{"id":73124,"name":"tok","description":"Tokenizers from HuggingFace","url":"https://github.com/mlverse/tok","last_synced_at":"2025-09-08T15:58:31.747Z","repository":{"id":154218307,"uuid":"630640283","full_name":"mlverse/tok","owner":"mlverse","description":"Tokenizers from HuggingFace","archived":false,"fork":false,"pushed_at":"2025-08-27T11:14:15.000Z","size":194784,"stargazers_count":43,"open_issues_count":1,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-01T12:27:26.757Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlverse.png","metadata":{"files":{"readme":"README.Rmd","changelog":"NEWS.md","contributing":null,"funding":null,"license":"LICENSE","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":"2023-04-20T20:25:27.000Z","updated_at":"2025-08-27T11:14:18.000Z","dependencies_parsed_at":"2024-06-25T13:34:23.517Z","dependency_job_id":"ba777df9-ea07-4329-88a4-eedadaa420ff","html_url":"https://github.com/mlverse/tok","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":"extendr/helloextendr","purl":"pkg:github/mlverse/tok","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse","download_url":"https://codeload.github.com/mlverse/tok/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274210203,"owners_count":25241789,"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":"2025-09-08T02:00:09.813Z","response_time":121,"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":"mlverse","name":"mlverse","uuid":"55406849","kind":"organization","description":"Open source libraries to scale Data Science","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/55406849?v=4","repositories_count":27,"last_synced_at":"2023-03-04T01:34:03.799Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/mlverse","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-14T07:43:12.619Z","updated_at":"2023-03-04T01:34:03.868Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse/repositories"},"packages":[{"id":7898389,"name":"tok","ecosystem":"cran","description":"Fast Text Tokenization","homepage":"https://github.com/mlverse/tok","licenses":"MIT + file LICENSE","normalized_licenses":["MIT"],"repository_url":"https://github.com/mlverse/tok","keywords_array":[],"namespace":null,"versions_count":6,"first_release_published_at":"2023-07-06T00:00:00.000Z","latest_release_published_at":"2025-08-27T00:00:00.000Z","latest_release_number":"0.2.0","last_synced_at":"2025-09-01T12:50:46.348Z","created_at":"2023-07-06T13:15:01.173Z","updated_at":"2025-09-01T12:50:46.348Z","registry_url":"https://cran.r-project.org/package=tok","install_command":null,"documentation_url":"http://cran.r-project.org/web/packages/tok/tok.pdf","metadata":{},"repo_metadata":{"uuid":"630640283","full_name":"mlverse/tok","owner":"mlverse","description":"Tokenizers from HuggingFace","archived":false,"fork":false,"pushed_at":"2023-09-01T19:05:51.000Z","size":10333,"stargazers_count":22,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2023-10-20T15:26:16.332Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlverse.png","metadata":{},"created_at":"2023-04-20T20:25:27.000Z","updated_at":"2023-10-19T21:22:04.000Z","dependencies_parsed_at":"2023-06-09T02:45:15.296Z","dependency_job_id":null,"html_url":"https://github.com/mlverse/tok","commit_stats":null,"previous_names":[],"tags_count":2,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse","download_url":"https://codeload.github.com/mlverse/tok/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":172206176,"owners_count":9795752,"icon_url":"https://github.com/github.png","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_record":{"login":"mlverse","name":"mlverse","uuid":"55406849","kind":"organization","description":"Open source libraries to scale Data Science","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/55406849?v=4","repositories_count":27,"last_synced_at":"2023-03-04T01:34:03.799Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/mlverse","created_at":"2022-11-14T07:43:12.619Z","updated_at":"2023-03-04T01:34:03.868Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlverse/repositories"},"tags":[{"name":"v0.1.1","sha":"7eeef0c6122c4c54610afddd44f20b17eb0ceaa2","kind":"commit","published_at":"2023-08-16T16:36:06.000Z","download_url":"https://codeload.github.com/mlverse/tok/tar.gz/v0.1.1","html_url":"https://github.com/mlverse/tok/releases/tag/v0.1.1","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags/v0.1.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags/v0.1.1/manifests"},{"name":"v0.1.0","sha":"ff3d530393f0fa92ea8f73abe9f4f0b1d135b032","kind":"commit","published_at":"2023-07-03T08:56:14.000Z","download_url":"https://codeload.github.com/mlverse/tok/tar.gz/v0.1.0","html_url":"https://github.com/mlverse/tok/releases/tag/v0.1.0","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags/v0.1.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/tags/v0.1.0/manifests"}]},"repo_metadata_updated_at":"2023-11-20T12:13:02.757Z","dependent_packages_count":0,"downloads":1312,"downloads_period":"last-month","dependent_repos_count":1,"rankings":{"downloads":81.61620658949244,"dependent_repos_count":23.9812959251837,"dependent_packages_count":28.750835003340015,"stargazers_count":11.179875333926981,"forks_count":17.056334892006234,"docker_downloads_count":null,"average":32.516909548789876},"purl":"pkg:cran/tok","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/cran/tok","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/cran/tok","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/cran/tok/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":null,"versions_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tok/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tok/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tok/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tok/related_packages","maintainers":[{"uuid":"daniel@posit.co","login":null,"name":"Daniel Falbel","email":"daniel@posit.co","url":null,"packages_count":5,"html_url":null,"role":null,"created_at":"2023-07-06T13:15:02.129Z","updated_at":"2023-07-06T13:15:02.129Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/maintainers/daniel@posit.co/packages"}],"registry":{"name":"cran.r-project.org","url":"https://cran.r-project.org","ecosystem":"cran","default":true,"packages_count":26181,"maintainers_count":14299,"namespaces_count":0,"keywords_count":8326,"github":"r-project-org","metadata":{"funded_packages_count":539},"icon_url":"https://github.com/r-project-org.png","created_at":"2022-04-06T16:32:25.637Z","updated_at":"2025-09-08T06:54:01.855Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/namespaces"}}],"commits":{"id":6643461,"full_name":"mlverse/tok","default_branch":"main","committers":[{"name":"Daniel Falbel","email":"dfalbel@gmail.com","login":"dfalbel","count":83},{"name":"cregouby","email":"cregouby","login":"cregouby","count":1}],"total_commits":84,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":42.0,"dds":0.011904761904761862,"past_year_committers":[{"name":"Daniel Falbel","email":"dfalbel@gmail.com","login":"dfalbel","count":21},{"name":"cregouby","email":"cregouby","login":"cregouby","count":1}],"past_year_total_commits":22,"past_year_total_committers":2,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":11.0,"past_year_dds":0.045454545454545414,"last_synced_at":"2025-05-26T13:50:59.421Z","last_synced_commit":"ff883e2dbac9175c8bb908424f8d0544b94388e0","created_at":"2024-11-22T22:12:30.557Z","updated_at":"2025-05-26T13:50:59.421Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","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":"mlverse/tok","html_url":"https://github.com/mlverse/tok","last_synced_at":"2025-05-20T09:04:48.035Z","status":null,"issues_count":12,"pull_requests_count":24,"avg_time_to_close_issue":735758.7,"avg_time_to_close_pull_request":184643.86363636365,"issues_closed_count":10,"pull_requests_closed_count":22,"pull_request_authors_count":2,"issue_authors_count":2,"avg_comments_per_issue":0.25,"avg_comments_per_pull_request":0.08333333333333333,"merged_pull_requests_count":20,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":8,"past_year_pull_requests_count":16,"past_year_avg_time_to_close_issue":468258.0,"past_year_avg_time_to_close_pull_request":233244.42857142858,"past_year_issues_closed_count":6,"past_year_pull_requests_closed_count":14,"past_year_pull_request_authors_count":2,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":0.125,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":12,"created_at":"2024-11-22T22:12:31.652Z","updated_at":"2025-09-02T10:05:41.738Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlverse%2Ftok/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"MEMBER":7,"NONE":2},"pull_request_author_associations_count":{"MEMBER":19,"NONE":1},"issue_authors":{"dfalbel":7,"eitsupi":1,"cregouby":1},"pull_request_authors":{"dfalbel":19,"cregouby":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-08T00:00:17.013Z","repositories_count":10168397,"issues_count":32020286,"pull_requests_count":100254366,"authors_count":10730288,"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":{"MEMBER":2,"NONE":1},"past_year_pull_request_author_associations_count":{"MEMBER":4},"past_year_issue_authors":{"dfalbel":2,"cregouby":1},"past_year_pull_request_authors":{"dfalbel":4},"maintainers":[{"login":"dfalbel","count":26,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/dfalbel"}],"active_maintainers":[{"login":"dfalbel","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/dfalbel"}]},"events":{"total":{"IssuesEvent":3,"WatchEvent":3,"PushEvent":10,"PullRequestEvent":2,"CreateEvent":2},"last_year":{"IssuesEvent":3,"WatchEvent":3,"PushEvent":10,"PullRequestEvent":2,"CreateEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/R-CMD-check.yaml","sha":null,"kind":"manifest","created_at":"2023-06-09T02:45:14.990Z","updated_at":"2023-06-09T02:45:14.990Z","repository_link":"https://github.com/mlverse/tok/blob/main/.github/workflows/R-CMD-check.yaml","dependencies":[{"id":10514474573,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":10514474574,"package_name":"actions-rs/toolchain","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":10514474575,"package_name":"r-lib/actions/setup-pandoc","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":10514474580,"package_name":"r-lib/actions/setup-r","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":10514474597,"package_name":"r-lib/actions/setup-r-dependencies","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":10514474607,"package_name":"r-lib/actions/check-r-package","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"cargo","filepath":"src/rust/Cargo.lock","sha":null,"kind":"lockfile","created_at":"2023-06-09T02:45:15.110Z","updated_at":"2023-06-09T02:45:15.110Z","repository_link":"https://github.com/mlverse/tok/blob/main/src/rust/Cargo.lock","dependencies":[{"id":10514474640,"package_name":"extendr-api","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":10514474641,"package_name":"extendr-engine","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":10514474642,"package_name":"extendr-macros","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":10514474643,"package_name":"lazy_static","ecosystem":"cargo","requirements":"1.4.0","direct":false,"kind":"runtime","optional":false},{"id":10514474644,"package_name":"libR-sys","ecosystem":"cargo","requirements":"0.3.0","direct":false,"kind":"runtime","optional":false},{"id":10514474645,"package_name":"paste","ecosystem":"cargo","requirements":"1.0.11","direct":false,"kind":"runtime","optional":false},{"id":10514474646,"package_name":"proc-macro2","ecosystem":"cargo","requirements":"1.0.49","direct":false,"kind":"runtime","optional":false},{"id":10514474647,"package_name":"quote","ecosystem":"cargo","requirements":"1.0.23","direct":false,"kind":"runtime","optional":false},{"id":10514474648,"package_name":"syn","ecosystem":"cargo","requirements":"1.0.107","direct":false,"kind":"runtime","optional":false},{"id":10514474649,"package_name":"unicode-ident","ecosystem":"cargo","requirements":"1.0.6","direct":false,"kind":"runtime","optional":false},{"id":10514474650,"package_name":"winapi","ecosystem":"cargo","requirements":"0.3.9","direct":false,"kind":"runtime","optional":false},{"id":10514474651,"package_name":"winapi-i686-pc-windows-gnu","ecosystem":"cargo","requirements":"0.4.0","direct":false,"kind":"runtime","optional":false},{"id":10514474652,"package_name":"winapi-x86_64-pc-windows-gnu","ecosystem":"cargo","requirements":"0.4.0","direct":false,"kind":"runtime","optional":false}]},{"ecosystem":"cran","filepath":"DESCRIPTION","sha":null,"kind":"manifest","created_at":"2023-06-09T02:45:15.234Z","updated_at":"2023-06-09T02:45:15.234Z","repository_link":"https://github.com/mlverse/tok/blob/main/DESCRIPTION","dependencies":[{"id":10514476544,"package_name":"R","ecosystem":"cran","requirements":"\u003e= 4.2.0","direct":true,"kind":"depends","optional":false},{"id":10514476545,"package_name":"R6","ecosystem":"cran","requirements":"*","direct":true,"kind":"imports","optional":false},{"id":10514476546,"package_name":"cli","ecosystem":"cran","requirements":"*","direct":true,"kind":"imports","optional":false},{"id":10514476547,"package_name":"rmarkdown","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false},{"id":10514476548,"package_name":"testthat","ecosystem":"cran","requirements":"\u003e= 3.0.0","direct":true,"kind":"suggests","optional":false},{"id":10514476549,"package_name":"hfhub","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false}]},{"ecosystem":"cargo","filepath":"src/rust/Cargo.toml","sha":null,"kind":"manifest","created_at":"2024-06-25T13:34:23.285Z","updated_at":"2024-06-25T13:34:23.285Z","repository_link":"https://github.com/mlverse/tok/blob/main/src/rust/Cargo.toml","dependencies":[]}],"score":11.658168013522761,"created_at":"2025-09-08T11:24:52.418Z","updated_at":"2025-10-07T08:26:35.143Z","avatar_url":"https://github.com/mlverse.png","language":"R","category":null,"sub_category":null,"monthly_downloads":1312,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/73124","html_url":"https://science.ecosyste.ms/projects/73124"}