BriefGPT.xyz
Sep, 2024
对超大型语言模型进行激进的后训练压缩
Aggressive Post-Training Compression on Extremely Large Language Models
HTML
PDF
Zining Zhang, Yao Chen, Bingsheng He, Zhenjie Zhang
TL;DR
本文研究了超大型语言模型在个人计算机和移动设备上的部署挑战，提出了一种新颖的网络剪枝技术，能够实现超过0.7的稀疏度和低于8位的量化，显著减少模型尺寸，同时保持相对较小的准确性损失。研究表明，该方法有效而且可实际应用，为自然语言处理应用的普及带来了广泛的影响。
Abstract
The increasing size and complexity of Large
Language Models
(LLMs) pose challenges for their deployment on personal computers and mobile devices. Aggressive post-training
Model Compression
is necessary to reduce
→