{"url":"/dataset/wanjuan","name":"WanJuan","full_name":null,"description_markdown":"**WanJuan** is a large-scale training corpus that includes multiple modalities. The dataset incorporates text, image-text, and video modalities, with a total volume exceeding 2TB.","description_withheld":null,"homepage":"https://github.com/opendatalab/WanJuan1.0","introduced_date":"2023-08-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/wanjuan-a-comprehensive-multimodal-dataset","title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models","first_author":"Conghui He","url":null},"license":{"name":"CC BY 4.0 License","url":"https://github.com/opendatalab/WanJuan1.0/blob/main/License"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["WanJuan"],"data_loaders":[],"num_papers_in_archive":19,"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."}