Skip to content

Pull requests: huggingface/trl

New pull request New
76 Open 1,906 Closed
76 Open 1,906 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

🧨 DFT
#4042 opened Sep 9, 2025 by qgallouedec Loading…
5 tasks
1
[GRPO] Fix potential hang in get_high_entropy_mask
#4041 opened Sep 9, 2025 by akakakakakaa Loading…
1
Remove average_tokens_across_devices default replacement
#4039 opened Sep 8, 2025 by qgallouedec Loading…
1
Fix label shifting logic in SFTTrainer for compatibility with CP
#4038 opened Sep 8, 2025 by qgallouedec Loading…
5 tasks
1
Remove setting chat template in sft script
#4037 opened Sep 8, 2025 by qgallouedec Loading…
1
Add autodoc for BestOfNSampler and improve docstrings
#4034 opened Sep 8, 2025 by albertvillanova Loading…
12
[GRPO VLM] Update split sizes to generalize
#4032 opened Sep 8, 2025 by zucchini-nlp Loading…
2
Enable XPU for vllm client
#4031 opened Sep 8, 2025 by jiqing-feng • Draft
vllm sleep mode support
#4028 opened Sep 8, 2025 by ved1beta Loading…
2 of 5 tasks
1
Made ref_model as None in PPO trainer for refined args
#4024 opened Sep 7, 2025 by complete-dope Loading…
1
Fix #3982: Fix DPO Trainer support for Gemma 3 vision models
#4022 opened Sep 6, 2025 by akshay-babbar Loading…
1
1
Fix passing model kwargs
#4019 opened Sep 5, 2025 by qgallouedec Loading…
1
Fix: undefined current_gradient_accumulation_steps
#4014 opened Sep 5, 2025 by ysjprojects Loading…
2 of 5 tasks
1
1
Fix: ignore precompute_ref_log_probs when use_liger_loss=True
#4008 opened Sep 4, 2025 by ginkyenglee Loading…
5 tasks
2
Improve typing of SFT trainer
#4007 opened Sep 4, 2025 by cyyever Loading…
1
⚖️ Align SFT and DPO for model creation and deprecate DPOConfig.padding_value in favour or pad_token_id
#4006 opened Sep 4, 2025 by qgallouedec Loading…
5 tasks
1
✨ Improve SFT doc
#4005 opened Sep 4, 2025 by qgallouedec Loading…
5 tasks
5
Remove attention mask when position ids is returned
#3997 opened Sep 2, 2025 by qgallouedec • Draft
Fix: Make sft script work when chat template is None
#3995 opened Sep 2, 2025 by rabinadk1 Loading…
1 of 5 tasks
6
[GFPO]: implement GFPO in GRPOTrainer
#3989 opened Sep 1, 2025 by Peter-Chou Loading…
3 of 5 tasks
8
Enable saving and loading precomputed reference log probabilities in …
#3986 opened Sep 1, 2025 by ginkyenglee Loading…
3 tasks
1
1
Dft
#3960 opened Aug 27, 2025 by 1485840691 Loading…
5 tasks
1
3
fix bug when using dataset streaming by accelerate
#3950 opened Aug 25, 2025 by kaixuanliu Loading…
5
Docker update
#3931 opened Aug 20, 2025 by qgallouedec Loading…
5 tasks
1
[DRAFT] Refactor DPO
#3906 opened Aug 15, 2025 by qgallouedec • Draft
5 tasks
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.