Skip to content

Pull requests: huggingface/trl

New pull request New
57 Open 1,253 Closed
57 Open 1,253 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix device placement for GRPO attention mask in compute_loss
#2747 opened Feb 3, 2025 by tgaddair Loading…
allow ref_model to be set in trainer to interface parity with other trainers
#2746 opened Feb 3, 2025 by winglian • Draft
5 tasks
Update unsloth_integration.md
#2742 opened Feb 2, 2025 by AdeebAldkheel Loading…
5 tasks
4
📖Nit Fix in Documentation
#2740 opened Feb 2, 2025 by ParagEkbote Loading…
1 task done
1
feat: Add cliprange to GRPO loss
#2739 opened Feb 2, 2025 by joey00072 • Draft
1 of 5 tasks
feat: Add vLLM dtype configuration for GRPO trainer
#2738 opened Feb 2, 2025 by joey00072 Loading…
5 tasks
1
Dynamically load LoRA weights when using vLLM
#2730 opened Feb 1, 2025 by tgaddair Loading…
GRPO: Expose vllm_init_kwargs to enable vllm configuration
#2728 opened Feb 1, 2025 by mirceapricop Loading…
5 tasks
13
⚡ Fix GRPO PEFT
#2725 opened Jan 31, 2025 by qgallouedec • Draft
5 tasks
5
WIP: RLOOV2
#2724 opened Jan 31, 2025 by mnoukhov • Draft
3 tasks
1
Update ppo_trainer.md documentation
#2720 opened Jan 31, 2025 by JohnConnor123 Loading…
5 tasks
1
🔁 🦈 Support iterative GRPO
#2700 opened Jan 30, 2025 by shirinyamani Loading…
4 of 5 tasks
7
[GRPO] add reward weight in multi-reward settings
#2676 opened Jan 28, 2025 by hesamsheikh Loading…
1 task
9
🔧 Optimize GRPO VRAM Usage by Computing Prompt Tokens Just Once
#2669 opened Jan 27, 2025 by andyl98 Loading…
2 of 5 tasks
29
share parameters between model and ref model
#2668 opened Jan 27, 2025 by GeeeekExplorer Loading…
2 of 5 tasks
Add Optional ZeRO-3 Weight Gathering for GRPO in Sequence Generation
#2667 opened Jan 27, 2025 by SeungyounShin Loading…
5 tasks done
1
Add special token to PRM vocabulary if not present
#2646 opened Jan 24, 2025 by plaguss • Draft
5 tasks
5
[SFT] add token accuracy metric
#2597 opened Jan 21, 2025 by kashif Loading…
5 tasks
2
[Not meant to be merged] Support branch for Trainer refactor
#2594 opened Jan 20, 2025 by qgallouedec • Draft
5 tasks
1
🐍 Support Python 3.13
#2593 opened Jan 20, 2025 by qgallouedec • Draft
5 tasks
[WIP] [Liger] liger JSD support
#2573 opened Jan 16, 2025 by Mecoli1219 • Draft
5 tasks
Reduce memory consumption when training with PPO
#2571 opened Jan 15, 2025 by summerspringwei Loading…
5 tasks
9
[Liger] liger DPO support
#2568 opened Jan 14, 2025 by kashif Loading…
5
Add _compute_score method to PPOTrainer
#2560 opened Jan 11, 2025 by oliveiraeliel • Draft
2 of 5 tasks
3
Add generation caching in TextEnvironment and fix bugs in TextEnvironment
#2556 opened Jan 10, 2025 by konrad-gerlach Loading…
32
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.