PaTaRM-8B

arXiv GitHub License

This is the PaTaRM-8B model, part of the PaTaRM series. For full details including overview, usage examples, training data, and citation, please refer to the main collection README:

👉 AIJian/PaTaRM — Main README

Models

Model Base Link
PaTaRM-8B Qwen3-8B AIJian/PaTaRM-8B
PaTaRM-14B Qwen3-14B AIJian/PaTaRM-14B

Citation

@misc{jian2026patarmbridgingpairwisepointwise,
      title={PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling}, 
      author={Ai Jian and Jingqing Ruan and Xing Ma and Dailin Li and Weipeng Zhang and Ke Zeng and Xunliang Cai},
      year={2026},
      eprint={2510.24235},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.24235}, 
}
Downloads last month
856
Safetensors
Model size
0.5B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AIJian/PaTaRM-8B

Finetuned
Qwen/Qwen3-8B
Finetuned
(1440)
this model
Quantizations
1 model

Collection including AIJian/PaTaRM-8B

Paper for AIJian/PaTaRM-8B