Vlm GRPO TRL updated version#233

Merged

danielhanchen merged 19 commits intounslothai:mainfrom

pluesclues:vlm_grpo_update_official

Sep 16, 2025

Commits on Aug 8, 2025

Update rl_replacements.py
pluesclues
authored

Commits on Aug 11, 2025

Commits on Aug 13, 2025

Commits on Aug 15, 2025

Update rl_replacements.py, changed log ratios to be torch.ones
pluesclues
authored

Commits on Aug 18, 2025

Commits on Aug 20, 2025

Merge branch 'unslothai:main' into vlm_grpo_update_official
pluesclues
authored

Commits on Sep 2, 2025

Merge branch 'unslothai:main' into vlm_grpo_update_official
pluesclues
authored

Commits on Sep 8, 2025

Commits on Sep 9, 2025

Commits on Sep 10, 2025

Commits on Sep 15, 2025

Update rl_replacements.py, added correct kl metrics
pluesclues
authored

Commits on Sep 16, 2025

Merge branch 'main' into vlm_grpo_update_official
pluesclues
authored