Skip to content

Pull requests: huggingface/trl

New pull request New
75 Open 2,166 Closed
75 Open 2,166 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

[Draft] Add configurable dataset column logging to GRPOTrainer W&B tables
#4045 opened Sep 9, 2025 by davanstrien • Draft
3
Fix #3982: Fix DPO Trainer support for Gemma 3 vision models
#4022 opened Sep 6, 2025 by akshay-babbar Loading…
1
5
Fix: undefined current_gradient_accumulation_steps
#4014 opened Sep 5, 2025 by ysjprojects Loading…
2 of 5 tasks
1
3
Fix: ignore precompute_ref_log_probs when use_liger_loss=True
#4008 opened Sep 4, 2025 by ginkyenglee Loading…
5 tasks
2
Remove attention mask when position ids is returned
#3997 opened Sep 2, 2025 by qgallouedec • Draft
Enable saving and loading precomputed reference log probabilities in …
#3986 opened Sep 1, 2025 by ginkyenglee Loading…
3 tasks
1
4
fix bug when using dataset streaming by accelerate
#3950 opened Aug 25, 2025 by kaixuanliu Loading…
11
[DRAFT] Refactor DPO
#3906 opened Aug 15, 2025 by qgallouedec • Draft
6 tasks
Test in distributed setting
#3902 opened Aug 15, 2025 by qgallouedec Loading…
5 tasks
1
Implement DPOP
#3864 opened Aug 7, 2025 by 1485840691 Loading…
5
[#3647] Fix: Assign default values in the GKDTrainer's constructor only when …
#3851 opened Aug 5, 2025 by seungduk-yanolja Loading…
2 of 5 tasks
1
2
dynamic temperature
#3844 opened Aug 4, 2025 by shirinyamani • Draft
5 tasks
1
[GSPO]: Refactor _compute_loss
#3835 opened Aug 1, 2025 by pramodith Loading…
2 of 5 tasks
1
3
Dynamic sampling option in GRPO trainer based on DAPO paper
#3758 opened Jul 23, 2025 by almeidava93 Loading…
2 of 5 tasks
1
13
Support dLLM in GRPO reference model creation
#3743 opened Jul 18, 2025 by xijia-tao Loading…
1
4
Add basic support for FSDP/Lora when using TRL/VLLM
#3735 opened Jul 14, 2025 by ojh31 Loading…
5 tasks
4
feat: Initial implementation of RePO trainer and components
#3655 opened Jun 26, 2025 by celsowm Loading…
5 tasks
2
[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 Entropy Control to GRPOTrainer
#3628 opened Jun 22, 2025 by 1485840691 Loading…
47
Feature: Add SGLang support for GRPO Trainer
#3627 opened Jun 21, 2025 by PrinsYin • Draft
5 tasks
5
ClearML logging of visualization in RewardTrainer evaluation
#3602 opened Jun 16, 2025 by ioverho Loading…
2 of 5 tasks
1
Fix: corrected fsdp in GRPO trainer
#3582 opened Jun 13, 2025 by tryumanshow Loading…
2 of 5 tasks
9
Chisquare regularized DPO
#3573 opened Jun 12, 2025 by asparius Loading…
3
Add Bidirectional Knowledge Distillation Option to GKDTrainer
#3508 opened May 29, 2025 by shaischaudhry Loading…
3 of 5 tasks
@kashif
3
ProTip! no:milestone will show everything without a milestone.