Skip to content

Support Phi3.5 and upgrade Transformers #184

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LianaMikael wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support Phi3.5 and upgrade Transformers #184

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,7 @@ Notes:
The following models from Hugging Face hub are currently supported
- [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
- [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
- [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)
- [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b)
- [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b)
- [meta-llama/Llama-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b)
Expand Down
2 changes: 1 addition & 1 deletion experiments/bo_options.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ def lora_target_map(model: str):
'lm_head',
],
}
case 'microsoft/Phi-3-mini-4k-instruct':
case 'microsoft/Phi-3-mini-4k-instruct' | 'microsoft/Phi-3.5-mini-instruct':
return {
'qkv_proj': ['qkv_proj'],
'attn_head': ['qkv_proj', 'o_proj'],
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ dependencies = [
"numpy",
"torch",
"tqdm",
"transformers==4.41.0",
"transformers==4.46.3",
]

[project.optional-dependencies]
Expand Down
2 changes: 1 addition & 1 deletion src/slicegpt/adapters/phi3_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,7 @@ def _from_pretrained(
local_files_only: bool = False,
token: str | bool | None = None,
) -> ModelAdapter | None:
if not model_name.startswith("microsoft/Phi-3-mini-4k-instruct"):
if (not model_name.startswith("microsoft/Phi-3-mini-4k-instruct") and not model_name.startswith("microsoft/Phi-3.5-mini-instruct")):
return None

model = Phi3ForCausalLM.from_pretrained(
Expand Down
Loading