{"id":23162,"name":"online-data-mixing","description":"An implementation of online data mixing for the Pile dataset, based on the GPT-NeoX library.","url":"https://github.com/alon-albalak/online-data-mixing","last_synced_at":"2025-09-05T01:53:12.147Z","repository":{"id":172091928,"uuid":"648826595","full_name":"alon-albalak/online-data-mixing","owner":"alon-albalak","description":"An implementation of online data mixing for the Pile dataset, based on the GPT-NeoX library.","archived":false,"fork":false,"pushed_at":"2024-01-09T19:20:14.000Z","size":38652,"stargazers_count":7,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"pythia","last_synced_at":"2025-04-13T05:23:42.448Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"EleutherAI/gpt-neox","license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alon-albalak.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":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-06-02T23:21:22.000Z","updated_at":"2024-08-14T14:16:34.000Z","dependencies_parsed_at":"2023-10-27T00:27:16.660Z","dependency_job_id":"156837a3-cc3d-4a6c-bf82-1537e89ad759","html_url":"https://github.com/alon-albalak/online-data-mixing","commit_stats":null,"previous_names":["alon-albalak/gpt-neox","alon-albalak/online-data-mixing"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/alon-albalak/online-data-mixing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alon-albalak","download_url":"https://codeload.github.com/alon-albalak/online-data-mixing/tar.gz/refs/heads/pythia","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273699716,"owners_count":25152285,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":"alon-albalak","name":"Alon Albalak","uuid":"25569766","kind":"user","description":"PhD student, Natural Language Processing and Deep Learning","email":"","website":"https://alon-albalak.github.io/","location":"Santa Barbara, CA","twitter":"AlbalakAlon","company":null,"icon_url":"https://avatars.githubusercontent.com/u/25569766?u=d5e6f90d2bd8873fb1cd463cf0ae0d9d331fc453\u0026v=4","repositories_count":5,"last_synced_at":"2023-03-04T13:55:28.975Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/alon-albalak","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-14T19:25:59.871Z","updated_at":"2023-03-04T13:55:28.986Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alon-albalak","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alon-albalak/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"alon-albalak/online-data-mixing","html_url":"https://github.com/alon-albalak/online-data-mixing","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":"2025-09-05T01:52:01.142Z","updated_at":"2025-09-05T01:52:01.142Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/alon-albalak%2Fonline-data-mixing/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":10082226,"issues_count":31213887,"pull_requests_count":96046612,"authors_count":10694202,"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":2},"last_year":{"WatchEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/cpu_ci.yml","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:30.440Z","updated_at":"2023-09-26T01:28:30.440Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/.github/workflows/cpu_ci.yml","dependencies":[{"id":13940944699,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":13940944700,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/docker_build.yml","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:30.586Z","updated_at":"2023-09-26T01:28:30.586Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/.github/workflows/docker_build.yml","dependencies":[{"id":13940944731,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":13940944732,"package_name":"crazy-max/ghaction-docker-meta","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":13940944733,"package_name":"docker/setup-qemu-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":13940944734,"package_name":"docker/setup-buildx-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":13940944735,"package_name":"docker/login-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":13940944736,"package_name":"docker/build-push-action","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/pull_request.yml","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:30.682Z","updated_at":"2023-09-26T01:28:30.682Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/.github/workflows/pull_request.yml","dependencies":[{"id":13940944754,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":13940944755,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":13940944756,"package_name":"pre-commit/action","ecosystem":"actions","requirements":"v2.0.3","direct":true,"kind":"composite","optional":false},{"id":13940944757,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"docker","filepath":"Dockerfile","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:30.730Z","updated_at":"2023-09-26T01:28:30.730Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/Dockerfile","dependencies":[{"id":13940944758,"package_name":"nvidia/cuda","ecosystem":"docker","requirements":"11.1.1-devel-ubuntu20.04","direct":true,"kind":"build","optional":false}]},{"ecosystem":"pypi","filepath":"megatron/fused_kernels/setup.py","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:30.953Z","updated_at":"2023-09-26T01:28:30.953Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/megatron/fused_kernels/setup.py","dependencies":[]},{"ecosystem":"pypi","filepath":"requirements/requirements-dev.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.055Z","updated_at":"2023-09-26T01:28:31.055Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements-dev.txt","dependencies":[{"id":13940945747,"package_name":"autopep8","ecosystem":"pypi","requirements":"==1.5.6","direct":true,"kind":"development","optional":false},{"id":13940945748,"package_name":"clang-format","ecosystem":"pypi","requirements":"==13.0.1","direct":true,"kind":"development","optional":false},{"id":13940945749,"package_name":"pre-commit","ecosystem":"pypi","requirements":"*","direct":true,"kind":"development","optional":false},{"id":13940945750,"package_name":"pytest","ecosystem":"pypi","requirements":"==6.2.3","direct":true,"kind":"development","optional":false},{"id":13940945751,"package_name":"pytest-cov","ecosystem":"pypi","requirements":"==2.11.1","direct":true,"kind":"development","optional":false},{"id":13940945752,"package_name":"pytest-forked","ecosystem":"pypi","requirements":"==1.3.0","direct":true,"kind":"development","optional":false},{"id":13940945753,"package_name":"pytest-xdist","ecosystem":"pypi","requirements":"*","direct":true,"kind":"development","optional":false},{"id":13940945754,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"development","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements-flashattention.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.304Z","updated_at":"2023-09-26T01:28:31.304Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements-flashattention.txt","dependencies":[{"id":13940945755,"package_name":"flash-attn","ecosystem":"pypi","requirements":"==0.2.2","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements-onebitadam.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.351Z","updated_at":"2023-09-26T01:28:31.351Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements-onebitadam.txt","dependencies":[{"id":13940945756,"package_name":"cupy-cuda111","ecosystem":"pypi","requirements":"==8.6.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements-sparseattention.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.468Z","updated_at":"2023-09-26T01:28:31.468Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements-sparseattention.txt","dependencies":[{"id":13940945766,"package_name":"triton","ecosystem":"pypi","requirements":"==0.4.2","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements-tensorboard.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.501Z","updated_at":"2023-09-26T01:28:31.501Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements-tensorboard.txt","dependencies":[{"id":13940945778,"package_name":"tensorboard","ecosystem":"pypi","requirements":"==2.5.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-09-26T01:28:31.626Z","updated_at":"2023-09-26T01:28:31.626Z","repository_link":"https://github.com/alon-albalak/online-data-mixing/blob/pythia/requirements/requirements.txt","dependencies":[{"id":13940945794,"package_name":"deepspeed","ecosystem":"pypi","requirements":"eb7f5cff36678625d23db8a8fe78b4a93e5d2c75","direct":true,"kind":"runtime","optional":false},{"id":13940945795,"package_name":"einops","ecosystem":"pypi","requirements":"==0.3.0","direct":true,"kind":"runtime","optional":false},{"id":13940945796,"package_name":"ftfy","ecosystem":"pypi","requirements":"==6.0.1","direct":true,"kind":"runtime","optional":false},{"id":13940945797,"package_name":"huggingface_hub","ecosystem":"pypi","requirements":"==0.11.0","direct":true,"kind":"runtime","optional":false},{"id":13940945804,"package_name":"lm_eval","ecosystem":"pypi","requirements":"==0.3.0","direct":true,"kind":"runtime","optional":false},{"id":13940945809,"package_name":"numpy","ecosystem":"pypi","requirements":"==1.22.0","direct":true,"kind":"runtime","optional":false},{"id":13940945810,"package_name":"pybind11","ecosystem":"pypi","requirements":"==2.6.2","direct":true,"kind":"runtime","optional":false},{"id":13940945811,"package_name":"regex","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":13940945812,"package_name":"sentencepiece","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":13940945813,"package_name":"six","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":13940945814,"package_name":"tiktoken","ecosystem":"pypi","requirements":"==0.1.2","direct":true,"kind":"runtime","optional":false},{"id":13940945815,"package_name":"tokenizers","ecosystem":"pypi","requirements":"==0.12.1","direct":true,"kind":"runtime","optional":false},{"id":13940945816,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":13940945817,"package_name":"wandb","ecosystem":"pypi","requirements":"==0.10.28","direct":true,"kind":"runtime","optional":false},{"id":13940945818,"package_name":"protobuf","ecosystem":"pypi","requirements":"==3.20.","direct":true,"kind":"runtime","optional":false},{"id":13940945819,"package_name":"best-download","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":13940945821,"package_name":"urllib3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:54.818Z","updated_at":"2025-10-07T08:10:52.253Z","avatar_url":"https://github.com/alon-albalak.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/23162","html_url":"https://science.ecosyste.ms/projects/23162","bibtex_url":"https://science.ecosyste.ms/projects/23162/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/23162/export.apalike"}