Prior-Labs/TabPFN-v2-reg

TabPFN v2: A Tabular Foundation Model

TabPFN is a transformer-based foundation model for tabular data that leverages prior-data based learning to achieve strong performance on small tabular regression tasks without requiring task-specific training.

Installation

pip install tabpfn

Model Details

• Developed by: Prior Labs
• Model type: Transformer-based foundation model for tabular data
• License: Prior Labs License (Apache 2.0 with additional attribution requirement)
• Paper: Published in Nature (January 2025)
• Repository: GitHub - priorlabs/tabpfn

📚 Citation

@article{hollmann2025tabpfn,
 title={Accurate predictions on small data with a tabular foundation model},
 author={Hollmann, Noah and M{\"u}ller, Samuel and Purucker, Lennart and
         Krishnakumar, Arjun and K{\"o}rfer, Max and Hoo, Shi Bin and
         Schirrmeister, Robin Tibor and Hutter, Frank},
 journal={Nature},
 year={2025},
 month={01},
 day={09},
 doi={10.1038/s41586-024-08328-6},
 publisher={Springer Nature},
 url={https://www.nature.com/articles/s41586-024-08328-6},
}

Quick Start

📚 For detailed usage examples and best practices, check out:

• Interactive Colab Tutorial

Technical Requirements

• Python ≥ 3.9
• PyTorch ≥ 2.1
• scikit-learn ≥ 1.0
• Hardware: 16GB+ RAM, CPU (GPU optional)

Limitations

• Not designed for very large datasets
• Not suitable for non-tabular data formats

Resources

• Documentation: https://priorlabs.ai/docs
• Source: https://github.com/priorlabs/tabpfn
• Paper: https://www.nature.com/articles/s41586-024-08328-6

Team

• Noah Hollmann
• Samuel Müller
• Lennart Purucker
• Arjun Krishnakumar
• Max Körfer
• Shi Bin Hoo
• Robin Tibor Schirrmeister
• Frank Hutter
• Eddie Bergman
• Léo Grinsztajn