BriefGPT.xyz
Feb, 2025
AdaSVD:用于大型语言模型的自适应奇异值分解
AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
HTML
PDF
Zhiteng Li, Mingyuan Xia, Jingyuan Zhang, Zheng Hui, Linghe Kong...
TL;DR
本研究解决了大型语言模型在资源受限设备上的内存需求高的问题,提出了自适应奇异值分解方法AdaSVD。该方法通过交替更新奇异矩阵来补偿奇异值分解截断误差,并根据各层的重要性动态分配压缩比例。实验表明,AdaSVD在内存效率和性能上均优于现有的最先进方法,具有显著的实用价值。
Abstract
Large Language Models
(LLMs) have achieved remarkable success in natural language processing (
NLP
) tasks, yet their substantial memory requirements present significant challenges for deployment on resource-constr
→