@inproceedings{artetxe-etal-2022-efficient,
    title = "Efficient Large Scale Language Modeling with Mixtures of Experts",
    author = "Artetxe, Mikel  and
      Bhosale, Shruti  and
      Goyal, Naman  and
      Mihaylov, Todor  and
      Ott, Myle  and
      Shleifer, Sam  and
      Lin, Xi Victoria  and
      Du, Jingfei  and
      Iyer, Srinivasan  and
      Pasunuru, Ramakanth  and
      Anantharaman, Giridharan  and
      Li, Xian  and
      Chen, Shuohui  and
      Akin, Halil  and
      Baines, Mandeep  and
      Martin, Louis  and
      Zhou, Xing  and
      Koura, Punit Singh  and
      O{'}Horo, Brian  and
      Wang, Jeffrey  and
      Zettlemoyer, Luke  and
      Diab, Mona  and
      Kozareva, Zornitsa  and
      Stoyanov, Veselin",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.804/",
    doi = "10.18653/v1/2022.emnlp-main.804",
    pages = "11699--11732"
}