Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nrusimha, Aniruddha, Mishra, Mayank, Wang, Naigang, Alistarh, Dan, Panda, Rameswar, Kim, Yoon
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/2404.03605