LLMZip: Lossless Text Compression using Large Language Models

Code

• github.com/vcskaushik/LLMzip
  Officialpytorch★ 65
• github.com/erika-n/GPTzip
  pytorch★ 13

Abstract

We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently available estimates in cover1978convergent, lutati2023focus. A natural byproduct is an algorithm for lossless compression of English text which combines the prediction from the large language model with a lossless compression scheme. Preliminary results from limited experiments suggest that our scheme outperforms state-of-the-art text compression schemes such as BSC, ZPAQ, and paq8h.

Tasks

Reproductions