Skip to content

Pull requests: huggingface/trl

New pull request New
29 Open 997 Closed
29 Open 997 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

🏷️ Model badges: select only TRL models
#2178 opened Oct 4, 2024 by qgallouedec Loading…
5 tasks
1
🕊️ Migration PPOv2 -> PPO
#2174 opened Oct 4, 2024 by qgallouedec • Draft
5 tasks
1
🃏 Model card: "unsloth" tag
#2173 opened Oct 4, 2024 by qgallouedec Loading…
5 tasks
2
Update incorrect data processing in DataCollatorForChatML
#2172 opened Oct 4, 2024 by ruijunfeng Loading…
4 of 5 tasks
1
2
Rename trainer arg tokenizer to processing_class
#2162 opened Oct 3, 2024 by qgallouedec Loading…
17 of 18 tasks
1
8
[CGPO] Mixture of judges judge
#2159 opened Oct 3, 2024 by gaetanlop Loading…
4 tasks done
12
Remove graph breaks for torch.compile() in padding free branch in DataCollatorForCompletionOnlyLM
#2158 opened Oct 3, 2024 by Abhishek-TAMU Loading…
1 of 5 tasks
1
populate SUPPORTED_COMMANDS cli
#2157 opened Oct 2, 2024 by grumpyp Loading…
4 of 5 tasks
1
7
[CGPO] Calibrated reward
#2155 opened Oct 2, 2024 by gaetanlop Loading…
4 tasks done
5
minor KTO setting changes + KL batch size
#2153 opened Oct 2, 2024 by kawine Loading…
2
CLI SFT Quantization Fix
#2151 opened Oct 1, 2024 by August-murr Loading…
5 tasks
1
[Open discusion] Multistep dataset
#2148 opened Oct 1, 2024 by qgallouedec • Draft
4 tasks
1
Refactor ScriptArguments
#2145 opened Sep 30, 2024 by qgallouedec • Draft
5 tasks
1
[DPO] Adding weighted preference optimization (WPO)
#2141 opened Sep 29, 2024 by gaetanlop Loading…
2 tasks done
7
DPO trainer supports num_logits_to_keep to save memory
#2129 opened Sep 26, 2024 by xyangk Loading…
3 of 5 tasks
3
Process-supervised RM Trainer
#2127 opened Sep 26, 2024 by gaetanlop Loading…
5 tasks done
51
[SCoRE] initial score stage 1
#2115 opened Sep 24, 2024 by kashif • Draft
1
Fix RLOO checkpointing
#2114 opened Sep 24, 2024 by bartoszzuk Loading…
7
Remove deprecated args in trainers
#2036 opened Sep 8, 2024 by qgallouedec • Draft
5 tasks
4
feat: add support for packing tokenized datasets
#2011 opened Sep 3, 2024 by kmehant Loading…
2 of 5 tasks
1
7
allow masking on consecutive messages with same roles
#2000 opened Aug 31, 2024 by lsy641 Loading…
4 of 5 tasks
feat: start working on revisions instead of preferences
#1999 opened Aug 30, 2024 by KarelDO • Draft
3 tasks
added initial TPO implementation
#1965 opened Aug 24, 2024 by sahsaeedi Loading…
4 of 5 tasks
9
[GRPO] initial GRPO trainer
#1954 opened Aug 21, 2024 by saisurbehera • Draft
3
Add SRPO algorithm.
#1772 opened Jun 25, 2024 by frasermince Loading…
1 of 7 tasks
@qgallouedec
23
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.