8b5fc6b9c487a09a7957188e0943c9ff08432c65e34567cabc1623b03a51/numpy-2.4.1-cp314-cp314t-win32.whl", hash = "sha256:5de60946f14ebe15e713a6f22850c2372fa72f4ff9a432ab44aa90edcadaa65a", size = 6152482, upload-time = "2026-01-10T06:44:36.798Z" }, + { url = "https://files.pythonhosted.org/packages/00/a5/9f8ca5856b8940492fc24fbe13c1bc34d65ddf4079097cf9e53164d094e1/numpy-2.4.1-cp314-cp314t-win_amd64.whl", hash = "sha256:8f085da926c0d491ffff3096f91078cc97ea67e7e6b65e490bc8dcda65663be2", size = 12627117, upload-time = "2026-01-10T06:44:38.828Z" }, + { url = "https://files.pythonhosted.org/packages/ad/0d/eca3d962f9eef265f01a8e0d20085c6dd1f443cbffc11b6dede81fd82356/numpy-2.4.1-cp314-cp314t-win_arm64.whl", hash = "sha256:6436cffb4f2bf26c974344439439c95e152c9a527013f26b3577be6c2ca64295", size = 10667121, upload-time = "2026-01-10T06:44:41.644Z" }, + { url = "https://files.pythonhosted.org/packages/1e/48/d86f97919e79314a1cdee4c832178763e6e98e623e123d0bada19e92c15a/numpy-2.4.1-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:8ad35f20be147a204e28b6a0575fbf3540c5e5f802634d4258d55b1ff5facce1", size = 16822202, upload-time = "2026-01-10T06:44:43.738Z" }, + { url = "https://files.pythonhosted.org/packages/51/e9/1e62a7f77e0f37dcfb0ad6a9744e65df00242b6ea37dfafb55debcbf5b55/numpy-2.4.1-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:8097529164c0f3e32bb89412a0905d9100bf434d9692d9fc275e18dcf53c9344", size = 12569985, upload-time = "2026-01-10T06:44:45.945Z" }, + { url = "https://files.pythonhosted.org/packages/c7/7e/914d54f0c801342306fdcdce3e994a56476f1b818c46c47fc21ae968088c/numpy-2.4.1-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:ea66d2b41ca4a1630aae5507ee0a71647d3124d1741980138aa8f28f44dac36e", size = 5398484, upload-time = "2026-01-10T06:44:48.012Z" }, + { url = "https://files.pythonhosted.org/packages/1c/d8/9570b68584e293a33474e7b5a77ca404f1dcc655e40050a600dee81d27fb/numpy-2.4.1-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:d3f8f0df9f4b8be57b3bf74a1d087fec68f927a2fab68231fdb442bf2c12e426", size = 6713216, upload-time = "2026-01-10T06:44:49.725Z" }, + { url = "https://files.pythonhosted.org/packages/33/9b/9dd6e2db8d49eb24f86acaaa5258e5f4c8ed38209a4ee9de2d1a0ca25045/numpy-2.4.1-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2023ef86243690c2791fd6353e5b4848eedaa88ca8a2d129f462049f6d484696", size = 14538937, upload-time = "2026-01-10T06:44:51.498Z" }, + { url = "https://files.pythonhosted.org/packages/53/87/d5bd995b0f798a37105b876350d346eea5838bd8f77ea3d7a48392f3812b/numpy-2.4.1-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8361ea4220d763e54cff2fbe7d8c93526b744f7cd9ddab47afeff7e14e8503be", size = 16479830, upload-time = "2026-01-10T06:44:53.931Z" }, + { url = "https://files.pythonhosted.org/packages/5b/c7/b801bf98514b6ae6475e941ac05c58e6411dd863ea92916bfd6d510b08c1/numpy-2.4.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:4f1b68ff47680c2925f8063402a693ede215f0257f02596b1318ecdfb1d79e33", size = 12492579, upload-time = "2026-01-10T06:44:57.094Z" }, ] [[package]] @@ -611,7 +644,7 @@ name = "nvidia-cudnn-cu12" version = "9.10.2.21" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12" }, + { name = "nvidia-cublas-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/ba/51/e123d997aa098c61d029f76663dedbfb9bc8dcf8c60cbd6adbe42f76d049/nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:949452be657fa16687d0930933f032835951ef0892b37d2d53824d1a84dc97a8", size = 706758467, upload-time = "2025-06-06T21:54:08.597Z" }, @@ -622,7 +655,7 @@ name = "nvidia-cufft-cu12" version = "11.3.3.83" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-nvjitlink-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/1f/13/ee4e00f30e676b66ae65b4f08cb5bcbb8392c03f54f2d5413ea99a5d1c80/nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4d2dd21ec0b88cf61b62e6b43564355e5222e4a3fb394cac0db101f2dd0d4f74", size = 193118695, upload-time = "2025-03-07T01:45:27.821Z" }, @@ -649,9 +682,9 @@ name = "nvidia-cusolver-cu12" version = "11.7.3.90" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12" }, - { name = "nvidia-cusparse-cu12" }, - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-cublas-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, + { name = "nvidia-cusparse-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, + { name = "nvidia-nvjitlink-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/85/48/9a13d2975803e8cf2777d5ed57b87a0b6ca2cc795f9a4f59796a910bfb80/nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:4376c11ad263152bd50ea295c05370360776f8c3427b30991df774f9fb26c450", size = 267506905, upload-time = "2025-03-07T01:47:16.273Z" }, @@ -662,7 +695,7 @@ name = "nvidia-cusparse-cu12" version = "12.5.8.93" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-nvjitlink-cu12", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/c2/f5/e1854cb2f2bcd4280c44736c93550cc300ff4b8c95ebe370d0aa7d2b473d/nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1ec05d76bbbd8b61b06a80e1eaf8cf4959c3d4ce8e711b65ebd0443bb0ebb13b", size = 288216466, upload-time = "2025-03-07T01:48:13.779Z" }, @@ -694,10 +727,10 @@ wheels = [ [[package]] name = "nvidia-nvshmem-cu12" -version = "3.3.20" +version = "3.4.5" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/3b/6c/99acb2f9eb85c29fc6f3a7ac4dccfd992e22666dd08a642b303311326a97/nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d00f26d3f9b2e3c3065be895e3059d6479ea5c638a3f38c9fec49b1b9dd7c1e5", size = 124657145, upload-time = "2025-08-04T20:25:19.995Z" }, + { url = "https://files.pythonhosted.org/packages/b5/09/6ea3ea725f82e1e76684f0708bbedd871fc96da89945adeba65c3835a64c/nvidia_nvshmem_cu12-3.4.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:042f2500f24c021db8a06c5eec2539027d57460e1c1a762055a6554f72c369bd", size = 139103095, upload-time = "2025-09-06T00:32:31.266Z" }, ] [[package]] @@ -710,11 +743,11 @@ wheels = [ [[package]] name = "packaging" -version = "25.0" +version = "26.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/a1/d4/1fc4078c65507b51b96ca8f8c3ba19e6a61c8253c72794544580a7b6c24d/packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f", size = 165727, upload-time = "2025-04-19T11:48:59.673Z" } +sdist = { url = "https://files.pythonhosted.org/packages/65/ee/299d360cdc32edc7d2cf530f3accf79c4fca01e96ffc950d8a52213bd8e4/packaging-26.0.tar.gz", hash = "sha256:00243ae351a257117b6a241061796684b084ed1c516a08c48a3f7e147a9d80b4", size = 143416, upload-time = "2026-01-21T20:50:39.064Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" }, + { url = "https://files.pythonhosted.org/packages/b7/b9/c538f279a4e237a006a2c98387d081e9eb060d203d8ed34467cc0f0b9b53/packaging-26.0-py3-none-any.whl", hash = "sha256:b36f1fef9334a5588b4166f8bcd26a14e521f2b55e6b9de3aaa80d3ff7a37529", size = 74366, upload-time = "2026-01-21T20:50:37.788Z" }, ] [[package]] @@ -951,15 +984,15 @@ wheels = [ [[package]] name = "pyright" -version = "1.1.407" +version = "1.1.408" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "nodeenv" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/a6/1b/0aa08ee42948b61745ac5b5b5ccaec4669e8884b53d31c8ec20b2fcd6b6f/pyright-1.1.407.tar.gz", hash = "sha256:099674dba5c10489832d4a4b2d302636152a9a42d317986c38474c76fe562262", size = 4122872, upload-time = "2025-10-24T23:17:15.145Z" } +sdist = { url = "https://files.pythonhosted.org/packages/74/b2/5db700e52554b8f025faa9c3c624c59f1f6c8841ba81ab97641b54322f16/pyright-1.1.408.tar.gz", hash = "sha256:f28f2321f96852fa50b5829ea492f6adb0e6954568d1caa3f3af3a5f555eb684", size = 4400578, upload-time = "2026-01-08T08:07:38.795Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/dc/93/b69052907d032b00c40cb656d21438ec00b3a471733de137a3f65a49a0a0/pyright-1.1.407-py3-none-any.whl", hash = "sha256:6dd419f54fcc13f03b52285796d65e639786373f433e243f8b94cf93a7444d21", size = 5997008, upload-time = "2025-10-24T23:17:13.159Z" }, + { url = "https://files.pythonhosted.org/packages/0c/82/a2c93e32800940d9573fb28c346772a14778b84ba7524e691b324620ab89/pyright-1.1.408-py3-none-any.whl", hash = "sha256:090b32865f4fdb1e0e6cd82bf5618480d48eecd2eb2e70f960982a3d9a4c17c1", size = 6399144, upload-time = "2026-01-08T08:07:37.082Z" }, ] [[package]] @@ -1060,94 +1093,106 @@ wheels = [ [[package]] name = "regex" -version = "2025.11.3" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/cc/a9/546676f25e573a4cf00fe8e119b78a37b6a8fe2dc95cda877b30889c9c45/regex-2025.11.3.tar.gz", hash = "sha256:1fedc720f9bb2494ce31a58a1631f9c82df6a09b49c19517ea5cc280b4541e01", size = 414669, upload-time = "2025-11-03T21:34:22.089Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/f7/90/4fb5056e5f03a7048abd2b11f598d464f0c167de4f2a51aa868c376b8c70/regex-2025.11.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eadade04221641516fa25139273505a1c19f9bf97589a05bc4cfcd8b4a618031", size = 488081, upload-time = "2025-11-03T21:31:11.946Z" }, - { url = "https://files.pythonhosted.org/packages/85/23/63e481293fac8b069d84fba0299b6666df720d875110efd0338406b5d360/regex-2025.11.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:feff9e54ec0dd3833d659257f5c3f5322a12eee58ffa360984b716f8b92983f4", size = 290554, upload-time = "2025-11-03T21:31:13.387Z" }, - { url = "https://files.pythonhosted.org/packages/2b/9d/b101d0262ea293a0066b4522dfb722eb6a8785a8c3e084396a5f2c431a46/regex-2025.11.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3b30bc921d50365775c09a7ed446359e5c0179e9e2512beec4a60cbcef6ddd50", size = 288407, upload-time = "2025-11-03T21:31:14.809Z" }, - { url = "https://files.pythonhosted.org/packages/0c/64/79241c8209d5b7e00577ec9dca35cd493cc6be35b7d147eda367d6179f6d/regex-2025.11.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f99be08cfead2020c7ca6e396c13543baea32343b7a9a5780c462e323bd8872f", size = 793418, upload-time = "2025-11-03T21:31:16.556Z" }, - { url = "https://files.pythonhosted.org/packages/3d/e2/23cd5d3573901ce8f9757c92ca4db4d09600b865919b6d3e7f69f03b1afd/regex-2025.11.3-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dd329a1b61c0ee95ba95385fb0c07ea0d3fe1a21e1349fa2bec272636217118", size = 860448, upload-time = "2025-11-03T21:31:18.12Z" }, - { url = "https://files.pythonhosted.org/packages/2a/4c/aecf31beeaa416d0ae4ecb852148d38db35391aac19c687b5d56aedf3a8b/regex-2025.11.3-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4c5238d32f3c5269d9e87be0cf096437b7622b6920f5eac4fd202468aaeb34d2", size = 907139, upload-time = "2025-11-03T21:31:20.753Z" }, - { url = "https://files.pythonhosted.org/packages/61/22/b8cb00df7d2b5e0875f60628594d44dba283e951b1ae17c12f99e332cc0a/regex-2025.11.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:10483eefbfb0adb18ee9474498c9a32fcf4e594fbca0543bb94c48bac6183e2e", size = 800439, upload-time = "2025-11-03T21:31:22.069Z" }, - { url = "https://files.pythonhosted.org/packages/02/a8/c4b20330a5cdc7a8eb265f9ce593f389a6a88a0c5f280cf4d978f33966bc/regex-2025.11.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:78c2d02bb6e1da0720eedc0bad578049cad3f71050ef8cd065ecc87691bed2b0", size = 782965, upload-time = "2025-11-03T21:31:23.598Z" }, - { url = "https://files.pythonhosted.org/packages/b4/4c/ae3e52988ae74af4b04d2af32fee4e8077f26e51b62ec2d12d246876bea2/regex-2025.11.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e6b49cd2aad93a1790ce9cffb18964f6d3a4b0b3dbdbd5de094b65296fce6e58", size = 854398, upload-time = "2025-11-03T21:31:25.008Z" }, - { url = "https://files.pythonhosted.org/packages/06/d1/a8b9cf45874eda14b2e275157ce3b304c87e10fb38d9fc26a6e14eb18227/regex-2025.11.3-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:885b26aa3ee56433b630502dc3d36ba78d186a00cc535d3806e6bfd9ed3c70ab", size = 845897, upload-time = "2025-11-03T21:31:26.427Z" }, - { url = "https://files.pythonhosted.org/packages/ea/fe/1830eb0236be93d9b145e0bd8ab499f31602fe0999b1f19e99955aa8fe20/regex-2025.11.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ddd76a9f58e6a00f8772e72cff8ebcff78e022be95edf018766707c730593e1e", size = 788906, upload-time = "2025-11-03T21:31:28.078Z" }, - { url = "https://files.pythonhosted.org/packages/66/47/dc2577c1f95f188c1e13e2e69d8825a5ac582ac709942f8a03af42ed6e93/regex-2025.11.3-cp311-cp311-win32.whl", hash = "sha256:3e816cc9aac1cd3cc9a4ec4d860f06d40f994b5c7b4d03b93345f44e08cc68bf", size = 265812, upload-time = "2025-11-03T21:31:29.72Z" }, - { url = "https://files.pythonhosted.org/packages/50/1e/15f08b2f82a9bbb510621ec9042547b54d11e83cb620643ebb54e4eb7d71/regex-2025.11.3-cp311-cp311-win_amd64.whl", hash = "sha256:087511f5c8b7dfbe3a03f5d5ad0c2a33861b1fc387f21f6f60825a44865a385a", size = 277737, upload-time = "2025-11-03T21:31:31.422Z" }, - { url = "https://files.pythonhosted.org/packages/f4/fc/6500eb39f5f76c5e47a398df82e6b535a5e345f839581012a418b16f9cc3/regex-2025.11.3-cp311-cp311-win_arm64.whl", hash = "sha256:1ff0d190c7f68ae7769cd0313fe45820ba07ffebfddfaa89cc1eb70827ba0ddc", size = 270290, upload-time = "2025-11-03T21:31:33.041Z" }, - { url = "https://files.pythonhosted.org/packages/e8/74/18f04cb53e58e3fb107439699bd8375cf5a835eec81084e0bddbd122e4c2/regex-2025.11.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:bc8ab71e2e31b16e40868a40a69007bc305e1109bd4658eb6cad007e0bf67c41", size = 489312, upload-time = "2025-11-03T21:31:34.343Z" }, - { url = "https://files.pythonhosted.org/packages/78/3f/37fcdd0d2b1e78909108a876580485ea37c91e1acf66d3bb8e736348f441/regex-2025.11.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:22b29dda7e1f7062a52359fca6e58e548e28c6686f205e780b02ad8ef710de36", size = 291256, upload-time = "2025-11-03T21:31:35.675Z" }, - { url = "https://files.pythonhosted.org/packages/bf/26/0a575f58eb23b7ebd67a45fccbc02ac030b737b896b7e7a909ffe43ffd6a/regex-2025.11.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3a91e4a29938bc1a082cc28fdea44be420bf2bebe2665343029723892eb073e1", size = 288921, upload-time = "2025-11-03T21:31:37.07Z" }, - { url = "https://files.pythonhosted.org/packages/ea/98/6a8dff667d1af907150432cf5abc05a17ccd32c72a3615410d5365ac167a/regex-2025.11.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:08b884f4226602ad40c5d55f52bf91a9df30f513864e0054bad40c0e9cf1afb7", size = 798568, upload-time = "2025-11-03T21:31:38.784Z" }, - { url = "https://files.pythonhosted.org/packages/64/15/92c1db4fa4e12733dd5a526c2dd2b6edcbfe13257e135fc0f6c57f34c173/regex-2025.11.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:3e0b11b2b2433d1c39c7c7a30e3f3d0aeeea44c2a8d0bae28f6b95f639927a69", size = 864165, upload-time = "2025-11-03T21:31:40.559Z" }, - { url = "https://files.pythonhosted.org/packages/f9/e7/3ad7da8cdee1ce66c7cd37ab5ab05c463a86ffeb52b1a25fe7bd9293b36c/regex-2025.11.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:87eb52a81ef58c7ba4d45c3ca74e12aa4b4e77816f72ca25258a85b3ea96cb48", size = 912182, upload-time = "2025-11-03T21:31:42.002Z" }, - { url = "https://files.pythonhosted.org/packages/84/bd/9ce9f629fcb714ffc2c3faf62b6766ecb7a585e1e885eb699bcf130a5209/regex-2025.11.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a12ab1f5c29b4e93db518f5e3872116b7e9b1646c9f9f426f777b50d44a09e8c", size = 803501, upload-time = "2025-11-03T21:31:43.815Z" }, - { url = "https://files.pythonhosted.org/packages/7c/0f/8dc2e4349d8e877283e6edd6c12bdcebc20f03744e86f197ab6e4492bf08/regex-2025.11.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:7521684c8c7c4f6e88e35ec89680ee1aa8358d3f09d27dfbdf62c446f5d4c695", size = 787842, upload-time = "2025-11-03T21:31:45.353Z" }, - { url = "https://files.pythonhosted.org/packages/f9/73/cff02702960bc185164d5619c0c62a2f598a6abff6695d391b096237d4ab/regex-2025.11.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:7fe6e5440584e94cc4b3f5f4d98a25e29ca12dccf8873679a635638349831b98", size = 858519, upload-time = "2025-11-03T21:31:46.814Z" }, - { url = "https://files.pythonhosted.org/packages/61/83/0e8d1ae71e15bc1dc36231c90b46ee35f9d52fab2e226b0e039e7ea9c10a/regex-2025.11.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:8e026094aa12b43f4fd74576714e987803a315c76edb6b098b9809db5de58f74", size = 850611, upload-time = "2025-11-03T21:31:48.289Z" }, - { url = "https://files.pythonhosted.org/packages/c8/f5/70a5cdd781dcfaa12556f2955bf170cd603cb1c96a1827479f8faea2df97/regex-2025.11.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:435bbad13e57eb5606a68443af62bed3556de2f46deb9f7d4237bc2f1c9fb3a0", size = 789759, upload-time = "2025-11-03T21:31:49.759Z" }, - { url = "https://files.pythonhosted.org/packages/59/9b/7c29be7903c318488983e7d97abcf8ebd3830e4c956c4c540005fcfb0462/regex-2025.11.3-cp312-cp312-win32.whl", hash = "sha256:3839967cf4dc4b985e1570fd8d91078f0c519f30491c60f9ac42a8db039be204", size = 266194, upload-time = "2025-11-03T21:31:51.53Z" }, - { url = "https://files.pythonhosted.org/packages/1a/67/3b92df89f179d7c367be654ab5626ae311cb28f7d5c237b6bb976cd5fbbb/regex-2025.11.3-cp312-cp312-win_amd64.whl", hash = "sha256:e721d1b46e25c481dc5ded6f4b3f66c897c58d2e8cfdf77bbced84339108b0b9", size = 277069, upload-time = "2025-11-03T21:31:53.151Z" }, - { url = "https://files.pythonhosted.org/packages/d7/55/85ba4c066fe5094d35b249c3ce8df0ba623cfd35afb22d6764f23a52a1c5/regex-2025.11.3-cp312-cp312-win_arm64.whl", hash = "sha256:64350685ff08b1d3a6fff33f45a9ca183dc1d58bbfe4981604e70ec9801bbc26", size = 270330, upload-time = "2025-11-03T21:31:54.514Z" }, - { url = "https://files.pythonhosted.org/packages/e1/a7/dda24ebd49da46a197436ad96378f17df30ceb40e52e859fc42cac45b850/regex-2025.11.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c1e448051717a334891f2b9a620fe36776ebf3dd8ec46a0b877c8ae69575feb4", size = 489081, upload-time = "2025-11-03T21:31:55.9Z" }, - { url = "https://files.pythonhosted.org/packages/19/22/af2dc751aacf88089836aa088a1a11c4f21a04707eb1b0478e8e8fb32847/regex-2025.11.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:9b5aca4d5dfd7fbfbfbdaf44850fcc7709a01146a797536a8f84952e940cca76", size = 291123, upload-time = "2025-11-03T21:31:57.758Z" }, - { url = "https://files.pythonhosted.org/packages/a3/88/1a3ea5672f4b0a84802ee9891b86743438e7c04eb0b8f8c4e16a42375327/regex-2025.11.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:04d2765516395cf7dda331a244a3282c0f5ae96075f728629287dfa6f76ba70a", size = 288814, upload-time = "2025-11-03T21:32:01.12Z" }, - { url = "https://files.pythonhosted.org/packages/fb/8c/f5987895bf42b8ddeea1b315c9fedcfe07cadee28b9c98cf50d00adcb14d/regex-2025.11.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d9903ca42bfeec4cebedba8022a7c97ad2aab22e09573ce9976ba01b65e4361", size = 798592, upload-time = "2025-11-03T21:32:03.006Z" }, - { url = "https://files.pythonhosted.org/packages/99/2a/6591ebeede78203fa77ee46a1c36649e02df9eaa77a033d1ccdf2fcd5d4e/regex-2025.11.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:639431bdc89d6429f6721625e8129413980ccd62e9d3f496be618a41d205f160", size = 864122, upload-time = "2025-11-03T21:32:04.553Z" }, - { url = "https://files.pythonhosted.org/packages/94/d6/be32a87cf28cf8ed064ff281cfbd49aefd90242a83e4b08b5a86b38e8eb4/regex-2025.11.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f117efad42068f9715677c8523ed2be1518116d1c49b1dd17987716695181efe", size = 912272, upload-time = "2025-11-03T21:32:06.148Z" }, - { url = "https://files.pythonhosted.org/packages/62/11/9bcef2d1445665b180ac7f230406ad80671f0fc2a6ffb93493b5dd8cd64c/regex-2025.11.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4aecb6f461316adf9f1f0f6a4a1a3d79e045f9b71ec76055a791affa3b285850", size = 803497, upload-time = "2025-11-03T21:32:08.162Z" }, - { url = "https://files.pythonhosted.org/packages/e5/a7/da0dc273d57f560399aa16d8a68ae7f9b57679476fc7ace46501d455fe84/regex-2025.11.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:3b3a5f320136873cc5561098dfab677eea139521cb9a9e8db98b7e64aef44cbc", size = 787892, upload-time = "2025-11-03T21:32:09.769Z" }, - { url = "https://files.pythonhosted.org/packages/da/4b/732a0c5a9736a0b8d6d720d4945a2f1e6f38f87f48f3173559f53e8d5d82/regex-2025.11.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:75fa6f0056e7efb1f42a1c34e58be24072cb9e61a601340cc1196ae92326a4f9", size = 858462, upload-time = "2025-11-03T21:32:11.769Z" }, - { url = "https://files.pythonhosted.org/packages/0c/f5/a2a03df27dc4c2d0c769220f5110ba8c4084b0bfa9ab0f9b4fcfa3d2b0fc/regex-2025.11.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:dbe6095001465294f13f1adcd3311e50dd84e5a71525f20a10bd16689c61ce0b", size = 850528, upload-time = "2025-11-03T21:32:13.906Z" }, - { url = "https://files.pythonhosted.org/packages/d6/09/e1cd5bee3841c7f6eb37d95ca91cdee7100b8f88b81e41c2ef426910891a/regex-2025.11.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:454d9b4ae7881afbc25015b8627c16d88a597479b9dea82b8c6e7e2e07240dc7", size = 789866, upload-time = "2025-11-03T21:32:15.748Z" }, - { url = "https://files.pythonhosted.org/packages/eb/51/702f5ea74e2a9c13d855a6a85b7f80c30f9e72a95493260193c07f3f8d74/regex-2025.11.3-cp313-cp313-win32.whl", hash = "sha256:28ba4d69171fc6e9896337d4fc63a43660002b7da53fc15ac992abcf3410917c", size = 266189, upload-time = "2025-11-03T21:32:17.493Z" }, - { url = "https://files.pythonhosted.org/packages/8b/00/6e29bb314e271a743170e53649db0fdb8e8ff0b64b4f425f5602f4eb9014/regex-2025.11.3-cp313-cp313-win_amd64.whl", hash = "sha256:bac4200befe50c670c405dc33af26dad5a3b6b255dd6c000d92fe4629f9ed6a5", size = 277054, upload-time = "2025-11-03T21:32:19.042Z" }, - { url = "https://files.pythonhosted.org/packages/25/f1/b156ff9f2ec9ac441710764dda95e4edaf5f36aca48246d1eea3f1fd96ec/regex-2025.11.3-cp313-cp313-win_arm64.whl", hash = "sha256:2292cd5a90dab247f9abe892ac584cb24f0f54680c73fcb4a7493c66c2bf2467", size = 270325, upload-time = "2025-11-03T21:32:21.338Z" }, - { url = "https://files.pythonhosted.org/packages/20/28/fd0c63357caefe5680b8ea052131acbd7f456893b69cc2a90cc3e0dc90d4/regex-2025.11.3-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:1eb1ebf6822b756c723e09f5186473d93236c06c579d2cc0671a722d2ab14281", size = 491984, upload-time = "2025-11-03T21:32:23.466Z" }, - { url = "https://files.pythonhosted.org/packages/df/ec/7014c15626ab46b902b3bcc4b28a7bae46d8f281fc7ea9c95e22fcaaa917/regex-2025.11.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:1e00ec2970aab10dc5db34af535f21fcf32b4a31d99e34963419636e2f85ae39", size = 292673, upload-time = "2025-11-03T21:32:25.034Z" }, - { url = "https://files.pythonhosted.org/packages/23/ab/3b952ff7239f20d05f1f99e9e20188513905f218c81d52fb5e78d2bf7634/regex-2025.11.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:a4cb042b615245d5ff9b3794f56be4138b5adc35a4166014d31d1814744148c7", size = 291029, upload-time = "2025-11-03T21:32:26.528Z" }, - { url = "https://files.pythonhosted.org/packages/21/7e/3dc2749fc684f455f162dcafb8a187b559e2614f3826877d3844a131f37b/regex-2025.11.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:44f264d4bf02f3176467d90b294d59bf1db9fe53c141ff772f27a8b456b2a9ed", size = 807437, upload-time = "2025-11-03T21:32:28.363Z" }, - { url = "https://files.pythonhosted.org/packages/1b/0b/d529a85ab349c6a25d1ca783235b6e3eedf187247eab536797021f7126c6/regex-2025.11.3-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7be0277469bf3bd7a34a9c57c1b6a724532a0d235cd0dc4e7f4316f982c28b19", size = 873368, upload-time = "2025-11-03T21:32:30.4Z" }, - { url = "https://files.pythonhosted.org/packages/7d/18/2d868155f8c9e3e9d8f9e10c64e9a9f496bb8f7e037a88a8bed26b435af6/regex-2025.11.3-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d31e08426ff4b5b650f68839f5af51a92a5b51abd8554a60c2fbc7c71f25d0b", size = 914921, upload-time = "2025-11-03T21:32:32.123Z" }, - { url = "https://files.pythonhosted.org/packages/2d/71/9d72ff0f354fa783fe2ba913c8734c3b433b86406117a8db4ea2bf1c7a2f/regex-2025.11.3-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e43586ce5bd28f9f285a6e729466841368c4a0353f6fd08d4ce4630843d3648a", size = 812708, upload-time = "2025-11-03T21:32:34.305Z" }, - { url = "https://files.pythonhosted.org/packages/e7/19/ce4bf7f5575c97f82b6e804ffb5c4e940c62609ab2a0d9538d47a7fdf7d4/regex-2025.11.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:0f9397d561a4c16829d4e6ff75202c1c08b68a3bdbfe29dbfcdb31c9830907c6", size = 795472, upload-time = "2025-11-03T21:32:36.364Z" }, - { url = "https://files.pythonhosted.org/packages/03/86/fd1063a176ffb7b2315f9a1b08d17b18118b28d9df163132615b835a26ee/regex-2025.11.3-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:dd16e78eb18ffdb25ee33a0682d17912e8cc8a770e885aeee95020046128f1ce", size = 868341, upload-time = "2025-11-03T21:32:38.042Z" }, - { url = "https://files.pythonhosted.org/packages/12/43/103fb2e9811205e7386366501bc866a164a0430c79dd59eac886a2822950/regex-2025.11.3-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:ffcca5b9efe948ba0661e9df0fa50d2bc4b097c70b9810212d6b62f05d83b2dd", size = 854666, upload-time = "2025-11-03T21:32:40.079Z" }, - { url = "https://files.pythonhosted.org/packages/7d/22/e392e53f3869b75804762c7c848bd2dd2abf2b70fb0e526f58724638bd35/regex-2025.11.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c56b4d162ca2b43318ac671c65bd4d563e841a694ac70e1a976ac38fcf4ca1d2", size = 799473, upload-time = "2025-11-03T21:32:42.148Z" }, - { url = "https://files.pythonhosted.org/packages/4f/f9/8bd6b656592f925b6845fcbb4d57603a3ac2fb2373344ffa1ed70aa6820a/regex-2025.11.3-cp313-cp313t-win32.whl", hash = "sha256:9ddc42e68114e161e51e272f667d640f97e84a2b9ef14b7477c53aac20c2d59a", size = 268792, upload-time = "2025-11-03T21:32:44.13Z" }, - { url = "https://files.pythonhosted.org/packages/e5/87/0e7d603467775ff65cd2aeabf1b5b50cc1c3708556a8b849a2fa4dd1542b/regex-2025.11.3-cp313-cp313t-win_amd64.whl", hash = "sha256:7a7c7fdf755032ffdd72c77e3d8096bdcb0eb92e89e17571a196f03d88b11b3c", size = 280214, upload-time = "2025-11-03T21:32:45.853Z" }, - { url = "https://files.pythonhosted.org/packages/8d/d0/2afc6f8e94e2b64bfb738a7c2b6387ac1699f09f032d363ed9447fd2bb57/regex-2025.11.3-cp313-cp313t-win_arm64.whl", hash = "sha256:df9eb838c44f570283712e7cff14c16329a9f0fb19ca492d21d4b7528ee6821e", size = 271469, upload-time = "2025-11-03T21:32:48.026Z" }, - { url = "https://files.pythonhosted.org/packages/31/e9/f6e13de7e0983837f7b6d238ad9458800a874bf37c264f7923e63409944c/regex-2025.11.3-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:9697a52e57576c83139d7c6f213d64485d3df5bf84807c35fa409e6c970801c6", size = 489089, upload-time = "2025-11-03T21:32:50.027Z" }, - { url = "https://files.pythonhosted.org/packages/a3/5c/261f4a262f1fa65141c1b74b255988bd2fa020cc599e53b080667d591cfc/regex-2025.11.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:e18bc3f73bd41243c9b38a6d9f2366cd0e0137a9aebe2d8ff76c5b67d4c0a3f4", size = 291059, upload-time = "2025-11-03T21:32:51.682Z" }, - { url = "https://files.pythonhosted.org/packages/8e/57/f14eeb7f072b0e9a5a090d1712741fd8f214ec193dba773cf5410108bb7d/regex-2025.11.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:61a08bcb0ec14ff4e0ed2044aad948d0659604f824cbd50b55e30b0ec6f09c73", size = 288900, upload-time = "2025-11-03T21:32:53.569Z" }, - { url = "https://files.pythonhosted.org/packages/3c/6b/1d650c45e99a9b327586739d926a1cd4e94666b1bd4af90428b36af66dc7/regex-2025.11.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c9c30003b9347c24bcc210958c5d167b9e4f9be786cb380a7d32f14f9b84674f", size = 799010, upload-time = "2025-11-03T21:32:55.222Z" }, - { url = "https://files.pythonhosted.org/packages/99/ee/d66dcbc6b628ce4e3f7f0cbbb84603aa2fc0ffc878babc857726b8aab2e9/regex-2025.11.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4e1e592789704459900728d88d41a46fe3969b82ab62945560a31732ffc19a6d", size = 864893, upload-time = "2025-11-03T21:32:57.239Z" }, - { url = "https://files.pythonhosted.org/packages/bf/2d/f238229f1caba7ac87a6c4153d79947fb0261415827ae0f77c304260c7d3/regex-2025.11.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:6538241f45eb5a25aa575dbba1069ad786f68a4f2773a29a2bd3dd1f9de787be", size = 911522, upload-time = "2025-11-03T21:32:59.274Z" }, - { url = "https://files.pythonhosted.org/packages/bd/3d/22a4eaba214a917c80e04f6025d26143690f0419511e0116508e24b11c9b/regex-2025.11.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bce22519c989bb72a7e6b36a199384c53db7722fe669ba891da75907fe3587db", size = 803272, upload-time = "2025-11-03T21:33:01.393Z" }, - { url = "https://files.pythonhosted.org/packages/84/b1/03188f634a409353a84b5ef49754b97dbcc0c0f6fd6c8ede505a8960a0a4/regex-2025.11.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:66d559b21d3640203ab9075797a55165d79017520685fb407b9234d72ab63c62", size = 787958, upload-time = "2025-11-03T21:33:03.379Z" }, - { url = "https://files.pythonhosted.org/packages/99/6a/27d072f7fbf6fadd59c64d210305e1ff865cc3b78b526fd147db768c553b/regex-2025.11.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:669dcfb2e38f9e8c69507bace46f4889e3abbfd9b0c29719202883c0a603598f", size = 859289, upload-time = "2025-11-03T21:33:05.374Z" }, - { url = "https://files.pythonhosted.org/packages/9a/70/1b3878f648e0b6abe023172dacb02157e685564853cc363d9961bcccde4e/regex-2025.11.3-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:32f74f35ff0f25a5021373ac61442edcb150731fbaa28286bbc8bb1582c89d02", size = 850026, upload-time = "2025-11-03T21:33:07.131Z" }, - { url = "https://files.pythonhosted.org/packages/dd/d5/68e25559b526b8baab8e66839304ede68ff6727237a47727d240006bd0ff/regex-2025.11.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:e6c7a21dffba883234baefe91bc3388e629779582038f75d2a5be918e250f0ed", size = 789499, upload-time = "2025-11-03T21:33:09.141Z" }, - { url = "https://files.pythonhosted.org/packages/fc/df/43971264857140a350910d4e33df725e8c94dd9dee8d2e4729fa0d63d49e/regex-2025.11.3-cp314-cp314-win32.whl", hash = "sha256:795ea137b1d809eb6836b43748b12634291c0ed55ad50a7d72d21edf1cd565c4", size = 271604, upload-time = "2025-11-03T21:33:10.9Z" }, - { url = "https://files.pythonhosted.org/packages/01/6f/9711b57dc6894a55faf80a4c1b5aa4f8649805cb9c7aef46f7d27e2b9206/regex-2025.11.3-cp314-cp314-win_amd64.whl", hash = "sha256:9f95fbaa0ee1610ec0fc6b26668e9917a582ba80c52cc6d9ada15e30aa9ab9ad", size = 280320, upload-time = "2025-11-03T21:33:12.572Z" }, - { url = "https://files.pythonhosted.org/packages/f1/7e/f6eaa207d4377481f5e1775cdeb5a443b5a59b392d0065f3417d31d80f87/regex-2025.11.3-cp314-cp314-win_arm64.whl", hash = "sha256:dfec44d532be4c07088c3de2876130ff0fbeeacaa89a137decbbb5f665855a0f", size = 273372, upload-time = "2025-11-03T21:33:14.219Z" }, - { url = "https://files.pythonhosted.org/packages/c3/06/49b198550ee0f5e4184271cee87ba4dfd9692c91ec55289e6282f0f86ccf/regex-2025.11.3-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:ba0d8a5d7f04f73ee7d01d974d47c5834f8a1b0224390e4fe7c12a3a92a78ecc", size = 491985, upload-time = "2025-11-03T21:33:16.555Z" }, - { url = "https://files.pythonhosted.org/packages/ce/bf/abdafade008f0b1c9da10d934034cb670432d6cf6cbe38bbb53a1cfd6cf8/regex-2025.11.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:442d86cf1cfe4faabf97db7d901ef58347efd004934da045c745e7b5bd57ac49", size = 292669, upload-time = "2025-11-03T21:33:18.32Z" }, - { url = "https://files.pythonhosted.org/packages/f9/ef/0c357bb8edbd2ad8e273fcb9e1761bc37b8acbc6e1be050bebd6475f19c1/regex-2025.11.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:fd0a5e563c756de210bb964789b5abe4f114dacae9104a47e1a649b910361536", size = 291030, upload-time = "2025-11-03T21:33:20.048Z" }, - { url = "https://files.pythonhosted.org/packages/79/06/edbb67257596649b8fb088d6aeacbcb248ac195714b18a65e018bf4c0b50/regex-2025.11.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bf3490bcbb985a1ae97b2ce9ad1c0f06a852d5b19dde9b07bdf25bf224248c95", size = 807674, upload-time = "2025-11-03T21:33:21.797Z" }, - { url = "https://files.pythonhosted.org/packages/f4/d9/ad4deccfce0ea336296bd087f1a191543bb99ee1c53093dcd4c64d951d00/regex-2025.11.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:3809988f0a8b8c9dcc0f92478d6501fac7200b9ec56aecf0ec21f4a2ec4b6009", size = 873451, upload-time = "2025-11-03T21:33:23.741Z" }, - { url = "https://files.pythonhosted.org/packages/13/75/a55a4724c56ef13e3e04acaab29df26582f6978c000ac9cd6810ad1f341f/regex-2025.11.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f4ff94e58e84aedb9c9fce66d4ef9f27a190285b451420f297c9a09f2b9abee9", size = 914980, upload-time = "2025-11-03T21:33:25.999Z" }, - { url = "https://files.pythonhosted.org/packages/67/1e/a1657ee15bd9116f70d4a530c736983eed997b361e20ecd8f5ca3759d5c5/regex-2025.11.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7eb542fd347ce61e1321b0a6b945d5701528dca0cd9759c2e3bb8bd57e47964d", size = 812852, upload-time = "2025-11-03T21:33:27.852Z" }, - { url = "https://files.pythonhosted.org/packages/b8/6f/f7516dde5506a588a561d296b2d0044839de06035bb486b326065b4c101e/regex-2025.11.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6c2d5919075a1f2e413c00b056ea0c2f065b3f5fe83c3d07d325ab92dce51d6", size = 795566, upload-time = "2025-11-03T21:33:32.364Z" }, - { url = "https://files.pythonhosted.org/packages/d9/dd/3d10b9e170cc16fb34cb2cef91513cf3df65f440b3366030631b2984a264/regex-2025.11.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:3f8bf11a4827cc7ce5a53d4ef6cddd5ad25595d3c1435ef08f76825851343154", size = 868463, upload-time = "2025-11-03T21:33:34.459Z" }, - { url = "https://files.pythonhosted.org/packages/f5/8e/935e6beff1695aa9085ff83195daccd72acc82c81793df480f34569330de/regex-2025.11.3-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:22c12d837298651e5550ac1d964e4ff57c3f56965fc1812c90c9fb2028eaf267", size = 854694, upload-time = "2025-11-03T21:33:36.793Z" }, - { url = "https://files.pythonhosted.org/packages/92/12/10650181a040978b2f5720a6a74d44f841371a3d984c2083fc1752e4acf6/regex-2025.11.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:62ba394a3dda9ad41c7c780f60f6e4a70988741415ae96f6d1bf6c239cf01379", size = 799691, upload-time = "2025-11-03T21:33:39.079Z" }, - { url = "https://files.pythonhosted.org/packages/67/90/8f37138181c9a7690e7e4cb388debbd389342db3c7381d636d2875940752/regex-2025.11.3-cp314-cp314t-win32.whl", hash = "sha256:4bf146dca15cdd53224a1bf46d628bd7590e4a07fbb69e720d561aea43a32b38", size = 274583, upload-time = "2025-11-03T21:33:41.302Z" }, - { url = "https://files.pythonhosted.org/packages/8f/cd/867f5ec442d56beb56f5f854f40abcfc75e11d10b11fdb1869dd39c63aaf/regex-2025.11.3-cp314-cp314t-win_amd64.whl", hash = "sha256:adad1a1bcf1c9e76346e091d22d23ac54ef28e1365117d99521631078dfec9de", size = 284286, upload-time = "2025-11-03T21:33:43.324Z" }, - { url = "https://files.pythonhosted.org/packages/20/31/32c0c4610cbc070362bf1d2e4ea86d1ea29014d400a6d6c2486fcfd57766/regex-2025.11.3-cp314-cp314t-win_arm64.whl", hash = "sha256:c54f768482cef41e219720013cd05933b6f971d9562544d691c68699bf2b6801", size = 274741, upload-time = "2025-11-03T21:33:45.557Z" }, +version = "2026.1.15" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/0b/86/07d5056945f9ec4590b518171c4254a5925832eb727b56d3c38a7476f316/regex-2026.1.15.tar.gz", hash = "sha256:164759aa25575cbc0651bef59a0b18353e54300d79ace8084c818ad8ac72b7d5", size = 414811, upload-time = "2026-01-14T23:18:02.775Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d0/c9/0c80c96eab96948363d270143138d671d5731c3a692b417629bf3492a9d6/regex-2026.1.15-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1ae6020fb311f68d753b7efa9d4b9a5d47a5d6466ea0d5e3b5a471a960ea6e4a", size = 488168, upload-time = "2026-01-14T23:14:16.129Z" }, + { url = "https://files.pythonhosted.org/packages/17/f0/271c92f5389a552494c429e5cc38d76d1322eb142fb5db3c8ccc47751468/regex-2026.1.15-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:eddf73f41225942c1f994914742afa53dc0d01a6e20fe14b878a1b1edc74151f", size = 290636, upload-time = "2026-01-14T23:14:17.715Z" }, + { url = "https://files.pythonhosted.org/packages/a0/f9/5f1fd077d106ca5655a0f9ff8f25a1ab55b92128b5713a91ed7134ff688e/regex-2026.1.15-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e8cd52557603f5c66a548f69421310886b28b7066853089e1a71ee710e1cdc1", size = 288496, upload-time = "2026-01-14T23:14:19.326Z" }, + { url = "https://files.pythonhosted.org/packages/b5/e1/8f43b03a4968c748858ec77f746c286d81f896c2e437ccf050ebc5d3128c/regex-2026.1.15-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5170907244b14303edc5978f522f16c974f32d3aa92109fabc2af52411c9433b", size = 793503, upload-time = "2026-01-14T23:14:20.922Z" }, + { url = "https://files.pythonhosted.org/packages/8d/4e/a39a5e8edc5377a46a7c875c2f9a626ed3338cb3bb06931be461c3e1a34a/regex-2026.1.15-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:2748c1ec0663580b4510bd89941a31560b4b439a0b428b49472a3d9944d11cd8", size = 860535, upload-time = "2026-01-14T23:14:22.405Z" }, + { url = "https://files.pythonhosted.org/packages/dc/1c/9dce667a32a9477f7a2869c1c767dc00727284a9fa3ff5c09a5c6c03575e/regex-2026.1.15-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2f2775843ca49360508d080eaa87f94fa248e2c946bbcd963bb3aae14f333413", size = 907225, upload-time = "2026-01-14T23:14:23.897Z" }, + { url = "https://files.pythonhosted.org/packages/a4/3c/87ca0a02736d16b6262921425e84b48984e77d8e4e572c9072ce96e66c30/regex-2026.1.15-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d9ea2604370efc9a174c1b5dcc81784fb040044232150f7f33756049edfc9026", size = 800526, upload-time = "2026-01-14T23:14:26.039Z" }, + { url = "https://files.pythonhosted.org/packages/4b/ff/647d5715aeea7c87bdcbd2f578f47b415f55c24e361e639fe8c0cc88878f/regex-2026.1.15-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0dcd31594264029b57bf16f37fd7248a70b3b764ed9e0839a8f271b2d22c0785", size = 773446, upload-time = "2026-01-14T23:14:28.109Z" }, + { url = "https://files.pythonhosted.org/packages/af/89/bf22cac25cb4ba0fe6bff52ebedbb65b77a179052a9d6037136ae93f42f4/regex-2026.1.15-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c08c1f3e34338256732bd6938747daa3c0d5b251e04b6e43b5813e94d503076e", size = 783051, upload-time = "2026-01-14T23:14:29.929Z" }, + { url = "https://files.pythonhosted.org/packages/1e/f4/6ed03e71dca6348a5188363a34f5e26ffd5db1404780288ff0d79513bce4/regex-2026.1.15-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e43a55f378df1e7a4fa3547c88d9a5a9b7113f653a66821bcea4718fe6c58763", size = 854485, upload-time = "2026-01-14T23:14:31.366Z" }, + { url = "https://files.pythonhosted.org/packages/d9/9a/8e8560bd78caded8eb137e3e47612430a05b9a772caf60876435192d670a/regex-2026.1.15-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:f82110ab962a541737bd0ce87978d4c658f06e7591ba899192e2712a517badbb", size = 762195, upload-time = "2026-01-14T23:14:32.802Z" }, + { url = "https://files.pythonhosted.org/packages/38/6b/61fc710f9aa8dfcd764fe27d37edfaa023b1a23305a0d84fccd5adb346ea/regex-2026.1.15-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:27618391db7bdaf87ac6c92b31e8f0dfb83a9de0075855152b720140bda177a2", size = 845986, upload-time = "2026-01-14T23:14:34.898Z" }, + { url = "https://files.pythonhosted.org/packages/fd/2e/fbee4cb93f9d686901a7ca8d94285b80405e8c34fe4107f63ffcbfb56379/regex-2026.1.15-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:bfb0d6be01fbae8d6655c8ca21b3b72458606c4aec9bbc932db758d47aba6db1", size = 788992, upload-time = "2026-01-14T23:14:37.116Z" }, + { url = "https://files.pythonhosted.org/packages/ed/14/3076348f3f586de64b1ab75a3fbabdaab7684af7f308ad43be7ef1849e55/regex-2026.1.15-cp311-cp311-win32.whl", hash = "sha256:b10e42a6de0e32559a92f2f8dc908478cc0fa02838d7dbe764c44dca3fa13569", size = 265893, upload-time = "2026-01-14T23:14:38.426Z" }, + { url = "https://files.pythonhosted.org/packages/0f/19/772cf8b5fc803f5c89ba85d8b1870a1ca580dc482aa030383a9289c82e44/regex-2026.1.15-cp311-cp311-win_amd64.whl", hash = "sha256:e9bf3f0bbdb56633c07d7116ae60a576f846efdd86a8848f8d62b749e1209ca7", size = 277840, upload-time = "2026-01-14T23:14:39.785Z" }, + { url = "https://files.pythonhosted.org/packages/78/84/d05f61142709474da3c0853222d91086d3e1372bcdab516c6fd8d80f3297/regex-2026.1.15-cp311-cp311-win_arm64.whl", hash = "sha256:41aef6f953283291c4e4e6850607bd71502be67779586a61472beacb315c97ec", size = 270374, upload-time = "2026-01-14T23:14:41.592Z" }, + { url = "https://files.pythonhosted.org/packages/92/81/10d8cf43c807d0326efe874c1b79f22bfb0fb226027b0b19ebc26d301408/regex-2026.1.15-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:4c8fcc5793dde01641a35905d6731ee1548f02b956815f8f1cab89e515a5bdf1", size = 489398, upload-time = "2026-01-14T23:14:43.741Z" }, + { url = "https://files.pythonhosted.org/packages/90/b0/7c2a74e74ef2a7c32de724658a69a862880e3e4155cba992ba04d1c70400/regex-2026.1.15-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:bfd876041a956e6a90ad7cdb3f6a630c07d491280bfeed4544053cd434901681", size = 291339, upload-time = "2026-01-14T23:14:45.183Z" }, + { url = "https://files.pythonhosted.org/packages/19/4d/16d0773d0c818417f4cc20aa0da90064b966d22cd62a8c46765b5bd2d643/regex-2026.1.15-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9250d087bc92b7d4899ccd5539a1b2334e44eee85d848c4c1aef8e221d3f8c8f", size = 289003, upload-time = "2026-01-14T23:14:47.25Z" }, + { url = "https://files.pythonhosted.org/packages/c6/e4/1fc4599450c9f0863d9406e944592d968b8d6dfd0d552a7d569e43bceada/regex-2026.1.15-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c8a154cf6537ebbc110e24dabe53095e714245c272da9c1be05734bdad4a61aa", size = 798656, upload-time = "2026-01-14T23:14:48.77Z" }, + { url = "https://files.pythonhosted.org/packages/b2/e6/59650d73a73fa8a60b3a590545bfcf1172b4384a7df2e7fe7b9aab4e2da9/regex-2026.1.15-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8050ba2e3ea1d8731a549e83c18d2f0999fbc99a5f6bd06b4c91449f55291804", size = 864252, upload-time = "2026-01-14T23:14:50.528Z" }, + { url = "https://files.pythonhosted.org/packages/6e/ab/1d0f4d50a1638849a97d731364c9a80fa304fec46325e48330c170ee8e80/regex-2026.1.15-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0bf065240704cb8951cc04972cf107063917022511273e0969bdb34fc173456c", size = 912268, upload-time = "2026-01-14T23:14:52.952Z" }, + { url = "https://files.pythonhosted.org/packages/dd/df/0d722c030c82faa1d331d1921ee268a4e8fb55ca8b9042c9341c352f17fa/regex-2026.1.15-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c32bef3e7aeee75746748643667668ef941d28b003bfc89994ecf09a10f7a1b5", size = 803589, upload-time = "2026-01-14T23:14:55.182Z" }, + { url = "https://files.pythonhosted.org/packages/66/23/33289beba7ccb8b805c6610a8913d0131f834928afc555b241caabd422a9/regex-2026.1.15-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d5eaa4a4c5b1906bd0d2508d68927f15b81821f85092e06f1a34a4254b0e1af3", size = 775700, upload-time = "2026-01-14T23:14:56.707Z" }, + { url = "https://files.pythonhosted.org/packages/e7/65/bf3a42fa6897a0d3afa81acb25c42f4b71c274f698ceabd75523259f6688/regex-2026.1.15-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:86c1077a3cc60d453d4084d5b9649065f3bf1184e22992bd322e1f081d3117fb", size = 787928, upload-time = "2026-01-14T23:14:58.312Z" }, + { url = "https://files.pythonhosted.org/packages/f4/f5/13bf65864fc314f68cdd6d8ca94adcab064d4d39dbd0b10fef29a9da48fc/regex-2026.1.15-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:2b091aefc05c78d286657cd4db95f2e6313375ff65dcf085e42e4c04d9c8d410", size = 858607, upload-time = "2026-01-14T23:15:00.657Z" }, + { url = "https://files.pythonhosted.org/packages/a3/31/040e589834d7a439ee43fb0e1e902bc81bd58a5ba81acffe586bb3321d35/regex-2026.1.15-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:57e7d17f59f9ebfa9667e6e5a1c0127b96b87cb9cede8335482451ed00788ba4", size = 763729, upload-time = "2026-01-14T23:15:02.248Z" }, + { url = "https://files.pythonhosted.org/packages/9b/84/6921e8129687a427edf25a34a5594b588b6d88f491320b9de5b6339a4fcb/regex-2026.1.15-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:c6c4dcdfff2c08509faa15d36ba7e5ef5fcfab25f1e8f85a0c8f45bc3a30725d", size = 850697, upload-time = "2026-01-14T23:15:03.878Z" }, + { url = "https://files.pythonhosted.org/packages/8a/87/3d06143d4b128f4229158f2de5de6c8f2485170c7221e61bf381313314b2/regex-2026.1.15-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:cf8ff04c642716a7f2048713ddc6278c5fd41faa3b9cab12607c7abecd012c22", size = 789849, upload-time = "2026-01-14T23:15:06.102Z" }, + { url = "https://files.pythonhosted.org/packages/77/69/c50a63842b6bd48850ebc7ab22d46e7a2a32d824ad6c605b218441814639/regex-2026.1.15-cp312-cp312-win32.whl", hash = "sha256:82345326b1d8d56afbe41d881fdf62f1926d7264b2fc1537f99ae5da9aad7913", size = 266279, upload-time = "2026-01-14T23:15:07.678Z" }, + { url = "https://files.pythonhosted.org/packages/f2/36/39d0b29d087e2b11fd8191e15e81cce1b635fcc845297c67f11d0d19274d/regex-2026.1.15-cp312-cp312-win_amd64.whl", hash = "sha256:4def140aa6156bc64ee9912383d4038f3fdd18fee03a6f222abd4de6357ce42a", size = 277166, upload-time = "2026-01-14T23:15:09.257Z" }, + { url = "https://files.pythonhosted.org/packages/28/32/5b8e476a12262748851fa8ab1b0be540360692325975b094e594dfebbb52/regex-2026.1.15-cp312-cp312-win_arm64.whl", hash = "sha256:c6c565d9a6e1a8d783c1948937ffc377dd5771e83bd56de8317c450a954d2056", size = 270415, upload-time = "2026-01-14T23:15:10.743Z" }, + { url = "https://files.pythonhosted.org/packages/f8/2e/6870bb16e982669b674cce3ee9ff2d1d46ab80528ee6bcc20fb2292efb60/regex-2026.1.15-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e69d0deeb977ffe7ed3d2e4439360089f9c3f217ada608f0f88ebd67afb6385e", size = 489164, upload-time = "2026-01-14T23:15:13.962Z" }, + { url = "https://files.pythonhosted.org/packages/dc/67/9774542e203849b0286badf67199970a44ebdb0cc5fb739f06e47ada72f8/regex-2026.1.15-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:3601ffb5375de85a16f407854d11cca8fe3f5febbe3ac78fb2866bb220c74d10", size = 291218, upload-time = "2026-01-14T23:15:15.647Z" }, + { url = "https://files.pythonhosted.org/packages/b2/87/b0cda79f22b8dee05f774922a214da109f9a4c0eca5da2c9d72d77ea062c/regex-2026.1.15-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4c5ef43b5c2d4114eb8ea424bb8c9cec01d5d17f242af88b2448f5ee81caadbc", size = 288895, upload-time = "2026-01-14T23:15:17.788Z" }, + { url = "https://files.pythonhosted.org/packages/3b/6a/0041f0a2170d32be01ab981d6346c83a8934277d82c780d60b127331f264/regex-2026.1.15-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:968c14d4f03e10b2fd960f1d5168c1f0ac969381d3c1fcc973bc45fb06346599", size = 798680, upload-time = "2026-01-14T23:15:19.342Z" }, + { url = "https://files.pythonhosted.org/packages/58/de/30e1cfcdbe3e891324aa7568b7c968771f82190df5524fabc1138cb2d45a/regex-2026.1.15-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:56a5595d0f892f214609c9f76b41b7428bed439d98dc961efafdd1354d42baae", size = 864210, upload-time = "2026-01-14T23:15:22.005Z" }, + { url = "https://files.pythonhosted.org/packages/64/44/4db2f5c5ca0ccd40ff052ae7b1e9731352fcdad946c2b812285a7505ca75/regex-2026.1.15-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0bf650f26087363434c4e560011f8e4e738f6f3e029b85d4904c50135b86cfa5", size = 912358, upload-time = "2026-01-14T23:15:24.569Z" }, + { url = "https://files.pythonhosted.org/packages/79/b6/e6a5665d43a7c42467138c8a2549be432bad22cbd206f5ec87162de74bd7/regex-2026.1.15-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:18388a62989c72ac24de75f1449d0fb0b04dfccd0a1a7c1c43af5eb503d890f6", size = 803583, upload-time = "2026-01-14T23:15:26.526Z" }, + { url = "https://files.pythonhosted.org/packages/e7/53/7cd478222169d85d74d7437e74750005e993f52f335f7c04ff7adfda3310/regex-2026.1.15-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:6d220a2517f5893f55daac983bfa9fe998a7dbcaee4f5d27a88500f8b7873788", size = 775782, upload-time = "2026-01-14T23:15:29.352Z" }, + { url = "https://files.pythonhosted.org/packages/ca/b5/75f9a9ee4b03a7c009fe60500fe550b45df94f0955ca29af16333ef557c5/regex-2026.1.15-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c9c08c2fbc6120e70abff5d7f28ffb4d969e14294fb2143b4b5c7d20e46d1714", size = 787978, upload-time = "2026-01-14T23:15:31.295Z" }, + { url = "https://files.pythonhosted.org/packages/72/b3/79821c826245bbe9ccbb54f6eadb7879c722fd3e0248c17bfc90bf54e123/regex-2026.1.15-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7ef7d5d4bd49ec7364315167a4134a015f61e8266c6d446fc116a9ac4456e10d", size = 858550, upload-time = "2026-01-14T23:15:33.558Z" }, + { url = "https://files.pythonhosted.org/packages/4a/85/2ab5f77a1c465745bfbfcb3ad63178a58337ae8d5274315e2cc623a822fa/regex-2026.1.15-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:6e42844ad64194fa08d5ccb75fe6a459b9b08e6d7296bd704460168d58a388f3", size = 763747, upload-time = "2026-01-14T23:15:35.206Z" }, + { url = "https://files.pythonhosted.org/packages/6d/84/c27df502d4bfe2873a3e3a7cf1bdb2b9cc10284d1a44797cf38bed790470/regex-2026.1.15-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:cfecdaa4b19f9ca534746eb3b55a5195d5c95b88cac32a205e981ec0a22b7d31", size = 850615, upload-time = "2026-01-14T23:15:37.523Z" }, + { url = "https://files.pythonhosted.org/packages/7d/b7/658a9782fb253680aa8ecb5ccbb51f69e088ed48142c46d9f0c99b46c575/regex-2026.1.15-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:08df9722d9b87834a3d701f3fca570b2be115654dbfd30179f30ab2f39d606d3", size = 789951, upload-time = "2026-01-14T23:15:39.582Z" }, + { url = "https://files.pythonhosted.org/packages/fc/2a/5928af114441e059f15b2f63e188bd00c6529b3051c974ade7444b85fcda/regex-2026.1.15-cp313-cp313-win32.whl", hash = "sha256:d426616dae0967ca225ab12c22274eb816558f2f99ccb4a1d52ca92e8baf180f", size = 266275, upload-time = "2026-01-14T23:15:42.108Z" }, + { url = "https://files.pythonhosted.org/packages/4f/16/5bfbb89e435897bff28cf0352a992ca719d9e55ebf8b629203c96b6ce4f7/regex-2026.1.15-cp313-cp313-win_amd64.whl", hash = "sha256:febd38857b09867d3ed3f4f1af7d241c5c50362e25ef43034995b77a50df494e", size = 277145, upload-time = "2026-01-14T23:15:44.244Z" }, + { url = "https://files.pythonhosted.org/packages/56/c1/a09ff7392ef4233296e821aec5f78c51be5e91ffde0d163059e50fd75835/regex-2026.1.15-cp313-cp313-win_arm64.whl", hash = "sha256:8e32f7896f83774f91499d239e24cebfadbc07639c1494bb7213983842348337", size = 270411, upload-time = "2026-01-14T23:15:45.858Z" }, + { url = "https://files.pythonhosted.org/packages/3c/38/0cfd5a78e5c6db00e6782fdae70458f89850ce95baa5e8694ab91d89744f/regex-2026.1.15-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:ec94c04149b6a7b8120f9f44565722c7ae31b7a6d2275569d2eefa76b83da3be", size = 492068, upload-time = "2026-01-14T23:15:47.616Z" }, + { url = "https://files.pythonhosted.org/packages/50/72/6c86acff16cb7c959c4355826bbf06aad670682d07c8f3998d9ef4fee7cd/regex-2026.1.15-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:40c86d8046915bb9aeb15d3f3f15b6fd500b8ea4485b30e1bbc799dab3fe29f8", size = 292756, upload-time = "2026-01-14T23:15:49.307Z" }, + { url = "https://files.pythonhosted.org/packages/4e/58/df7fb69eadfe76526ddfce28abdc0af09ffe65f20c2c90932e89d705153f/regex-2026.1.15-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:726ea4e727aba21643205edad8f2187ec682d3305d790f73b7a51c7587b64bdd", size = 291114, upload-time = "2026-01-14T23:15:51.484Z" }, + { url = "https://files.pythonhosted.org/packages/ed/6c/a4011cd1cf96b90d2cdc7e156f91efbd26531e822a7fbb82a43c1016678e/regex-2026.1.15-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1cb740d044aff31898804e7bf1181cc72c03d11dfd19932b9911ffc19a79070a", size = 807524, upload-time = "2026-01-14T23:15:53.102Z" }, + { url = "https://files.pythonhosted.org/packages/1d/25/a53ffb73183f69c3e9f4355c4922b76d2840aee160af6af5fac229b6201d/regex-2026.1.15-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:05d75a668e9ea16f832390d22131fe1e8acc8389a694c8febc3e340b0f810b93", size = 873455, upload-time = "2026-01-14T23:15:54.956Z" }, + { url = "https://files.pythonhosted.org/packages/66/0b/8b47fc2e8f97d9b4a851736f3890a5f786443aa8901061c55f24c955f45b/regex-2026.1.15-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d991483606f3dbec93287b9f35596f41aa2e92b7c2ebbb935b63f409e243c9af", size = 915007, upload-time = "2026-01-14T23:15:57.041Z" }, + { url = "https://files.pythonhosted.org/packages/c2/fa/97de0d681e6d26fabe71968dbee06dd52819e9a22fdce5dac7256c31ed84/regex-2026.1.15-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:194312a14819d3e44628a44ed6fea6898fdbecb0550089d84c403475138d0a09", size = 812794, upload-time = "2026-01-14T23:15:58.916Z" }, + { url = "https://files.pythonhosted.org/packages/22/38/e752f94e860d429654aa2b1c51880bff8dfe8f084268258adf9151cf1f53/regex-2026.1.15-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fe2fda4110a3d0bc163c2e0664be44657431440722c5c5315c65155cab92f9e5", size = 781159, upload-time = "2026-01-14T23:16:00.817Z" }, + { url = "https://files.pythonhosted.org/packages/e9/a7/d739ffaef33c378fc888302a018d7f81080393d96c476b058b8c64fd2b0d/regex-2026.1.15-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:124dc36c85d34ef2d9164da41a53c1c8c122cfb1f6e1ec377a1f27ee81deb794", size = 795558, upload-time = "2026-01-14T23:16:03.267Z" }, + { url = "https://files.pythonhosted.org/packages/3e/c4/542876f9a0ac576100fc73e9c75b779f5c31e3527576cfc9cb3009dcc58a/regex-2026.1.15-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:a1774cd1981cd212506a23a14dba7fdeaee259f5deba2df6229966d9911e767a", size = 868427, upload-time = "2026-01-14T23:16:05.646Z" }, + { url = "https://files.pythonhosted.org/packages/fc/0f/d5655bea5b22069e32ae85a947aa564912f23758e112cdb74212848a1a1b/regex-2026.1.15-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:b5f7d8d2867152cdb625e72a530d2ccb48a3d199159144cbdd63870882fb6f80", size = 769939, upload-time = "2026-01-14T23:16:07.542Z" }, + { url = "https://files.pythonhosted.org/packages/20/06/7e18a4fa9d326daeda46d471a44ef94201c46eaa26dbbb780b5d92cbfdda/regex-2026.1.15-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:492534a0ab925d1db998defc3c302dae3616a2fc3fe2e08db1472348f096ddf2", size = 854753, upload-time = "2026-01-14T23:16:10.395Z" }, + { url = "https://files.pythonhosted.org/packages/3b/67/dc8946ef3965e166f558ef3b47f492bc364e96a265eb4a2bb3ca765c8e46/regex-2026.1.15-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c661fc820cfb33e166bf2450d3dadbda47c8d8981898adb9b6fe24e5e582ba60", size = 799559, upload-time = "2026-01-14T23:16:12.347Z" }, + { url = "https://files.pythonhosted.org/packages/a5/61/1bba81ff6d50c86c65d9fd84ce9699dd106438ee4cdb105bf60374ee8412/regex-2026.1.15-cp313-cp313t-win32.whl", hash = "sha256:99ad739c3686085e614bf77a508e26954ff1b8f14da0e3765ff7abbf7799f952", size = 268879, upload-time = "2026-01-14T23:16:14.049Z" }, + { url = "https://files.pythonhosted.org/packages/e9/5e/cef7d4c5fb0ea3ac5c775fd37db5747f7378b29526cc83f572198924ff47/regex-2026.1.15-cp313-cp313t-win_amd64.whl", hash = "sha256:32655d17905e7ff8ba5c764c43cb124e34a9245e45b83c22e81041e1071aee10", size = 280317, upload-time = "2026-01-14T23:16:15.718Z" }, + { url = "https://files.pythonhosted.org/packages/b4/52/4317f7a5988544e34ab57b4bde0f04944c4786128c933fb09825924d3e82/regex-2026.1.15-cp313-cp313t-win_arm64.whl", hash = "sha256:b2a13dd6a95e95a489ca242319d18fc02e07ceb28fa9ad146385194d95b3c829", size = 271551, upload-time = "2026-01-14T23:16:17.533Z" }, + { url = "https://files.pythonhosted.org/packages/52/0a/47fa888ec7cbbc7d62c5f2a6a888878e76169170ead271a35239edd8f0e8/regex-2026.1.15-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:d920392a6b1f353f4aa54328c867fec3320fa50657e25f64abf17af054fc97ac", size = 489170, upload-time = "2026-01-14T23:16:19.835Z" }, + { url = "https://files.pythonhosted.org/packages/ac/c4/d000e9b7296c15737c9301708e9e7fbdea009f8e93541b6b43bdb8219646/regex-2026.1.15-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:b5a28980a926fa810dbbed059547b02783952e2efd9c636412345232ddb87ff6", size = 291146, upload-time = "2026-01-14T23:16:21.541Z" }, + { url = "https://files.pythonhosted.org/packages/f9/b6/921cc61982e538682bdf3bdf5b2c6ab6b34368da1f8e98a6c1ddc503c9cf/regex-2026.1.15-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:621f73a07595d83f28952d7bd1e91e9d1ed7625fb7af0064d3516674ec93a2a2", size = 288986, upload-time = "2026-01-14T23:16:23.381Z" }, + { url = "https://files.pythonhosted.org/packages/ca/33/eb7383dde0bbc93f4fb9d03453aab97e18ad4024ac7e26cef8d1f0a2cff0/regex-2026.1.15-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3d7d92495f47567a9b1669c51fc8d6d809821849063d168121ef801bbc213846", size = 799098, upload-time = "2026-01-14T23:16:25.088Z" }, + { url = "https://files.pythonhosted.org/packages/27/56/b664dccae898fc8d8b4c23accd853f723bde0f026c747b6f6262b688029c/regex-2026.1.15-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8dd16fba2758db7a3780a051f245539c4451ca20910f5a5e6ea1c08d06d4a76b", size = 864980, upload-time = "2026-01-14T23:16:27.297Z" }, + { url = "https://files.pythonhosted.org/packages/16/40/0999e064a170eddd237bae9ccfcd8f28b3aa98a38bf727a086425542a4fc/regex-2026.1.15-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1e1808471fbe44c1a63e5f577a1d5f02fe5d66031dcbdf12f093ffc1305a858e", size = 911607, upload-time = "2026-01-14T23:16:29.235Z" }, + { url = "https://files.pythonhosted.org/packages/07/78/c77f644b68ab054e5a674fb4da40ff7bffb2c88df58afa82dbf86573092d/regex-2026.1.15-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0751a26ad39d4f2ade8fe16c59b2bf5cb19eb3d2cd543e709e583d559bd9efde", size = 803358, upload-time = "2026-01-14T23:16:31.369Z" }, + { url = "https://files.pythonhosted.org/packages/27/31/d4292ea8566eaa551fafc07797961c5963cf5235c797cc2ae19b85dfd04d/regex-2026.1.15-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0f0c7684c7f9ca241344ff95a1de964f257a5251968484270e91c25a755532c5", size = 775833, upload-time = "2026-01-14T23:16:33.141Z" }, + { url = "https://files.pythonhosted.org/packages/ce/b2/cff3bf2fea4133aa6fb0d1e370b37544d18c8350a2fa118c7e11d1db0e14/regex-2026.1.15-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:74f45d170a21df41508cb67165456538425185baaf686281fa210d7e729abc34", size = 788045, upload-time = "2026-01-14T23:16:35.005Z" }, + { url = "https://files.pythonhosted.org/packages/8d/99/2cb9b69045372ec877b6f5124bda4eb4253bc58b8fe5848c973f752bc52c/regex-2026.1.15-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:f1862739a1ffb50615c0fde6bae6569b5efbe08d98e59ce009f68a336f64da75", size = 859374, upload-time = "2026-01-14T23:16:36.919Z" }, + { url = "https://files.pythonhosted.org/packages/09/16/710b0a5abe8e077b1729a562d2f297224ad079f3a66dce46844c193416c8/regex-2026.1.15-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:453078802f1b9e2b7303fb79222c054cb18e76f7bdc220f7530fdc85d319f99e", size = 763940, upload-time = "2026-01-14T23:16:38.685Z" }, + { url = "https://files.pythonhosted.org/packages/dd/d1/7585c8e744e40eb3d32f119191969b91de04c073fca98ec14299041f6e7e/regex-2026.1.15-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:a30a68e89e5a218b8b23a52292924c1f4b245cb0c68d1cce9aec9bbda6e2c160", size = 850112, upload-time = "2026-01-14T23:16:40.646Z" }, + { url = "https://files.pythonhosted.org/packages/af/d6/43e1dd85df86c49a347aa57c1f69d12c652c7b60e37ec162e3096194a278/regex-2026.1.15-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:9479cae874c81bf610d72b85bb681a94c95722c127b55445285fb0e2c82db8e1", size = 789586, upload-time = "2026-01-14T23:16:42.799Z" }, + { url = "https://files.pythonhosted.org/packages/93/38/77142422f631e013f316aaae83234c629555729a9fbc952b8a63ac91462a/regex-2026.1.15-cp314-cp314-win32.whl", hash = "sha256:d639a750223132afbfb8f429c60d9d318aeba03281a5f1ab49f877456448dcf1", size = 271691, upload-time = "2026-01-14T23:16:44.671Z" }, + { url = "https://files.pythonhosted.org/packages/4a/a9/ab16b4649524ca9e05213c1cdbb7faa85cc2aa90a0230d2f796cbaf22736/regex-2026.1.15-cp314-cp314-win_amd64.whl", hash = "sha256:4161d87f85fa831e31469bfd82c186923070fc970b9de75339b68f0c75b51903", size = 280422, upload-time = "2026-01-14T23:16:46.607Z" }, + { url = "https://files.pythonhosted.org/packages/be/2a/20fd057bf3521cb4791f69f869635f73e0aaf2b9ad2d260f728144f9047c/regex-2026.1.15-cp314-cp314-win_arm64.whl", hash = "sha256:91c5036ebb62663a6b3999bdd2e559fd8456d17e2b485bf509784cd31a8b1705", size = 273467, upload-time = "2026-01-14T23:16:48.967Z" }, + { url = "https://files.pythonhosted.org/packages/ad/77/0b1e81857060b92b9cad239104c46507dd481b3ff1fa79f8e7f865aae38a/regex-2026.1.15-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:ee6854c9000a10938c79238de2379bea30c82e4925a371711af45387df35cab8", size = 492073, upload-time = "2026-01-14T23:16:51.154Z" }, + { url = "https://files.pythonhosted.org/packages/70/f3/f8302b0c208b22c1e4f423147e1913fd475ddd6230565b299925353de644/regex-2026.1.15-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:2c2b80399a422348ce5de4fe40c418d6299a0fa2803dd61dc0b1a2f28e280fcf", size = 292757, upload-time = "2026-01-14T23:16:53.08Z" }, + { url = "https://files.pythonhosted.org/packages/bf/f0/ef55de2460f3b4a6da9d9e7daacd0cb79d4ef75c64a2af316e68447f0df0/regex-2026.1.15-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:dca3582bca82596609959ac39e12b7dad98385b4fefccb1151b937383cec547d", size = 291122, upload-time = "2026-01-14T23:16:55.383Z" }, + { url = "https://files.pythonhosted.org/packages/cf/55/bb8ccbacabbc3a11d863ee62a9f18b160a83084ea95cdfc5d207bfc3dd75/regex-2026.1.15-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ef71d476caa6692eea743ae5ea23cde3260677f70122c4d258ca952e5c2d4e84", size = 807761, upload-time = "2026-01-14T23:16:57.251Z" }, + { url = "https://files.pythonhosted.org/packages/8f/84/f75d937f17f81e55679a0509e86176e29caa7298c38bd1db7ce9c0bf6075/regex-2026.1.15-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c243da3436354f4af6c3058a3f81a97d47ea52c9bd874b52fd30274853a1d5df", size = 873538, upload-time = "2026-01-14T23:16:59.349Z" }, + { url = "https://files.pythonhosted.org/packages/b8/d9/0da86327df70349aa8d86390da91171bd3ca4f0e7c1d1d453a9c10344da3/regex-2026.1.15-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8355ad842a7c7e9e5e55653eade3b7d1885ba86f124dd8ab1f722f9be6627434", size = 915066, upload-time = "2026-01-14T23:17:01.607Z" }, + { url = "https://files.pythonhosted.org/packages/2a/5e/f660fb23fc77baa2a61aa1f1fe3a4eea2bbb8a286ddec148030672e18834/regex-2026.1.15-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f192a831d9575271a22d804ff1a5355355723f94f31d9eef25f0d45a152fdc1a", size = 812938, upload-time = "2026-01-14T23:17:04.366Z" }, + { url = "https://files.pythonhosted.org/packages/69/33/a47a29bfecebbbfd1e5cd3f26b28020a97e4820f1c5148e66e3b7d4b4992/regex-2026.1.15-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:166551807ec20d47ceaeec380081f843e88c8949780cd42c40f18d16168bed10", size = 781314, upload-time = "2026-01-14T23:17:06.378Z" }, + { url = "https://files.pythonhosted.org/packages/65/ec/7ec2bbfd4c3f4e494a24dec4c6943a668e2030426b1b8b949a6462d2c17b/regex-2026.1.15-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f9ca1cbdc0fbfe5e6e6f8221ef2309988db5bcede52443aeaee9a4ad555e0dac", size = 795652, upload-time = "2026-01-14T23:17:08.521Z" }, + { url = "https://files.pythonhosted.org/packages/46/79/a5d8651ae131fe27d7c521ad300aa7f1c7be1dbeee4d446498af5411b8a9/regex-2026.1.15-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:b30bcbd1e1221783c721483953d9e4f3ab9c5d165aa709693d3f3946747b1aea", size = 868550, upload-time = "2026-01-14T23:17:10.573Z" }, + { url = "https://files.pythonhosted.org/packages/06/b7/25635d2809664b79f183070786a5552dd4e627e5aedb0065f4e3cf8ee37d/regex-2026.1.15-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:2a8d7b50c34578d0d3bf7ad58cde9652b7d683691876f83aedc002862a35dc5e", size = 769981, upload-time = "2026-01-14T23:17:12.871Z" }, + { url = "https://files.pythonhosted.org/packages/16/8b/fc3fcbb2393dcfa4a6c5ffad92dc498e842df4581ea9d14309fcd3c55fb9/regex-2026.1.15-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:9d787e3310c6a6425eb346be4ff2ccf6eece63017916fd77fe8328c57be83521", size = 854780, upload-time = "2026-01-14T23:17:14.837Z" }, + { url = "https://files.pythonhosted.org/packages/d0/38/dde117c76c624713c8a2842530be9c93ca8b606c0f6102d86e8cd1ce8bea/regex-2026.1.15-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:619843841e220adca114118533a574a9cd183ed8a28b85627d2844c500a2b0db", size = 799778, upload-time = "2026-01-14T23:17:17.369Z" }, + { url = "https://files.pythonhosted.org/packages/e3/0d/3a6cfa9ae99606afb612d8fb7a66b245a9d5ff0f29bb347c8a30b6ad561b/regex-2026.1.15-cp314-cp314t-win32.whl", hash = "sha256:e90b8db97f6f2c97eb045b51a6b2c5ed69cedd8392459e0642d4199b94fabd7e", size = 274667, upload-time = "2026-01-14T23:17:19.301Z" }, + { url = "https://files.pythonhosted.org/packages/5b/b2/297293bb0742fd06b8d8e2572db41a855cdf1cae0bf009b1cb74fe07e196/regex-2026.1.15-cp314-cp314t-win_amd64.whl", hash = "sha256:5ef19071f4ac9f0834793af85bd04a920b4407715624e40cb7a0631a11137cdf", size = 284386, upload-time = "2026-01-14T23:17:21.231Z" }, + { url = "https://files.pythonhosted.org/packages/95/e4/a3b9480c78cf8ee86626cb06f8d931d74d775897d44201ccb813097ae697/regex-2026.1.15-cp314-cp314t-win_arm64.whl", hash = "sha256:ca89c5e596fc05b015f27561b3793dc2fa0917ea0d7507eebb448efd35274a70", size = 274837, upload-time = "2026-01-14T23:17:23.146Z" }, ] [[package]] @@ -1167,28 +1212,28 @@ wheels = [ [[package]] name = "ruff" -version = "0.14.10" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/57/08/52232a877978dd8f9cf2aeddce3e611b40a63287dfca29b6b8da791f5e8d/ruff-0.14.10.tar.gz", hash = "sha256:9a2e830f075d1a42cd28420d7809ace390832a490ed0966fe373ba288e77aaf4", size = 5859763, upload-time = "2025-12-18T19:28:57.98Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/60/01/933704d69f3f05ee16ef11406b78881733c186fe14b6a46b05cfcaf6d3b2/ruff-0.14.10-py3-none-linux_armv6l.whl", hash = "sha256:7a3ce585f2ade3e1f29ec1b92df13e3da262178df8c8bdf876f48fa0e8316c49", size = 13527080, upload-time = "2025-12-18T19:29:25.642Z" }, - { url = "https://files.pythonhosted.org/packages/df/58/a0349197a7dfa603ffb7f5b0470391efa79ddc327c1e29c4851e85b09cc5/ruff-0.14.10-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:674f9be9372907f7257c51f1d4fc902cb7cf014b9980152b802794317941f08f", size = 13797320, upload-time = "2025-12-18T19:29:02.571Z" }, - { url = "https://files.pythonhosted.org/packages/7b/82/36be59f00a6082e38c23536df4e71cdbc6af8d7c707eade97fcad5c98235/ruff-0.14.10-py3-none-macosx_11_0_arm64.whl", hash = "sha256:d85713d522348837ef9df8efca33ccb8bd6fcfc86a2cde3ccb4bc9d28a18003d", size = 12918434, upload-time = "2025-12-18T19:28:51.202Z" }, - { url = "https://files.pythonhosted.org/packages/a6/00/45c62a7f7e34da92a25804f813ebe05c88aa9e0c25e5cb5a7d23dd7450e3/ruff-0.14.10-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6987ebe0501ae4f4308d7d24e2d0fe3d7a98430f5adfd0f1fead050a740a3a77", size = 13371961, upload-time = "2025-12-18T19:29:04.991Z" }, - { url = "https://files.pythonhosted.org/packages/40/31/a5906d60f0405f7e57045a70f2d57084a93ca7425f22e1d66904769d1628/ruff-0.14.10-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:16a01dfb7b9e4eee556fbfd5392806b1b8550c9b4a9f6acd3dbe6812b193c70a", size = 13275629, upload-time = "2025-12-18T19:29:21.381Z" }, - { url = "https://files.pythonhosted.org/packages/3e/60/61c0087df21894cf9d928dc04bcd4fb10e8b2e8dca7b1a276ba2155b2002/ruff-0.14.10-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7165d31a925b7a294465fa81be8c12a0e9b60fb02bf177e79067c867e71f8b1f", size = 14029234, upload-time = "2025-12-18T19:29:00.132Z" }, - { url = "https://files.pythonhosted.org/packages/44/84/77d911bee3b92348b6e5dab5a0c898d87084ea03ac5dc708f46d88407def/ruff-0.14.10-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:c561695675b972effb0c0a45db233f2c816ff3da8dcfbe7dfc7eed625f218935", size = 15449890, upload-time = "2025-12-18T19:28:53.573Z" }, - { url = "https://files.pythonhosted.org/packages/e9/36/480206eaefa24a7ec321582dda580443a8f0671fdbf6b1c80e9c3e93a16a/ruff-0.14.10-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4bb98fcbbc61725968893682fd4df8966a34611239c9fd07a1f6a07e7103d08e", size = 15123172, upload-time = "2025-12-18T19:29:23.453Z" }, - { url = "https://files.pythonhosted.org/packages/5c/38/68e414156015ba80cef5473d57919d27dfb62ec804b96180bafdeaf0e090/ruff-0.14.10-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f24b47993a9d8cb858429e97bdf8544c78029f09b520af615c1d261bf827001d", size = 14460260, upload-time = "2025-12-18T19:29:27.808Z" }, - { url = "https://files.pythonhosted.org/packages/b3/19/9e050c0dca8aba824d67cc0db69fb459c28d8cd3f6855b1405b3f29cc91d/ruff-0.14.10-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59aabd2e2c4fd614d2862e7939c34a532c04f1084476d6833dddef4afab87e9f", size = 14229978, upload-time = "2025-12-18T19:29:11.32Z" }, - { url = "https://files.pythonhosted.org/packages/51/eb/e8dd1dd6e05b9e695aa9dd420f4577debdd0f87a5ff2fedda33c09e9be8c/ruff-0.14.10-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:213db2b2e44be8625002dbea33bb9c60c66ea2c07c084a00d55732689d697a7f", size = 14338036, upload-time = "2025-12-18T19:29:09.184Z" }, - { url = "https://files.pythonhosted.org/packages/6a/12/f3e3a505db7c19303b70af370d137795fcfec136d670d5de5391e295c134/ruff-0.14.10-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b914c40ab64865a17a9a5b67911d14df72346a634527240039eb3bd650e5979d", size = 13264051, upload-time = "2025-12-18T19:29:13.431Z" }, - { url = "https://files.pythonhosted.org/packages/08/64/8c3a47eaccfef8ac20e0484e68e0772013eb85802f8a9f7603ca751eb166/ruff-0.14.10-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:1484983559f026788e3a5c07c81ef7d1e97c1c78ed03041a18f75df104c45405", size = 13283998, upload-time = "2025-12-18T19:29:06.994Z" }, - { url = "https://files.pythonhosted.org/packages/12/84/534a5506f4074e5cc0529e5cd96cfc01bb480e460c7edf5af70d2bcae55e/ruff-0.14.10-py3-none-musllinux_1_2_i686.whl", hash = "sha256:c70427132db492d25f982fffc8d6c7535cc2fd2c83fc8888f05caaa248521e60", size = 13601891, upload-time = "2025-12-18T19:28:55.811Z" }, - { url = "https://files.pythonhosted.org/packages/0d/1e/14c916087d8598917dbad9b2921d340f7884824ad6e9c55de948a93b106d/ruff-0.14.10-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5bcf45b681e9f1ee6445d317ce1fa9d6cba9a6049542d1c3d5b5958986be8830", size = 14336660, upload-time = "2025-12-18T19:29:16.531Z" }, - { url = "https://files.pythonhosted.org/packages/f2/1c/d7b67ab43f30013b47c12b42d1acd354c195351a3f7a1d67f59e54227ede/ruff-0.14.10-py3-none-win32.whl", hash = "sha256:104c49fc7ab73f3f3a758039adea978869a918f31b73280db175b43a2d9b51d6", size = 13196187, upload-time = "2025-12-18T19:29:19.006Z" }, - { url = "https://files.pythonhosted.org/packages/fb/9c/896c862e13886fae2af961bef3e6312db9ebc6adc2b156fe95e615dee8c1/ruff-0.14.10-py3-none-win_amd64.whl", hash = "sha256:466297bd73638c6bdf06485683e812db1c00c7ac96d4ddd0294a338c62fdc154", size = 14661283, upload-time = "2025-12-18T19:29:30.16Z" }, - { url = "https://files.pythonhosted.org/packages/74/31/b0e29d572670dca3674eeee78e418f20bdf97fa8aa9ea71380885e175ca0/ruff-0.14.10-py3-none-win_arm64.whl", hash = "sha256:e51d046cf6dda98a4633b8a8a771451107413b0f07183b2bef03f075599e44e6", size = 13729839, upload-time = "2025-12-18T19:28:48.636Z" }, +version = "0.14.14" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/2e/06/f71e3a86b2df0dfa2d2f72195941cd09b44f87711cb7fa5193732cb9a5fc/ruff-0.14.14.tar.gz", hash = "sha256:2d0f819c9a90205f3a867dbbd0be083bee9912e170fd7d9704cc8ae45824896b", size = 4515732, upload-time = "2026-01-22T22:30:17.527Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d2/89/20a12e97bc6b9f9f68343952da08a8099c57237aef953a56b82711d55edd/ruff-0.14.14-py3-none-linux_armv6l.whl", hash = "sha256:7cfe36b56e8489dee8fbc777c61959f60ec0f1f11817e8f2415f429552846aed", size = 10467650, upload-time = "2026-01-22T22:30:08.578Z" }, + { url = "https://files.pythonhosted.org/packages/a3/b1/c5de3fd2d5a831fcae21beda5e3589c0ba67eec8202e992388e4b17a6040/ruff-0.14.14-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6006a0082336e7920b9573ef8a7f52eec837add1265cc74e04ea8a4368cd704c", size = 10883245, upload-time = "2026-01-22T22:30:04.155Z" }, + { url = "https://files.pythonhosted.org/packages/b8/7c/3c1db59a10e7490f8f6f8559d1db8636cbb13dccebf18686f4e3c9d7c772/ruff-0.14.14-py3-none-macosx_11_0_arm64.whl", hash = "sha256:026c1d25996818f0bf498636686199d9bd0d9d6341c9c2c3b62e2a0198b758de", size = 10231273, upload-time = "2026-01-22T22:30:34.642Z" }, + { url = "https://files.pythonhosted.org/packages/a1/6e/5e0e0d9674be0f8581d1f5e0f0a04761203affce3232c1a1189d0e3b4dad/ruff-0.14.14-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f666445819d31210b71e0a6d1c01e24447a20b85458eea25a25fe8142210ae0e", size = 10585753, upload-time = "2026-01-22T22:30:31.781Z" }, + { url = "https://files.pythonhosted.org/packages/23/09/754ab09f46ff1884d422dc26d59ba18b4e5d355be147721bb2518aa2a014/ruff-0.14.14-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3c0f18b922c6d2ff9a5e6c3ee16259adc513ca775bcf82c67ebab7cbd9da5bc8", size = 10286052, upload-time = "2026-01-22T22:30:24.827Z" }, + { url = "https://files.pythonhosted.org/packages/c8/cc/e71f88dd2a12afb5f50733851729d6b571a7c3a35bfdb16c3035132675a0/ruff-0.14.14-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1629e67489c2dea43e8658c3dba659edbfd87361624b4040d1df04c9740ae906", size = 11043637, upload-time = "2026-01-22T22:30:13.239Z" }, + { url = "https://files.pythonhosted.org/packages/67/b2/397245026352494497dac935d7f00f1468c03a23a0c5db6ad8fc49ca3fb2/ruff-0.14.14-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:27493a2131ea0f899057d49d303e4292b2cae2bb57253c1ed1f256fbcd1da480", size = 12194761, upload-time = "2026-01-22T22:30:22.542Z" }, + { url = "https://files.pythonhosted.org/packages/5b/06/06ef271459f778323112c51b7587ce85230785cd64e91772034ddb88f200/ruff-0.14.14-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:01ff589aab3f5b539e35db38425da31a57521efd1e4ad1ae08fc34dbe30bd7df", size = 12005701, upload-time = "2026-01-22T22:30:20.499Z" }, + { url = "https://files.pythonhosted.org/packages/41/d6/99364514541cf811ccc5ac44362f88df66373e9fec1b9d1c4cc830593fe7/ruff-0.14.14-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1cc12d74eef0f29f51775f5b755913eb523546b88e2d733e1d701fe65144e89b", size = 11282455, upload-time = "2026-01-22T22:29:59.679Z" }, + { url = "https://files.pythonhosted.org/packages/ca/71/37daa46f89475f8582b7762ecd2722492df26421714a33e72ccc9a84d7a5/ruff-0.14.14-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb8481604b7a9e75eff53772496201690ce2687067e038b3cc31aaf16aa0b974", size = 11215882, upload-time = "2026-01-22T22:29:57.032Z" }, + { url = "https://files.pythonhosted.org/packages/2c/10/a31f86169ec91c0705e618443ee74ede0bdd94da0a57b28e72db68b2dbac/ruff-0.14.14-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:14649acb1cf7b5d2d283ebd2f58d56b75836ed8c6f329664fa91cdea19e76e66", size = 11180549, upload-time = "2026-01-22T22:30:27.175Z" }, + { url = "https://files.pythonhosted.org/packages/fd/1e/c723f20536b5163adf79bdd10c5f093414293cdf567eed9bdb7b83940f3f/ruff-0.14.14-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e8058d2145566510790eab4e2fad186002e288dec5e0d343a92fe7b0bc1b3e13", size = 10543416, upload-time = "2026-01-22T22:30:01.964Z" }, + { url = "https://files.pythonhosted.org/packages/3e/34/8a84cea7e42c2d94ba5bde1d7a4fae164d6318f13f933d92da6d7c2041ff/ruff-0.14.14-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:e651e977a79e4c758eb807f0481d673a67ffe53cfa92209781dfa3a996cf8412", size = 10285491, upload-time = "2026-01-22T22:30:29.51Z" }, + { url = "https://files.pythonhosted.org/packages/55/ef/b7c5ea0be82518906c978e365e56a77f8de7678c8bb6651ccfbdc178c29f/ruff-0.14.14-py3-none-musllinux_1_2_i686.whl", hash = "sha256:cc8b22da8d9d6fdd844a68ae937e2a0adf9b16514e9a97cc60355e2d4b219fc3", size = 10733525, upload-time = "2026-01-22T22:30:06.499Z" }, + { url = "https://files.pythonhosted.org/packages/6a/5b/aaf1dfbcc53a2811f6cc0a1759de24e4b03e02ba8762daabd9b6bd8c59e3/ruff-0.14.14-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:16bc890fb4cc9781bb05beb5ab4cd51be9e7cb376bf1dd3580512b24eb3fda2b", size = 11315626, upload-time = "2026-01-22T22:30:36.848Z" }, + { url = "https://files.pythonhosted.org/packages/2c/aa/9f89c719c467dfaf8ad799b9bae0df494513fb21d31a6059cb5870e57e74/ruff-0.14.14-py3-none-win32.whl", hash = "sha256:b530c191970b143375b6a68e6f743800b2b786bbcf03a7965b06c4bf04568167", size = 10502442, upload-time = "2026-01-22T22:30:38.93Z" }, + { url = "https://files.pythonhosted.org/packages/87/44/90fa543014c45560cae1fffc63ea059fb3575ee6e1cb654562197e5d16fb/ruff-0.14.14-py3-none-win_amd64.whl", hash = "sha256:3dde1435e6b6fe5b66506c1dff67a421d0b7f6488d466f651c07f4cab3bf20fd", size = 11630486, upload-time = "2026-01-22T22:30:10.852Z" }, + { url = "https://files.pythonhosted.org/packages/9e/6a/40fee331a52339926a92e17ae748827270b288a35ef4a15c9c8f2ec54715/ruff-0.14.14-py3-none-win_arm64.whl", hash = "sha256:56e6981a98b13a32236a72a8da421d7839221fa308b223b9283312312e5ac76c", size = 10920448, upload-time = "2026-01-22T22:30:15.417Z" }, ] [[package]] @@ -1271,11 +1316,11 @@ wheels = [ [[package]] name = "setuptools" -version = "80.9.0" +version = "80.10.1" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/18/5d/3bf57dcd21979b887f014ea83c24ae194cfcd12b9e0fda66b957c69d1fca/setuptools-80.9.0.tar.gz", hash = "sha256:f36b47402ecde768dbfafc46e8e4207b4360c654f1f3bb84475f0a28628fb19c", size = 1319958, upload-time = "2025-05-27T00:56:51.443Z" } +sdist = { url = "https://files.pythonhosted.org/packages/86/ff/f75651350db3cf2ef767371307eb163f3cc1ac03e16fdf3ac347607f7edb/setuptools-80.10.1.tar.gz", hash = "sha256:bf2e513eb8144c3298a3bd28ab1a5edb739131ec5c22e045ff93cd7f5319703a", size = 1229650, upload-time = "2026-01-21T09:42:03.061Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/a3/dc/17031897dae0efacfea57dfd3a82fdd2a2aeb58e0ff71b77b87e44edc772/setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922", size = 1201486, upload-time = "2025-05-27T00:56:49.664Z" }, + { url = "https://files.pythonhosted.org/packages/e0/76/f963c61683a39084aa575f98089253e1e852a4417cb8a3a8a422923a5246/setuptools-80.10.1-py3-none-any.whl", hash = "sha256:fc30c51cbcb8199a219c12cc9c281b5925a4978d212f84229c909636d9f6984e", size = 1099859, upload-time = "2026-01-21T09:42:00.688Z" }, ] [[package]] @@ -1327,9 +1372,10 @@ wheels = [ [[package]] name = "torch" -version = "2.9.1" +version = "2.10.0" source = { registry = "https://pypi.org/simple" } dependencies = [ + { name = "cuda-bindings", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "filelock" }, { name = "fsspec" }, { name = "jinja2" }, @@ -1355,35 +1401,35 @@ dependencies = [ { name = "typing-extensions" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/15/db/c064112ac0089af3d2f7a2b5bfbabf4aa407a78b74f87889e524b91c5402/torch-2.9.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:62b3fd888277946918cba4478cf849303da5359f0fb4e3bfb86b0533ba2eaf8d", size = 104220430, upload-time = "2025-11-12T15:20:31.705Z" }, - { url = "https://files.pythonhosted.org/packages/56/be/76eaa36c9cd032d3b01b001e2c5a05943df75f26211f68fae79e62f87734/torch-2.9.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:d033ff0ac3f5400df862a51bdde9bad83561f3739ea0046e68f5401ebfa67c1b", size = 899821446, upload-time = "2025-11-12T15:20:15.544Z" }, - { url = "https://files.pythonhosted.org/packages/47/cc/7a2949e38dfe3244c4df21f0e1c27bce8aedd6c604a587dd44fc21017cb4/torch-2.9.1-cp311-cp311-win_amd64.whl", hash = "sha256:0d06b30a9207b7c3516a9e0102114024755a07045f0c1d2f2a56b1819ac06bcb", size = 110973074, upload-time = "2025-11-12T15:21:39.958Z" }, - { url = "https://files.pythonhosted.org/packages/1e/ce/7d251155a783fb2c1bb6837b2b7023c622a2070a0a72726ca1df47e7ea34/torch-2.9.1-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:52347912d868653e1528b47cafaf79b285b98be3f4f35d5955389b1b95224475", size = 74463887, upload-time = "2025-11-12T15:20:36.611Z" }, - { url = "https://files.pythonhosted.org/packages/0f/27/07c645c7673e73e53ded71705045d6cb5bae94c4b021b03aa8d03eee90ab/torch-2.9.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:da5f6f4d7f4940a173e5572791af238cb0b9e21b1aab592bd8b26da4c99f1cd6", size = 104126592, upload-time = "2025-11-12T15:20:41.62Z" }, - { url = "https://files.pythonhosted.org/packages/19/17/e377a460603132b00760511299fceba4102bd95db1a0ee788da21298ccff/torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:27331cd902fb4322252657f3902adf1c4f6acad9dcad81d8df3ae14c7c4f07c4", size = 899742281, upload-time = "2025-11-12T15:22:17.602Z" }, - { url = "https://files.pythonhosted.org/packages/b1/1a/64f5769025db846a82567fa5b7d21dba4558a7234ee631712ee4771c436c/torch-2.9.1-cp312-cp312-win_amd64.whl", hash = "sha256:81a285002d7b8cfd3fdf1b98aa8df138d41f1a8334fd9ea37511517cedf43083", size = 110940568, upload-time = "2025-11-12T15:21:18.689Z" }, - { url = "https://files.pythonhosted.org/packages/6e/ab/07739fd776618e5882661d04c43f5b5586323e2f6a2d7d84aac20d8f20bd/torch-2.9.1-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:c0d25d1d8e531b8343bea0ed811d5d528958f1dcbd37e7245bc686273177ad7e", size = 74479191, upload-time = "2025-11-12T15:21:25.816Z" }, - { url = "https://files.pythonhosted.org/packages/20/60/8fc5e828d050bddfab469b3fe78e5ab9a7e53dda9c3bdc6a43d17ce99e63/torch-2.9.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:c29455d2b910b98738131990394da3e50eea8291dfeb4b12de71ecf1fdeb21cb", size = 104135743, upload-time = "2025-11-12T15:21:34.936Z" }, - { url = "https://files.pythonhosted.org/packages/f2/b7/6d3f80e6918213babddb2a37b46dbb14c15b14c5f473e347869a51f40e1f/torch-2.9.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:524de44cd13931208ba2c4bde9ec7741fd4ae6bfd06409a604fc32f6520c2bc9", size = 899749493, upload-time = "2025-11-12T15:24:36.356Z" }, - { url = "https://files.pythonhosted.org/packages/a6/47/c7843d69d6de8938c1cbb1eba426b1d48ddf375f101473d3e31a5fc52b74/torch-2.9.1-cp313-cp313-win_amd64.whl", hash = "sha256:545844cc16b3f91e08ce3b40e9c2d77012dd33a48d505aed34b7740ed627a1b2", size = 110944162, upload-time = "2025-11-12T15:21:53.151Z" }, - { url = "https://files.pythonhosted.org/packages/28/0e/2a37247957e72c12151b33a01e4df651d9d155dd74d8cfcbfad15a79b44a/torch-2.9.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5be4bf7496f1e3ffb1dd44b672adb1ac3f081f204c5ca81eba6442f5f634df8e", size = 74830751, upload-time = "2025-11-12T15:21:43.792Z" }, - { url = "https://files.pythonhosted.org/packages/4b/f7/7a18745edcd7b9ca2381aa03353647bca8aace91683c4975f19ac233809d/torch-2.9.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:30a3e170a84894f3652434b56d59a64a2c11366b0ed5776fab33c2439396bf9a", size = 104142929, upload-time = "2025-11-12T15:21:48.319Z" }, - { url = "https://files.pythonhosted.org/packages/f4/dd/f1c0d879f2863ef209e18823a988dc7a1bf40470750e3ebe927efdb9407f/torch-2.9.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:8301a7b431e51764629208d0edaa4f9e4c33e6df0f2f90b90e261d623df6a4e2", size = 899748978, upload-time = "2025-11-12T15:23:04.568Z" }, - { url = "https://files.pythonhosted.org/packages/1f/9f/6986b83a53b4d043e36f3f898b798ab51f7f20fdf1a9b01a2720f445043d/torch-2.9.1-cp313-cp313t-win_amd64.whl", hash = "sha256:2e1c42c0ae92bf803a4b2409fdfed85e30f9027a66887f5e7dcdbc014c7531db", size = 111176995, upload-time = "2025-11-12T15:22:01.618Z" }, - { url = "https://files.pythonhosted.org/packages/40/60/71c698b466dd01e65d0e9514b5405faae200c52a76901baf6906856f17e4/torch-2.9.1-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:2c14b3da5df416cf9cb5efab83aa3056f5b8cd8620b8fde81b4987ecab730587", size = 74480347, upload-time = "2025-11-12T15:21:57.648Z" }, - { url = "https://files.pythonhosted.org/packages/48/50/c4b5112546d0d13cc9eaa1c732b823d676a9f49ae8b6f97772f795874a03/torch-2.9.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1edee27a7c9897f4e0b7c14cfc2f3008c571921134522d5b9b5ec4ebbc69041a", size = 74433245, upload-time = "2025-11-12T15:22:39.027Z" }, - { url = "https://files.pythonhosted.org/packages/81/c9/2628f408f0518b3bae49c95f5af3728b6ab498c8624ab1e03a43dd53d650/torch-2.9.1-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:19d144d6b3e29921f1fc70503e9f2fc572cde6a5115c0c0de2f7ca8b1483e8b6", size = 104134804, upload-time = "2025-11-12T15:22:35.222Z" }, - { url = "https://files.pythonhosted.org/packages/28/fc/5bc91d6d831ae41bf6e9e6da6468f25330522e92347c9156eb3f1cb95956/torch-2.9.1-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:c432d04376f6d9767a9852ea0def7b47a7bbc8e7af3b16ac9cf9ce02b12851c9", size = 899747132, upload-time = "2025-11-12T15:23:36.068Z" }, - { url = "https://files.pythonhosted.org/packages/63/5d/e8d4e009e52b6b2cf1684bde2a6be157b96fb873732542fb2a9a99e85a83/torch-2.9.1-cp314-cp314-win_amd64.whl", hash = "sha256:d187566a2cdc726fc80138c3cdb260970fab1c27e99f85452721f7759bbd554d", size = 110934845, upload-time = "2025-11-12T15:22:48.367Z" }, - { url = "https://files.pythonhosted.org/packages/bd/b2/2d15a52516b2ea3f414643b8de68fa4cb220d3877ac8b1028c83dc8ca1c4/torch-2.9.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:cb10896a1f7fedaddbccc2017ce6ca9ecaaf990f0973bdfcf405439750118d2c", size = 74823558, upload-time = "2025-11-12T15:22:43.392Z" }, - { url = "https://files.pythonhosted.org/packages/86/5c/5b2e5d84f5b9850cd1e71af07524d8cbb74cba19379800f1f9f7c997fc70/torch-2.9.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:0a2bd769944991c74acf0c4ef23603b9c777fdf7637f115605a4b2d8023110c7", size = 104145788, upload-time = "2025-11-12T15:23:52.109Z" }, - { url = "https://files.pythonhosted.org/packages/a9/8c/3da60787bcf70add986c4ad485993026ac0ca74f2fc21410bc4eb1bb7695/torch-2.9.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:07c8a9660bc9414c39cac530ac83b1fb1b679d7155824144a40a54f4a47bfa73", size = 899735500, upload-time = "2025-11-12T15:24:08.788Z" }, - { url = "https://files.pythonhosted.org/packages/db/2b/f7818f6ec88758dfd21da46b6cd46af9d1b3433e53ddbb19ad1e0da17f9b/torch-2.9.1-cp314-cp314t-win_amd64.whl", hash = "sha256:c88d3299ddeb2b35dcc31753305612db485ab6f1823e37fb29451c8b2732b87e", size = 111163659, upload-time = "2025-11-12T15:23:20.009Z" }, + { url = "https://files.pythonhosted.org/packages/78/89/f5554b13ebd71e05c0b002f95148033e730d3f7067f67423026cc9c69410/torch-2.10.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:3282d9febd1e4e476630a099692b44fdc214ee9bf8ee5377732d9d9dfe5712e4", size = 145992610, upload-time = "2026-01-21T16:25:26.327Z" }, + { url = "https://files.pythonhosted.org/packages/ae/30/a3a2120621bf9c17779b169fc17e3dc29b230c29d0f8222f499f5e159aa8/torch-2.10.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a2f9edd8dbc99f62bc4dfb78af7bf89499bca3d753423ac1b4e06592e467b763", size = 915607863, upload-time = "2026-01-21T16:25:06.696Z" }, + { url = "https://files.pythonhosted.org/packages/6f/3d/c87b33c5f260a2a8ad68da7147e105f05868c281c63d65ed85aa4da98c66/torch-2.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:29b7009dba4b7a1c960260fc8ac85022c784250af43af9fb0ebafc9883782ebd", size = 113723116, upload-time = "2026-01-21T16:25:21.916Z" }, + { url = "https://files.pythonhosted.org/packages/61/d8/15b9d9d3a6b0c01b883787bd056acbe5cc321090d4b216d3ea89a8fcfdf3/torch-2.10.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:b7bd80f3477b830dd166c707c5b0b82a898e7b16f59a7d9d42778dd058272e8b", size = 79423461, upload-time = "2026-01-21T16:24:50.266Z" }, + { url = "https://files.pythonhosted.org/packages/cc/af/758e242e9102e9988969b5e621d41f36b8f258bb4a099109b7a4b4b50ea4/torch-2.10.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:5fd4117d89ffd47e3dcc71e71a22efac24828ad781c7e46aaaf56bf7f2796acf", size = 145996088, upload-time = "2026-01-21T16:24:44.171Z" }, + { url = "https://files.pythonhosted.org/packages/23/8e/3c74db5e53bff7ed9e34c8123e6a8bfef718b2450c35eefab85bb4a7e270/torch-2.10.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:787124e7db3b379d4f1ed54dd12ae7c741c16a4d29b49c0226a89bea50923ffb", size = 915711952, upload-time = "2026-01-21T16:23:53.503Z" }, + { url = "https://files.pythonhosted.org/packages/6e/01/624c4324ca01f66ae4c7cd1b74eb16fb52596dce66dbe51eff95ef9e7a4c/torch-2.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:2c66c61f44c5f903046cc696d088e21062644cbe541c7f1c4eaae88b2ad23547", size = 113757972, upload-time = "2026-01-21T16:24:39.516Z" }, + { url = "https://files.pythonhosted.org/packages/c9/5c/dee910b87c4d5c0fcb41b50839ae04df87c1cfc663cf1b5fca7ea565eeaa/torch-2.10.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:6d3707a61863d1c4d6ebba7be4ca320f42b869ee657e9b2c21c736bf17000294", size = 79498198, upload-time = "2026-01-21T16:24:34.704Z" }, + { url = "https://files.pythonhosted.org/packages/c9/6f/f2e91e34e3fcba2e3fc8d8f74e7d6c22e74e480bbd1db7bc8900fdf3e95c/torch-2.10.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:5c4d217b14741e40776dd7074d9006fd28b8a97ef5654db959d8635b2fe5f29b", size = 146004247, upload-time = "2026-01-21T16:24:29.335Z" }, + { url = "https://files.pythonhosted.org/packages/98/fb/5160261aeb5e1ee12ee95fe599d0541f7c976c3701d607d8fc29e623229f/torch-2.10.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:6b71486353fce0f9714ca0c9ef1c850a2ae766b409808acd58e9678a3edb7738", size = 915716445, upload-time = "2026-01-21T16:22:45.353Z" }, + { url = "https://files.pythonhosted.org/packages/6a/16/502fb1b41e6d868e8deb5b0e3ae926bbb36dab8ceb0d1b769b266ad7b0c3/torch-2.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:c2ee399c644dc92ef7bc0d4f7e74b5360c37cdbe7c5ba11318dda49ffac2bc57", size = 113757050, upload-time = "2026-01-21T16:24:19.204Z" }, + { url = "https://files.pythonhosted.org/packages/1a/0b/39929b148f4824bc3ad6f9f72a29d4ad865bcf7ebfc2fa67584773e083d2/torch-2.10.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:3202429f58309b9fa96a614885eace4b7995729f44beb54d3e4a47773649d382", size = 79851305, upload-time = "2026-01-21T16:24:09.209Z" }, + { url = "https://files.pythonhosted.org/packages/d8/14/21fbce63bc452381ba5f74a2c0a959fdf5ad5803ccc0c654e752e0dbe91a/torch-2.10.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:aae1b29cd68e50a9397f5ee897b9c24742e9e306f88a807a27d617f07adb3bd8", size = 146005472, upload-time = "2026-01-21T16:22:29.022Z" }, + { url = "https://files.pythonhosted.org/packages/54/fd/b207d1c525cb570ef47f3e9f836b154685011fce11a2f444ba8a4084d042/torch-2.10.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:6021db85958db2f07ec94e1bc77212721ba4920c12a18dc552d2ae36a3eb163f", size = 915612644, upload-time = "2026-01-21T16:21:47.019Z" }, + { url = "https://files.pythonhosted.org/packages/36/53/0197f868c75f1050b199fe58f9bf3bf3aecac9b4e85cc9c964383d745403/torch-2.10.0-cp313-cp313t-win_amd64.whl", hash = "sha256:ff43db38af76fda183156153983c9a096fc4c78d0cd1e07b14a2314c7f01c2c8", size = 113997015, upload-time = "2026-01-21T16:23:00.767Z" }, + { url = "https://files.pythonhosted.org/packages/0e/13/e76b4d9c160e89fff48bf16b449ea324bda84745d2ab30294c37c2434c0d/torch-2.10.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:cdf2a523d699b70d613243211ecaac14fe9c5df8a0b0a9c02add60fb2a413e0f", size = 79498248, upload-time = "2026-01-21T16:23:09.315Z" }, + { url = "https://files.pythonhosted.org/packages/4f/93/716b5ac0155f1be70ed81bacc21269c3ece8dba0c249b9994094110bfc51/torch-2.10.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:bf0d9ff448b0218e0433aeb198805192346c4fd659c852370d5cc245f602a06a", size = 79464992, upload-time = "2026-01-21T16:23:05.162Z" }, + { url = "https://files.pythonhosted.org/packages/69/2b/51e663ff190c9d16d4a8271203b71bc73a16aa7619b9f271a69b9d4a936b/torch-2.10.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:233aed0659a2503b831d8a67e9da66a62c996204c0bba4f4c442ccc0c68a3f60", size = 146018567, upload-time = "2026-01-21T16:22:23.393Z" }, + { url = "https://files.pythonhosted.org/packages/5e/cd/4b95ef7f293b927c283db0b136c42be91c8ec6845c44de0238c8c23bdc80/torch-2.10.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:682497e16bdfa6efeec8cde66531bc8d1fbbbb4d8788ec6173c089ed3cc2bfe5", size = 915721646, upload-time = "2026-01-21T16:21:16.983Z" }, + { url = "https://files.pythonhosted.org/packages/56/97/078a007208f8056d88ae43198833469e61a0a355abc0b070edd2c085eb9a/torch-2.10.0-cp314-cp314-win_amd64.whl", hash = "sha256:6528f13d2a8593a1a412ea07a99812495bec07e9224c28b2a25c0a30c7da025c", size = 113752373, upload-time = "2026-01-21T16:22:13.471Z" }, + { url = "https://files.pythonhosted.org/packages/d8/94/71994e7d0d5238393df9732fdab607e37e2b56d26a746cb59fdb415f8966/torch-2.10.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:f5ab4ba32383061be0fb74bda772d470140a12c1c3b58a0cfbf3dae94d164c28", size = 79850324, upload-time = "2026-01-21T16:22:09.494Z" }, + { url = "https://files.pythonhosted.org/packages/e2/65/1a05346b418ea8ccd10360eef4b3e0ce688fba544e76edec26913a8d0ee0/torch-2.10.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:716b01a176c2a5659c98f6b01bf868244abdd896526f1c692712ab36dbaf9b63", size = 146006482, upload-time = "2026-01-21T16:22:18.42Z" }, + { url = "https://files.pythonhosted.org/packages/1d/b9/5f6f9d9e859fc3235f60578fa64f52c9c6e9b4327f0fe0defb6de5c0de31/torch-2.10.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:d8f5912ba938233f86361e891789595ff35ca4b4e2ac8fe3670895e5976731d6", size = 915613050, upload-time = "2026-01-21T16:20:49.035Z" }, + { url = "https://files.pythonhosted.org/packages/66/4d/35352043ee0eaffdeff154fad67cd4a31dbed7ff8e3be1cc4549717d6d51/torch-2.10.0-cp314-cp314t-win_amd64.whl", hash = "sha256:71283a373f0ee2c89e0f0d5f446039bdabe8dbc3c9ccf35f0f784908b0acd185", size = 113995816, upload-time = "2026-01-21T16:22:05.312Z" }, ] [[package]] name = "torchvision" -version = "0.24.1" +version = "0.25.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "numpy" }, @@ -1391,30 +1437,30 @@ dependencies = [ { name = "torch" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/e7/69/30f5f03752aa1a7c23931d2519b31e557f3f10af5089d787cddf3b903ecf/torchvision-0.24.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:056c525dc875f18fe8e9c27079ada166a7b2755cea5a2199b0bc7f1f8364e600", size = 1891436, upload-time = "2025-11-12T15:25:04.3Z" }, - { url = "https://files.pythonhosted.org/packages/0c/69/49aae86edb75fe16460b59a191fcc0f568c2378f780bb063850db0fe007a/torchvision-0.24.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:1e39619de698e2821d71976c92c8a9e50cdfd1e993507dfb340f2688bfdd8283", size = 2387757, upload-time = "2025-11-12T15:25:06.795Z" }, - { url = "https://files.pythonhosted.org/packages/11/c9/1dfc3db98797b326f1d0c3f3bb61c83b167a813fc7eab6fcd2edb8c7eb9d/torchvision-0.24.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a0f106663e60332aa4fcb1ca2159ef8c3f2ed266b0e6df88de261048a840e0df", size = 8047682, upload-time = "2025-11-12T15:25:21.125Z" }, - { url = "https://files.pythonhosted.org/packages/fa/bb/cfc6a6f6ccc84a534ed1fdf029ae5716dd6ff04e57ed9dc2dab38bf652d5/torchvision-0.24.1-cp311-cp311-win_amd64.whl", hash = "sha256:a9308cdd37d8a42e14a3e7fd9d271830c7fecb150dd929b642f3c1460514599a", size = 4037588, upload-time = "2025-11-12T15:25:14.402Z" }, - { url = "https://files.pythonhosted.org/packages/f0/af/18e2c6b9538a045f60718a0c5a058908ccb24f88fde8e6f0fc12d5ff7bd3/torchvision-0.24.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e48bf6a8ec95872eb45763f06499f87bd2fb246b9b96cb00aae260fda2f96193", size = 1891433, upload-time = "2025-11-12T15:25:03.232Z" }, - { url = "https://files.pythonhosted.org/packages/9d/43/600e5cfb0643d10d633124f5982d7abc2170dfd7ce985584ff16edab3e76/torchvision-0.24.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:7fb7590c737ebe3e1c077ad60c0e5e2e56bb26e7bccc3b9d04dbfc34fd09f050", size = 2386737, upload-time = "2025-11-12T15:25:08.288Z" }, - { url = "https://files.pythonhosted.org/packages/93/b1/db2941526ecddd84884132e2742a55c9311296a6a38627f9e2627f5ac889/torchvision-0.24.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:66a98471fc18cad9064123106d810a75f57f0838eee20edc56233fd8484b0cc7", size = 8049868, upload-time = "2025-11-12T15:25:13.058Z" }, - { url = "https://files.pythonhosted.org/packages/69/98/16e583f59f86cd59949f59d52bfa8fc286f86341a229a9d15cbe7a694f0c/torchvision-0.24.1-cp312-cp312-win_amd64.whl", hash = "sha256:4aa6cb806eb8541e92c9b313e96192c6b826e9eb0042720e2fa250d021079952", size = 4302006, upload-time = "2025-11-12T15:25:16.184Z" }, - { url = "https://files.pythonhosted.org/packages/e4/97/ab40550f482577f2788304c27220e8ba02c63313bd74cf2f8920526aac20/torchvision-0.24.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:8a6696db7fb71eadb2c6a48602106e136c785642e598eb1533e0b27744f2cce6", size = 1891435, upload-time = "2025-11-12T15:25:28.642Z" }, - { url = "https://files.pythonhosted.org/packages/30/65/ac0a3f9be6abdbe4e1d82c915d7e20de97e7fd0e9a277970508b015309f3/torchvision-0.24.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:db2125c46f9cb25dc740be831ce3ce99303cfe60439249a41b04fd9f373be671", size = 2338718, upload-time = "2025-11-12T15:25:26.19Z" }, - { url = "https://files.pythonhosted.org/packages/10/b5/5bba24ff9d325181508501ed7f0c3de8ed3dd2edca0784d48b144b6c5252/torchvision-0.24.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:f035f0cacd1f44a8ff6cb7ca3627d84c54d685055961d73a1a9fb9827a5414c8", size = 8049661, upload-time = "2025-11-12T15:25:22.558Z" }, - { url = "https://files.pythonhosted.org/packages/5c/ec/54a96ae9ab6a0dd66d4bba27771f892e36478a9c3489fa56e51c70abcc4d/torchvision-0.24.1-cp313-cp313-win_amd64.whl", hash = "sha256:16274823b93048e0a29d83415166a2e9e0bf4e1b432668357b657612a4802864", size = 4319808, upload-time = "2025-11-12T15:25:17.318Z" }, - { url = "https://files.pythonhosted.org/packages/d5/f3/a90a389a7e547f3eb8821b13f96ea7c0563cdefbbbb60a10e08dda9720ff/torchvision-0.24.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:e3f96208b4bef54cd60e415545f5200346a65024e04f29a26cd0006dbf9e8e66", size = 2005342, upload-time = "2025-11-12T15:25:11.871Z" }, - { url = "https://files.pythonhosted.org/packages/a9/fe/ff27d2ed1b524078164bea1062f23d2618a5fc3208e247d6153c18c91a76/torchvision-0.24.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:f231f6a4f2aa6522713326d0d2563538fa72d613741ae364f9913027fa52ea35", size = 2341708, upload-time = "2025-11-12T15:25:25.08Z" }, - { url = "https://files.pythonhosted.org/packages/b1/b9/d6c903495cbdfd2533b3ef6f7b5643ff589ea062f8feb5c206ee79b9d9e5/torchvision-0.24.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:1540a9e7f8cf55fe17554482f5a125a7e426347b71de07327d5de6bfd8d17caa", size = 8177239, upload-time = "2025-11-12T15:25:18.554Z" }, - { url = "https://files.pythonhosted.org/packages/4f/2b/ba02e4261369c3798310483028495cf507e6cb3f394f42e4796981ecf3a7/torchvision-0.24.1-cp313-cp313t-win_amd64.whl", hash = "sha256:d83e16d70ea85d2f196d678bfb702c36be7a655b003abed84e465988b6128938", size = 4251604, upload-time = "2025-11-12T15:25:34.069Z" }, - { url = "https://files.pythonhosted.org/packages/42/84/577b2cef8f32094add5f52887867da4c2a3e6b4261538447e9b48eb25812/torchvision-0.24.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:cccf4b4fec7fdfcd3431b9ea75d1588c0a8596d0333245dafebee0462abe3388", size = 2005319, upload-time = "2025-11-12T15:25:23.827Z" }, - { url = "https://files.pythonhosted.org/packages/5f/34/ecb786bffe0159a3b49941a61caaae089853132f3cd1e8f555e3621f7e6f/torchvision-0.24.1-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:1b495edd3a8f9911292424117544f0b4ab780452e998649425d1f4b2bed6695f", size = 2338844, upload-time = "2025-11-12T15:25:32.625Z" }, - { url = "https://files.pythonhosted.org/packages/51/99/a84623786a6969504c87f2dc3892200f586ee13503f519d282faab0bb4f0/torchvision-0.24.1-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:ab211e1807dc3e53acf8f6638df9a7444c80c0ad050466e8d652b3e83776987b", size = 8175144, upload-time = "2025-11-12T15:25:31.355Z" }, - { url = "https://files.pythonhosted.org/packages/6d/ba/8fae3525b233e109317ce6a9c1de922ab2881737b029a7e88021f81e068f/torchvision-0.24.1-cp314-cp314-win_amd64.whl", hash = "sha256:18f9cb60e64b37b551cd605a3d62c15730c086362b40682d23e24b616a697d41", size = 4234459, upload-time = "2025-11-12T15:25:19.859Z" }, - { url = "https://files.pythonhosted.org/packages/50/33/481602c1c72d0485d4b3a6b48c9534b71c2957c9d83bf860eb837bf5a620/torchvision-0.24.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ec9d7379c519428395e4ffda4dbb99ec56be64b0a75b95989e00f9ec7ae0b2d7", size = 2005336, upload-time = "2025-11-12T15:25:27.225Z" }, - { url = "https://files.pythonhosted.org/packages/d0/7f/372de60bf3dd8f5593bd0d03f4aecf0d1fd58f5bc6943618d9d913f5e6d5/torchvision-0.24.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:af9201184c2712d808bd4eb656899011afdfce1e83721c7cb08000034df353fe", size = 2341704, upload-time = "2025-11-12T15:25:29.857Z" }, - { url = "https://files.pythonhosted.org/packages/36/9b/0f3b9ff3d0225ee2324ec663de0e7fb3eb855615ca958ac1875f22f1f8e5/torchvision-0.24.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:9ef95d819fd6df81bc7cc97b8f21a15d2c0d3ac5dbfaab5cbc2d2ce57114b19e", size = 8177422, upload-time = "2025-11-12T15:25:37.357Z" }, - { url = "https://files.pythonhosted.org/packages/d6/ab/e2bcc7c2f13d882a58f8b30ff86f794210b075736587ea50f8c545834f8a/torchvision-0.24.1-cp314-cp314t-win_amd64.whl", hash = "sha256:480b271d6edff83ac2e8d69bbb4cf2073f93366516a50d48f140ccfceedb002e", size = 4335190, upload-time = "2025-11-12T15:25:35.745Z" }, + { url = "https://files.pythonhosted.org/packages/3e/be/c704bceaf11c4f6b19d64337a34a877fcdfe3bd68160a8c9ae9bea4a35a3/torchvision-0.25.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:db74a551946b75d19f9996c419a799ffdf6a223ecf17c656f90da011f1d75b20", size = 1874923, upload-time = "2026-01-21T16:27:46.574Z" }, + { url = "https://files.pythonhosted.org/packages/ae/e9/f143cd71232430de1f547ceab840f68c55e127d72558b1061a71d0b193cd/torchvision-0.25.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:f49964f96644dbac2506dffe1a0a7ec0f2bf8cf7a588c3319fed26e6329ffdf3", size = 2344808, upload-time = "2026-01-21T16:27:43.191Z" }, + { url = "https://files.pythonhosted.org/packages/43/ae/ad5d6165797de234c9658752acb4fce65b78a6a18d82efdf8367c940d8da/torchvision-0.25.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:153c0d2cbc34b7cf2da19d73450f24ba36d2b75ec9211b9962b5022fb9e4ecee", size = 8070752, upload-time = "2026-01-21T16:27:33.748Z" }, + { url = "https://files.pythonhosted.org/packages/23/19/55b28aecdc7f38df57b8eb55eb0b14a62b470ed8efeb22cdc74224df1d6a/torchvision-0.25.0-cp311-cp311-win_amd64.whl", hash = "sha256:ea580ffd6094cc01914ad32f8c8118174f18974629af905cea08cb6d5d48c7b7", size = 4038722, upload-time = "2026-01-21T16:27:41.355Z" }, + { url = "https://files.pythonhosted.org/packages/56/3a/6ea0d73f49a9bef38a1b3a92e8dd455cea58470985d25635beab93841748/torchvision-0.25.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:c2abe430c90b1d5e552680037d68da4eb80a5852ebb1c811b2b89d299b10573b", size = 1874920, upload-time = "2026-01-21T16:27:45.348Z" }, + { url = "https://files.pythonhosted.org/packages/51/f8/c0e1ef27c66e15406fece94930e7d6feee4cb6374bbc02d945a630d6426e/torchvision-0.25.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:b75deafa2dfea3e2c2a525559b04783515e3463f6e830cb71de0fb7ea36fe233", size = 2344556, upload-time = "2026-01-21T16:27:40.125Z" }, + { url = "https://files.pythonhosted.org/packages/68/2f/f24b039169db474e8688f649377de082a965fbf85daf4e46c44412f1d15a/torchvision-0.25.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:f25aa9e380865b11ea6e9d99d84df86b9cc959f1a007cd966fc6f1ab2ed0e248", size = 8072351, upload-time = "2026-01-21T16:27:21.074Z" }, + { url = "https://files.pythonhosted.org/packages/ad/16/8f650c2e288977cf0f8f85184b90ee56ed170a4919347fc74ee99286ed6f/torchvision-0.25.0-cp312-cp312-win_amd64.whl", hash = "sha256:f9c55ae8d673ab493325d1267cbd285bb94d56f99626c00ac4644de32a59ede3", size = 4303059, upload-time = "2026-01-21T16:27:11.08Z" }, + { url = "https://files.pythonhosted.org/packages/f5/5b/1562a04a6a5a4cf8cf40016a0cdeda91ede75d6962cff7f809a85ae966a5/torchvision-0.25.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:24e11199e4d84ba9c5ee7825ebdf1cd37ce8deec225117f10243cae984ced3ec", size = 1874918, upload-time = "2026-01-21T16:27:39.02Z" }, + { url = "https://files.pythonhosted.org/packages/36/b1/3d6c42f62c272ce34fcce609bb8939bdf873dab5f1b798fd4e880255f129/torchvision-0.25.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:5f271136d2d2c0b7a24c5671795c6e4fd8da4e0ea98aeb1041f62bc04c4370ef", size = 2309106, upload-time = "2026-01-21T16:27:30.624Z" }, + { url = "https://files.pythonhosted.org/packages/c7/60/59bb9c8b67cce356daeed4cb96a717caa4f69c9822f72e223a0eae7a9bd9/torchvision-0.25.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:855c0dc6d37f462482da7531c6788518baedca1e0847f3df42a911713acdfe52", size = 8071522, upload-time = "2026-01-21T16:27:29.392Z" }, + { url = "https://files.pythonhosted.org/packages/32/a5/9a9b1de0720f884ea50dbf9acb22cbe5312e51d7b8c4ac6ba9b51efd9bba/torchvision-0.25.0-cp313-cp313-win_amd64.whl", hash = "sha256:cef0196be31be421f6f462d1e9da1101be7332d91984caa6f8022e6c78a5877f", size = 4321911, upload-time = "2026-01-21T16:27:35.195Z" }, + { url = "https://files.pythonhosted.org/packages/52/99/dca81ed21ebaeff2b67cc9f815a20fdaa418b69f5f9ea4c6ed71721470db/torchvision-0.25.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:a8f8061284395ce31bcd460f2169013382ccf411148ceb2ee38e718e9860f5a7", size = 1896209, upload-time = "2026-01-21T16:27:32.159Z" }, + { url = "https://files.pythonhosted.org/packages/28/cc/2103149761fdb4eaed58a53e8437b2d716d48f05174fab1d9fcf1e2a2244/torchvision-0.25.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:146d02c9876858420adf41f3189fe90e3d6a409cbfa65454c09f25fb33bf7266", size = 2310735, upload-time = "2026-01-21T16:27:22.327Z" }, + { url = "https://files.pythonhosted.org/packages/76/ad/f4c985ad52ddd3b22711c588501be1b330adaeaf6850317f66751711b78c/torchvision-0.25.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:c4d395cb2c4a2712f6eb93a34476cdf7aae74bb6ea2ea1917f858e96344b00aa", size = 8089557, upload-time = "2026-01-21T16:27:27.666Z" }, + { url = "https://files.pythonhosted.org/packages/63/cc/0ea68b5802e5e3c31f44b307e74947bad5a38cc655231d845534ed50ddb8/torchvision-0.25.0-cp313-cp313t-win_amd64.whl", hash = "sha256:5e6b449e9fa7d642142c0e27c41e5a43b508d57ed8e79b7c0a0c28652da8678c", size = 4344260, upload-time = "2026-01-21T16:27:17.018Z" }, + { url = "https://files.pythonhosted.org/packages/9e/1f/fa839532660e2602b7e704d65010787c5bb296258b44fa8b9c1cd6175e7d/torchvision-0.25.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:620a236288d594dcec7634c754484542dc0a5c1b0e0b83a34bda5e91e9b7c3a1", size = 1896193, upload-time = "2026-01-21T16:27:24.785Z" }, + { url = "https://files.pythonhosted.org/packages/80/ed/d51889da7ceaf5ff7a0574fb28f9b6b223df19667265395891f81b364ab3/torchvision-0.25.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:0b5e7f50002a8145a98c5694a018e738c50e2972608310c7e88e1bd4c058f6ce", size = 2309331, upload-time = "2026-01-21T16:27:19.97Z" }, + { url = "https://files.pythonhosted.org/packages/90/a5/f93fcffaddd8f12f9e812256830ec9c9ca65abbf1bc369379f9c364d1ff4/torchvision-0.25.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:632db02300e83793812eee4f61ae6a2686dab10b4cfd628b620dc47747aa9d03", size = 8088713, upload-time = "2026-01-21T16:27:15.281Z" }, + { url = "https://files.pythonhosted.org/packages/1f/eb/d0096eed5690d962853213f2ee00d91478dfcb586b62dbbb449fb8abc3a6/torchvision-0.25.0-cp314-cp314-win_amd64.whl", hash = "sha256:d1abd5ed030c708f5dbf4812ad5f6fbe9384b63c40d6bd79f8df41a4a759a917", size = 4325058, upload-time = "2026-01-21T16:27:26.165Z" }, + { url = "https://files.pythonhosted.org/packages/97/36/96374a4c7ab50dea9787ce987815614ccfe988a42e10ac1a2e3e5b60319a/torchvision-0.25.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ad9a8a5877782944d99186e4502a614770fe906626d76e9cd32446a0ac3075f2", size = 1896207, upload-time = "2026-01-21T16:27:23.383Z" }, + { url = "https://files.pythonhosted.org/packages/b5/e2/7abb10a867db79b226b41da419b63b69c0bd5b82438c4a4ed50e084c552f/torchvision-0.25.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:40a122c3cf4d14b651f095e0f672b688dde78632783fc5cd3d4d5e4f6a828563", size = 2310741, upload-time = "2026-01-21T16:27:18.712Z" }, + { url = "https://files.pythonhosted.org/packages/08/e6/0927784e6ffc340b6676befde1c60260bd51641c9c574b9298d791a9cda4/torchvision-0.25.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:846890161b825b38aa85fc37fb3ba5eea74e7091ff28bab378287111483b6443", size = 8089772, upload-time = "2026-01-21T16:27:14.048Z" }, + { url = "https://files.pythonhosted.org/packages/b6/37/e7ca4ec820d434c0f23f824eb29f0676a0c3e7a118f1514f5b949c3356da/torchvision-0.25.0-cp314-cp314t-win_amd64.whl", hash = "sha256:f07f01d27375ad89d72aa2b3f2180f07da95dd9d2e4c758e015c0acb2da72977", size = 4425879, upload-time = "2026-01-21T16:27:12.579Z" }, ] [[package]] @@ -1432,7 +1478,7 @@ wheels = [ [[package]] name = "transformers" version = "5.0.0.dev0" -source = { git = "https://github.com/huggingface/transformers#e8c51d1848187b9e58d00bf7d638811686ab2a4b" } +source = { git = "https://github.com/huggingface/transformers#3af2eb7a29272ed58c9d1935a5d86ad283c563c4" } dependencies = [ { name = "filelock" }, { name = "huggingface-hub" }, @@ -1440,7 +1486,6 @@ dependencies = [ { name = "packaging" }, { name = "pyyaml" }, { name = "regex" }, - { name = "requests" }, { name = "safetensors" }, { name = "tokenizers" }, { name = "tqdm" }, @@ -1449,28 +1494,28 @@ dependencies = [ [[package]] name = "triton" -version = "3.5.1" +version = "3.6.0" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/b0/72/ec90c3519eaf168f22cb1757ad412f3a2add4782ad3a92861c9ad135d886/triton-3.5.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:61413522a48add32302353fdbaaf92daaaab06f6b5e3229940d21b5207f47579", size = 170425802, upload-time = "2025-11-11T17:40:53.209Z" }, - { url = "https://files.pythonhosted.org/packages/f2/50/9a8358d3ef58162c0a415d173cfb45b67de60176e1024f71fbc4d24c0b6d/triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d2c6b915a03888ab931a9fd3e55ba36785e1fe70cbea0b40c6ef93b20fc85232", size = 170470207, upload-time = "2025-11-11T17:41:00.253Z" }, - { url = "https://files.pythonhosted.org/packages/27/46/8c3bbb5b0a19313f50edcaa363b599e5a1a5ac9683ead82b9b80fe497c8d/triton-3.5.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f3f4346b6ebbd4fad18773f5ba839114f4826037c9f2f34e0148894cd5dd3dba", size = 170470410, upload-time = "2025-11-11T17:41:06.319Z" }, - { url = "https://files.pythonhosted.org/packages/37/92/e97fcc6b2c27cdb87ce5ee063d77f8f26f19f06916aa680464c8104ef0f6/triton-3.5.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0b4d2c70127fca6a23e247f9348b8adde979d2e7a20391bfbabaac6aebc7e6a8", size = 170579924, upload-time = "2025-11-11T17:41:12.455Z" }, - { url = "https://files.pythonhosted.org/packages/a4/e6/c595c35e5c50c4bc56a7bac96493dad321e9e29b953b526bbbe20f9911d0/triton-3.5.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d0637b1efb1db599a8e9dc960d53ab6e4637db7d4ab6630a0974705d77b14b60", size = 170480488, upload-time = "2025-11-11T17:41:18.222Z" }, - { url = "https://files.pythonhosted.org/packages/16/b5/b0d3d8b901b6a04ca38df5e24c27e53afb15b93624d7fd7d658c7cd9352a/triton-3.5.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bac7f7d959ad0f48c0e97d6643a1cc0fd5786fe61cb1f83b537c6b2d54776478", size = 170582192, upload-time = "2025-11-11T17:41:23.963Z" }, + { url = "https://files.pythonhosted.org/packages/e0/12/b05ba554d2c623bffa59922b94b0775673de251f468a9609bc9e45de95e9/triton-3.6.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e8e323d608e3a9bfcc2d9efcc90ceefb764a82b99dea12a86d643c72539ad5d3", size = 188214640, upload-time = "2026-01-20T16:00:35.869Z" }, + { url = "https://files.pythonhosted.org/packages/ab/a8/cdf8b3e4c98132f965f88c2313a4b493266832ad47fb52f23d14d4f86bb5/triton-3.6.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:74caf5e34b66d9f3a429af689c1c7128daba1d8208df60e81106b115c00d6fca", size = 188266850, upload-time = "2026-01-20T16:00:43.041Z" }, + { url = "https://files.pythonhosted.org/packages/f9/0b/37d991d8c130ce81a8728ae3c25b6e60935838e9be1b58791f5997b24a54/triton-3.6.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:10c7f76c6e72d2ef08df639e3d0d30729112f47a56b0c81672edc05ee5116ac9", size = 188289450, upload-time = "2026-01-20T16:00:49.136Z" }, + { url = "https://files.pythonhosted.org/packages/35/f8/9c66bfc55361ec6d0e4040a0337fb5924ceb23de4648b8a81ae9d33b2b38/triton-3.6.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d002e07d7180fd65e622134fbd980c9a3d4211fb85224b56a0a0efbd422ab72f", size = 188400296, upload-time = "2026-01-20T16:00:56.042Z" }, + { url = "https://files.pythonhosted.org/packages/df/3d/9e7eee57b37c80cec63322c0231bb6da3cfe535a91d7a4d64896fcb89357/triton-3.6.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a17a5d5985f0ac494ed8a8e54568f092f7057ef60e1b0fa09d3fd1512064e803", size = 188273063, upload-time = "2026-01-20T16:01:07.278Z" }, + { url = "https://files.pythonhosted.org/packages/f6/56/6113c23ff46c00aae423333eb58b3e60bdfe9179d542781955a5e1514cb3/triton-3.6.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:46bd1c1af4b6704e554cad2eeb3b0a6513a980d470ccfa63189737340c7746a7", size = 188397994, upload-time = "2026-01-20T16:01:14.236Z" }, ] [[package]] name = "typer-slim" -version = "0.21.0" +version = "0.21.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/f9/3b/2f60ce16f578b1db5b8816d37d6a4d9786b33b76407fc8c13b0b86312c31/typer_slim-0.21.0.tar.gz", hash = "sha256:f2dbd150cfa0fead2242e21fa9f654dfc64773763ddf07c6be9a49ad34f79557", size = 106841, upload-time = "2025-12-25T09:54:55.998Z" } +sdist = { url = "https://files.pythonhosted.org/packages/17/d4/064570dec6358aa9049d4708e4a10407d74c99258f8b2136bb8702303f1a/typer_slim-0.21.1.tar.gz", hash = "sha256:73495dd08c2d0940d611c5a8c04e91c2a0a98600cbd4ee19192255a233b6dbfd", size = 110478, upload-time = "2026-01-06T11:21:11.176Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/b4/84/e97abf10e4a699194ff07fd586ec7f4cf867d9d04bead559a65f9e7aff84/typer_slim-0.21.0-py3-none-any.whl", hash = "sha256:92aee2188ac6fc2b2924bd75bb61a340b78bd8cd51fd9735533ce5a856812c8e", size = 47174, upload-time = "2025-12-25T09:54:54.609Z" }, + { url = "https://files.pythonhosted.org/packages/c8/0a/4aca634faf693e33004796b6cee0ae2e1dba375a800c16ab8d3eff4bb800/typer_slim-0.21.1-py3-none-any.whl", hash = "sha256:6e6c31047f171ac93cc5a973c9e617dbc5ab2bddc4d0a3135dc161b4e2020e0d", size = 47444, upload-time = "2026-01-06T11:21:12.441Z" }, ] [[package]] @@ -1496,20 +1541,20 @@ wheels = [ [[package]] name = "urllib3" -version = "2.6.2" +version = "2.6.3" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/1e/24/a2a2ed9addd907787d7aa0355ba36a6cadf1768b934c652ea78acbd59dcd/urllib3-2.6.2.tar.gz", hash = "sha256:016f9c98bb7e98085cb2b4b17b87d2c702975664e4f060c6532e64d1c1a5e797", size = 432930, upload-time = "2025-12-11T15:56:40.252Z" } +sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/6d/b9/4095b668ea3678bf6a0af005527f39de12fb026516fb3df17495a733b7f8/urllib3-2.6.2-py3-none-any.whl", hash = "sha256:ec21cddfe7724fc7cb4ba4bea7aa8e2ef36f607a4bab81aa6ce42a13dc3f03dd", size = 131182, upload-time = "2025-12-11T15:56:38.584Z" }, + { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" }, ] [[package]] name = "wcwidth" -version = "0.2.14" +version = "0.3.3" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/24/30/6b0809f4510673dc723187aeaf24c7f5459922d01e2f794277a3dfb90345/wcwidth-0.2.14.tar.gz", hash = "sha256:4d478375d31bc5395a3c55c40ccdf3354688364cd61c4f6adacaa9215d0b3605", size = 102293, upload-time = "2025-09-22T16:29:53.023Z" } +sdist = { url = "https://files.pythonhosted.org/packages/b5/3a/c63d2afd6dc2cad55a44bea48c7db75edde859e320bdceb9351ba63fceb6/wcwidth-0.3.3.tar.gz", hash = "sha256:f8f7d42c8a067d909b80b425342d02c423c5edc546347475e1d402fe3d35bb63", size = 233784, upload-time = "2026-01-24T16:23:58.578Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/af/b5/123f13c975e9f27ab9c0770f514345bd406d0e8d3b7a0723af9d43f710af/wcwidth-0.2.14-py2.py3-none-any.whl", hash = "sha256:a7bb560c8aee30f9957e5f9895805edd20602f2d7f720186dfd906e82b4982e1", size = 37286, upload-time = "2025-09-22T16:29:51.641Z" }, + { url = "https://files.pythonhosted.org/packages/4f/bc/ab575ebf0254577034d23908299b0d13ea5d7ceb35f43a5c08acf2252826/wcwidth-0.3.3-py3-none-any.whl", hash = "sha256:8e9056c446f21c7393514946d143a748c56aad72476844d3f215f7915276508f", size = 86509, upload-time = "2026-01-24T16:23:56.966Z" }, ] [[package]]