"Symmetric Dot-Product Attention for Efficient Training of BERT Language ..."

Martin Courtois et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2406.06366

access: open

type: Informal or Other Publication

metadata version: 2024-07-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics