"LongHeads: Multi-Head Attention is Secretly a Long Context Processor."

Yi Lu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.10685

access: open

type: Informal or Other Publication

metadata version: 2024-03-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics