"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts."

Sejik Park (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.11530

access: open

type: Informal or Other Publication

metadata version: 2024-06-12

a service of  Schloss Dagstuhl - Leibniz Center for Informatics