"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models."

Elias Frantar, Dan Alistarh (2023)

Details and statistics

DOI: 10.48550/ARXIV.2310.16795

access: open

type: Informal or Other Publication

metadata version: 2023-10-31

a service of  Schloss Dagstuhl - Leibniz Center for Informatics