Extreme Compression of Large Language Models via Additive Quantization

Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh
January, 2024
PDF Cite Code Paper arXiv

Abstract

AQLM compresses language model weights through additive quantization, targeting accurate inference at very low bit widths.

Type
Conference paper
Publication
ICML 2024
Andrei Panferov
Andrei Panferov
PhD Candidate in Computer Science

I work on efficient large language models, with a focus on low-precision training, quantization, and scaling laws.