Skip to content

Pull requests: huggingface/open-r1

New pull request New
36 Open 144 Closed
36 Open 144 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

Simplify dependencies set up for development mode: update makefile and readme
#449 opened Feb 28, 2025 by ocramz Loading…
1
SFT configs for Qwen coder models
#438 opened Feb 26, 2025 by edbeeching • Draft
translate readme to Chinese(traditional)
#432 opened Feb 25, 2025 by JillChen525 Loading…
Flash Attention Padding Fix
#422 opened Feb 25, 2025 by Kidand Loading…
2
Start agent traces
#414 opened Feb 24, 2025 by aymeric-roucher • Draft
feat: make reward functions to support parallel computation
#398 opened Feb 23, 2025 by 0x404 Loading…
6
New GRPO dataset and task: formally-verified program correctness
#379 opened Feb 20, 2025 by ocramz Loading…
1
WIP "Faster" grpo trainer
#371 opened Feb 19, 2025 by edbeeching • Draft
7
Fix dataset url
#347 opened Feb 17, 2025 by Zzhiter Loading…
1
Fix reasoning_steps_reward function
#335 opened Feb 16, 2025 by rocke2020 Loading…
fix bug, solutions not found
#334 opened Feb 15, 2025 by hellen9527 Loading…
Update sglang README.md
#330 opened Feb 15, 2025 by yh-yao Loading…
Update grpo.py
#325 opened Feb 14, 2025 by tpoisonooo Loading…
add text similarity for more common accuracy reward
#322 opened Feb 14, 2025 by sungatetop Loading…
fix: sft fix
#307 opened Feb 13, 2025 by pointerhacker Loading…
Fix: Default value of cosine_min_value_wrong parameter
#305 opened Feb 13, 2025 by zhangsheng377 Loading…
Simplified installation requirements to support more accelerators
#303 opened Feb 13, 2025 by ji-huazhong Loading…
1
2
Fix eval max length
#297 opened Feb 12, 2025 by Some-random Loading…
1
[rewards] use dense rep penalty
#296 opened Feb 12, 2025 by kashif Loading…
1
Update README.md
#291 opened Feb 12, 2025 by tpoisonooo Loading…
Performance improvements of reward calculation
#286 opened Feb 11, 2025 by saidineshpola Loading…
[GRPO] generate with prompt containing the first <think> tag
#283 opened Feb 11, 2025 by kashif Loading…
2
Fix: Avoid empty keyword argument in VLLMModelConfig from Makefile
#246 opened Feb 8, 2025 by mattdepaolis Loading…
1
1
fix: easier environment setup; pin trl, transformers
#199 opened Feb 6, 2025 by ctjlewis Loading…
2
6
Replace the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B to Qwen/Qwen2.5-1.5B-Instruct in GRPO
#198 opened Feb 5, 2025 by DVampire Loading…
ProTip! What’s not been updated in a month: updated:<2025-01-28.