Saved in:
Bibliographic Details
Main Authors: Cai, Wen-Pu, Li, Ming-Yang, Li, Wu-Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.20973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916605283270656
author Cai, Wen-Pu
Li, Ming-Yang
Li, Wu-Jun
author_facet Cai, Wen-Pu
Li, Ming-Yang
Li, Wu-Jun
contents Large language models~(LLMs) have recently demonstrated promising performance in many tasks. However, the high storage and computational cost of LLMs has become a challenge for deploying LLMs. Weight quantization has been widely used for model compression, which can reduce both storage and computational cost. Most existing weight quantization methods for LLMs use a rank-one codebook for quantization, which results in substantial accuracy loss when the compression ratio is high. In this paper, we propose a novel weight quantization method, called low-rank codebook based quantization~(LCQ), for LLMs. LCQ adopts a low-rank codebook, the rank of which can be larger than one, for quantization. Experiments show that LCQ can achieve better accuracy than existing methods with a negligibly extra storage cost.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20973
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LCQ: Low-Rank Codebook based Quantization for Large Language Models
Cai, Wen-Pu
Li, Ming-Yang
Li, Wu-Jun
Machine Learning
Computation and Language
Large language models~(LLMs) have recently demonstrated promising performance in many tasks. However, the high storage and computational cost of LLMs has become a challenge for deploying LLMs. Weight quantization has been widely used for model compression, which can reduce both storage and computational cost. Most existing weight quantization methods for LLMs use a rank-one codebook for quantization, which results in substantial accuracy loss when the compression ratio is high. In this paper, we propose a novel weight quantization method, called low-rank codebook based quantization~(LCQ), for LLMs. LCQ adopts a low-rank codebook, the rank of which can be larger than one, for quantization. Experiments show that LCQ can achieve better accuracy than existing methods with a negligibly extra storage cost.
title LCQ: Low-Rank Codebook based Quantization for Large Language Models
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2405.20973