{"id":178348,"name":null,"description":"zero-vocab or low-vocab embeddings","url":"https://github.com/chenghaomou/embeddings","last_synced_at":"2025-09-10T00:03:08.795Z","repository":{"id":45814684,"uuid":"358908122","full_name":"ChenghaoMou/embeddings","owner":"ChenghaoMou","description":"zero-vocab or low-vocab embeddings","archived":false,"fork":false,"pushed_at":"2022-07-17T02:52:33.000Z","size":6637,"stargazers_count":18,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-08-29T04:26:49.880Z","etag":null,"topics":["embeddings","nlp","text-processing","transformers"],"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/ChenghaoMou.png","metadata":{},"created_at":"2021-04-17T15:02:14.000Z","updated_at":"2025-01-06T08:58:23.000Z","dependencies_parsed_at":"2022-09-16T16:53:11.532Z","dependency_job_id":null,"html_url":"https://github.com/ChenghaoMou/embeddings","commit_stats":null,"previous_names":[],"tags_count":15,"template":false,"template_full_name":null,"purl":"pkg:github/ChenghaoMou/embeddings","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fembeddings","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fembeddings/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fembeddings/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fembeddings/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou","download_url":"https://codeload.github.com/ChenghaoMou/embeddings/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fembeddings/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274388849,"owners_count":25276205,"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":"ChenghaoMou","name":"Chenghao Mou","uuid":"32014649","kind":"user","description":"NLP/AI\r\n","email":"","website":"https://sleeplessindebugging.blog/","location":"Ireland","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/32014649?u=bf7b28ce77de4c43a90023474dd208c971e8a872\u0026v=4","repositories_count":32,"last_synced_at":"2025-09-04T22:57:35.666Z","metadata":{"has_sponsors_listing":true},"html_url":"https://github.com/ChenghaoMou","funding_links":["https://github.com/sponsors/ChenghaoMou"],"total_stars":623,"followers":130,"following":254,"created_at":"2022-11-14T19:51:49.742Z","updated_at":"2025-09-04T22:57:35.666Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou/repositories"},"packages":null,"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"chenghaomou/embeddings","html_url":"https://github.com/chenghaomou/embeddings","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":"2025-09-10T00:02:31.254Z","updated_at":"2025-09-10T00:02:31.254Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenghaomou%2Fembeddings","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/chenghaomou%2Fembeddings/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":"2025-09-10T00:00:25.260Z","repositories_count":10198088,"issues_count":32233623,"pull_requests_count":101763769,"authors_count":10741856,"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":{"WatchEvent":1},"last_year":{"WatchEvent":1}},"keywords":["embeddings","nlp","text-processing","transformers"],"dependencies":[{"ecosystem":"pypi","filepath":"poetry.lock","sha":null,"kind":"lockfile","created_at":"2022-09-16T16:53:11.490Z","updated_at":"2022-09-16T16:53:11.490Z","repository_link":"https://github.com/ChenghaoMou/embeddings/blob/main/poetry.lock","dependencies":[{"id":5071193242,"package_name":"absl-py","ecosystem":"pypi","requirements":"1.1.0","direct":false,"kind":"develop","optional":false},{"id":5071193243,"package_name":"aiohttp","ecosystem":"pypi","requirements":"3.8.1","direct":false,"kind":"develop","optional":false},{"id":5071193244,"package_name":"aiosignal","ecosystem":"pypi","requirements":"1.2.0","direct":false,"kind":"develop","optional":false},{"id":5071193245,"package_name":"async-timeout","ecosystem":"pypi","requirements":"4.0.2","direct":false,"kind":"develop","optional":false},{"id":5071193246,"package_name":"atomicwrites","ecosystem":"pypi","requirements":"1.4.1","direct":false,"kind":"runtime","optional":false},{"id":5071193247,"package_name":"attrs","ecosystem":"pypi","requirements":"21.4.0","direct":false,"kind":"runtime","optional":false},{"id":5071193248,"package_name":"cachetools","ecosystem":"pypi","requirements":"5.2.0","direct":false,"kind":"develop","optional":false},{"id":5071193249,"package_name":"certifi","ecosystem":"pypi","requirements":"2022.6.15","direct":false,"kind":"runtime","optional":false},{"id":5071193250,"package_name":"charset-normalizer","ecosystem":"pypi","requirements":"2.1.0","direct":false,"kind":"runtime","optional":false},{"id":5071193251,"package_name":"colorama","ecosystem":"pypi","requirements":"0.4.5","direct":false,"kind":"runtime","optional":false},{"id":5071193252,"package_name":"datasets","ecosystem":"pypi","requirements":"1.18.4","direct":false,"kind":"develop","optional":false},{"id":5071193253,"package_name":"dill","ecosystem":"pypi","requirements":"0.3.5.1","direct":false,"kind":"develop","optional":false},{"id":5071193254,"package_name":"einops","ecosystem":"pypi","requirements":"0.3.2","direct":false,"kind":"runtime","optional":false},{"id":5071193255,"package_name":"filelock","ecosystem":"pypi","requirements":"3.7.1","direct":false,"kind":"runtime","optional":false},{"id":5071193256,"package_name":"frozenlist","ecosystem":"pypi","requirements":"1.3.0","direct":false,"kind":"develop","optional":false},{"id":5071193257,"package_name":"fsspec","ecosystem":"pypi","requirements":"2022.5.0","direct":false,"kind":"develop","optional":false},{"id":5071193258,"package_name":"google-auth","ecosystem":"pypi","requirements":"2.9.1","direct":false,"kind":"develop","optional":false},{"id":5071193259,"package_name":"google-auth-oauthlib","ecosystem":"pypi","requirements":"0.4.6","direct":false,"kind":"develop","optional":false},{"id":5071193260,"package_name":"grpcio","ecosystem":"pypi","requirements":"1.38.1","direct":false,"kind":"runtime","optional":false},{"id":5071193261,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"0.8.1","direct":false,"kind":"runtime","optional":false},{"id":5071193262,"package_name":"idna","ecosystem":"pypi","requirements":"3.3","direct":false,"kind":"runtime","optional":false},{"id":5071193263,"package_name":"importlib-metadata","ecosystem":"pypi","requirements":"4.12.0","direct":false,"kind":"runtime","optional":false},{"id":5071193264,"package_name":"iniconfig","ecosystem":"pypi","requirements":"1.1.1","direct":false,"kind":"runtime","optional":false},{"id":5071193265,"package_name":"joblib","ecosystem":"pypi","requirements":"1.1.0","direct":false,"kind":"runtime","optional":false},{"id":5071193266,"package_name":"loguru","ecosystem":"pypi","requirements":"0.5.3","direct":false,"kind":"runtime","optional":false},{"id":5071193267,"package_name":"mako","ecosystem":"pypi","requirements":"1.2.1","direct":false,"kind":"runtime","optional":false},{"id":5071193268,"package_name":"markdown","ecosystem":"pypi","requirements":"3.4.1","direct":false,"kind":"runtime","optional":false},{"id":5071193269,"package_name":"markupsafe","ecosystem":"pypi","requirements":"2.1.1","direct":false,"kind":"runtime","optional":false},{"id":5071193270,"package_name":"mmh3","ecosystem":"pypi","requirements":"3.0.0","direct":false,"kind":"runtime","optional":false},{"id":5071193271,"package_name":"multidict","ecosystem":"pypi","requirements":"6.0.2","direct":false,"kind":"develop","optional":false},{"id":5071193272,"package_name":"multiprocess","ecosystem":"pypi","requirements":"0.70.13","direct":false,"kind":"develop","optional":false},{"id":5071193273,"package_name":"numpy","ecosystem":"pypi","requirements":"1.23.1","direct":false,"kind":"runtime","optional":false},{"id":5071193274,"package_name":"oauthlib","ecosystem":"pypi","requirements":"3.2.0","direct":false,"kind":"develop","optional":false},{"id":5071193275,"package_name":"packaging","ecosystem":"pypi","requirements":"21.3","direct":false,"kind":"runtime","optional":false},{"id":5071193276,"package_name":"pandas","ecosystem":"pypi","requirements":"1.4.3","direct":false,"kind":"develop","optional":false},{"id":5071193277,"package_name":"pdoc3","ecosystem":"pypi","requirements":"0.9.2","direct":false,"kind":"runtime","optional":false},{"id":5071193278,"package_name":"pillow","ecosystem":"pypi","requirements":"8.4.0","direct":false,"kind":"runtime","optional":false},{"id":5071193279,"package_name":"pluggy","ecosystem":"pypi","requirements":"1.0.0","direct":false,"kind":"runtime","optional":false},{"id":5071193280,"package_name":"protobuf","ecosystem":"pypi","requirements":"3.20.1","direct":false,"kind":"develop","optional":false},{"id":5071193281,"package_name":"py","ecosystem":"pypi","requirements":"1.11.0","direct":false,"kind":"runtime","optional":false},{"id":5071193282,"package_name":"pyarrow","ecosystem":"pypi","requirements":"8.0.0","direct":false,"kind":"develop","optional":false},{"id":5071193283,"package_name":"pyasn1","ecosystem":"pypi","requirements":"0.4.8","direct":false,"kind":"develop","optional":false},{"id":5071193284,"package_name":"pyasn1-modules","ecosystem":"pypi","requirements":"0.2.8","direct":false,"kind":"develop","optional":false},{"id":5071193285,"package_name":"pydeprecate","ecosystem":"pypi","requirements":"0.3.2","direct":false,"kind":"develop","optional":false},{"id":5071193286,"package_name":"pyparsing","ecosystem":"pypi","requirements":"3.0.9","direct":false,"kind":"runtime","optional":false},{"id":5071193287,"package_name":"pytest","ecosystem":"pypi","requirements":"6.2.5","direct":false,"kind":"runtime","optional":false},{"id":5071193288,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"2.8.2","direct":false,"kind":"develop","optional":false},{"id":5071193289,"package_name":"pytorch-lightning","ecosystem":"pypi","requirements":"1.6.5","direct":false,"kind":"develop","optional":false},{"id":5071193290,"package_name":"pytz","ecosystem":"pypi","requirements":"2022.1","direct":false,"kind":"develop","optional":false},{"id":5071193291,"package_name":"pyyaml","ecosystem":"pypi","requirements":"6.0","direct":false,"kind":"runtime","optional":false},{"id":5071193292,"package_name":"regex","ecosystem":"pypi","requirements":"2022.7.9","direct":false,"kind":"runtime","optional":false},{"id":5071193293,"package_name":"requests","ecosystem":"pypi","requirements":"2.28.1","direct":false,"kind":"runtime","optional":false},{"id":5071193294,"package_name":"requests-oauthlib","ecosystem":"pypi","requirements":"1.3.1","direct":false,"kind":"develop","optional":false},{"id":5071193295,"package_name":"responses","ecosystem":"pypi","requirements":"0.18.0","direct":false,"kind":"develop","optional":false},{"id":5071193296,"package_name":"rsa","ecosystem":"pypi","requirements":"4.8","direct":false,"kind":"develop","optional":false},{"id":5071193297,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"1.1.1","direct":false,"kind":"runtime","optional":false},{"id":5071193298,"package_name":"scipy","ecosystem":"pypi","requirements":"1.8.1","direct":false,"kind":"runtime","optional":false},{"id":5071193299,"package_name":"six","ecosystem":"pypi","requirements":"1.16.0","direct":false,"kind":"runtime","optional":false},{"id":5071193300,"package_name":"tensorboard","ecosystem":"pypi","requirements":"2.9.0","direct":false,"kind":"develop","optional":false},{"id":5071193301,"package_name":"tensorboard-data-server","ecosystem":"pypi","requirements":"0.6.1","direct":false,"kind":"develop","optional":false},{"id":5071193302,"package_name":"tensorboard-plugin-wit","ecosystem":"pypi","requirements":"1.8.1","direct":false,"kind":"develop","optional":false},{"id":5071193303,"package_name":"threadpoolctl","ecosystem":"pypi","requirements":"3.1.0","direct":false,"kind":"runtime","optional":false},{"id":5071193304,"package_name":"tokenizers","ecosystem":"pypi","requirements":"0.12.1","direct":false,"kind":"runtime","optional":false},{"id":5071193305,"package_name":"toml","ecosystem":"pypi","requirements":"0.10.2","direct":false,"kind":"runtime","optional":false},{"id":5071193306,"package_name":"torch","ecosystem":"pypi","requirements":"1.12.0","direct":false,"kind":"runtime","optional":false},{"id":5071193307,"package_name":"torchmetrics","ecosystem":"pypi","requirements":"0.9.2","direct":false,"kind":"develop","optional":false},{"id":5071193308,"package_name":"tqdm","ecosystem":"pypi","requirements":"4.64.0","direct":false,"kind":"runtime","optional":false},{"id":5071193309,"package_name":"transformers","ecosystem":"pypi","requirements":"4.20.1","direct":false,"kind":"runtime","optional":false},{"id":5071193310,"package_name":"typing-extensions","ecosystem":"pypi","requirements":"4.3.0","direct":false,"kind":"runtime","optional":false},{"id":5071193311,"package_name":"urllib3","ecosystem":"pypi","requirements":"1.26.10","direct":false,"kind":"runtime","optional":false},{"id":5071193312,"package_name":"werkzeug","ecosystem":"pypi","requirements":"2.1.2","direct":false,"kind":"develop","optional":false},{"id":5071193313,"package_name":"win32-setctime","ecosystem":"pypi","requirements":"1.1.0","direct":false,"kind":"runtime","optional":false},{"id":5071193314,"package_name":"xxhash","ecosystem":"pypi","requirements":"3.0.0","direct":false,"kind":"develop","optional":false},{"id":5071193315,"package_name":"yarl","ecosystem":"pypi","requirements":"1.7.2","direct":false,"kind":"develop","optional":false},{"id":5071193316,"package_name":"zipp","ecosystem":"pypi","requirements":"3.8.1","direct":false,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2022-09-16T16:53:11.516Z","updated_at":"2022-09-16T16:53:11.516Z","repository_link":"https://github.com/ChenghaoMou/embeddings/blob/main/pyproject.toml","dependencies":[{"id":5071193325,"package_name":"pdoc3","ecosystem":"pypi","requirements":"^0.9.2","direct":true,"kind":"runtime","optional":false},{"id":5071193317,"package_name":"python","ecosystem":"pypi","requirements":"\u003e=3.8,\u003c3.11","direct":true,"kind":"runtime","optional":false},{"id":5071193318,"package_name":"loguru","ecosystem":"pypi","requirements":"^0.5.3","direct":true,"kind":"runtime","optional":false},{"id":5071193319,"package_name":"transformers","ecosystem":"pypi","requirements":"^4.8.2","direct":true,"kind":"runtime","optional":false},{"id":5071193320,"package_name":"numpy","ecosystem":"pypi","requirements":"^1.21.1","direct":true,"kind":"runtime","optional":false},{"id":5071193321,"package_name":"einops","ecosystem":"pypi","requirements":"^0.3.0","direct":true,"kind":"runtime","optional":false},{"id":5071193322,"package_name":"Pillow","ecosystem":"pypi","requirements":"^8.3.1","direct":true,"kind":"runtime","optional":false},{"id":5071193323,"package_name":"pytest","ecosystem":"pypi","requirements":"^6.2.4","direct":true,"kind":"runtime","optional":false},{"id":5071193324,"package_name":"mmh3","ecosystem":"pypi","requirements":"^3.0.0","direct":true,"kind":"runtime","optional":false},{"id":5071193326,"package_name":"grpcio","ecosystem":"pypi","requirements":"1.38.1","direct":true,"kind":"runtime","optional":false},{"id":5071193327,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"^1.1.1","direct":true,"kind":"runtime","optional":false},{"id":5071193328,"package_name":"scipy","ecosystem":"pypi","requirements":"^1.8.1","direct":true,"kind":"runtime","optional":false},{"id":5071193329,"package_name":"tokenizers","ecosystem":"pypi","requirements":"^0.12.1","direct":true,"kind":"runtime","optional":false},{"id":5071193330,"package_name":"torch","ecosystem":"pypi","requirements":"^1.12.0","direct":true,"kind":"runtime","optional":false},{"id":5071193331,"package_name":"datasets","ecosystem":"pypi","requirements":"^1.9.0","direct":true,"kind":"develop","optional":false},{"id":5071193332,"package_name":"tqdm","ecosystem":"pypi","requirements":"^4.61.2","direct":true,"kind":"develop","optional":false},{"id":5071193333,"package_name":"pytorch-lightning","ecosystem":"pypi","requirements":"^1.3.8","direct":true,"kind":"develop","optional":false}]}],"score":null,"created_at":"2025-09-09T01:50:01.678Z","updated_at":"2025-10-07T08:40:54.413Z","avatar_url":"https://github.com/ChenghaoMou.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/178348","html_url":"https://science.ecosyste.ms/projects/178348"}