Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yanshu, He, Wenyang, Yang, Tong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.17470
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916263326908416
author Wang, Yanshu
He, Wenyang
Yang, Tong
author_facet Wang, Yanshu
He, Wenyang
Yang, Tong
contents Large Language Models (LLMs) have significantly advanced natural language processing tasks such as machine translation, text generation, and sentiment analysis. However, their large size, often consisting of billions of parameters, poses challenges for storage, computation, and deployment, particularly in resource-constrained environments like mobile devices and edge computing platforms. Effective compression and quantization techniques are crucial for addressing these issues, reducing memory footprint and computational requirements without significantly compromising performance. Traditional methods that uniformly map parameters to compressed spaces fail to account for the uneven distribution of parameters, leading to substantial accuracy loss. In this work, we propose Athena, a novel algorithm for efficient block-wise post-training quantization of LLMs. Athena leverages Second-Order Matrix Derivative Information to guide the quantization process using the curvature information of the loss landscape. By grouping parameters by columns or rows and iteratively optimizing the quantization process, Athena updates the model parameters and Hessian matrix to achieve significant compression while maintaining high accuracy. This makes Athena a practical solution for deploying LLMs in various settings.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17470
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information
Wang, Yanshu
He, Wenyang
Yang, Tong
Machine Learning
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) have significantly advanced natural language processing tasks such as machine translation, text generation, and sentiment analysis. However, their large size, often consisting of billions of parameters, poses challenges for storage, computation, and deployment, particularly in resource-constrained environments like mobile devices and edge computing platforms. Effective compression and quantization techniques are crucial for addressing these issues, reducing memory footprint and computational requirements without significantly compromising performance. Traditional methods that uniformly map parameters to compressed spaces fail to account for the uneven distribution of parameters, leading to substantial accuracy loss. In this work, we propose Athena, a novel algorithm for efficient block-wise post-training quantization of LLMs. Athena leverages Second-Order Matrix Derivative Information to guide the quantization process using the curvature information of the loss landscape. By grouping parameters by columns or rows and iteratively optimizing the quantization process, Athena updates the model parameters and Hessian matrix to achieve significant compression while maintaining high accuracy. This makes Athena a practical solution for deploying LLMs in various settings.
title Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2405.17470