{"id":42383,"name":"transformer-reinforced-learning","description":null,"url":"https://github.com/jurgen-paul/transformer-reinforced-learning","last_synced_at":"2025-09-05T09:22:42.170Z","repository":{"id":304341271,"uuid":"1018501262","full_name":"jurgen-paul/transformer-reinforced-learning","owner":"jurgen-paul","description":null,"archived":false,"fork":false,"pushed_at":"2025-07-12T12:00:17.000Z","size":42964,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"add_spin","last_synced_at":"2025-07-12T14:22:57.398Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jurgen-paul.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-12T11:54:08.000Z","updated_at":"2025-07-12T12:00:20.000Z","dependencies_parsed_at":"2025-07-12T14:23:03.143Z","dependency_job_id":"865247d3-0ee0-4377-b24a-6a863b8a5a95","html_url":"https://github.com/jurgen-paul/transformer-reinforced-learning","commit_stats":null,"previous_names":["jurgen-paul/transformer-reinforced-learning"],"tags_count":59,"template":false,"template_full_name":null,"purl":"pkg:github/jurgen-paul/transformer-reinforced-learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jurgen-paul","download_url":"https://codeload.github.com/jurgen-paul/transformer-reinforced-learning/tar.gz/refs/heads/add_spin","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273735945,"owners_count":25158550,"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":"jurgen-paul","name":null,"uuid":"126770103","kind":"user","description":null,"email":"","website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/126770103?v=4","repositories_count":1,"last_synced_at":"2023-08-19T22:38:19.344Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/jurgen-paul","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-08-19T22:38:19.347Z","updated_at":"2023-08-19T22:38:19.347Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jurgen-paul","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jurgen-paul/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"jurgen-paul/transformer-reinforced-learning","html_url":"https://github.com/jurgen-paul/transformer-reinforced-learning","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":"2025-09-05T09:21:51.145Z","updated_at":"2025-09-05T09:21:51.145Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/jurgen-paul%2Ftransformer-reinforced-learning/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":10095926,"issues_count":31397479,"pull_requests_count":97150418,"authors_count":10700329,"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":20},"last_year":{"PushEvent":1,"CreateEvent":20}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/benchmark.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:00.057Z","updated_at":"2025-07-12T14:23:00.057Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/benchmark.yml","dependencies":[{"id":24108009126,"package_name":"xt0rted/pull-request-comment-branch","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":24108009127,"package_name":"myrotvorets/set-commit-status-action","ecosystem":"actions","requirements":"master","direct":true,"kind":"composite","optional":false},{"id":24108009128,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":24108009129,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":24108009130,"package_name":"actions/setup-node","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":24108009131,"package_name":"actions/github-script","ecosystem":"actions","requirements":"v6","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/build_documentation.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.270Z","updated_at":"2025-07-12T14:23:01.270Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/build_documentation.yml","dependencies":[]},{"ecosystem":"actions","filepath":".github/workflows/build_pr_documentation.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.334Z","updated_at":"2025-07-12T14:23:01.334Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/build_pr_documentation.yml","dependencies":[]},{"ecosystem":"actions","filepath":".github/workflows/clear_cache.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.407Z","updated_at":"2025-07-12T14:23:01.407Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/clear_cache.yml","dependencies":[{"id":24108009132,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/docker-build.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.474Z","updated_at":"2025-07-12T14:23:01.474Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/docker-build.yml","dependencies":[{"id":24108009133,"package_name":"docker/setup-buildx-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":24108009134,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":24108009135,"package_name":"docker/login-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":24108009136,"package_name":"docker/build-push-action","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/python-package-conda.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.552Z","updated_at":"2025-07-12T14:23:01.552Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/python-package-conda.yml","dependencies":[]},{"ecosystem":"actions","filepath":".github/workflows/slow-tests.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.614Z","updated_at":"2025-07-12T14:23:01.614Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/slow-tests.yml","dependencies":[{"id":24108009137,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/stale.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.682Z","updated_at":"2025-07-12T14:23:01.682Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/stale.yml","dependencies":[{"id":24108009138,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":24108009139,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/tests.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.754Z","updated_at":"2025-07-12T14:23:01.754Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/tests.yml","dependencies":[{"id":24108009140,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":24108009141,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":24108009142,"package_name":"pre-commit/action","ecosystem":"actions","requirements":"v2.0.3","direct":true,"kind":"composite","optional":false},{"id":24108009143,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":24108009144,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/upload_pr_documentation.yml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.844Z","updated_at":"2025-07-12T14:23:01.844Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/.github/workflows/upload_pr_documentation.yml","dependencies":[]},{"ecosystem":"docker","filepath":"docker/trl-latest-gpu/Dockerfile","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:01.897Z","updated_at":"2025-07-12T14:23:01.897Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/docker/trl-latest-gpu/Dockerfile","dependencies":[{"id":24108009145,"package_name":"continuumio/miniconda3","ecosystem":"docker","requirements":"latest","direct":true,"kind":"build","optional":false},{"id":24108009146,"package_name":"nvidia/cuda","ecosystem":"docker","requirements":"12.2.2-devel-ubuntu22.04","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"docker/trl-source-gpu/Dockerfile","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:02.482Z","updated_at":"2025-07-12T14:23:02.482Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/docker/trl-source-gpu/Dockerfile","dependencies":[{"id":24108009147,"package_name":"continuumio/miniconda3","ecosystem":"docker","requirements":"latest","direct":true,"kind":"build","optional":false},{"id":24108009148,"package_name":"nvidia/cuda","ecosystem":"docker","requirements":"12.2.2-devel-ubuntu22.04","direct":true,"kind":"build","optional":false}]},{"ecosystem":"pypi","filepath":"examples/research_projects/stack_llama_2/scripts/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:02.549Z","updated_at":"2025-07-12T14:23:02.549Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/examples/research_projects/stack_llama_2/scripts/requirements.txt","dependencies":[{"id":24108009149,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009150,"package_name":"trl","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009151,"package_name":"peft","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009152,"package_name":"accelerate","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009153,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009154,"package_name":"bitsandbytes","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009155,"package_name":"wandb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:02.925Z","updated_at":"2025-07-12T14:23:02.925Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/pyproject.toml","dependencies":[]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:02.978Z","updated_at":"2025-07-12T14:23:02.978Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/requirements.txt","dependencies":[{"id":24108009156,"package_name":"datasets","ecosystem":"pypi","requirements":"\u003e=1.17.0","direct":true,"kind":"runtime","optional":false},{"id":24108009157,"package_name":"torch","ecosystem":"pypi","requirements":"\u003e=1.4.0","direct":true,"kind":"runtime","optional":false},{"id":24108009158,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009159,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009160,"package_name":"accelerate","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":24108009161,"package_name":"peft","ecosystem":"pypi","requirements":"\u003e=0.3.0","direct":true,"kind":"runtime","optional":false},{"id":24108009162,"package_name":"tyro","ecosystem":"pypi","requirements":"\u003e=0.5.7","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2025-07-12T14:23:03.057Z","updated_at":"2025-07-12T14:23:03.057Z","repository_link":"https://github.com/jurgen-paul/transformer-reinforced-learning/blob/add_spin/setup.py","dependencies":[]}],"score":null,"created_at":"2025-09-04T15:51:17.244Z","updated_at":"2025-10-07T08:17:15.163Z","avatar_url":"https://github.com/jurgen-paul.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/42383","html_url":"https://science.ecosyste.ms/projects/42383","bibtex_url":"https://science.ecosyste.ms/projects/42383/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/42383/export.apalike"}