notesum.ai

Published at April 22

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models

NeurIPS

Released Date: April 22, 2024

Authors: Lujun Li¹, Peijie Dong², Zhenheng Tang³, Xiang Liu², Qiang Wang⁴, Wenhan Luo¹, Wei Xue¹, Qifeng Liu¹, Xiaowen Chu², Yike Guo¹

Aff.: ¹Hong Kong University of Science and Technology; ²Hong Kong University of Science and Technology (Guangzhou); ³Hong Kong Baptist University; ⁴Harbin Institute of Technology (Shenzhen)

Arxiv: https://openreview.net/pdf/c742f770723557fe9f03c7f7eb1944b07bd68423.pdf