BriefGPT.xyz
Feb, 2024
学会高效:在大型语言模型中构建结构化稀疏性
Learn To be Efficient: Build Structured Sparsity in Large Language Models
HTML
PDF
Haizhong Zheng, Xiaoyan Bai, Beidi Chen, Fan Lai, Atul Prakash
TL;DR
使用Learn-To-be-Efficient算法能够实现大型语言模型的效率提升,通过激活较少神经元来获得更好的稀疏性和性能平衡,取得了较好的结果。
Abstract
large language models
(LLMs) have achieved remarkable success with their billion-level parameters, yet they incur high inference overheads. The emergence of
activation sparsity
in LLMs provides a natural approach
→