{"url":"/dataset/mc4","name":"mC4","full_name":null,"description_markdown":"**mC4** is a multilingual variant of the [C4](https://paperswithcode.com/dataset/c4) dataset called mC4. mC4 comprises natural text in 101 languages drawn from the public Common Crawl web scrape. \r\n\r\nSource: [mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer](https://arxiv.org/pdf/2010.11934v3.pdf)","description_withheld":null,"homepage":"https://github.com/google-research/multilingual-t5","introduced_date":"2020-10-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","first_author":"Linting Xue","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["mC4"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clemsadand/small_mc4","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bertin-project/mc4-sampling","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mc4","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/gsarti/clean-mc4-it","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/gsarti/clean_mc4_it","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/saied/persian_news_dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/munggok/mc4-id","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/indonesian-nlp/mc4-id","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/its5Q/mc4","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hiroshi-matsuda-rit/filtered_mc4","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/legacy-datasets/mc4","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research/multilingual-t5","url":"https://github.com/google-research/multilingual-t5","frameworks":["tf"]}],"num_papers_in_archive":142,"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."}