LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oğuz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, Vikas Chandra
Abstract
Zechun Liu, Barlas Oguz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, Vikas Chandra. Findings of the Association for Computational Linguistics: ACL 2024. 2024.
Topics & Concepts
Computer scienceQuantization (signal processing)Language modelData modelingArtificial intelligenceNatural language processingDatabaseAlgorithmTopic ModelingNatural Language Processing TechniquesSpeech Recognition and Synthesis