@article{indicllmsuiteablueprintforcreatingpre,
  title = {IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages},
  author = {Mohammed Safi Ur Rahman Khan and Priyam Mehta and Ananth Sankar and Umashankar Kumaravelan and Sumanth Doddapaneni and Suriyaprasaad B and Varun Balan G and Sparsh Jain and Anoop Kunchukuttan and Pratyush Kumar and Raj Dabre and Mitesh M. Khapra},
  year = {2024},
  eprint = {2403.06350},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.06350v2},
}