@article{compressinglargelanguagemodelsby,
  title = {Streamlining Redundant Layers to Compress Large Language Models},
  author = {Xiaodong Chen and Yuxuan Hu and Jing Zhang and Yanling Wang and Cuiping Li and Hong Chen},
  year = {2024},
  eprint = {2403.19135},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.19135v5},
}