@article{gptqtquantizelargelanguagemodelstwiceto,
  title = {GPTQT: Quantize Large Language Models Twice to Push the Efficiency},
  author = {Yipin Guo and Yilin Lang and Qinyuan Ren},
  year = {2024},
  eprint = {2407.02891},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.02891v1},
}