{"id":59949,"name":"minicorpus","description":"Investigating, reproducing, and improving MiniPile with PyTorch and HuggingFace","url":"https://github.com/mk2112/minicorpus","last_synced_at":"2025-09-05T15:43:07.051Z","repository":{"id":274154610,"uuid":"862971060","full_name":"MK2112/minicorpus","owner":"MK2112","description":"Investigating, reproducing, and improving MiniPile with PyTorch and HuggingFace","archived":false,"fork":false,"pushed_at":"2025-02-20T19:22:54.000Z","size":26294,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-20T20:26:37.439Z","etag":null,"topics":["huggingface","pytorch","subset-selection"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MK2112.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.md","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-25T13:52:49.000Z","updated_at":"2025-02-20T19:22:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"98487467-a125-4e63-bf8a-ce17d9b8fd8c","html_url":"https://github.com/MK2112/minicorpus","commit_stats":null,"previous_names":["mk2112/minicorpus"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MK2112/minicorpus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MK2112%2Fminicorpus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MK2112%2Fminicorpus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MK2112%2Fminicorpus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MK2112%2Fminicorpus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MK2112","download_url":"https://codeload.github.com/MK2112/minicorpus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MK2112%2Fminicorpus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273780263,"owners_count":25166978,"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","status":"online","status_checked_at":"2025-09-05T02:00:09.113Z","response_time":402,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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"}},"owner":{"login":"MK2112","name":"Marcus","uuid":"29037335","kind":"user","description":"","email":"","website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/29037335?u=1b15a01c43ee9e63f78e2ad0633dd3fc6e32c460\u0026v=4","repositories_count":2,"last_synced_at":"2023-06-02T18:24:39.010Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/MK2112","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-06-02T18:24:39.025Z","updated_at":"2023-06-02T18:24:39.025Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MK2112","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MK2112/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"mk2112/minicorpus","html_url":"https://github.com/mk2112/minicorpus","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-05T15:42:28.628Z","updated_at":"2025-09-05T15:42:28.628Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mk2112%2Fminicorpus","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mk2112%2Fminicorpus/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.444Z","repositories_count":10103789,"issues_count":31523126,"pull_requests_count":97734489,"authors_count":10703676,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"WatchEvent":2,"PushEvent":28,"PublicEvent":1},"last_year":{"WatchEvent":2,"PushEvent":28,"PublicEvent":1}},"keywords":["huggingface","pytorch","subset-selection"],"dependencies":[],"score":null,"created_at":"2025-09-04T15:51:36.667Z","updated_at":"2025-10-07T08:23:33.371Z","avatar_url":"https://github.com/MK2112.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/59949","html_url":"https://science.ecosyste.ms/projects/59949","bibtex_url":"https://science.ecosyste.ms/projects/59949/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/59949/export.apalike"}