@article{qprunerprobabilisticdecisionquantization,
  title = {QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models},
  author = {Changhai Zhou and Yuhua Zhou and Shijie Han and Qian Qiao and Hongguang Li},
  year = {2024},
  eprint = {2412.11629},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.11629v1},
}