@article{selfdistilledquantizationachievinghigh,
  title = {Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models},
  author = {James O' Neill and Sourav Dutta},
  year = {2023},
  eprint = {2307.05972},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.05972v1},
}