"Infinite Limits of Multi-head Transformer Dynamics."

Blake Bordelon, Hamza Tahir Chaudhry, Cengiz Pehlevan (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.15712

access: open

type: Informal or Other Publication

metadata version: 2024-06-24

a service of  Schloss Dagstuhl - Leibniz Center for Informatics