Skip to content

Issues: huggingface/open-r1

How to contribute
#23 opened Jan 25, 2025 by lewtun
Open 7
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

101 Open 37 Closed
101 Open 37 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

Add sequence parallel
#285 opened Feb 11, 2025 by BaohaoLiao
Failed to Install flash-attn==2.7.4.post1 with ModuleNotFoundError: No module named 'torch' on Pre-Configured Image
#282 opened Feb 11, 2025 by island99
Can anyone give an example code for single instance inference like what demo.py does
#279 opened Feb 11, 2025 by Liu0329
Attention bias and Query/Key/Value should be on the same device
#278 opened Feb 11, 2025 by calledice
1
Can this project be easily ported to 64GPU or 128GPU to support larger models?
#277 opened Feb 11, 2025 by nnnoooppprrrooo
Wrong repetition penalty imported
#276 opened Feb 10, 2025 by casper-hansen
Support stop strings list for GRPO
#271 opened Feb 10, 2025 by haoxiongliu
The lighteval script results is much lower than the open-r1 reported
#269 opened Feb 10, 2025 by bannima
2
How to use tensor_parallel_size for vllm in GRPO?
#260 opened Feb 10, 2025 by bannima
1
Is it possible to make the model training log public?
#259 opened Feb 10, 2025 by asirgogogo
3
Therefore, since the prime factorization of $n$ only has primes from $2$ to $59$
#258 opened Feb 10, 2025 by hellen9527
Why will the final accuracy_reward be 0?
#257 opened Feb 10, 2025 by hellen9527
Reward improvement plateau after few steps
#256 opened Feb 9, 2025 by ali-cogni
'rewards/accuracy_reward': 0.0
#255 opened Feb 9, 2025 by HarveyYi
13
failed (exitcode: -8) local_rank: 6 (pid: 58423) of binary: /opt/miniconda/bin/python When run GRPO
#254 opened Feb 9, 2025 by lmx760581375
2
Error when VLLM Capturing CUDA graph shapes:
#253 opened Feb 9, 2025 by lmx760581375
3
The program has been running for a long time without any output related to the model loss. Is this normal?
#250 opened Feb 9, 2025 by princepride
data-parallel evaluation cause an error of no GPU available
#245 opened Feb 8, 2025 by BaohaoLiao
Could you please let us know your roadmap and the planned completion date for Step 3 development?
#244 opened Feb 8, 2025 by Ginray
Cannot replicate the performance of AIME_24@PASS1
#242 opened Feb 8, 2025 by deepdata-foundation
2
How to do knowledge distillation training
#240 opened Feb 8, 2025 by RyanOvO
3
When I run the GRPO demo, I find that format_reward is always 0！！！
#235 opened Feb 8, 2025 by asirgogogo
13
About the doubts regarding the data processing of the first phase SFT section
#225 opened Feb 7, 2025 by mlshenkai
Eval Numbers - Not Matching
#224 opened Feb 7, 2025 by satpalsr
6
Unable to reproduce the performance of "mathematical reasoning"
#223 opened Feb 7, 2025 by jasonaidm
ProTip! What’s not been updated in a month: updated:<2025-01-11.