{"url":"/dataset/tinystories","name":"TinyStories","full_name":null,"description_markdown":"Dataset containing synthetically generated (by GPT-3.5 and GPT-4) short stories that only use a small vocabulary.","description_withheld":null,"homepage":"https://huggingface.co/datasets/roneneldan/TinyStories","introduced_date":"2023-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","first_author":"Ronen Eldan","url":null},"license":{"name":"CDLA-Sharing-1.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TinyStories"],"data_loaders":[],"num_papers_in_archive":62,"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."}