Skip to content

Pull requests: huggingface/trl

New pull request New
74 Open 1,728 Closed
74 Open 1,728 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

Add uv scripts headers
#3767 opened Jul 24, 2025 by lhoestq Loading…
2
support model str in onlinedpo
#3765 opened Jul 24, 2025 by kashif Loading…
1
2
Fix clone_chat_template vocab size and support PEFT instruction tuning
#3763 opened Jul 24, 2025 by qgallouedec Loading…
1
Prevent NCCL Device Conflicts Between vLLM Server and Trainers
#3762 opened Jul 23, 2025 by CarlosArguilar Loading…
5 tasks done
2
change doc for num_iterations and steps_per_generation to hopefully make them more clear and differentiate between them more clearly
#3761 opened Jul 23, 2025 by avishaiElmakies Loading…
2 of 5 tasks
1
3
[GRPO] add support for pixel_attention_mask (smolvlm2) and image_sizes (llavanext)
#3760 opened Jul 23, 2025 by kashif Loading…
2
Dynamic sampling option in GRPO trainer based on DAPO paper
#3758 opened Jul 23, 2025 by almeidava93 Loading…
2 of 5 tasks
1
3
🔔 Add deprecation warnings for AlignPropTrainer and DDPOTrainer
#3755 opened Jul 22, 2025 by qgallouedec Loading…
5 tasks
2
Support dLLM in GRPO reference model creation
#3743 opened Jul 18, 2025 by xijia-tao Loading…
1
3
Add basic support for FSDP/Lora when using TRL/VLLM
#3735 opened Jul 14, 2025 by ojh31 Loading…
5 tasks
2
Add warn0 utility and replace warnings.warn with rank-aware warnings in trainer
#3734 opened Jul 14, 2025 by yafshar Loading…
1 of 5 tasks
2
[WIP] Fix ppo example accelerator initialization error
#3732 opened Jul 14, 2025 by ccs96307 • Draft
2 of 5 tasks
[GRPO] Log generation entropy
#3700 opened Jul 7, 2025 by LeonEricsson Loading…
2 of 5 tasks
1
19
FSDP2+GRPO
#3687 opened Jul 3, 2025 by SalmanMohammadi Loading…
5 tasks
2
Support FSDP2 in GRPOTrainer
#3670 opened Jun 30, 2025 by thepowerfuldeez Loading…
1
[SFT] Dry up the sft tests
#3657 opened Jun 27, 2025 by kashif Loading…
5 tasks
1
feat: Initial implementation of RePO trainer and components
#3655 opened Jun 26, 2025 by celsowm Loading…
5 tasks
2
Ensure Chat Template Safe Prompt Truncation
#3646 opened Jun 25, 2025 by pramodith Loading…
4 of 5 tasks
21
[WIP] vllm-server-spec-dec-support
#3643 opened Jun 24, 2025 by shirinyamani Loading…
5 tasks
1
GRPO: Pack Responses within the same group.
#3642 opened Jun 24, 2025 by pramodith • Draft
4 of 5 tasks
1
🔍 Add guidance on choosing max_length value and include visualizati…
#3630 opened Jun 22, 2025 by qgallouedec Loading…
5 tasks
1
Add Entropy Control to GRPOTrainer
#3628 opened Jun 22, 2025 by 1485840691 Loading…
15
Feature: Add SGLang support for GRPO Trainer
#3627 opened Jun 21, 2025 by PrinsYin • Draft
5 tasks
5
[WIP] [SFT] SFT doc rewrite
#3619 opened Jun 18, 2025 by qgallouedec Loading…
1
ClearML logging of visualization in RewardTrainer evaluation
#3602 opened Jun 16, 2025 by ioverho Loading…
2 of 5 tasks
ProTip! Add no:assignee to see everything that’s not assigned.