Modelpublic

2stacks/s1-0.5B

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

1likes15downloads

Model Card

Model Summary

s1-0.5B is a reasoning model finetuned from Qwen2.5-0.5B-Instruct on just 1,000 examples. This model was created simply to test the process used to train the original S1 cited below using consumer grade GPUs.

—Repository: simplescaling/s1
—Paper: https://arxiv.org/abs/2501.19393

Use

The model usage is documented here.

Citation

bibtex

@misc{muennighoff2025s1simpletesttimescaling,
      title={s1: Simple test-time scaling}, 
      author={Niklas Muennighoff and Zitong Yang and Weijia Shi and Xiang Lisa Li and Li Fei-Fei and Hannaneh Hajishirzi and Luke Zettlemoyer and Percy Liang and Emmanuel Candès and Tatsunori Hashimoto},
      year={2025},
      eprint={2501.19393},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.19393}, 
}