{"url":"/dataset/pg-19","name":"PG-19","full_name":null,"description_markdown":"A new open-vocabulary language modelling benchmark derived from books.\r\n\r\nSource: [Compressive Transformers for Long-Range Sequence Modelling](/paper/compressive-transformers-for-long-range-1)","description_withheld":null,"homepage":"https://github.com/deepmind/pg19","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/compressive-transformers-for-long-range-1","title":"Compressive Transformers for Long-Range Sequence Modelling","first_author":"Jack W. Rae","url":null},"license":null,"modalities":[],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"}],"languages":[],"variants":["PG-19"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/deepmind/pg19","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fzkuji/pg19","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pg19","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/pg19","frameworks":["tf","jax"]},{"repo":"https://github.com/deepmind/pg19","url":"https://github.com/deepmind/pg19","frameworks":[]}],"num_papers_in_archive":147,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dialogue-generation-on-pg-19","task":"Dialogue Generation","dataset_variant":"PG-19","rows":1,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"∞-former (Sticky memories + initialized GPT-2 Small)","paper":"/paper/infty-former-infinite-memory-transformer","metrics":{"Perplexity":"32.48"},"code_links":[{"title":"deep-spin/infinite-former","url":"https://github.com/deep-spin/infinite-former"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/infty-former-infinite-memory-transformer","title":"$\\infty$-former: Infinite Memory Transformer","date":"2021-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}