"Blockwise Compression of Transformer-based Models without Retraining."

Gaochen Dong, Wei Chen (2023)

Details and statistics

DOI: 10.48550/ARXIV.2304.01483

access: open

type: Informal or Other Publication

metadata version: 2023-04-17

a service of  Schloss Dagstuhl - Leibniz Center for Informatics