@misc{chen2024compressing,
  title={Compressing Large Language Models by Streamlining the Unimportant Layer},
  author={Xiaodong Chen and Yuxuan Hu and Jing Zhang},
  year={2024},
  eprint={2403.19135},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2403.19135}
}