{"url":"/dataset/hplt-v2","name":"HPLT v2","full_name":null,"description_markdown":"Multilingual text collection extracted from the Internet Archive and Common Crawl archives.\r\nIntended to train large language models.","description_withheld":null,"homepage":"https://hplt-project.org/datasets/v2.0","introduced_date":"2025-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/an-expanded-massive-multilingual-dataset-for","title":"An Expanded Massive Multilingual Dataset for High-Performance Language Technologies","first_author":"Laurie Burchell","url":null},"license":{"name":"Creative Commons CC0 license (\"no rights reserved\")","url":"https://creativecommons.org/share-your-work/public-domain/cc0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["HPLT v2"],"data_loaders":[],"num_papers_in_archive":3,"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."}