# GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

> Research article (Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023) · cited 299× · AI/ML

**Wikidata**: [openalex:W4389518760](https://www.wikidata.org/wiki/openalex:W4389518760)  
**Source**: https://4ort.xyz/entity/gqa-training-generalized-multi-query-transformer-models-from-multi-head-checkpoints