Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models

arXiv:2403.18159v1 Announce Type: new
Abstract: Large generative models, such as large language models (LLMs) and diffusion models have as revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it challenging to deploy them on edge devices. In this study, we propose a light-weight quantization aware fine tuning technique using knowledge distillation (KD-QAT) to improve the performance of 4-bit weight quantized LLMs using commonly available datasets to realize a popular language …

abstract analysis arxiv computation computer computer vision cs.ai cs.cl cs.lg deploy diffusion diffusion models distillation edge fields generative generative models however improving inference knowledge language language models large language large language models llms memory nlp propagation signal them type via vision