Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Mingyu, Li, Gen, Ji, Jie, Zhang, Jiaqi, Jaiswal, Ajay, Shen, Li, Ma, Xiaolong, Liu, Shiwei, Yin, Lu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.00069