Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
Jeonghoon Kim, Sungdong Kim, Se Jung Kwon, Dongsoo Lee, Jung Hyun Lee, Joonsuk Park, Kang Min Yoo
Topics & Concepts
Computer scienceAlgorithmInteger (computer science)Quantization (signal processing)MathematicsData compressionArtificial intelligenceTheoretical computer scienceNatural languageDiscrete mathematicsCompression (physics)Context (archaeology)Vector quantizationAlgebra over a fieldSet (abstract data type)Big Data and Digital EconomyNatural Language Processing TechniquesSpeech Recognition and Synthesis