{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/openflamingo-an-open-source-framework-for","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","arxiv_id":"2308.01390","date":"2023-08-02","proceeding":null,"authors":["Anas Awadalla","Irena Gao","Josh Gardner","Jack Hessel","Yusuf Hanafy","Wanrong Zhu","Kalyani Marathe","Yonatan Bitton","Samir Gadre","Shiori Sagawa","Jenia Jitsev","Simon Kornblith","Pang Wei Koh","Gabriel Ilharco","Mitchell Wortsman","Ludwig Schmidt"],"abstract":"We introduce OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters. OpenFlamingo is an ongoing effort to produce an open-source replication of DeepMind's Flamingo models. On seven vision-language datasets, OpenFlamingo models average between 80 - 89% of corresponding Flamingo performance. This technical report describes our models, training data, hyperparameters, and evaluation suite. We share our models and code at https://github.com/mlfoundations/open_flamingo.","url_abs":"https://arxiv.org/abs/2308.01390v2","url_pdf":"https://arxiv.org/pdf/2308.01390v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"openflamingo-an-open-source-framework-for","repo_url":"https://github.com/mlfoundations/open_flamingo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"openflamingo-an-open-source-framework-for","repo_url":"https://github.com/luodian/otter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"OpenFlamingo-9B (MPT-7B)","rank_in_archive_order":221,"of":231,"metrics":{"GPT-4 score":"24.8±0.2","Params":"9B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"OpenFlamingo-9B (LLaMA-7B)","rank_in_archive_order":228,"of":231,"metrics":{"GPT-4 score":"21.8±0.1","Params":"9B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"OpenFlamingo-9B","rank_in_archive_order":24,"of":24,"metrics":{"GPT-4 score":"17.6±0.2","Params":"9B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-core-mm","task":"Visual Question Answering (VQA)","dataset":"InfiMM-Eval","model":"OpenFlamingo-v2","rank_in_archive_order":14,"of":14,"metrics":{"Abductive":"5.3","Analogical":"1.11","Deductive":"8.88","Overall score":"6.82","Params":"9B"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.01390","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}