Thinking Like Transformers

Alexander M Rush, Gail Weiss

Keywords: Transformers

Abstract: Thinking like Transformers proposes a computational framework for Transformer-like calculations. The framework uses discrete computation to simulate Transformer computations. The resulting language RASP is a programming language where every program compiles down to a specific Transformer. In this blog post, we reimplement a variant of RASP in Python (RASPy). The language is roughly compatible with the original version, but with some syntactic changes for simplicity. With this language, we consider a challenging set of puzzles to walk through and understand how it works.

Blogpost Url: https://iclr-blogposts.github.io/2023/blog/2023/raspy/

ICLR Papers: https://arxiv.org/abs/2106.06981

ID Of The Authors Of The ICLR Paper: ~Gail_Weiss1

Conflict Of Interest: No

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/thinking-like-transformers/code)