@inproceedings{compressionofgenerativepretrained,
  title = {Compression of Generative Pre-trained Language Models via Quantization},
  author = {Chaofan Tao and Lu Hou and Wei zhang and Lifeng Shang and Xin Jiang and Qun Liu and Ping Luo and Ngai Wong},
  year = {2022},
  booktitle = {ACL 2022 5},
  eprint = {2203.10705},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.10705v2},
}