"LSG Attention: Extrapolation of pretrained Transformers to long sequences."

Charles Condevaux, Sébastien Harispe (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.15497

access: open

type: Informal or Other Publication

metadata version: 2023-06-26

a service of  Schloss Dagstuhl - Leibniz Center for Informatics