Skip to content

Pull requests: huggingface/trl

New pull request New
18 Open 720 Closed
18 Open 720 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Remove extra whitespaces
#1647 opened May 17, 2024 by qgallouedec • Draft
1
Prototype Dataset Processor
#1646 opened May 16, 2024 by vwxyzjn • Draft
3
[DRAFT] Vllm integration
#1628 opened May 7, 2024 by vwxyzjn • Draft
1
[ORPO] Enable batched tokenization & multiprocessing to process large datasets
#1624 opened May 6, 2024 by lewtun Loading…
7
Integrate f-divergence to DPO (Follow up)
#1610 opened May 1, 2024 by 1485840691 Loading…
1
Adds Online DPO
#1605 opened Apr 30, 2024 by edbeeching • Draft
1
Minimal examples
#1603 opened Apr 30, 2024 by vwxyzjn • Draft
2
[WIP] Add WinRateCallback
#1598 opened Apr 29, 2024 by lewtun • Draft
2 of 5 tasks
1
🤫 TR-DPO implementation
#1593 opened Apr 26, 2024 by syrn1k Loading…
13
Added DataCollatorForMultiTurnCompletions
#1592 opened Apr 26, 2024 by AswanthManoj Loading…
3
Fix max_completion_length for encoder_decoder models in KTO Trainer
#1588 opened Apr 25, 2024 by samuki Loading…
[WIP] Unify Policy Trainers
#1586 opened Apr 25, 2024 by lapp0 • Draft
4 tasks
13
Added Reward Backpropogation Support
#1585 opened Apr 25, 2024 by mihirp1998 Loading…
A pull request for POVIDTrainer
#1573 opened Apr 23, 2024 by gzcch Loading…
3
Apply deprecated evaluation_strategy
#1559 opened Apr 18, 2024 by muellerzr Loading…
2
PPO / Reinforce Trainers
#1540 opened Apr 15, 2024 by vwxyzjn Loading…
163
Adds reward bootstrapping to PPOTrainer
#1536 opened Apr 13, 2024 by ejmejm Loading…
3
Ability to store generation logits and vals for training
#1535 opened Apr 13, 2024 by ejmejm Loading…
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.