"DeepNet: Scaling Transformers to 1, 000 Layers."

Hongyu Wang et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2203.00555

access: open

type: Informal or Other Publication

metadata version: 2022-12-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics