@article{babyllamaknowledgedistillationfroman,
  title = {Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty},
  author = {Inar Timiryasov and Jean-Loup Tastet},
  year = {2023},
  eprint = {2308.02019},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.02019v2},
}