Skip to content

Pull requests: huggingface/trl

New pull request New
91 Open 2,489 Closed
91 Open 2,489 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

Expose generation index to tool callables in GRPOTrainer
#4894 opened Jan 25, 2026 by lukehinds Loading…
4 of 5 tasks
1
Upgrade GitHub Actions to latest versions
#4893 opened Jan 24, 2026 by salmanmkc Loading…
2
docs: add DoRA (2402.09353) to Paper Index
#4892 opened Jan 24, 2026 by billycrapediem Loading…
3 of 5 tasks
3
[GRPO] feat: Geometric Sequence Masking
#4891 opened Jan 24, 2026 by LeonEricsson • Draft
5 tasks
5
Fix grpo tool calling
#4890 opened Jan 23, 2026 by akshayballal95 Loading…
2 tasks done
1
fix(vLLM): Add tool calling support to VLLMClient.chat()
#4889 opened Jan 23, 2026 by kansalaman Loading…
1 of 2 tasks
1
GOLD training speed up
#4888 opened Jan 22, 2026 by 141forever Loading…
1
Add History-Aware Adaptive Difficulty Weighting (HA-DW) to GRPO
#4872 opened Jan 20, 2026 by anonx3247 Loading…
1
NeMo-Gym Integration
#4848 opened Jan 17, 2026 by cmunley1 Loading…
7
make dpo compatible with fsdp2
#4838 opened Jan 16, 2026 by flutist Loading…
4 of 5 tasks
feat: Support log_completion for swanlab backend
#4826 opened Jan 14, 2026 by ZiyiTsang Loading…
2 of 5 tasks
1
Add support for training with multiple OpenEnv environments
#4824 opened Jan 13, 2026 by lewtun • Draft
5 tasks
9
[GRPO] Add parquet logging for completions with individual rewards
#4818 opened Jan 13, 2026 by qgallouedec Loading…
27
Add Entropy Adaptive Fine Tuning to SFT Trainer
#4802 opened Jan 10, 2026 by electroglyph Loading…
1
2
forward_masked_logits in SFTTrainer
#4794 opened Jan 8, 2026 by qgallouedec • Draft
5 tasks
1
Refactor KTO [3/N]: Extract dataset processing to _prepare_dataset method
#4788 opened Jan 8, 2026 by albertvillanova Loading…
3
Refactor KTO [2/N]: Improve config validation in KTOConfig
#4787 opened Jan 8, 2026 by albertvillanova Loading…
4
make dpo compatible with qwen3vl
#4773 opened Jan 4, 2026 by flutist Loading…
16
feat(sft): add generation-based evaluation support to SFTTrainer
#4768 opened Jan 2, 2026 by CodersAcademy006 Loading…
1
5
Extend CLI to orpo trainer
#4757 opened Dec 27, 2025 by murilo-cunha Loading…
3 of 5 tasks
fix: handle None eval_dataset in example code
#4756 opened Dec 27, 2025 by ciaoyizhen Loading…
1 of 4 tasks
1
perf: avoid output_hidden_states when only last_hidden_state is used
#4755 opened Dec 27, 2025 by ciaoyizhen Loading…
2 of 5 tasks
1
Clarify Accelerate usage in SFTTrainer documentation
#4744 opened Dec 23, 2025 by Likhita-17 Loading…
1 task done
2
fix minillm trainer
#4743 opened Dec 23, 2025 by t1101675 Loading…
5 tasks
3
feat: Bidirectional masked importance sampling ratio (MIS) for IcePop
#4732 opened Dec 20, 2025 by casinca Loading…
4 of 5 tasks
1
10
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.