{"id":146801,"name":null,"description":"Ongoing research training transformer language models at scale, including: BERT \u0026 GPT-2","url":"https://github.com/bigscience-workshop/megatron-deepspeed","last_synced_at":"2025-09-09T14:40:58.121Z","repository":{"id":37492262,"uuid":"382420841","full_name":"bigscience-workshop/Megatron-DeepSpeed","owner":"bigscience-workshop","description":"Ongoing research training transformer language models at scale, including: BERT \u0026 GPT-2","archived":false,"fork":false,"pushed_at":"2024-03-20T16:10:21.000Z","size":6622,"stargazers_count":1387,"open_issues_count":121,"forks_count":223,"subscribers_count":22,"default_branch":"main","last_synced_at":"2025-05-22T16:09:49.943Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bigscience-workshop.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":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-07-02T17:40:35.000Z","updated_at":"2025-05-22T02:43:53.000Z","dependencies_parsed_at":"2024-09-20T16:20:48.633Z","dependency_job_id":"33a23ca7-3fad-4b33-a0ba-5c640d90af82","html_url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed","commit_stats":null,"previous_names":[],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/bigscience-workshop/Megatron-DeepSpeed","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","download_url":"https://codeload.github.com/bigscience-workshop/Megatron-DeepSpeed/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274314284,"owners_count":25262606,"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":"2025-09-09T02:00:10.223Z","response_time":80,"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":"bigscience-workshop","name":"BigScience Workshop","uuid":"82455566","kind":"organization","description":"Research workshop on large language models - The Summer of Language Models 21","email":"bigscience-contact@googlegroups.com","website":"https://bigscience.huggingface.co","location":null,"twitter":"BigScienceW","company":null,"icon_url":"https://avatars.githubusercontent.com/u/82455566?v=4","repositories_count":28,"last_synced_at":"2023-03-03T19:53:10.825Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/bigscience-workshop","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-14T05:10:07.455Z","updated_at":"2023-03-03T19:53:10.861Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop/repositories"},"packages":[],"commits":{"id":1774608,"full_name":"bigscience-workshop/Megatron-DeepSpeed","default_branch":"main","committers":[{"name":"mohammad","email":"mshoeybi@nvidia.com","login":"shoeybi","count":202},{"name":"Neel Kant","email":"nkant@nvidia.com","login":"kantneel","count":139},{"name":"Stas Bekman","email":"stas00","login":"stas00","count":119},{"name":"Jared Casper","email":"jcasper@nvidia.com","login":"jaredcasper","count":65},{"name":"Deepak Narayanan","email":"dnarayanan@nvidia.com","login":"deepakn94","count":53},{"name":"Mostofa Patwary","email":"mostofa.patwary@gmail.com","login":"mpatwary","count":35},{"name":"Vijay Korthikanti","email":"vkorthikanti@nvidia.com","login":"kvareddy","count":34},{"name":"Thomas Wang","email":"24695242+thomasw21","login":"thomasw21","count":34},{"name":"Mostofa Patwary","email":"mpatwary@nvidia.com","login":null,"count":29},{"name":"Raul Puri","email":"raulp@nvidia.com","login":null,"count":24},{"name":"Teven","email":"teven.lescao@gmail.com","login":"TevenLeScao","count":20},{"name":"Boris Fomitchev","email":"bfomitchev@nvidia.com","login":"borisfom","count":19},{"name":"Evelina Bakhturina","email":"ebakhturina@nvidia.com","login":"ekmb","count":16},{"name":"Jake Tae","email":"jaesungtae@gmail.com","login":"jaketae","count":11},{"name":"Steven Steinke","email":"ststeinke@nvidia.com","login":null,"count":10},{"name":"Adam Moody","email":"moody20@llnl.gov","login":"adammoody","count":7},{"name":"Jeff Rasley","email":"jerasley@microsoft.com","login":"jeffra","count":5},{"name":"Tunji Ruwase","email":"olruwase@microsoft.com","login":"tjruwase","count":5},{"name":"SaulLu","email":"55560583+SaulLu","login":"SaulLu","count":4},{"name":"Raul Puri","email":"raulpuric@berkeley.edu","login":"raulpuric","count":4},{"name":"Conglong Li","email":"conglong.li@gmail.com","login":"conglongli","count":4},{"name":"Rewon Child","email":"rchild@nvidia.com","login":null,"count":4},{"name":"Shaden Smith","email":"shaden.smith@microsoft.com","login":null,"count":4},{"name":"Victor SANH","email":"victorsanh@gmail.com","login":"VictorSanh","count":3},{"name":"DanielHesslow","email":"Daniel.hesslow@gmail.com","login":"DanielHesslow","count":2},{"name":"Lintang Sutawika","email":"lintang@sutawika.com","login":"lintangsutawika","count":2},{"name":"Mayank Mishra","email":"32954280+mayank31398","login":"mayank31398","count":2},{"name":"Nako Sung","email":"deif79@gmail.com","login":"nakosung","count":2},{"name":"Niklas Muennighoff","email":"n.muennighoff@gmail.com","login":"Muennighoff","count":2},{"name":"Seungju Han(Wade)","email":"wade3han@gmail.com","login":"wade3han","count":2},{"name":"ontocord","email":"ontocord@gmail.com","login":"huu4ontocord","count":2},{"name":"janEbert","email":"janpublicebert@posteo.net","login":"janEbert","count":1},{"name":"Quentin Anthony","email":"qganthony@yahoo.com","login":"Quentin-Anthony","count":1},{"name":"Ofir Press","email":"ofirp@cs.washington.edu","login":"ofirpress","count":1},{"name":"Devendra Singh Sachan","email":"dsachan@nvidia.com","login":null,"count":1},{"name":"Lintang Sutawika","email":"lintang@datasaur.ai","login":null,"count":1},{"name":"root","email":"root@luna-0006.selene.nvidia.com","login":null,"count":1},{"name":"M Saiful Bari","email":"32699797+sbmaruf","login":"sbmaruf","count":1},{"name":"Kazuhiro Yamasaki","email":"kyamasaki@nvidia.com","login":"lazykyama","count":1},{"name":"Heungsub Lee","email":"heungsub@subl.ee","login":"sublee","count":1},{"name":"Hady Elsahar","email":"hadyelsahar@gmail.com","login":"hadyelsahar","count":1},{"name":"David E. Weekly","email":"david@weekly.org","login":"dweekly","count":1},{"name":"Bhavitvya Malik","email":"bhavitvya.malik@gmail.com","login":"bhavitvyamalik","count":1},{"name":"Akhilesh Gotmare","email":"dg.akhilesh@gmail.com","login":"akhileshgotmare","count":1},{"name":"Abdullah Mohammed","email":"554032+abodacs","login":"abodacs","count":1}],"total_commits":878,"total_committers":45,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":19.511111111111113,"dds":0.7699316628701595,"past_year_committers":[],"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2025-05-16T01:14:31.103Z","last_synced_commit":"8387ae17c4704f6579f88a84500b535d19d7fbbf","created_at":"2024-09-20T16:20:31.666Z","updated_at":"2025-05-16T01:14:31.119Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:17:06.873Z","repositories_count":5524511,"commits_count":868166479,"contributors_count":31942272,"owners_count":917070,"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":"bigscience-workshop/Megatron-DeepSpeed","html_url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed","last_synced_at":"2025-05-22T16:11:13.636Z","status":null,"issues_count":99,"pull_requests_count":102,"avg_time_to_close_issue":7490883.857142857,"avg_time_to_close_pull_request":642005.2771084338,"issues_closed_count":42,"pull_requests_closed_count":83,"pull_request_authors_count":24,"issue_authors_count":62,"avg_comments_per_issue":3.3737373737373737,"avg_comments_per_pull_request":4.245098039215686,"merged_pull_requests_count":57,"bot_issues_count":0,"bot_pull_requests_count":1,"past_year_issues_count":4,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":13545.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":2,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":4,"past_year_avg_comments_per_issue":0.25,"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":"2024-09-20T16:20:33.572Z","updated_at":"2025-09-02T03:56:56.006Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2FMegatron-DeepSpeed/issues","issue_labels_count":{"arch\u0026scale":13,"Good First Issue":5,"enhancement":4,"bug":2,"eval":1,"tokenization":1,"🌍 Carbon":1,"Feature Request":1,"test":1,"MLFlow":1},"pull_request_labels_count":{"enhancement":3,"arch\u0026scale":1,"multilinguality":1},"issue_author_associations_count":{"NONE":61,"MEMBER":27,"CONTRIBUTOR":5,"COLLABORATOR":4},"pull_request_author_associations_count":{"MEMBER":50,"COLLABORATOR":21,"CONTRIBUTOR":19,"NONE":12},"issue_authors":{"ibeltagy":13,"stas00":7,"thomasw21":6,"SeekPoint":3,"drxmy":3,"adammoody":3,"misska1":3,"mayank31398":2,"cdj0311":2,"henan991201":2,"TevenLeScao":2,"lvcc2018":2,"aitorormazabal":1,"sarthaklangde":1,"CloudedLeopard17":1,"coorful":1,"520jefferson":1,"tianjianjiang":1,"joan126":1,"etoilestar":1,"qazwsx042":1,"nanyyyyyy":1,"gordicaleksa":1,"sashavor":1,"yayaQAQ":1,"zll0000":1,"Heelim-Hong":1,"xuyifan-0731":1,"jaketae":1,"PhdShi":1,"Luoyang144":1,"RomanCast":1,"hyunwoongko":1,"listwebit":1,"LordEdison":1,"moseshu":1,"Bob-cby":1,"ShinoharaHare":1,"robin087":1,"dz1iang":1,"hadyelsahar":1,"AnaRhisT94":1,"alphanlp":1,"thies1006":1,"asaparov":1,"slippylolo":1,"4thGardenOfQMH":1,"saxh":1,"xiu-ze":1,"flyingdown":1,"BrucePeng92":1,"MatejUlcar":1,"nicosouth":1,"13416157913":1,"BilgehanSel":1,"pai4451":1,"chelseajohn":1,"philippmtk":1,"9LLPPLL6":1,"yinfangchen":1,"RGraham1931":1},"pull_request_authors":{"stas00":34,"adammoody":12,"thomasw21":11,"Muennighoff":8,"jaketae":4,"mayank31398":4,"lintangsutawika":3,"janEbert":3,"sbmaruf":3,"younesbelkada":3,"TevenLeScao":2,"huu4ontocord":2,"i4never":2,"VictorSanh":1,"hepj987":1,"EastInsure":1,"MagellaX":1,"philschmid":1,"luukkonenr":1,"tjruwase":1,"NouamaneTazi":1,"savitamittal1":1,"hadyelsahar":1,"xyn1201":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:00:11.778Z","repositories_count":10193878,"issues_count":32254962,"pull_requests_count":101822519,"authors_count":10740620,"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":{"NONE":3},"past_year_pull_request_author_associations_count":{"NONE":1},"past_year_issue_authors":{"9LLPPLL6":1,"RGraham1931":1,"SeekPoint":1},"past_year_pull_request_authors":{"MagellaX":1},"maintainers":[{"login":"stas00","count":41,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/stas00"},{"login":"thomasw21","count":17,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/thomasw21"},{"login":"ibeltagy","count":13,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ibeltagy"},{"login":"Muennighoff","count":8,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Muennighoff"},{"login":"mayank31398","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/mayank31398"},{"login":"jaketae","count":5,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/jaketae"},{"login":"TevenLeScao","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/TevenLeScao"},{"login":"sbmaruf","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/sbmaruf"},{"login":"janEbert","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/janEbert"},{"login":"VictorSanh","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/VictorSanh"},{"login":"tjruwase","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/tjruwase"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":4,"WatchEvent":96,"IssueCommentEvent":3,"PullRequestEvent":1,"ForkEvent":15},"last_year":{"IssuesEvent":4,"WatchEvent":96,"IssueCommentEvent":3,"PullRequestEvent":1,"ForkEvent":15}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T20:30:40.067Z","updated_at":"2022-08-08T20:30:40.067Z","repository_link":"https://github.com/bigscience-workshop/Megatron-DeepSpeed/blob/main/requirements.txt","dependencies":[{"id":693695761,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695762,"package_name":"nltk","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695763,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695764,"package_name":"parameterized","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695765,"package_name":"pybind11","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695766,"package_name":"regex","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695767,"package_name":"six","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695768,"package_name":"tensorboard","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695769,"package_name":"torch","ecosystem":"pypi","requirements":"\u003e=1.7","direct":true,"kind":"runtime","optional":false},{"id":693695770,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":693695771,"package_name":"black","ecosystem":"pypi","requirements":"==21.4b0","direct":true,"kind":"runtime","optional":false},{"id":693695772,"package_name":"isort","ecosystem":"pypi","requirements":"\u003e=5.5.4","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/main.yml","sha":null,"kind":"manifest","created_at":"2023-02-15T07:31:11.137Z","updated_at":"2023-02-15T07:31:11.137Z","repository_link":"https://github.com/bigscience-workshop/Megatron-DeepSpeed/blob/main/.github/workflows/main.yml","dependencies":[{"id":7679262849,"package_name":"aws-actions/configure-aws-credentials","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":7679262850,"package_name":"machulav/ec2-github-runner","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":7679262851,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2023-12-08T01:37:53.735Z","updated_at":"2023-12-08T01:37:53.735Z","repository_link":"https://github.com/bigscience-workshop/Megatron-DeepSpeed/blob/main/pyproject.toml","dependencies":[]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2023-12-08T01:37:54.098Z","updated_at":"2023-12-08T01:37:54.098Z","repository_link":"https://github.com/bigscience-workshop/Megatron-DeepSpeed/blob/main/setup.py","dependencies":[]}],"score":11.125202038338221,"created_at":"2025-09-09T00:23:01.135Z","updated_at":"2025-10-07T08:36:45.207Z","avatar_url":"https://github.com/bigscience-workshop.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":["transformer","speech-recognition","vlm","qwen","pytorch-transformers","pretrained-models","model-hub","glm","gemma","deepseek"],"project_url":"https://science.ecosyste.ms/api/v1/projects/146801","html_url":"https://science.ecosyste.ms/projects/146801"}