{"url":"/dataset/french-wikipedia","name":"French Wikipedia","full_name":"French Wikipedia","description_markdown":"**French Wikipedia** is a dataset used for pretraining the CamemBERT French language model. It uses the official 2019 French Wikipedia dumps","description_withheld":null,"homepage":"","introduced_date":"2019-11-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","first_author":"Louis Martin","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"French","url":"/datasets/language/french"}],"variants":["French Wikipedia"],"data_loaders":[],"num_papers_in_archive":6,"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."}