{"id":24641457,"url":"https://github.com/jiauzhang/textok","last_synced_at":"2026-02-10T17:33:05.782Z","repository":{"id":271933249,"uuid":"915029034","full_name":"JiauZhang/textok","owner":"JiauZhang","description":"Text Tokenizer in C++","archived":false,"fork":false,"pushed_at":"2025-01-10T20:49:47.000Z","size":15,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-26T09:17:41.626Z","etag":null,"topics":["byte-pair-encoding","language-model","llm","nlp","tokenizer"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JiauZhang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"custom":["https://jiauzhang.github.io"]}},"created_at":"2025-01-10T20:12:10.000Z","updated_at":"2025-01-11T14:26:57.000Z","dependencies_parsed_at":"2025-01-10T21:09:24.082Z","dependency_job_id":"740af223-0918-4034-9cc6-76f8a81860fd","html_url":"https://github.com/JiauZhang/textok","commit_stats":null,"previous_names":["jiauzhang/textok"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JiauZhang%2Ftextok","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JiauZhang%2Ftextok/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JiauZhang%2Ftextok/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JiauZhang%2Ftextok/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JiauZhang","download_url":"https://codeload.github.com/JiauZhang/textok/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244609446,"owners_count":20480781,"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":["byte-pair-encoding","language-model","llm","nlp","tokenizer"],"created_at":"2025-01-25T12:13:32.946Z","updated_at":"2026-02-10T17:33:00.761Z","avatar_url":"https://github.com/JiauZhang.png","language":"Python","funding_links":["https://jiauzhang.github.io"],"categories":[],"sub_categories":[],"readme":"### Install\n```shell\npip install textok\n```\n\n### Sponsor\n\u003ctable align=\"center\"\u003e\n    \u003cthead\u003e\n        \u003ctr\u003e\n            \u003cth colspan=\"2\"\u003e公众号\u003c/th\u003e\n        \u003c/tr\u003e\n    \u003c/thead\u003e\n    \u003ctbody align=\"center\" valign=\"center\"\u003e\n        \u003ctr\u003e\n            \u003ctd colspan=\"2\"\u003e\u003cimg src=\"https://jiauzhang.github.io/ghstatic/images/ofa_m.png\" style=\"height: 196px\" alt=\"AliPay.png\"\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n    \u003cthead\u003e\n        \u003ctr\u003e\n            \u003cth\u003eAliPay\u003c/th\u003e\n            \u003cth\u003eWeChatPay\u003c/th\u003e\n        \u003c/tr\u003e\n    \u003c/thead\u003e\n    \u003ctbody align=\"center\" valign=\"center\"\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003cimg src=\"https://jiauzhang.github.io/AliPay.png\" style=\"width: 196px; height: 196px\" alt=\"AliPay.png\"\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003cimg src=\"https://jiauzhang.github.io/WeChatPay.png\" style=\"width: 196px; height: 196px\" alt=\"WeChatPay.png\"\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiauzhang%2Ftextok","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjiauzhang%2Ftextok","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiauzhang%2Ftextok/lists"}