@inproceedings{moeficationconditionalcomputationof,
  title = {MoEfication: Transformer Feed-forward Layers are Mixtures of Experts},
  author = {Zhengyan Zhang and Yankai Lin and Zhiyuan Liu and Peng Li and Maosong Sun and Jie zhou},
  year = {2021},
  booktitle = {Findings (ACL) 2022 5},
  eprint = {2110.01786},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.01786v3},
}