"Efficient GPT Model Pre-training using Tensor Train Matrix Representation."

Viktoria Chekalina et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2306.02697

access: open

type: Informal or Other Publication

metadata version: 2023-06-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics