@article{gqatraininggeneralizedmultiquery, title = {GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints}, author = {Joshua Ainslie and James Lee-Thorp and Michiel de Jong and Yury Zemlyanskiy and Federico Lebrón and Sumit Sanghai}, year = {2023}, eprint = {2305.13245}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.13245v3}, }