Model Card for AtomThink-LlamaV

The model is post-trained based on llava-v1.5-7b and the AtomThink framework, and can be used to solve complex multimodal mathematical problems.

Citation

If you use this dataset in your research, please cite:

@article{xiang2025can,
  title={Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?},
  author={Xiang, Kun and Liu, Zhili and Jiang, Zihao and Nie, Yunshuang and Cai, Kaixin and Yin, Yiyang and Huang, Runhui and Fan, Haoxiang and Li, Hanhui and Huang, Weiran and others},
  journal={arXiv preprint arXiv:2503.06252},
  year={2025}
}

@article{xiang2024atomthink,
  title={AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning},
  author={Xiang, Kun and Liu, Zhili and Jiang, Zihao and Nie, Yunshuang and Huang, Runhui and Fan, Haoxiang and Li, Hanhui and Huang, Weiran and Zeng, Yihan and Han, Jianhua and others},
  journal={arXiv preprint arXiv:2411.11930},
  year={2024}
}

License

The checkpoint is released under the Apache 2.0 license. Please ensure proper attribution when using this checkpoint.

Downloads last month
2
Safetensors
Model size
7.06B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for Quinn777/AtomThink-LLaVA1.5-7B

Finetuned
(12)
this model

Dataset used to train Quinn777/AtomThink-LLaVA1.5-7B