GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.
Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebrn, Sumit Sanghai
Browse the full EMNLP paper archive.
Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebrn, Sumit Sanghai
Browse the full EMNLP paper archive.