Skip to content

Pull requests: huggingface/trl

New pull request New
38 Open 1,164 Closed
38 Open 1,164 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

KTO refactor
#2507 opened Dec 20, 2024 by qgallouedec • Draft
5 tasks
1
[WIP] Integrate Liger CPO & SimPO
#2506 opened Dec 20, 2024 by Mecoli1219 • Draft
1 of 6 tasks
1
Update Comet integration to include LogCompletionsCallback and Trainer.evaluation_loop()
#2501 opened Dec 18, 2024 by yaricom Loading…
2 of 5 tasks
4
🚜 Use field in dataclasses
#2494 opened Dec 17, 2024 by qgallouedec Loading…
1
adding readme for datasets
#2491 opened Dec 16, 2024 by August-murr • Draft
5 tasks
1
3
[Liger] add native liger-kernel orpo loss
#2482 opened Dec 15, 2024 by kashif Loading…
17
Tool fine-tuning support DPO
#2479 opened Dec 14, 2024 by August-murr • Draft
2 of 5 tasks
5
Allow eval in Online DPO
#2476 opened Dec 13, 2024 by qgallouedec • Draft
5 tasks
2
1
dpo_trainer gather metrics across ranks before logging
#2474 opened Dec 13, 2024 by zhc7 Loading…
2 of 5 tasks
1
5
Add length-normalized DPO
#2458 opened Dec 10, 2024 by hugoabonizio Loading…
1 of 5 tasks
1
Padding free dpo
#2437 opened Dec 4, 2024 by dame-cell Loading…
2 of 5 tasks
1
34
Add "Language Modeling to Unpaired Preference" in Utilities for converting dataset types 😴 stale No update from the author, will be closed soon
#2436 opened Dec 4, 2024 by AMindToThink Loading…
1
[Reward] initial CLoud Reward trainer
#2432 opened Dec 3, 2024 by kashif Loading…
4
peft_config & is_loaded_in_4bit check added to Reward_Trainer
#2427 opened Dec 2, 2024 by shirinyamani Loading…
5 tasks
6
added eos token for ppotrainer
#2420 opened Nov 30, 2024 by dame-cell Loading…
3 of 5 tasks
1
2
🔬 SFT simplification
#2405 opened Nov 28, 2024 by qgallouedec Loading…
5 tasks
4
🧪 [Experimental] Train LeRobot policy with TRL
#2359 opened Nov 15, 2024 by qgallouedec • Draft
5 tasks
1
👩‍🏫 Add SFT notebook for chatbot development
#2321 opened Nov 4, 2024 by qgallouedec • Draft
5 tasks
1
[Draft] Add eval_data_collator arg
#2311 opened Nov 3, 2024 by pdufour • Draft
1 of 5 tasks
1
[Draft] Add autocast to prediction_step for SFTTrainer
#2310 opened Nov 3, 2024 by pdufour • Draft
2 of 5 tasks
Asynchronous RLHF: Faster and More Efficient Online DPO
#2278 opened Oct 24, 2024 by mnoukhov Loading…
1 of 3 tasks
7
[GKD] add ULD type loss to GKD Trainer
#2263 opened Oct 22, 2024 by kashif Loading…
5
[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
5
[online-DPO] evaluaiton step error 🐛 bug Something isn't working
#2231 opened Oct 15, 2024 by kashif • Draft
1
1
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
1
ProTip! Filter pull requests by the default branch with base:main.