{"id":142781,"name":null,"description":"Tokenization for Low-Resource Congolese Languages: Efficiency, Coverage, and Downstream Impact","url":"https://github.com/bernard-ng/drc-native-tokenizer","last_synced_at":"2025-09-09T13:51:08.674Z","repository":{"id":310543142,"uuid":"1040209248","full_name":"bernard-ng/drc-native-tokenizer","owner":"bernard-ng","description":"Tokenization for Low-Resource Congolese Languages: Efficiency, Coverage, and Downstream Impact","archived":false,"fork":false,"pushed_at":"2025-08-18T20:15:52.000Z","size":21,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-02T18:52:33.154Z","etag":null,"topics":["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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bernard-ng.png","metadata":{"files":{"readme":"README.md","changelog":null,"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,"zenodo":null}},"created_at":"2025-08-18T16:08:50.000Z","updated_at":"2025-08-20T20:19:05.000Z","dependencies_parsed_at":"2025-08-18T20:18:35.568Z","dependency_job_id":"48e81b0c-019c-4dd8-9d99-56e5a6779fb7","html_url":"https://github.com/bernard-ng/drc-native-tokenizer","commit_stats":null,"previous_names":["bernard-ng/drc-native-tokenizer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bernard-ng/drc-native-tokenizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bernard-ng","download_url":"https://codeload.github.com/bernard-ng/drc-native-tokenizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274307267,"owners_count":25261216,"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":"2025-09-09T02:00:10.223Z","response_time":80,"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":"bernard-ng","name":"Bernard Ngandu","uuid":"31113941","kind":"user","description":"Building a community of skilled developers : @devscast\r\n","email":"","website":"https://devscast.tech","location":"Lubumbashi RDC","twitter":"BernardNgandu","company":"@devscast ","icon_url":"https://avatars.githubusercontent.com/u/31113941?u=bd26b809399539e8135372e9605ea16b2b445a13\u0026v=4","repositories_count":7,"last_synced_at":"2023-05-11T21:26:15.923Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/bernard-ng","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-05-11T21:26:15.937Z","updated_at":"2023-05-11T21:26:15.937Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bernard-ng","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bernard-ng/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"bernard-ng/drc-native-tokenizer","html_url":"https://github.com/bernard-ng/drc-native-tokenizer","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-02T18:52:14.508Z","updated_at":"2025-09-02T18:52:14.508Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bernard-ng%2Fdrc-native-tokenizer/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:00:11.778Z","repositories_count":10182778,"issues_count":32029690,"pull_requests_count":100720980,"authors_count":10737440,"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":[],"active_maintainers":[]},"events":{"total":{"PushEvent":1},"last_year":{"PushEvent":1}},"keywords":["llm","nlp","tokenizer"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.lock.txt","sha":null,"kind":"manifest","created_at":"2025-08-18T20:18:35.380Z","updated_at":"2025-08-18T20:18:35.380Z","repository_link":"https://github.com/bernard-ng/drc-native-tokenizer/blob/main/requirements.lock.txt","dependencies":[{"id":24733369059,"package_name":"altair","ecosystem":"pypi","requirements":"==5.5.0","direct":true,"kind":"runtime","optional":false},{"id":24733369060,"package_name":"attrs","ecosystem":"pypi","requirements":"==25.3.0","direct":true,"kind":"runtime","optional":false},{"id":24733369061,"package_name":"blinker","ecosystem":"pypi","requirements":"==1.9.0","direct":true,"kind":"runtime","optional":false},{"id":24733369062,"package_name":"cachetools","ecosystem":"pypi","requirements":"==6.1.0","direct":true,"kind":"runtime","optional":false},{"id":24733369063,"package_name":"certifi","ecosystem":"pypi","requirements":"==2025.8.3","direct":true,"kind":"runtime","optional":false},{"id":24733369064,"package_name":"charset-normalizer","ecosystem":"pypi","requirements":"==3.4.3","direct":true,"kind":"runtime","optional":false},{"id":24733369065,"package_name":"click","ecosystem":"pypi","requirements":"==8.2.1","direct":true,"kind":"runtime","optional":false},{"id":24733369066,"package_name":"filelock","ecosystem":"pypi","requirements":"==3.19.1","direct":true,"kind":"runtime","optional":false},{"id":24733369067,"package_name":"fsspec","ecosystem":"pypi","requirements":"==2025.7.0","direct":true,"kind":"runtime","optional":false},{"id":24733369068,"package_name":"gitdb","ecosystem":"pypi","requirements":"==4.0.12","direct":true,"kind":"runtime","optional":false},{"id":24733369069,"package_name":"GitPython","ecosystem":"pypi","requirements":"==3.1.45","direct":true,"kind":"runtime","optional":false},{"id":24733369070,"package_name":"hf-xet","ecosystem":"pypi","requirements":"==1.1.7","direct":true,"kind":"runtime","optional":false},{"id":24733369071,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"==0.34.4","direct":true,"kind":"runtime","optional":false},{"id":24733369072,"package_name":"idna","ecosystem":"pypi","requirements":"==3.10","direct":true,"kind":"runtime","optional":false},{"id":24733369073,"package_name":"Jinja2","ecosystem":"pypi","requirements":"==3.1.6","direct":true,"kind":"runtime","optional":false},{"id":24733369074,"package_name":"jsonschema","ecosystem":"pypi","requirements":"==4.25.1","direct":true,"kind":"runtime","optional":false},{"id":24733369075,"package_name":"jsonschema-specifications","ecosystem":"pypi","requirements":"==2025.4.1","direct":true,"kind":"runtime","optional":false},{"id":24733369076,"package_name":"markdown-it-py","ecosystem":"pypi","requirements":"==4.0.0","direct":true,"kind":"runtime","optional":false},{"id":24733369077,"package_name":"MarkupSafe","ecosystem":"pypi","requirements":"==3.0.2","direct":true,"kind":"runtime","optional":false},{"id":24733369078,"package_name":"mdurl","ecosystem":"pypi","requirements":"==0.1.2","direct":true,"kind":"runtime","optional":false},{"id":24733369079,"package_name":"narwhals","ecosystem":"pypi","requirements":"==2.1.2","direct":true,"kind":"runtime","optional":false},{"id":24733369080,"package_name":"numpy","ecosystem":"pypi","requirements":"==2.3.2","direct":true,"kind":"runtime","optional":false},{"id":24733369081,"package_name":"packaging","ecosystem":"pypi","requirements":"==25.0","direct":true,"kind":"runtime","optional":false},{"id":24733369082,"package_name":"pandas","ecosystem":"pypi","requirements":"==2.3.1","direct":true,"kind":"runtime","optional":false},{"id":24733369083,"package_name":"pillow","ecosystem":"pypi","requirements":"==11.3.0","direct":true,"kind":"runtime","optional":false},{"id":24733369084,"package_name":"protobuf","ecosystem":"pypi","requirements":"==6.32.0","direct":true,"kind":"runtime","optional":false},{"id":24733369085,"package_name":"pyarrow","ecosystem":"pypi","requirements":"==21.0.0","direct":true,"kind":"runtime","optional":false},{"id":24733369086,"package_name":"pydeck","ecosystem":"pypi","requirements":"==0.9.1","direct":true,"kind":"runtime","optional":false},{"id":24733369087,"package_name":"Pygments","ecosystem":"pypi","requirements":"==2.19.2","direct":true,"kind":"runtime","optional":false},{"id":24733369088,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"==2.9.0.post0","direct":true,"kind":"runtime","optional":false},{"id":24733369089,"package_name":"pytz","ecosystem":"pypi","requirements":"==2025.2","direct":true,"kind":"runtime","optional":false},{"id":24733369090,"package_name":"PyYAML","ecosystem":"pypi","requirements":"==6.0.2","direct":true,"kind":"runtime","optional":false},{"id":24733369091,"package_name":"referencing","ecosystem":"pypi","requirements":"==0.36.2","direct":true,"kind":"runtime","optional":false},{"id":24733369092,"package_name":"regex","ecosystem":"pypi","requirements":"==2025.7.34","direct":true,"kind":"runtime","optional":false},{"id":24733369093,"package_name":"requests","ecosystem":"pypi","requirements":"==2.32.4","direct":true,"kind":"runtime","optional":false},{"id":24733369094,"package_name":"rich","ecosystem":"pypi","requirements":"==14.1.0","direct":true,"kind":"runtime","optional":false},{"id":24733369095,"package_name":"rpds-py","ecosystem":"pypi","requirements":"==0.27.0","direct":true,"kind":"runtime","optional":false},{"id":24733369096,"package_name":"safetensors","ecosystem":"pypi","requirements":"==0.6.2","direct":true,"kind":"runtime","optional":false},{"id":24733369097,"package_name":"shellingham","ecosystem":"pypi","requirements":"==1.5.4","direct":true,"kind":"runtime","optional":false},{"id":24733369098,"package_name":"six","ecosystem":"pypi","requirements":"==1.17.0","direct":true,"kind":"runtime","optional":false},{"id":24733369099,"package_name":"smmap","ecosystem":"pypi","requirements":"==5.0.2","direct":true,"kind":"runtime","optional":false},{"id":24733369100,"package_name":"streamlit","ecosystem":"pypi","requirements":"==1.48.1","direct":true,"kind":"runtime","optional":false},{"id":24733369101,"package_name":"tenacity","ecosystem":"pypi","requirements":"==9.1.2","direct":true,"kind":"runtime","optional":false},{"id":24733369102,"package_name":"tiktoken","ecosystem":"pypi","requirements":"==0.11.0","direct":true,"kind":"runtime","optional":false},{"id":24733369103,"package_name":"tokenizers","ecosystem":"pypi","requirements":"==0.21.4","direct":true,"kind":"runtime","optional":false},{"id":24733369104,"package_name":"toml","ecosystem":"pypi","requirements":"==0.10.2","direct":true,"kind":"runtime","optional":false},{"id":24733369105,"package_name":"tornado","ecosystem":"pypi","requirements":"==6.5.2","direct":true,"kind":"runtime","optional":false},{"id":24733369106,"package_name":"tqdm","ecosystem":"pypi","requirements":"==4.67.1","direct":true,"kind":"runtime","optional":false},{"id":24733369107,"package_name":"transformers","ecosystem":"pypi","requirements":"==4.55.2","direct":true,"kind":"runtime","optional":false},{"id":24733369108,"package_name":"typer","ecosystem":"pypi","requirements":"==0.16.0","direct":true,"kind":"runtime","optional":false},{"id":24733369109,"package_name":"typing_extensions","ecosystem":"pypi","requirements":"==4.14.1","direct":true,"kind":"runtime","optional":false},{"id":24733369110,"package_name":"tzdata","ecosystem":"pypi","requirements":"==2025.2","direct":true,"kind":"runtime","optional":false},{"id":24733369111,"package_name":"urllib3","ecosystem":"pypi","requirements":"==2.5.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-08-18T20:18:35.469Z","updated_at":"2025-08-18T20:18:35.469Z","repository_link":"https://github.com/bernard-ng/drc-native-tokenizer/blob/main/requirements.txt","dependencies":[{"id":24733369112,"package_name":"pandas","ecosystem":"pypi","requirements":"==2.2.2","direct":true,"kind":"runtime","optional":false},{"id":24733369113,"package_name":"numpy","ecosystem":"pypi","requirements":"==1.26.4","direct":true,"kind":"runtime","optional":false},{"id":24733369114,"package_name":"tokenizers","ecosystem":"pypi","requirements":"==0.15.2","direct":true,"kind":"runtime","optional":false},{"id":24733369115,"package_name":"transformers","ecosystem":"pypi","requirements":"==4.41.2","direct":true,"kind":"runtime","optional":false},{"id":24733369116,"package_name":"tiktoken","ecosystem":"pypi","requirements":"==0.7.0","direct":true,"kind":"runtime","optional":false},{"id":24733369117,"package_name":"rich","ecosystem":"pypi","requirements":"==13.7.1","direct":true,"kind":"runtime","optional":false},{"id":24733369118,"package_name":"typer","ecosystem":"pypi","requirements":"==0.12.3","direct":true,"kind":"runtime","optional":false},{"id":24733369119,"package_name":"pyyaml","ecosystem":"pypi","requirements":"==6.0.1","direct":true,"kind":"runtime","optional":false},{"id":24733369120,"package_name":"tqdm","ecosystem":"pypi","requirements":"==4.66.4","direct":true,"kind":"runtime","optional":false},{"id":24733369121,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"==1.4.2","direct":true,"kind":"runtime","optional":false},{"id":24733369122,"package_name":"streamlit","ecosystem":"pypi","requirements":"==1.36.0","direct":true,"kind":"runtime","optional":false},{"id":24733369123,"package_name":"altair","ecosystem":"pypi","requirements":"==5.3.0","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-09T00:14:37.891Z","updated_at":"2025-10-07T08:36:09.816Z","avatar_url":"https://github.com/bernard-ng.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/142781","html_url":"https://science.ecosyste.ms/projects/142781"}