URSA-MATH/URSA-RM-8B

URSA-8B

URSA-RM-8B is the first open-source, small-sized reward model that operates in multimodal mathematics.

Installation

from huggingface_hub import snapshot_download

repo_id = "URSA-MATH/URSA-RM-8B"
local_dir = YOUR_LOCAL_PATH  

snapshot_path = snapshot_download(
    repo_id=repo_id,
    local_dir=local_dir,
    revision="main", 
    cache_dir=None, 
)

Inference

Please refer to the GitHub repository for inference.

Citation

If you find our paper, model, or data helpful, please give this repo a star 🌟 and cite our article ✏️.

@article{luo2025ursa,
  title={URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics},
  author={Luo, Ruilin and Zheng, Zhuofan and Wang, Yifan and Yu, Yiyao and Ni, Xinzhe and Lin, Zicheng and Zeng, Jin and Yang, Yujiu},
  journal={arXiv preprint arXiv:2501.04686},
  year={2025}
}