{"id":35738,"name":"dpo-rlhf-paraphrase-types","description":"Enhancing paraphrase-type generation using Direct Preference Optimization (DPO) and Reinforcement Learning from Human Feedback (RLHF), with large-scale HPC support. This project aligns model outputs to human-ranked data for robust, safety-focused NLP.","url":"https://github.com/cluebbers/dpo-rlhf-paraphrase-types","last_synced_at":"2025-09-05T06:50:55.853Z","repository":{"id":297202946,"uuid":"842829651","full_name":"cluebbers/dpo-rlhf-paraphrase-types","owner":"cluebbers","description":"Enhancing paraphrase-type generation using Direct Preference Optimization (DPO) and Reinforcement Learning from Human Feedback (RLHF), with large-scale HPC support. This project aligns model outputs to human-ranked data for robust, safety-focused NLP.","archived":false,"fork":false,"pushed_at":"2025-06-04T09:44:08.000Z","size":34432,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-02T12:48:03.483Z","etag":null,"topics":["alignment","deep-learning","direct-preference-optimization","human-feedback","paraphrase-generation","paraphrase-type-generation","reinforcement-learning","transformers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cluebbers.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-08-15T07:18:07.000Z","updated_at":"2025-06-04T09:44:10.000Z","dependencies_parsed_at":"2025-06-08T05:31:03.206Z","dependency_job_id":null,"html_url":"https://github.com/cluebbers/dpo-rlhf-paraphrase-types","commit_stats":null,"previous_names":["cluebbers/dpo-rlhf-paraphrase-types"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/cluebbers/dpo-rlhf-paraphrase-types","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cluebbers","download_url":"https://codeload.github.com/cluebbers/dpo-rlhf-paraphrase-types/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273723194,"owners_count":25156304,"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":"cluebbers","name":null,"uuid":"157066905","kind":"user","description":"studying Applied Data Science\r\nInterested in Natural Language Processing.","email":"","website":null,"location":"Göttingen","twitter":null,"company":"University of Göttingen","icon_url":"https://avatars.githubusercontent.com/u/157066905?v=4","repositories_count":1,"last_synced_at":"2024-03-18T10:29:13.832Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/cluebbers","funding_links":[],"total_stars":0,"followers":null,"following":null,"created_at":"2024-03-18T10:29:13.835Z","updated_at":"2024-03-18T10:29:13.835Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cluebbers","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cluebbers/repositories"},"packages":[],"commits":{"id":10207816,"full_name":"cluebbers/dpo-rlhf-paraphrase-types","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2025-06-07T01:30:37.525Z","updated_at":"2025-06-07T01:30:37.525Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"cluebbers/dpo-rlhf-paraphrase-types","html_url":"https://github.com/cluebbers/dpo-rlhf-paraphrase-types","last_synced_at":"2025-06-07T01:30:56.896Z","status":null,"issues_count":0,"pull_requests_count":0,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":0,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2025-06-07T01:30:37.735Z","updated_at":"2025-06-07T01:30:56.896Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/cluebbers%2Fdpo-rlhf-paraphrase-types/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":10087320,"issues_count":31306968,"pull_requests_count":96469683,"authors_count":10696025,"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,"PublicEvent":1},"last_year":{"PushEvent":1,"PublicEvent":1}},"keywords":["alignment","deep-learning","direct-preference-optimization","human-feedback","paraphrase-generation","paraphrase-type-generation","reinforcement-learning","transformers"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-06-04T17:04:31.627Z","updated_at":"2025-06-04T17:04:31.627Z","repository_link":"https://github.com/cluebbers/dpo-rlhf-paraphrase-types/blob/main/requirements.txt","dependencies":[{"id":23453001639,"package_name":"setuptools","ecosystem":"pypi","requirements":"==75.3.0","direct":true,"kind":"runtime","optional":false},{"id":23453001640,"package_name":"accelerate","ecosystem":"pypi","requirements":"==1.1.1","direct":true,"kind":"runtime","optional":false},{"id":23453001641,"package_name":"bitsandbytes","ecosystem":"pypi","requirements":"==0.44.1","direct":true,"kind":"runtime","optional":false},{"id":23453001642,"package_name":"datasets","ecosystem":"pypi","requirements":"==3.1.0","direct":true,"kind":"runtime","optional":false},{"id":23453001643,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"==0.26.2","direct":true,"kind":"runtime","optional":false},{"id":23453001644,"package_name":"krippendorff","ecosystem":"pypi","requirements":"==0.8.0","direct":true,"kind":"runtime","optional":false},{"id":23453001675,"package_name":"matplotlib","ecosystem":"pypi","requirements":"==3.9.2","direct":true,"kind":"runtime","optional":false},{"id":23453001676,"package_name":"nltk","ecosystem":"pypi","requirements":"==3.9.1","direct":true,"kind":"runtime","optional":false},{"id":23453001677,"package_name":"numpy","ecosystem":"pypi","requirements":"==2.1.3","direct":true,"kind":"runtime","optional":false},{"id":23453001678,"package_name":"pandas","ecosystem":"pypi","requirements":"==2.2.3","direct":true,"kind":"runtime","optional":false},{"id":23453001679,"package_name":"peft","ecosystem":"pypi","requirements":"==0.13.2","direct":true,"kind":"runtime","optional":false},{"id":23453001680,"package_name":"rouge","ecosystem":"pypi","requirements":"==1.0.1","direct":true,"kind":"runtime","optional":false},{"id":23453001681,"package_name":"SciencePlots","ecosystem":"pypi","requirements":"==2.1.1","direct":true,"kind":"runtime","optional":false},{"id":23453001747,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"==1.5.2","direct":true,"kind":"runtime","optional":false},{"id":23453001748,"package_name":"scipy","ecosystem":"pypi","requirements":"==1.14.1","direct":true,"kind":"runtime","optional":false},{"id":23453001749,"package_name":"seaborn","ecosystem":"pypi","requirements":"==0.13.2","direct":true,"kind":"runtime","optional":false},{"id":23453001750,"package_name":"torch","ecosystem":"pypi","requirements":"==2.5.1","direct":true,"kind":"runtime","optional":false},{"id":23453001751,"package_name":"torchaudio","ecosystem":"pypi","requirements":"==2.5.1","direct":true,"kind":"runtime","optional":false},{"id":23453001752,"package_name":"torchvision","ecosystem":"pypi","requirements":"==0.20.1","direct":true,"kind":"runtime","optional":false},{"id":23453001753,"package_name":"transformers","ecosystem":"pypi","requirements":"==4.46.2","direct":true,"kind":"runtime","optional":false},{"id":23453001754,"package_name":"triton","ecosystem":"pypi","requirements":"==3.1.0","direct":true,"kind":"runtime","optional":false},{"id":23453001755,"package_name":"trl","ecosystem":"pypi","requirements":"==0.12.0","direct":true,"kind":"runtime","optional":false},{"id":23453001756,"package_name":"tensorboardx","ecosystem":"pypi","requirements":"==2.6.2.2","direct":true,"kind":"runtime","optional":false},{"id":23453001757,"package_name":"evaluate","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23453001758,"package_name":"optuna","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23453001759,"package_name":"parascore","ecosystem":"pypi","requirements":"==1.0.5","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:51:09.245Z","updated_at":"2025-10-07T08:14:50.200Z","avatar_url":"https://github.com/cluebbers.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/35738","html_url":"https://science.ecosyste.ms/projects/35738","bibtex_url":"https://science.ecosyste.ms/projects/35738/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/35738/export.apalike"}