"Analyzing the Scaling Characteristics of Transformer Feed-Forward Networks ..."

Taehyun Kim, Hyuk-Jae Lee (2024)

Details and statistics

DOI: 10.1109/ICEIC61013.2024.10457210

access: closed

type: Conference or Workshop Paper

metadata version: 2024-04-02

a service of  Schloss Dagstuhl - Leibniz Center for Informatics