@misc{zhu2023survey, title={A Survey on Model Compression for Large Language Models}, author={Xunyu Zhu and Jian Li and Yong Liu and Can Ma and Weiping Wang}, year={2023}, eprint={2308.07633}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2308.07633} }