{"id":200935,"name":null,"description":"Introducing Filtered Direct Preference Optimization (fDPO) that enhances language model alignment with human preferences by discarding lower-quality samples compared to those generated by the learning model","url":"https://github.com/cyberagentailab/filtered-dpo","last_synced_at":"2025-09-10T05:38:47.302Z","repository":{"id":235039384,"uuid":"786694117","full_name":"CyberAgentAILab/filtered-dpo","owner":"CyberAgentAILab","description":"Introducing Filtered Direct Preference Optimization (fDPO) that enhances language model alignment with human preferences by discarding lower-quality samples compared to those generated by the learning model","archived":false,"fork":false,"pushed_at":"2024-11-27T09:49:40.000Z","size":108,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2024-11-27T10:33:14.015Z","etag":null,"topics":["alignment","dpo","rlhf"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2404.13846","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/CyberAgentAILab.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}},"created_at":"2024-04-15T06:03:47.000Z","updated_at":"2024-11-27T09:49:44.000Z","dependencies_parsed_at":"2024-10-23T00:46:32.399Z","dependency_job_id":null,"html_url":"https://github.com/CyberAgentAILab/filtered-dpo","commit_stats":null,"previous_names":["cyberagentailab/filtered-dpo"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CyberAgentAILab/filtered-dpo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Ffiltered-dpo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Ffiltered-dpo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Ffiltered-dpo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Ffiltered-dpo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab","download_url":"https://codeload.github.com/CyberAgentAILab/filtered-dpo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Ffiltered-dpo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274417410,"owners_count":25281108,"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":"2025-09-10T02:00:12.551Z","response_time":83,"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":"CyberAgentAILab","name":"CyberAgent AI Lab","uuid":"88431400","kind":"organization","description":"","email":null,"website":"https://cyberagent.ai/ailab/","location":"Japan","twitter":"cyberagent_ai","company":null,"icon_url":"https://avatars.githubusercontent.com/u/88431400?v=4","repositories_count":7,"last_synced_at":"2023-03-05T02:04:10.614Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/CyberAgentAILab","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-15T04:10:16.626Z","updated_at":"2023-03-05T02:04:10.617Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"cyberagentailab/filtered-dpo","html_url":"https://github.com/cyberagentailab/filtered-dpo","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":"2025-09-10T05:38:32.310Z","updated_at":"2025-09-10T05:38:32.310Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberagentailab%2Ffiltered-dpo","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyberagentailab%2Ffiltered-dpo/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":10198638,"issues_count":32085755,"pull_requests_count":101563920,"authors_count":10742772,"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":8,"PushEvent":3,"ForkEvent":1},"last_year":{"WatchEvent":8,"PushEvent":3,"ForkEvent":1}},"keywords":["alignment","dpo","rlhf"],"dependencies":[{"ecosystem":"pypi","filepath":"poetry.lock","sha":null,"kind":"lockfile","created_at":"2024-04-22T04:05:27.823Z","updated_at":"2024-04-22T04:05:27.823Z","repository_link":"https://github.com/CyberAgentAILab/filtered-dpo/blob/main/poetry.lock","dependencies":[{"id":17590647530,"package_name":"platformdirs","ecosystem":"pypi","requirements":"4.2.0","direct":false,"kind":"runtime","optional":false},{"id":17590647531,"package_name":"protobuf","ecosystem":"pypi","requirements":"5.26.1","direct":false,"kind":"runtime","optional":false},{"id":17590647532,"package_name":"psutil","ecosystem":"pypi","requirements":"5.9.8","direct":false,"kind":"runtime","optional":false},{"id":17590647533,"package_name":"pyarrow","ecosystem":"pypi","requirements":"15.0.2","direct":false,"kind":"runtime","optional":false},{"id":17590647534,"package_name":"pyarrow-hotfix","ecosystem":"pypi","requirements":"0.6","direct":false,"kind":"runtime","optional":false},{"id":17590647535,"package_name":"pygments","ecosystem":"pypi","requirements":"2.17.2","direct":false,"kind":"runtime","optional":false},{"id":17590647536,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"2.9.0.post0","direct":false,"kind":"runtime","optional":false},{"id":17590647537,"package_name":"pytz","ecosystem":"pypi","requirements":"2024.1","direct":false,"kind":"runtime","optional":false},{"id":17590647538,"package_name":"pyyaml","ecosystem":"pypi","requirements":"6.0.1","direct":false,"kind":"runtime","optional":false},{"id":17590647539,"package_name":"regex","ecosystem":"pypi","requirements":"2023.12.25","direct":false,"kind":"runtime","optional":false},{"id":17590647540,"package_name":"requests","ecosystem":"pypi","requirements":"2.31.0","direct":false,"kind":"runtime","optional":false},{"id":17590647541,"package_name":"rich","ecosystem":"pypi","requirements":"13.7.1","direct":false,"kind":"runtime","optional":false},{"id":17590647542,"package_name":"safetensors","ecosystem":"pypi","requirements":"0.4.2","direct":false,"kind":"runtime","optional":false},{"id":17590647543,"package_name":"setuptools","ecosystem":"pypi","requirements":"69.5.1","direct":false,"kind":"runtime","optional":false},{"id":17590647544,"package_name":"shtab","ecosystem":"pypi","requirements":"1.7.1","direct":false,"kind":"runtime","optional":false},{"id":17590647545,"package_name":"six","ecosystem":"pypi","requirements":"1.16.0","direct":false,"kind":"runtime","optional":false},{"id":17590647546,"package_name":"sympy","ecosystem":"pypi","requirements":"1.12","direct":false,"kind":"runtime","optional":false},{"id":17590647547,"package_name":"tensorboard","ecosystem":"pypi","requirements":"2.16.2","direct":false,"kind":"runtime","optional":false},{"id":17590647548,"package_name":"tensorboard-data-server","ecosystem":"pypi","requirements":"0.7.2","direct":false,"kind":"runtime","optional":false},{"id":17590647549,"package_name":"tensorboardx","ecosystem":"pypi","requirements":"2.6.2.2","direct":false,"kind":"runtime","optional":false},{"id":17590647550,"package_name":"tokenizers","ecosystem":"pypi","requirements":"0.15.2","direct":false,"kind":"runtime","optional":false},{"id":17590647551,"package_name":"tomli","ecosystem":"pypi","requirements":"2.0.1","direct":false,"kind":"runtime","optional":false},{"id":17590647552,"package_name":"torch","ecosystem":"pypi","requirements":"2.2.2","direct":false,"kind":"runtime","optional":false},{"id":17590647553,"package_name":"tqdm","ecosystem":"pypi","requirements":"4.66.2","direct":false,"kind":"runtime","optional":false},{"id":17590647554,"package_name":"transformers","ecosystem":"pypi","requirements":"4.36.2","direct":false,"kind":"runtime","optional":false},{"id":17590647555,"package_name":"triton","ecosystem":"pypi","requirements":"2.2.0","direct":false,"kind":"runtime","optional":false},{"id":17590647556,"package_name":"trl","ecosystem":"pypi","requirements":"0.7.4","direct":false,"kind":"runtime","optional":false},{"id":17590647557,"package_name":"typing-extensions","ecosystem":"pypi","requirements":"4.11.0","direct":false,"kind":"runtime","optional":false},{"id":17590647558,"package_name":"tyro","ecosystem":"pypi","requirements":"0.8.3","direct":false,"kind":"runtime","optional":false},{"id":17590647559,"package_name":"tzdata","ecosystem":"pypi","requirements":"2024.1","direct":false,"kind":"runtime","optional":false},{"id":17590647560,"package_name":"urllib3","ecosystem":"pypi","requirements":"2.2.1","direct":false,"kind":"runtime","optional":false},{"id":17590647561,"package_name":"werkzeug","ecosystem":"pypi","requirements":"3.0.2","direct":false,"kind":"runtime","optional":false},{"id":17590647562,"package_name":"xxhash","ecosystem":"pypi","requirements":"3.4.1","direct":false,"kind":"runtime","optional":false},{"id":17590647563,"package_name":"yarl","ecosystem":"pypi","requirements":"1.9.4","direct":false,"kind":"runtime","optional":false},{"id":17590647477,"package_name":"absl-py","ecosystem":"pypi","requirements":"2.1.0","direct":false,"kind":"runtime","optional":false},{"id":17590647478,"package_name":"accelerate","ecosystem":"pypi","requirements":"0.29.2","direct":false,"kind":"runtime","optional":false},{"id":17590647479,"package_name":"aiohttp","ecosystem":"pypi","requirements":"3.9.4","direct":false,"kind":"runtime","optional":false},{"id":17590647480,"package_name":"aiosignal","ecosystem":"pypi","requirements":"1.3.1","direct":false,"kind":"runtime","optional":false},{"id":17590647481,"package_name":"async-timeout","ecosystem":"pypi","requirements":"4.0.3","direct":false,"kind":"runtime","optional":false},{"id":17590647482,"package_name":"attrs","ecosystem":"pypi","requirements":"23.2.0","direct":false,"kind":"runtime","optional":false},{"id":17590647483,"package_name":"black","ecosystem":"pypi","requirements":"24.3.0","direct":false,"kind":"runtime","optional":false},{"id":17590647484,"package_name":"certifi","ecosystem":"pypi","requirements":"2024.2.2","direct":false,"kind":"runtime","optional":false},{"id":17590647485,"package_name":"charset-normalizer","ecosystem":"pypi","requirements":"3.3.2","direct":false,"kind":"runtime","optional":false},{"id":17590647486,"package_name":"click","ecosystem":"pypi","requirements":"8.1.7","direct":false,"kind":"runtime","optional":false},{"id":17590647487,"package_name":"colorama","ecosystem":"pypi","requirements":"0.4.6","direct":false,"kind":"runtime","optional":false},{"id":17590647488,"package_name":"datasets","ecosystem":"pypi","requirements":"2.18.0","direct":false,"kind":"runtime","optional":false},{"id":17590647489,"package_name":"dill","ecosystem":"pypi","requirements":"0.3.8","direct":false,"kind":"runtime","optional":false},{"id":17590647490,"package_name":"docstring-parser","ecosystem":"pypi","requirements":"0.16","direct":false,"kind":"runtime","optional":false},{"id":17590647491,"package_name":"filelock","ecosystem":"pypi","requirements":"3.13.4","direct":false,"kind":"runtime","optional":false},{"id":17590647492,"package_name":"frozenlist","ecosystem":"pypi","requirements":"1.4.1","direct":false,"kind":"runtime","optional":false},{"id":17590647493,"package_name":"fsspec","ecosystem":"pypi","requirements":"2024.2.0","direct":false,"kind":"runtime","optional":false},{"id":17590647494,"package_name":"grpcio","ecosystem":"pypi","requirements":"1.62.1","direct":false,"kind":"runtime","optional":false},{"id":17590647495,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"0.22.2","direct":false,"kind":"runtime","optional":false},{"id":17590647496,"package_name":"idna","ecosystem":"pypi","requirements":"3.7","direct":false,"kind":"runtime","optional":false},{"id":17590647497,"package_name":"isort","ecosystem":"pypi","requirements":"5.13.2","direct":false,"kind":"runtime","optional":false},{"id":17590647498,"package_name":"jinja2","ecosystem":"pypi","requirements":"3.1.3","direct":false,"kind":"runtime","optional":false},{"id":17590647499,"package_name":"markdown","ecosystem":"pypi","requirements":"3.6","direct":false,"kind":"runtime","optional":false},{"id":17590647500,"package_name":"markdown-it-py","ecosystem":"pypi","requirements":"3.0.0","direct":false,"kind":"runtime","optional":false},{"id":17590647501,"package_name":"markupsafe","ecosystem":"pypi","requirements":"2.1.5","direct":false,"kind":"runtime","optional":false},{"id":17590647502,"package_name":"mdurl","ecosystem":"pypi","requirements":"0.1.2","direct":false,"kind":"runtime","optional":false},{"id":17590647503,"package_name":"mpmath","ecosystem":"pypi","requirements":"1.3.0","direct":false,"kind":"runtime","optional":false},{"id":17590647504,"package_name":"multidict","ecosystem":"pypi","requirements":"6.0.5","direct":false,"kind":"runtime","optional":false},{"id":17590647505,"package_name":"multiprocess","ecosystem":"pypi","requirements":"0.70.16","direct":false,"kind":"runtime","optional":false},{"id":17590647506,"package_name":"mypy-extensions","ecosystem":"pypi","requirements":"1.0.0","direct":false,"kind":"runtime","optional":false},{"id":17590647507,"package_name":"networkx","ecosystem":"pypi","requirements":"3.3","direct":false,"kind":"runtime","optional":false},{"id":17590647508,"package_name":"numpy","ecosystem":"pypi","requirements":"1.26.4","direct":false,"kind":"runtime","optional":false},{"id":17590647509,"package_name":"nvidia-cublas-cu12","ecosystem":"pypi","requirements":"12.1.3.1","direct":false,"kind":"runtime","optional":false},{"id":17590647511,"package_name":"nvidia-cuda-cupti-cu12","ecosystem":"pypi","requirements":"12.1.105","direct":false,"kind":"runtime","optional":false},{"id":17590647512,"package_name":"nvidia-cuda-nvrtc-cu12","ecosystem":"pypi","requirements":"12.1.105","direct":false,"kind":"runtime","optional":false},{"id":17590647515,"package_name":"nvidia-cuda-runtime-cu12","ecosystem":"pypi","requirements":"12.1.105","direct":false,"kind":"runtime","optional":false},{"id":17590647517,"package_name":"nvidia-cudnn-cu12","ecosystem":"pypi","requirements":"8.9.2.26","direct":false,"kind":"runtime","optional":false},{"id":17590647519,"package_name":"nvidia-cufft-cu12","ecosystem":"pypi","requirements":"11.0.2.54","direct":false,"kind":"runtime","optional":false},{"id":17590647521,"package_name":"nvidia-curand-cu12","ecosystem":"pypi","requirements":"10.3.2.106","direct":false,"kind":"runtime","optional":false},{"id":17590647522,"package_name":"nvidia-cusolver-cu12","ecosystem":"pypi","requirements":"11.4.5.107","direct":false,"kind":"runtime","optional":false},{"id":17590647523,"package_name":"nvidia-cusparse-cu12","ecosystem":"pypi","requirements":"12.1.0.106","direct":false,"kind":"runtime","optional":false},{"id":17590647524,"package_name":"nvidia-nccl-cu12","ecosystem":"pypi","requirements":"2.19.3","direct":false,"kind":"runtime","optional":false},{"id":17590647525,"package_name":"nvidia-nvjitlink-cu12","ecosystem":"pypi","requirements":"12.4.127","direct":false,"kind":"runtime","optional":false},{"id":17590647526,"package_name":"nvidia-nvtx-cu12","ecosystem":"pypi","requirements":"12.1.105","direct":false,"kind":"runtime","optional":false},{"id":17590647527,"package_name":"packaging","ecosystem":"pypi","requirements":"24.0","direct":false,"kind":"runtime","optional":false},{"id":17590647528,"package_name":"pandas","ecosystem":"pypi","requirements":"2.2.2","direct":false,"kind":"runtime","optional":false},{"id":17590647529,"package_name":"pathspec","ecosystem":"pypi","requirements":"0.12.1","direct":false,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2024-04-22T04:05:28.278Z","updated_at":"2024-04-22T04:05:28.278Z","repository_link":"https://github.com/CyberAgentAILab/filtered-dpo/blob/main/pyproject.toml","dependencies":[{"id":17590647714,"package_name":"python","ecosystem":"pypi","requirements":"^3.10","direct":true,"kind":"runtime","optional":false},{"id":17590647717,"package_name":"trl","ecosystem":"pypi","requirements":"0.7.4","direct":true,"kind":"runtime","optional":false},{"id":17590647719,"package_name":"transformers","ecosystem":"pypi","requirements":"4.36.2","direct":true,"kind":"runtime","optional":false},{"id":17590647721,"package_name":"tensorboardx","ecosystem":"pypi","requirements":"^2.6.2.2","direct":true,"kind":"runtime","optional":false},{"id":17590647723,"package_name":"tensorboard","ecosystem":"pypi","requirements":"^2.16.2","direct":true,"kind":"runtime","optional":false},{"id":17590647726,"package_name":"isort","ecosystem":"pypi","requirements":"^5.13.2","direct":true,"kind":"develop","optional":false},{"id":17590647729,"package_name":"black","ecosystem":"pypi","requirements":"^24.3.0","direct":true,"kind":"develop","optional":false}]}],"score":null,"created_at":"2025-09-09T03:46:11.299Z","updated_at":"2025-10-07T08:43:36.414Z","avatar_url":"https://github.com/CyberAgentAILab.png","language":"Jupyter Notebook","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/200935","html_url":"https://science.ecosyste.ms/projects/200935"}