BriefGPT.xyz
Jan, 2024
SliceGPT:通过删除行和列来压缩大型语言模型
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
HTML
PDF
Saleh Ashkboos, Maximilian L. Croci, Marcelo Gennari do Nascimento, Torsten Hoefler, James Hensman
TL;DR
SliceGPT是一种新的后训练稀疏化方法,可以将模型的参数减少25%,同时保持密集模型的99%,99%和90%的性能,并减少内存和计算需求。
Abstract
large language models
have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources.
sparsification
provides a solution to allevia
→