"Layer-wise Pruning of Transformer Attention Heads for Efficient Language ..."

Kyuhong Shim et al. (2021)

Details and statistics

DOI: 10.1109/ISOCC53507.2021.9613933

access: closed

type: Conference or Workshop Paper

metadata version: 2021-12-06

a service of  Schloss Dagstuhl - Leibniz Center for Informatics