Skip to content

Pull requests: huggingface/trl

New pull request New
Clear current search query, filters, and sorts
33 Open 1,053 Closed
33 Open 1,053 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

feat: start working on revisions instead of preferences
#1999 opened Aug 30, 2024 by KarelDO • Draft
3 tasks
allow masking on consecutive messages with same roles
#2000 opened Aug 31, 2024 by lsy641 Loading…
4 of 5 tasks
Add VAS to TRL ✨ enhancement New feature or request
#2195 opened Oct 7, 2024 by idanshen Loading…
Remove ds_config scheuduler params to prevent deepseed from creating scheduler for ref_model
#2224 opened Oct 11, 2024 by Ben-Schneider-code Loading…
2 of 5 tasks
1
Data mixer Integration
#2240 opened Oct 16, 2024 by August-murr • Draft
3 of 5 tasks
1
Add simplified version of BCO loss
#1731 opened Jun 13, 2024 by Trangle Loading…
1
Remove deprecated args in trainers
#2036 opened Sep 8, 2024 by qgallouedec • Draft
5 tasks
4
[SCoRE] initial score stage 1
#2115 opened Sep 24, 2024 by kashif • Draft
1
[Open discusion] Multistep dataset
#2148 opened Oct 1, 2024 by qgallouedec • Draft
4 tasks
4
[CGPO] CGPO Trainer (single task single objective) ✨ enhancement New feature or request
#2190 opened Oct 6, 2024 by gaetanlop • Draft
9 of 10 tasks
1
[online-DPO] evaluaiton step error 🐛 bug Something isn't working
#2231 opened Oct 15, 2024 by kashif • Draft
1
1
[GKD] add ULD type loss to GKD Trainer
#2263 opened Oct 22, 2024 by kashif Loading…
2
MergeModelCallBack
#2282 opened Oct 25, 2024 by August-murr Loading…
3 of 5 tasks
1
2
New models for tests
#2287 opened Oct 27, 2024 by qgallouedec • Draft
5 tasks
1
1
[SFT VLM] Added support for Molmo models via standalone script sft_vlm_molmo
#2236 opened Oct 15, 2024 by sergiopaniego Loading…
2 of 5 tasks
1
2
Add Error Handling for Stale Issue Script in GitHub Action
#2258 opened Oct 21, 2024 by Ananya54321 Loading…
2 of 5 tasks
2
Fix error text in BCO and KTO tokenizer function.
#2286 opened Oct 26, 2024 by PhilipMay Loading…
2
[GRPO] initial GRPO trainer
#1954 opened Aug 21, 2024 by saisurbehera • Draft
1
3
Asynchronous RLHF: Faster and More Efficient Online DPO
#2278 opened Oct 24, 2024 by mnoukhov Loading…
1 of 3 tasks
3
[DRAFT] Vllm integration
#1628 opened May 7, 2024 by vwxyzjn • Draft
4
DPO trainer supports num_logits_to_keep to save memory 🏋 DPO Related to DPO
#2129 opened Sep 26, 2024 by xyangk Loading…
3 of 5 tasks
@kashif
4
Remove graph breaks for torch.compile() in padding free branch in DataCollatorForCompletionOnlyLM 🐛 bug Something isn't working 🏋 SFT Related to SFT
#2158 opened Oct 3, 2024 by Abhishek-TAMU Loading…
1 of 5 tasks
4
feat: add support for packing tokenized datasets
#2011 opened Sep 3, 2024 by kmehant Loading…
3 of 5 tasks
1
9
Prototype Dataset Processor
#1646 opened May 16, 2024 by vwxyzjn • Draft
8
Add SRPO algorithm.
#1772 opened Jun 25, 2024 by frasermince Loading…
1 of 7 tasks
@qgallouedec
23
ProTip! Mix and match filters to narrow down what you’re looking for.