Skip to content

Issues: huggingface/open-r1

How to contribute
#23 opened Jan 25, 2025 by lewtun
Open 10
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

199 Open 67 Closed
199 Open 67 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

SFT model make repetitions during the inference phase
#492 opened Mar 8, 2025 by 0205090923
2
Prefix Caching should be turned off for GRPO
#491 opened Mar 7, 2025 by damanimehul
4
训练的Num examples加载数目错误
#490 opened Mar 7, 2025 by rainylover
Inference output format does not match reward function
#489 opened Mar 7, 2025 by ryan-minato
low performence in evaluation with sft distilled model
#487 opened Mar 7, 2025 by Jiehon
1
RLOO (including REINFORCE++) support
#486 opened Mar 7, 2025 by jssuncx
Is there a smaller data set that supports GRPO training?
#485 opened Mar 6, 2025 by laogonggong847
How to calculate total optimization steps
#483 opened Mar 6, 2025 by HelloWorld506
[ROCm] GRPO Training with vLLM is hanging on MI300X system, w/o vLLM it works properly
#482 opened Mar 5, 2025 by nikhil-tensorwave
grpo with multiple GPUs got stuck
#478 opened Mar 5, 2025 by SuMeng123
1
GRPO OOM
#475 opened Mar 5, 2025 by samma1570
6
Why don't rewards increase instead of staying at a certain value in GRPO？
#474 opened Mar 5, 2025 by AXy1527
Inconsistent chat_template during training and evaluation
#473 opened Mar 5, 2025 by 0205090923
3
how to set the max_model_length, max_new_tokens and generation_size when evaluate ?
#472 opened Mar 5, 2025 by ItGirls
1
Can I use two GPUs for VLLM?
#471 opened Mar 4, 2025 by RL4LLM
2
different max_position_embeddings and rope_theta in and OpenR1-Qwen-7B-SFT and it's base Qwen2.5-Math-7B-Instruct ?
#469 opened Mar 4, 2025 by ItGirls
lighteval script failed
#468 opened Mar 4, 2025 by foamliu
6
Can grpo run on single H20?
#467 opened Mar 4, 2025 by ListentoMe0112
1
Is it normal for a 1.5B model on an H100 80G to require several hundred hours for LiveCodeBench?
#466 opened Mar 4, 2025 by wccccp
1
Questions Regarding Completion Length Change in Reproducing SimpleRL-Reason
#465 opened Mar 4, 2025 by nonstopfor
5
Max_model_length error for Math-7B model
#458 opened Mar 3, 2025 by 0205090923
1
How to run reject sampling
#457 opened Mar 3, 2025 by JavaZeroo
Run code reward locally
#456 opened Mar 2, 2025 by shouldnotappearcalm
trainer = GRPOTrainer() 出现 requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/repos/create
#455 opened Mar 2, 2025 by lijiayi980130
1
I used lighteval accelerate for evaluation. However, the output results of the model seem to be truncated. (Pred: ["To"]) This led to an evaluation score of 0.
#452 opened Feb 28, 2025 by jackwwy
5
ProTip! Follow long discussions with comments:>50.