Skip to content

Pull requests: huggingface/trl

New pull request New
86 Open 1,783 Closed
86 Open 1,783 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 reward_processing_classes validation in GRPOTrainer (#2839)
#3876 opened Aug 9, 2025 by chi2liu Loading…
4 tasks done
1
1
Optimize truncate_with_protected_tokens to use vectorized operations
#3875 opened Aug 9, 2025 by chi2liu Loading…
2 of 5 tasks
2
Optimize completion_ids list conversion in GRPO trainer
#3874 opened Aug 9, 2025 by chi2liu Loading…
2 of 5 tasks
3
Improve quickstart documentation with updated API examples
#3873 opened Aug 9, 2025 by behroozazarkhalili Loading…
7
vLLM rollout numerical differences causing off-policy RL.
#3867 opened Aug 7, 2025 by LeonEricsson • Draft
5 tasks
2
Implement DPOP
#3864 opened Aug 7, 2025 by 1485840691 • Draft
Replaced unittest.TestCase with TrlTestCase that handles tmp dir
#3863 opened Aug 7, 2025 by qgallouedec Loading…
1
🔮 Native VLM support for SFTTrainer
#3862 opened Aug 7, 2025 by qgallouedec Loading…
7
[GRPO]: Fix BOS duplication bug when using VLLM
#3856 opened Aug 6, 2025 by pramodith • Draft
3 of 5 tasks
[Callbacks] BEMA
#3855 opened Aug 6, 2025 by kashif Loading…
7
[#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
Update profiling.py: fix scoping problems for wandb and mlflow
#3845 opened Aug 4, 2025 by markshinyounglee Loading…
5 tasks done
1
dynamic temperature
#3844 opened Aug 4, 2025 by shirinyamani • Draft
5 tasks
1
Add py.typed
#3841 opened Aug 4, 2025 by cyyever Loading…
2
Optimize RLOO Trainer memory usage with string-level processing
#3837 opened Aug 2, 2025 by luckyvickyricky Loading…
2 of 5 tasks
1
3
[GSPO]: Refactor _compute_loss
#3835 opened Aug 1, 2025 by pramodith Loading…
2 of 5 tasks
1
3
[CPO] Add AlphaPO method via CPOTrainer
#3824 opened Jul 31, 2025 by kashif Loading…
3
Fix SFTTrainer token accuracy computation with PromptEncoder
#3821 opened Jul 31, 2025 by zk-quantum Loading…
5 tasks done
1
1
support GSPO-token
#3820 opened Jul 31, 2025 by hjh0119 Loading…
11
GSPO docs - Sequence importance ratio and differences in relation to GRPO
#3816 opened Jul 31, 2025 by almeidava93 Loading…
2 of 5 tasks
2
Adding support for different losses which are now supported by Liger
#3815 opened Jul 31, 2025 by Manan17 Loading…
1 of 5 tasks
2
💇 Add soft overlong punishment reward function and update documentation
#3804 opened Jul 30, 2025 by qgallouedec Loading…
4
Rloo final
#3801 opened Jul 29, 2025 by shirinyamani Loading…
5 tasks
1
Add dataset mixer
#3791 opened Jul 28, 2025 by lewtun Loading…
1 of 5 tasks
2
[GRPO] update transformer version for CB
#3786 opened Jul 28, 2025 by kashif Loading…
7
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.