"Mixture of Attention Heads: Selecting Attention Heads Per Token."

Xiaofeng Zhang et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.05144

access: open

type: Informal or Other Publication

metadata version: 2024-03-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics