{"id":45975,"name":"lm-evaluation-harness","description":"A private fork of lm-evaluation-harness by EleutherAI","url":"https://github.com/flowaicom/lm-evaluation-harness","last_synced_at":"2025-09-05T10:38:03.187Z","repository":{"id":272625607,"uuid":"858170244","full_name":"flowaicom/lm-evaluation-harness","owner":"flowaicom","description":"A private fork of lm-evaluation-harness by EleutherAI","archived":false,"fork":false,"pushed_at":"2025-01-15T16:10:20.000Z","size":24006,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"Flow-Judge-v0.1_evals","last_synced_at":"2025-01-15T18:04:51.889Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/flowaicom.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.bib","codeowners":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-16T12:39:08.000Z","updated_at":"2024-09-18T06:15:40.000Z","dependencies_parsed_at":"2025-01-15T18:20:05.640Z","dependency_job_id":null,"html_url":"https://github.com/flowaicom/lm-evaluation-harness","commit_stats":null,"previous_names":["flowaicom/lm-evaluation-harness"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/flowaicom/lm-evaluation-harness","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flowaicom","download_url":"https://codeload.github.com/flowaicom/lm-evaluation-harness/tar.gz/refs/heads/Flow-Judge-v0.1_evals","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273747092,"owners_count":25160648,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":"flowaicom","name":"Flow AI","uuid":"178139656","kind":"organization","description":"Flow AI is the system for evaluating and improving your LLM application.","email":"hello@flow-ai.com","website":"https://www.flow-ai.com/","location":"Finland","twitter":"flowaicom","company":null,"icon_url":"https://avatars.githubusercontent.com/u/178139656?v=4","repositories_count":1,"last_synced_at":"2024-09-15T12:36:30.995Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/flowaicom","funding_links":[],"total_stars":0,"followers":1,"following":0,"created_at":"2024-09-15T12:36:31.005Z","updated_at":"2024-09-15T12:36:31.005Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flowaicom","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flowaicom/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"flowaicom/lm-evaluation-harness","html_url":"https://github.com/flowaicom/lm-evaluation-harness","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":"2025-09-05T10:37:11.669Z","updated_at":"2025-09-05T10:37:11.669Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/flowaicom%2Flm-evaluation-harness/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":"2025-09-05T00:00:10.444Z","repositories_count":10097320,"issues_count":31426573,"pull_requests_count":97235070,"authors_count":10701179,"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,"CreateEvent":2},"last_year":{"PushEvent":1,"CreateEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/new_tasks.yml","sha":null,"kind":"manifest","created_at":"2025-01-15T18:19:54.317Z","updated_at":"2025-01-15T18:19:54.317Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/.github/workflows/new_tasks.yml","dependencies":[{"id":21487740802,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21487740803,"package_name":"tj-actions/changed-files","ecosystem":"actions","requirements":"v44.5.2","direct":true,"kind":"composite","optional":false},{"id":21487740804,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/publish.yml","sha":null,"kind":"manifest","created_at":"2025-01-15T18:19:54.981Z","updated_at":"2025-01-15T18:19:54.981Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/.github/workflows/publish.yml","dependencies":[{"id":21487740898,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21487740929,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21487740930,"package_name":"actions/upload-artifact","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21487740964,"package_name":"actions/download-artifact","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21487740965,"package_name":"pypa/gh-action-pypi-publish","ecosystem":"actions","requirements":"release/v1","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/unit_tests.yml","sha":null,"kind":"manifest","created_at":"2025-01-15T18:19:56.493Z","updated_at":"2025-01-15T18:19:56.493Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/.github/workflows/unit_tests.yml","dependencies":[{"id":21487741016,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21487741025,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v5","direct":true,"kind":"composite","optional":false},{"id":21487741027,"package_name":"pre-commit/action","ecosystem":"actions","requirements":"v3.0.1","direct":true,"kind":"composite","optional":false},{"id":21487741050,"package_name":"actions/upload-artifact","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2025-01-15T18:19:58.369Z","updated_at":"2025-01-15T18:19:58.369Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/pyproject.toml","dependencies":[{"id":21487741139,"package_name":"accelerate","ecosystem":"pypi","requirements":"\u003e=0.26.0","direct":true,"kind":"runtime","optional":false},{"id":21487741140,"package_name":"evaluate","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741141,"package_name":"datasets","ecosystem":"pypi","requirements":"\u003e=2.16.0","direct":true,"kind":"runtime","optional":false},{"id":21487741174,"package_name":"evaluate","ecosystem":"pypi","requirements":"\u003e=0.4.0","direct":true,"kind":"runtime","optional":false},{"id":21487741175,"package_name":"jsonlines","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741176,"package_name":"numexpr","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741190,"package_name":"peft","ecosystem":"pypi","requirements":"\u003e=0.2.0","direct":true,"kind":"runtime","optional":false},{"id":21487741191,"package_name":"pybind11","ecosystem":"pypi","requirements":"\u003e=2.6.2","direct":true,"kind":"runtime","optional":false},{"id":21487741192,"package_name":"pytablewriter","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741241,"package_name":"rouge-score","ecosystem":"pypi","requirements":"\u003e=0.0.4","direct":true,"kind":"runtime","optional":false},{"id":21487741282,"package_name":"sacrebleu","ecosystem":"pypi","requirements":"\u003e=1.5.0","direct":true,"kind":"runtime","optional":false},{"id":21487741283,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"\u003e=0.24.1","direct":true,"kind":"runtime","optional":false},{"id":21487741284,"package_name":"sqlitedict","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741386,"package_name":"torch","ecosystem":"pypi","requirements":"\u003e=1.8","direct":true,"kind":"runtime","optional":false},{"id":21487741387,"package_name":"tqdm-multiprocess","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741466,"package_name":"transformers","ecosystem":"pypi","requirements":"\u003e=4.1","direct":true,"kind":"runtime","optional":false},{"id":21487741495,"package_name":"zstandard","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741496,"package_name":"dill","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741497,"package_name":"word2number","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21487741584,"package_name":"more_itertools","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-01-15T18:20:04.725Z","updated_at":"2025-01-15T18:20:04.725Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/requirements.txt","dependencies":[]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2025-01-15T18:20:05.268Z","updated_at":"2025-01-15T18:20:05.268Z","repository_link":"https://github.com/flowaicom/lm-evaluation-harness/blob/Flow-Judge-v0.1_evals/setup.py","dependencies":[]}],"score":null,"created_at":"2025-09-04T15:51:21.425Z","updated_at":"2025-10-07T08:18:22.676Z","avatar_url":"https://github.com/flowaicom.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":["https://doi.org/10.5281/zenodo.10256836"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/45975","html_url":"https://science.ecosyste.ms/projects/45975","bibtex_url":"https://science.ecosyste.ms/projects/45975/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/45975/export.apalike"}