"MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts."

Zhitian Xie et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.00893

access: open

type: Informal or Other Publication

metadata version: 2024-02-09

a service of  Schloss Dagstuhl - Leibniz Center for Informatics