@article{shortenedllamaasimpledepthpruningfor,
  title = {Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods},
  author = {Bo-Kyeong Kim and Geonmin Kim and Tae-Ho Kim and Thibault Castells and Shinkook Choi and Junho Shin and Hyoung-Kyu Song},
  year = {2024},
  eprint = {2402.02834},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.02834v2},
}