{
 "id": "ai4bharat/sangraha",
 "owner": "ai4bharat",
 "name": "sangraha",
 "downloads": 45680,
 "likes": 87,
 "last_modified": "2025-03-05T06:35:50.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{khan2024indicllmsuite,\n  title   = {IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages},\n  author  = {Mohammed Safi Ur Rahman Khan and Priyam Mehta and Ananth Sankar and Umashankar Kumaravelan and Sumanth Doddapaneni and Suriyaprasaad G and Varun Balan G and Sparsh Jain and Anoop Kunchukuttan and Pratyush Kumar and Raj Dabre and Mitesh M. Khapra},\n  year    = {2024},\n  journal = {arXiv preprint arXiv: 2403.06350}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "8b813c3f62d37b2fa174d68c31e8b35ae2fe85e8",
 "stated_evidence": "https://huggingface.co/datasets/ai4bharat/sangraha/blob/8b813c3f62d37b2fa174d68c31e8b35ae2fe85e8/README.md",
 "file_evidence": "https://huggingface.co/datasets/ai4bharat/sangraha/tree/8b813c3f62d37b2fa174d68c31e8b35ae2fe85e8",
 "card_nc": false
}