{"id":19428944,"url":"https://github.com/eleutherai/pile-explorer","last_synced_at":"2025-07-10T19:03:21.599Z","repository":{"id":54894373,"uuid":"308082468","full_name":"EleutherAI/pile-explorer","owner":"EleutherAI","description":"For exploring the data and documenting its limitations","archived":false,"fork":false,"pushed_at":"2021-01-21T16:43:55.000Z","size":40,"stargazers_count":5,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-24T18:48:22.381Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EleutherAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":null,"support":null}},"created_at":"2020-10-28T16:49:33.000Z","updated_at":"2024-07-17T12:31:31.000Z","dependencies_parsed_at":"2022-08-14T06:00:43.254Z","dependency_job_id":null,"html_url":"https://github.com/EleutherAI/pile-explorer","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EleutherAI/pile-explorer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fpile-explorer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fpile-explorer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fpile-explorer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fpile-explorer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EleutherAI","download_url":"https://codeload.github.com/EleutherAI/pile-explorer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fpile-explorer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264638018,"owners_count":23642095,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-10T14:17:17.944Z","updated_at":"2025-07-10T19:03:21.572Z","avatar_url":"https://github.com/EleutherAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Exploring the Pile\nThis repository contains code for exploring the Pile and documenting its limitations\n\n## Language Modeling Data Format\n\nThe data in the Pile is stored in the [lm_dataformat](https://github.com/leogao2/lm_dataformat). This repository is designed to be used on data stored in that format. For documentation, see the linked repository.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Fpile-explorer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feleutherai%2Fpile-explorer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Fpile-explorer/lists"}