Skip to content

Issues: huggingface/open-r1

How to contribute
#23 opened Jan 25, 2025 by lewtun
Open 5
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

72 Open 16 Closed
72 Open 16 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

Collaborative Effort to Replicate DeepSeek-R1 Model Training
#192 opened Feb 5, 2025 by climbtop
Feature Request: Enhanced Documentation for DeepSeek-R1 Model Training
#191 opened Feb 5, 2025 by climbtop
Request for Guidance on Replicating DeepSeek-R1 Model Training
#190 opened Feb 5, 2025 by climbtop
Does this setup support training the original deepseekv3/r1 671b models? Or it just supports training the distilled models which are smaller in size?
#189 opened Feb 5, 2025 by vamshi-rvk
[ERROR]: [rank0]: RuntimeError: The size of tensor a (893) must match the size of tensor b (894) at non-singleton dimension 2
#187 opened Feb 5, 2025 by Desperado-Jia
Error: "Can only compare inequalities with Expr" when using zero2.yaml to grpo.py
#186 opened Feb 5, 2025 by pyh314
TypeError: LatexExtractionConfig.__init__() got an unexpected keyword argument 'boxed_match_priority'
#184 opened Feb 5, 2025 by xiaobanli
How to directly input embeddings into the model?
#183 opened Feb 4, 2025 by CCCC1800
Error in create_model_card() when running grpo.py
#182 opened Feb 4, 2025 by LaolaoRkkk
2
How to launch GRPO with vLLM on multi-node slurm?
#180 opened Feb 4, 2025 by pbelevich
Dear Hugging Face / open‑r1 Project Team,
#175 opened Feb 4, 2025 by bbylw
Evaluation script fails to work for Qwen-Math models.
#174 opened Feb 4, 2025 by ChenDRAG
3
evaluation error: TypeError: EngineArgs.__init__() got an unexpected keyword argument 'worker_use_ray'
#173 opened Feb 4, 2025 by ChenDRAG
1
Website purporting to be run by this project
#172 opened Feb 3, 2025 by jmtn
3
# Potential Inconsistency in Evaluation Method with Original DeepSeek RL-Zero Paper
#170 opened Feb 3, 2025 by rabihchamas
2
GRPO training error related to sympy/math expressions
#168 opened Feb 3, 2025 by guizhenn
2
Thinking Duration Controller
#167 opened Feb 3, 2025 by rs545837
1
Is Data Preprocessing Recommended for AI-MO/NuminaMath-TIR?
#165 opened Feb 2, 2025 by laolaorkkkkk
2
Error in make evaluate: TypeError: VLLMModelConfig.__init__() got an unexpected keyword argument ''
#163 opened Feb 2, 2025 by mattdepaolis
RuntimeError: CUDA driver error: invalid argument
#162 opened Feb 2, 2025 by stars79689
Slow Training Time in GRPO
#161 opened Feb 2, 2025 by troy12x
1
NCCL problem occured when multiple GPU cards are saving model.safetensors
#160 opened Feb 2, 2025 by pyh314
Should skips really get reward 1?
#159 opened Feb 2, 2025 by ctjlewis
7
Continual Training for DeepSeek R1
#156 opened Feb 2, 2025 by 14H034160212
Is the pipeline described in Step 3 diagram in the README.md correct?
#154 opened Feb 1, 2025 by wuwowuyi
ProTip! Find all open issues with in progress development work with linked:pr.