Skip to content

Pull requests: huggingface/trl

New pull request New
83 Open 2,139 Closed
83 Open 2,139 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

Fix add_generation_prompt arg in GRPOTrainer for paged transformers
#4370 opened Oct 29, 2025 by albertvillanova Loading…
1
1
Add tip for logging evaluation metrics during regular evaluations
#4367 opened Oct 29, 2025 by cam1llynha Loading…
1
2
Fix CI experimental tests TypeError for GRPOWithReplayBufferTrainer.update_with_replay_buffer
#4366 opened Oct 29, 2025 by albertvillanova Loading…
1
1
Remove liger loss in favor of liger kernel
#4364 opened Oct 29, 2025 by sergiopaniego Loading…
5 tasks
@kashif
3
Add support for Trackio completions logging in GRPOTrainer
#4359 opened Oct 28, 2025 by taha-yassine Loading…
2 of 5 tasks
Openenv wordle example
#4357 opened Oct 28, 2025 by burtenshaw Loading…
8
Support chat_template_kwargs
#4350 opened Oct 27, 2025 by pramodith Loading…
3 of 5 tasks
1
11
[experimental] GOLD Trainer
#4349 opened Oct 27, 2025 by kashif • Draft
5 tasks
28
[OpenENV] Openenv rollout_func signature proposal
#4344 opened Oct 27, 2025 by kashif Loading…
5 tasks
3
docs: Add RapidFire AI integration guide
#4340 opened Oct 26, 2025 by kamran-rapidfireAI Loading…
5 tasks done
5
Update SFT QLoRA notebook with **14B** model on free Colab
#4336 opened Oct 24, 2025 by sergiopaniego Loading…
5 tasks
6
feat(trainer): add PAPOTrainer for preference-based optimization
#4334 opened Oct 24, 2025 by SolarWindRider Loading…
4 tasks done
6
Use explicit tiny-Qwen2ForCausalLM-2.5 model_id param in CI tests
#4331 opened Oct 23, 2025 by albertvillanova Loading…
2
wip - env
#4320 opened Oct 22, 2025 by qgallouedec Loading…
5 tasks
1
refactor: simplify parameter freezing in modeling_base.py
#4305 opened Oct 20, 2025 by Ki-Seki Loading…
2 of 5 tasks
2
GRPO: ScaleRL -> Support casting LM Head to FP32
#4303 opened Oct 18, 2025 by pramodith Loading…
4 of 5 tasks
27
[SFT] Log mean token accuracy from Liger kernel
#4302 opened Oct 18, 2025 by kashif Loading…
5 tasks
5
Tool call
#4300 opened Oct 18, 2025 by qgallouedec • Draft
5 tasks
Add CISPO loss option and documentation
#4298 opened Oct 16, 2025 by gustavorubim Loading…
4
feat: Add Multi-Token Prediction (MTP) support to SFTTrainer
#4290 opened Oct 15, 2025 by KLGR123 Loading…
1
[SFT] add support for unified conversion logic for both images and videos
#4264 opened Oct 13, 2025 by kashif Loading…
3
Remove FSDP1 support: use FSDP2 exclusively
#4260 opened Oct 11, 2025 by behroozazarkhalili Loading…
2
Fix DPO Trainer Bug For Qwen2-VL (Issue 2660)
#4257 opened Oct 11, 2025 by FabianSchuetze Loading…
1 of 3 tasks
4
Online-dpo-ben
#4252 opened Oct 10, 2025 by burtenshaw • Draft
5 tasks
[Utils] fix DataCollatorForChatML
#4231 opened Oct 8, 2025 by kashif • Draft
5
ProTip! no:milestone will show everything without a milestone.