{"id":26897504,"url":"https://github.com/wassemgtk/supertokenizer","last_synced_at":"2025-04-01T04:42:41.039Z","repository":{"id":284407181,"uuid":"954846225","full_name":"wassemgtk/SuperTokenizer","owner":"wassemgtk","description":"A high-performance tokenizer built to rival GPT-4, trained on the C4 dataset.","archived":false,"fork":false,"pushed_at":"2025-03-25T18:15:49.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T18:42:12.861Z","etag":null,"topics":["tokenizer","tokenizer-framework","tokenizers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/wassemgtk.png","metadata":{},"created_at":"2025-03-25T17:51:10.000Z","updated_at":"2025-03-25T18:15:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"86838b55-bb23-45cd-b719-38ef3b2acc61","html_url":"https://github.com/wassemgtk/SuperTokenizer","commit_stats":null,"previous_names":["wassemgtk/tokenizer-demo"],"tags_count":null,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wassemgtk%2FSuperTokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wassemgtk%2FSuperTokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wassemgtk%2FSuperTokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wassemgtk%2FSuperTokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wassemgtk","download_url":"https://codeload.github.com/wassemgtk/SuperTokenizer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246586064,"owners_count":20801026,"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":["tokenizer","tokenizer-framework","tokenizers"],"created_at":"2025-04-01T04:42:40.450Z","updated_at":"2025-04-01T04:42:41.031Z","avatar_url":"https://github.com/wassemgtk.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwassemgtk%2Fsupertokenizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwassemgtk%2Fsupertokenizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwassemgtk%2Fsupertokenizer/lists"}