@article{babyllama2ensembledistilledmodels,
  title = {BabyLlama-2: Ensemble-Distilled Models Consistently Outperform Teachers With Limited Data},
  author = {Jean-Loup Tastet and Inar Timiryasov},
  year = {2024},
  eprint = {2409.17312},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.17312v1},
}