{"id":22354684,"url":"https://github.com/pprp/cleanstream","last_synced_at":"2025-03-26T12:41:47.940Z","repository":{"id":254651487,"uuid":"846464487","full_name":"pprp/CleanStream","owner":"pprp","description":"Local version of dclm","archived":false,"fork":false,"pushed_at":"2024-08-25T02:17:42.000Z","size":43,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-31T13:43:53.823Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pprp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-23T09:10:02.000Z","updated_at":"2024-08-31T11:55:32.000Z","dependencies_parsed_at":"2024-08-25T04:27:13.718Z","dependency_job_id":"2fa3feb9-f93f-4ecc-acf7-9735e4ff3243","html_url":"https://github.com/pprp/CleanStream","commit_stats":null,"previous_names":["pprp/cleanstream"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pprp%2FCleanStream","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pprp%2FCleanStream/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pprp%2FCleanStream/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pprp%2FCleanStream/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pprp","download_url":"https://codeload.github.com/pprp/CleanStream/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245658981,"owners_count":20651519,"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":"2024-12-04T13:14:37.081Z","updated_at":"2025-03-26T12:41:47.920Z","avatar_url":"https://github.com/pprp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CleanStream \n\nThis is a repo for data cleaning targeting LLM training for personal use. \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpprp%2Fcleanstream","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpprp%2Fcleanstream","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpprp%2Fcleanstream/lists"}