Xdoc Base Squad2.0

🚀 XDoc

XDoc is a unified pre-trained model that can handle various document formats within a single model. Despite having only 36.7% of the parameters, it achieves comparable or superior performance on downstream tasks, making it highly cost - effective for real - world deployment.

🚀 Quick Start

XDoc is a unified pre - trained model designed to handle different document formats in a single model. It offers cost - effective solutions for real - world deployment due to its relatively small parameter size and good performance on downstream tasks.

📚 Documentation

Paper

XDoc: Unified Pre - training for Cross - Format Document Understanding Jingye Chen, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei, EMNLP 2022

Citation

If you find XDoc helpful, please cite us:

@article{chen2022xdoc,
  title={XDoc: Unified Pre-training for Cross-Format Document Understanding},
  author={Chen, Jingye and Lv, Tengchao and Cui, Lei and Zhang, Cha and Wei, Furu},
  journal={arXiv preprint arXiv:2210.02849},
  year={2022}
}

📄 License

This project is licensed under the MIT license.