@article{continualpretrainingoflargelanguage,
  title = {Continual Pre-Training of Large Language Models: How to (re)warm your model?},
  author = {Kshitij Gupta and Benjamin Thérien and Adam Ibrahim and Mats L. Richter and Quentin Anthony and Eugene Belilovsky and Irina Rish and Timothée Lesort},
  year = {2023},
  eprint = {2308.04014},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.04014v2},
}