{"id":16323,"name":"language-pretraining","description":"Pre-training Language Models for Japanese","url":"https://github.com/retarfi/language-pretraining","last_synced_at":"2025-09-04T23:08:57.721Z","repository":{"id":37822013,"uuid":"383658621","full_name":"retarfi/language-pretraining","owner":"retarfi","description":"Pre-training Language Models for Japanese","archived":false,"fork":false,"pushed_at":"2023-07-02T07:30:42.000Z","size":208,"stargazers_count":49,"open_issues_count":1,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-13T11:49:15.755Z","etag":null,"topics":["bert","electra","implementation","japanese","language-model","language-models","natural-language-processing","nlp","pytorch","transformer","transformers"],"latest_commit_sha":null,"homepage":"","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/retarfi.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.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-07-07T03:07:22.000Z","updated_at":"2024-11-26T01:05:44.000Z","dependencies_parsed_at":"2024-11-15T14:43:44.007Z","dependency_job_id":null,"html_url":"https://github.com/retarfi/language-pretraining","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/retarfi/language-pretraining","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/retarfi","download_url":"https://codeload.github.com/retarfi/language-pretraining/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273685604,"owners_count":25149722,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":"retarfi","name":"Masahiro Suzuki","uuid":"32985371","kind":"user","description":"Ph. D. student in the University of Tokyo / NLP Engineer in Finance","email":"","website":"https://msuzuki.me/","location":"Tokyo","twitter":"retarfi_","company":"Nikko Asset Management Co., Ltd.","icon_url":"https://avatars.githubusercontent.com/u/32985371?u=6389c49f8a5bc341c1ec18251978c9a6829d33c0\u0026v=4","repositories_count":4,"last_synced_at":"2023-03-05T21:48:57.450Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/retarfi","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-15T23:27:45.371Z","updated_at":"2023-03-05T21:48:57.473Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/retarfi","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/retarfi/repositories"},"packages":[],"commits":{"id":5846673,"full_name":"retarfi/language-pretraining","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2024-11-15T14:33:20.555Z","updated_at":"2024-11-15T14:33:20.555Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.936Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"retarfi/language-pretraining","html_url":"https://github.com/retarfi/language-pretraining","last_synced_at":"2025-04-13T11:43:03.673Z","status":null,"issues_count":6,"pull_requests_count":12,"avg_time_to_close_issue":2835008.8,"avg_time_to_close_pull_request":2836.0,"issues_closed_count":5,"pull_requests_closed_count":12,"pull_request_authors_count":2,"issue_authors_count":3,"avg_comments_per_issue":3.1666666666666665,"avg_comments_per_pull_request":0.08333333333333333,"merged_pull_requests_count":12,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-11-15T14:33:20.984Z","updated_at":"2025-04-13T11:43:03.674Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/retarfi%2Flanguage-pretraining/issues","issue_labels_count":{"bug":1,"enhancement":1},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":4},"pull_request_author_associations_count":{"OWNER":9,"CONTRIBUTOR":1},"issue_authors":{"kajyuuen":2,"KoichiYasuoka":1,"ghost":1},"pull_request_authors":{"retarfi":9,"upura":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10081047,"issues_count":31277651,"pull_requests_count":96104459,"authors_count":10693669,"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":[{"login":"retarfi","count":9,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/retarfi"}],"active_maintainers":[]},"events":{"total":{"WatchEvent":1,"ForkEvent":1},"last_year":{"WatchEvent":1,"ForkEvent":1}},"keywords":["bert","electra","implementation","japanese","language-model","language-models","natural-language-processing","nlp","pytorch","transformer","transformers"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T22:01:32.029Z","updated_at":"2022-08-08T22:01:32.029Z","repository_link":"https://github.com/retarfi/language-pretraining/blob/main/requirements.txt","dependencies":[{"id":697270731,"package_name":"datasets","ecosystem":"pypi","requirements":"\u003e=1.10.0","direct":true,"kind":"runtime","optional":false},{"id":697270732,"package_name":"fugashi","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":697270733,"package_name":"tensorflow","ecosystem":"pypi","requirements":"\u003e=2.5.0","direct":true,"kind":"runtime","optional":false},{"id":697270734,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":697270735,"package_name":"transformers","ecosystem":"pypi","requirements":"\u003e=4.7.0","direct":true,"kind":"runtime","optional":false},{"id":697270736,"package_name":"tokenizers","ecosystem":"pypi","requirements":"\u003e=0.10.0","direct":true,"kind":"runtime","optional":false},{"id":697270737,"package_name":"torch","ecosystem":"pypi","requirements":"\u003e=1.8.0","direct":true,"kind":"runtime","optional":false},{"id":697270738,"package_name":"ipadic","ecosystem":"pypi","requirements":"==1.0.0","direct":true,"kind":"runtime","optional":false},{"id":697270739,"package_name":"unidic","ecosystem":"pypi","requirements":"==1.0.3","direct":true,"kind":"runtime","optional":false},{"id":697270740,"package_name":"unidic-lite","ecosystem":"pypi","requirements":"==1.0.8","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2024-11-15T14:43:43.158Z","updated_at":"2024-11-15T14:43:43.158Z","repository_link":"https://github.com/retarfi/language-pretraining/blob/main/pyproject.toml","dependencies":[{"id":20745064413,"package_name":"python","ecosystem":"pypi","requirements":"^3.8","direct":true,"kind":"runtime","optional":false},{"id":20745064414,"package_name":"datasets","ecosystem":"pypi","requirements":"^1.10.0","direct":true,"kind":"runtime","optional":false},{"id":20745064415,"package_name":"fugashi","ecosystem":"pypi","requirements":"^1.1.0","direct":true,"kind":"runtime","optional":false},{"id":20745064535,"package_name":"tensorflow","ecosystem":"pypi","requirements":"^2.5.0","direct":true,"kind":"runtime","optional":false},{"id":20745064536,"package_name":"tqdm","ecosystem":"pypi","requirements":"^4.63.0","direct":true,"kind":"runtime","optional":false},{"id":20745064537,"package_name":"transformers","ecosystem":"pypi","requirements":"4.20.1","direct":true,"kind":"runtime","optional":false},{"id":20745064538,"package_name":"tokenizers","ecosystem":"pypi","requirements":"^0.11","direct":true,"kind":"runtime","optional":false},{"id":20745064539,"package_name":"torch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":20745064540,"package_name":"jptranstokenizer","ecosystem":"pypi","requirements":"^0.3.1","direct":true,"kind":"runtime","optional":false},{"id":20745064541,"package_name":"sentencepiece","ecosystem":"pypi","requirements":"^0.1.98","direct":true,"kind":"runtime","optional":false},{"id":20745064542,"package_name":"psutil","ecosystem":"pypi","requirements":"^5.9.3","direct":true,"kind":"runtime","optional":false},{"id":20745064543,"package_name":"black","ecosystem":"pypi","requirements":"^22.6.0","direct":true,"kind":"develop","optional":false},{"id":20745064544,"package_name":"isort","ecosystem":"pypi","requirements":"^5.10.1","direct":true,"kind":"develop","optional":false},{"id":20745064545,"package_name":"mypy","ecosystem":"pypi","requirements":"^0.971","direct":true,"kind":"develop","optional":false},{"id":20745064546,"package_name":"pytest","ecosystem":"pypi","requirements":"^7.1.2","direct":true,"kind":"develop","optional":false},{"id":20745064547,"package_name":"spacy","ecosystem":"pypi","requirements":"^3.2.0","direct":true,"kind":"develop","optional":false},{"id":20745064548,"package_name":"unidic","ecosystem":"pypi","requirements":"^1.1.0","direct":true,"kind":"develop","optional":false},{"id":20745064551,"package_name":"ipadic","ecosystem":"pypi","requirements":"^1.0.0","direct":true,"kind":"develop","optional":false},{"id":20745064556,"package_name":"unidic-lite","ecosystem":"pypi","requirements":"1.0.8","direct":true,"kind":"develop","optional":false},{"id":20745064557,"package_name":"ja-gsdluw","ecosystem":"pypi","requirements":"*","direct":true,"kind":"develop","optional":false},{"id":20745064559,"package_name":"SudachiTra","ecosystem":"pypi","requirements":"^0.1.7","direct":true,"kind":"develop","optional":false},{"id":20745064560,"package_name":"deepspeed","ecosystem":"pypi","requirements":"^0.8.1","direct":true,"kind":"develop","optional":false},{"id":20745064561,"package_name":"mpi4py","ecosystem":"pypi","requirements":"^3.1.3","direct":true,"kind":"develop","optional":false},{"id":20745064599,"package_name":"pre-commit","ecosystem":"pypi","requirements":"^2.21.0","direct":true,"kind":"develop","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:47.327Z","updated_at":"2025-10-07T08:08:42.190Z","avatar_url":"https://github.com/retarfi.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/16323","html_url":"https://science.ecosyste.ms/projects/16323","bibtex_url":"https://science.ecosyste.ms/projects/16323/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/16323/export.apalike"}