Skip to content

Issues: huggingface/open-r1

How to contribute
#23 opened Jan 25, 2025 by lewtun
Open 11
Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

257 Open 93 Closed
257 Open 93 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Unreasonable design of the code of accuracy reward
#628 opened Apr 27, 2025 by andyclsr
1
how can I get the prediction using the provided evaluation script?
#625 opened Apr 25, 2025 by CurryxIaoHu
Is "solution" necessary for the grpo dataset?
#624 opened Apr 25, 2025 by yy9996
Requiring the recipe for training the GRPO model of OlympicCoder
#623 opened Apr 24, 2025 by sluxsr
OpenR1-Qwen-7B achieves 47.40 on AIME24, better than reported!
#622 opened Apr 24, 2025 by Hasuer
17
GRPO stuck with NCCL error
#620 opened Apr 24, 2025 by JoeyXuquant11
A strange format reward issue
#616 opened Apr 18, 2025 by MiracleLin001
a efficient GRPO LOSS kernel by triton, reduce 46G memory
#615 opened Apr 18, 2025 by mdy666
2
clip grad not working
#609 opened Apr 17, 2025 by jiangix-paper
1
The diffenernce of these scripts
#606 opened Apr 15, 2025 by Alan-D-Chen
unsatisfactory result and strange reward
#605 opened Apr 15, 2025 by qianfantianyuzhouzhou
1
Is vllm==0.8.3 causing some incompatible problems
#602 opened Apr 15, 2025 by roaminwind
10
Does the Qwen-2.5-VL model in the GRPO project currently support multi-image input?
#601 opened Apr 14, 2025 by zby1218
model.generate produces right-padded completions, causing incompatibility with Flash Attention 2
#599 opened Apr 14, 2025 by PolarisHsu
src/open_r1/evaluate.py Missing
#598 opened Apr 13, 2025 by Zoeyyao27
1
weird....why the new version become worse?????
#594 opened Apr 11, 2025 by yanghu819
1
GRPO config for finetuning Qwen-7B-Math-Instruct on OpenR1-Math-220k
#589 opened Apr 9, 2025 by toslali-ibm
1
GRPO with a lora model after SFT
#588 opened Apr 9, 2025 by Pandasea
grpo inference error
#587 opened Apr 9, 2025 by jiangyuan1018
what is next for this project?
#586 opened Apr 7, 2025 by Mnaik2
vllm generate n responses, some responses stop after generating </answer>, some can not stop.
#582 opened Apr 6, 2025 by LaoWangGB
1
understanding GRPO code pipeline. is this fully online learning in code?
#581 opened Apr 5, 2025 by dongje
Is possible release intermediate checkpoints and wandb logs?
#580 opened Apr 5, 2025 by Qinghao-Hu
Sequence length problem
#579 opened Apr 5, 2025 by zhangtianhong-1998
2
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
#578 opened Apr 4, 2025 by BiNLP
ProTip! What’s not been updated in a month: updated:<2025-03-29.