@inproceedings{timiryasov-tastet-2023-baby,
    title = "Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty",
    author = "Timiryasov, Inar  and
      Tastet, Jean-Loup",
    editor = "Warstadt, Alex  and
      Mueller, Aaron  and
      Choshen, Leshem  and
      Wilcox, Ethan  and
      Zhuang, Chengxu  and
      Ciro, Juan  and
      Mosquera, Rafael  and
      Paranjabe, Bhargavi  and
      Williams, Adina  and
      Linzen, Tal  and
      Cotterell, Ryan",
    booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.conll-babylm.24/",
    doi = "10.18653/v1/2023.conll-babylm.24",
    pages = "279--289"
}