Int2Int: a framework for mathematics with transformers

TL;DR

Int2Int is an open-source PyTorch framework that applies transformer models to mathematical research problems, especially in number theory, providing tools for data handling, model training, and visualization.

Contribution

This work introduces a comprehensive transformer-based framework tailored for mathematical research, with tools for data processing, model training, and extensibility.

Findings

Provides a complete PyTorch implementation of transformers for math problems

Includes data preparation and visualization tools

Facilitates research in mathematical problem-solving with transformers

Abstract

This paper documents Int2Int, an open source code base for using transformers on problems of mathematical research, with a focus on number theory and other problems involving integers. Int2Int is a complete PyTorch implementation of a transformer architecture, together with training and evaluation loops, and classes and functions to represent, generate and decode common mathematical objects. Ancillary code for data preparation, and Jupyter Notebooks for visualizing experimental results are also provided. This document presents the main features of Int2Int, serves as its user manual, and provides guidelines on how to extend it. Int2Int is released under the MIT licence, at https://github.com/f-charton/Int2Int.