Cite
Notes
Only stored in your browser.
Attribution
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
arXiv 2024
from 1 papers
Kaipeng Zhang
Mengzhao Chen
Peng Gao
Peng Xu
Ping Luo
Shitao Tang
Wenqi Shao
Yu Qiao