@inproceedings{minitron2024,
  title = {Compact Language Models via Pruning and Knowledge Distillation},
  author = {Saurav Muralidharan and Sharath Turuvekere Sreenivas and Raviraj Joshi and Marcin Chochowski and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Jan Kautz and Pavlo Molchanov},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2407.14679},
  archiveprefix = {arxiv},
}
