Nemotron Nano Omni V3 RL assets#168
Merged
marcromeyn merged 3 commits intoNVIDIA-NeMo:mainfrom Apr 28, 2026
Merged
Conversation
marcromeyn
approved these changes
Apr 28, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add Nemotron-3-Nano-Omni GRPO training cookbooks
Step-by-step guides for GRPO/GSPO-style RL fine-tuning of Nemotron Nano V3 Omni on the MMPR-Tiny visual reasoning dataset using NeMo-RL on a single DGX H100 node (8× H100 80 GB).
grpo/ — native NeMo-RL path (run_vlm_grpo.py) with built-in MMPR-Tiny loader; includes training config vlm_grpo_nanov3omni_mmpr_tiny_1node.yaml (TP=8, EP=8).
grpo_nemo_gym/ — NeMo-Gym rollout path (run_grpo_nemo_gym.py) with async vLLM HTTP server and rule-based MCQA + numeric verifiers; includes JSONL data converter and config grpo_mmpr_tiny_nanov3omni_gym.yaml.