"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated ..."

Yixin Song et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2406.05955

access: open

type: Informal or Other Publication

metadata version: 2024-07-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics