DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yanfeng, Yang, Zelan, Chen, Bohua, Li, Shen, Li, Yong, Li, Tao
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.08666