3 papers
cs.SD2024
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition
Hang Shao, Bei Liu, Wei Wang +2
As a popular multilingual and multitask pre-trained speech model, Whisper has the problem of curse of multilinguality. To enhance multilingual capabilities in small Whisper models,…
cs.LG2024
CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs
Haoyu Wang, Bei Liu, Hang Shao +4
Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approach…
cs.CL2024
One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
Hang Shao, Bei Liu, Bo Xiao +3
Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However…