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

223 Open 74 Closed
223 Open 74 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

Almost successfully reproducing open-r1/OpenR1-Qwen-7B based on Qwen/Qwen2.5-Math-7B-Instruct. Here are the training configurations.
#545 opened Mar 25, 2025 by kiseliu
3
saving checkpoints error while grpo
#544 opened Mar 25, 2025 by Maochenhui123
1
Error with latest setup.py trl.extras.vllm_client - Server is not up yet
#543 opened Mar 24, 2025 by ECMGit
4
SFT on Qwen2.5-1.5B-Instruct is failed
#539 opened Mar 24, 2025 by HwangYej1
Reproducing GRPO based on Qwen2.5-1.5B-Instruct and using Math-220K dataset Yields Unexpected Results
#538 opened Mar 24, 2025 by undyingjoker
get error when set packing=false
#536 opened Mar 22, 2025 by ltm920716
can not reproduce the eval accuracy by demo code
#530 opened Mar 21, 2025 by ltm920716
1
🚀 Surpass o1-preview with just 7,000 samples and $42 on DeepSeek-R1-Distill-Qwen-1.5B—scoring AIME 46.7% (vs. o1-preview’s 44.6%)! 📝
#527 opened Mar 21, 2025 by QuyAnh2005
1
文件 图片 14/10000 实时翻译 划译 The training results cannot be uploaded to Wandb
#526 opened Mar 20, 2025 by hardworkers440
Evaluation on math_500 task fails with SyntaxError due to invalid character in gemma-3-1b-it model output
#525 opened Mar 20, 2025 by winterdrive
Different learning rates of SimpleRL
#524 opened Mar 20, 2025 by undyingjoker
Questions about Fine-tuning with Specialized Model Variants for Open-R1
#522 opened Mar 19, 2025 by doublelei
How to use my own dataset in sft?
#521 opened Mar 18, 2025 by dongdongzhaoUP
1
After SFT, the model make repetitions
#520 opened Mar 18, 2025 by cnlinxi
1
"label" and "input_ids" are identical during SFT, instruction is not masked with -100
#517 opened Mar 18, 2025 by Ultramarine-spec
1
After SFT trained，the <think> tag disappeared
#515 opened Mar 18, 2025 by dayL-W
1
Multi-gpu vllm inference with tensor parallelism, colocating policy model + ref model + vllm engine on the same node
#514 opened Mar 17, 2025 by nhannguyen2709
3
Can't find nvmlDeviceGetNvLinkRemoteDeviceType: /home/opt/gpuproxy/lib64/libnvidia-ml.so.1: undefined symbol: nvmlDeviceGetNvLinkRemoteDeviceType
#511 opened Mar 16, 2025 by singstreetwithu
[Installation] Failed to Build vllm on ARM Architecture with uv pip install - Unknown Runtime Environment
#510 opened Mar 16, 2025 by EricLabile
OOM, SFT Qwen2.5-1.5B-Instruct OpenR1-Math-220k
#506 opened Mar 14, 2025 by KeyKy
3
Fail to parse gold solution
#503 opened Mar 12, 2025 by Lynnzake
10
How to use vllm with 2 GPUs?
#502 opened Mar 12, 2025 by greatxue
3
Managed resource "pipeline" is not used within its block and is closed before it's returned
#501 opened Mar 11, 2025 by keskival
'int' object is not iterable
#500 opened Mar 11, 2025 by Stilwl
1
SFT model make repetitions during the inference phase
#492 opened Mar 8, 2025 by 0205090923
5
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.