{"url":"/dataset/the-pile","name":"The Pile","full_name":"The Pile","description_markdown":"The Pile is a 825 GiB diverse, open source language modelling data set that consists of 22 smaller, high-quality datasets combined together.\r\n\r\nDatasheet: [Datasheet for the Pile](https://paperswithcode.com/paper/datasheet-for-the-pile)","description_withheld":null,"homepage":"https://pile.eleuther.ai/","introduced_date":"2020-12-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","first_author":"Leo Gao","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["The Pile"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/the_pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jonatli/the_pile_mystic","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/the_pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-spanish","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-pt_br","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":467,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-the-pile","task":"Language Modelling","dataset_variant":"The Pile","rows":39,"metrics":["Bits per byte","Test perplexity"],"first_row_in_archive_order":{"model":"Test-Time Fine-Tuning with SIFT + Llama-3.2 (3B)","paper":"/paper/efficiently-learning-at-test-time-active-fine","metrics":{"Bits per byte":"0.557"},"code_links":[{"title":"jonhue/activeft","url":"https://github.com/jonhue/activeft"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficiently-learning-at-test-time-active-fine","title":"Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs","date":"2024-10-10","rows_on_this_dataset":15,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/specialized-language-models-with-cheap","title":"Need a Small Specialized Language Model? Plan Early!","date":"2024-02-02","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":7,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":5,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/knowledge-unlearning-for-mitigating-privacy","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","date":"2022-10-04","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","rows_on_this_dataset":8,"code_links":22,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":44,"samples_ran":15,"samples_unverified":29,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}