Skip to content

Pull requests: huggingface/trl

New pull request New
57 Open 1,285 Closed
57 Open 1,285 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

Allow bootstrap GRPO
#2829 opened Feb 11, 2025 by qgallouedec • Draft
5 tasks
1
🔁 Add retry mechanism for GRPO training with configurable reward thre…
#2823 opened Feb 10, 2025 by mandeep511 Loading…
3 of 5 tasks
3
GRPO + PEFT + vLLM
#2818 opened Feb 10, 2025 by winglian Loading…
5 tasks
11
[draft]add grpo support for third-party devices
#2815 opened Feb 10, 2025 by ji-huazhong Loading…
5 tasks
[WIP] [Liger] Liger KTO support
#2812 opened Feb 10, 2025 by vaibhavjindal • Draft
5 tasks
✨ Add vLLM guided decoding support to GRPO Trainer
#2811 opened Feb 10, 2025 by kldzj Loading…
1 of 5 tasks
5
GRPO Environments for custom multi-step rollouts (vLLM-only)
#2810 opened Feb 9, 2025 by willccbb Loading…
5 tasks done
2
GRPO - Do not load reference model when beta == 0
#2806 opened Feb 8, 2025 by ingambe Loading…
9
[draft] Use vLLM in LogCompletionsCallback
#2797 opened Feb 7, 2025 by tchang1997 • Draft
2 of 4 tasks
Remote GRPO ref model
#2763 opened Feb 4, 2025 by edbeeching • Draft
8
Fix device placement for GRPO attention mask in compute_loss 😴 stale No update from the author, will be closed soon
#2747 opened Feb 3, 2025 by tgaddair Loading…
2
allow ref_model to be set in trainer to interface parity with other trainers
#2746 opened Feb 3, 2025 by winglian • Draft
5 tasks
feat: Add cliprange to GRPO loss
#2739 opened Feb 2, 2025 by joey00072 • Draft
1 of 5 tasks
6
Dynamically load LoRA weights when using vLLM
#2730 opened Feb 1, 2025 by tgaddair Loading…
10
⚡ Fix GRPO PEFT
#2725 opened Jan 31, 2025 by qgallouedec • Draft
5 tasks
13
WIP: RLOOV2
#2724 opened Jan 31, 2025 by mnoukhov • Draft
3 tasks
1
🔧 Optimize GRPO VRAM Usage
#2669 opened Jan 27, 2025 by andyl98 Loading…
2 of 5 tasks
36
share parameters between model and ref model
#2668 opened Jan 27, 2025 by GeeeekExplorer Loading…
2 of 5 tasks
Add special token to PRM vocabulary if not present
#2646 opened Jan 24, 2025 by plaguss • Draft
5 tasks
5
[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
ProTip! Adding no:label will show everything without a label.