{"url":"/dataset/sangraha","name":"Sangraha","full_name":null,"description_markdown":"Sangraha is the largest high-quality, cleaned Indic language pretraining data containing 251B tokens summed up over 22 languages, extracted from curated sources, existing multilingual corpora and large-scale translations.","description_withheld":null,"homepage":"https://huggingface.co/datasets/ai4bharat/sangraha","introduced_date":"2024-03-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/indicllmsuite-a-blueprint-for-creating-pre","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","first_author":"Mohammed Safi Ur Rahman Khan","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[],"tasks":[],"languages":[],"variants":["Sangraha"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}