{"id":27232947,"url":"https://github.com/ZhuoruLin/fast-wordpiece","last_synced_at":"2025-04-10T14:11:12.291Z","repository":{"id":229214025,"uuid":"776059625","full_name":"ZhuoruLin/fast-wordpiece","owner":"ZhuoruLin","description":"Implementation of fast wordpiece tokenization algorithm from https://aclanthology.org/2021.emnlp-main.160.pdf in rust","archived":false,"fork":false,"pushed_at":"2024-03-22T19:03:12.000Z","size":13,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-03-22T20:24:24.359Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Rust","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/ZhuoruLin.png","metadata":{"files":{"readme":null,"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}},"created_at":"2024-03-22T15:45:02.000Z","updated_at":"2024-03-22T20:24:29.370Z","dependencies_parsed_at":"2024-03-22T20:24:27.805Z","dependency_job_id":"7634f721-861c-41f2-913e-051363229b61","html_url":"https://github.com/ZhuoruLin/fast-wordpiece","commit_stats":null,"previous_names":["zhuorulin/fast-wordpiece"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhuoruLin%2Ffast-wordpiece","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhuoruLin%2Ffast-wordpiece/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhuoruLin%2Ffast-wordpiece/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhuoruLin%2Ffast-wordpiece/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZhuoruLin","download_url":"https://codeload.github.com/ZhuoruLin/fast-wordpiece/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248232418,"owners_count":21069487,"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":"2025-04-10T14:11:10.290Z","updated_at":"2025-04-10T14:11:12.270Z","avatar_url":"https://github.com/ZhuoruLin.png","language":"Rust","funding_links":[],"categories":["🔹 **WordPiece Tokenizer Implementations**"],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZhuoruLin%2Ffast-wordpiece","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FZhuoruLin%2Ffast-wordpiece","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZhuoruLin%2Ffast-wordpiece/lists"}