Skip to content

Pull requests: huggingface/trl

New pull request New
88 Open 2,397 Closed
88 Open 2,397 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

[GOLD] add probability merging fix to implement chain rule
#4765 opened Dec 30, 2025 by kashif Loading…
5 tasks
1
5
ORPO: Avoid catastrophic cancellation in loss function
#4763 opened Dec 29, 2025 by hartmans Loading…
3 tasks
Sudoku GRPO example script using TextArena
#4762 opened Dec 29, 2025 by sergiopaniego Loading…
5 tasks
1
Add a config to limit the number of tool calling iterations.
#4761 opened Dec 29, 2025 by pramodith Loading…
4 of 5 tasks
1
1
[Docs] Add SRL (Supervised Reinforcement Learning) to Community Tutorials
#4758 opened Dec 29, 2025 by s23deepak Loading…
2 tasks done
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
vllm parameter passthrough for stop sequences
#4754 opened Dec 26, 2025 by kdubovikov Loading…
Fix GRPO scale_rewards type specification to fix __post_init__ validation
#4752 opened Dec 26, 2025 by apalmas-saifh Loading…
1 of 5 tasks
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
[GRPOTrainer]: Agent Training Supports Async Tool Calls
#4742 opened Dec 23, 2025 by pramodith Loading…
5 tasks done
9
[WIP - Awaiting Feedback] feat: Bidirectional masked importance sampling ratio (MIS) for IcePop
#4732 opened Dec 20, 2025 by casinca • Draft
5 tasks
1
Fix MiniLLM Training
#4731 opened Dec 20, 2025 by t1101675 Loading…
2
Up to 50% less VRAM during forward with forward_masked_logits function
#4729 opened Dec 20, 2025 by qgallouedec Loading…
4
Improve PEFT integration
#4723 opened Dec 19, 2025 by qgallouedec Loading…
2
Refactor vLLM generation [2/N]: Decouple rollout_func and vLLM functionalities
#4712 opened Dec 17, 2025 by albertvillanova • Draft
1
Refactor vLLM generation [1/N]: Extract vLLM generation
#4700 opened Dec 16, 2025 by albertvillanova Loading…
18
fix: invalidate ZeRO-3 param coordinator trace in add_hooks
#4693 opened Dec 15, 2025 by roycho96 Loading…
1 of 5 tasks
@kashif
6
feat: DeepSeek V3.2 Off-policy sequence masking
#4689 opened Dec 13, 2025 by casinca Loading…
4 of 5 tasks
1
10
GKDTrainer: Fix return_outputs in Liger kernel path and update tests
#4688 opened Dec 13, 2025 by roycho96 Loading…
2 of 5 tasks
2
Update import structure
#4665 opened Dec 11, 2025 by qgallouedec Loading…
1
[WIP] GRPO-inspired Online DPO refactor
#4659 opened Dec 10, 2025 by d-tiapkin • Draft
2 of 7 tasks
@kashif
feature: Add RTPO Trainer
#4652 opened Dec 9, 2025 by SolarWindRider Loading…
6 tasks done
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.