Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head ..."

Joshua Ainslie et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2305.13245

access: open

type: Informal or Other Publication

metadata version: 2023-05-26