@inproceedings{zhu-etal-2024-llama,
    title = "{LL}a{MA}-{M}o{E}: Building Mixture-of-Experts from {LL}a{MA} with Continual Pre-Training",
    author = "Zhu, Tong  and
      Qu, Xiaoye  and
      Dong, Daize  and
      Ruan, Jiacheng  and
      Tong, Jingqi  and
      He, Conghui  and
      Cheng, Yu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.890/",
    doi = "10.18653/v1/2024.emnlp-main.890",
    pages = "15913--15923"
}