This repository contains the code and models for our paper:

How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes
Harmon Bhasin, Tim Ossowski, Yiqiao Zhong, Junjie Hu
Paper: https://openreview.net/forum?id=ZJ91L3XvqF

    @inproceedings{bhasin2024how,
        title={How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes},
        author={Harmon Bhasin and Timothy Ossowski and Yiqiao Zhong and Junjie Hu},
        booktitle={2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
        year={2024},
        url={https://openreview.net/forum?id=ZJ91L3XvqF}
    }

Models used in the paper can be found by going to Box and downloading the folder found here: https://uwmadison.box.com/s/09ip5oht977fxp3mvebkykxwbbwvl4ls

Maintainers

• Harmon Bhasin