arxiv:2308.01390

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Published on Aug 2, 2023

· Submitted by

AK on Aug 4, 2023

#2 Paper of the day

Upvote

Authors:

Anas Awadalla ,

Josh Gardner ,

Jack Hessel ,

Wanrong Zhu ,

Kalyani Marathe ,

Yonatan Bitton ,

Samir Gadre ,

Jenia Jitsev ,

Simon Kornblith ,

Gabriel Ilharco ,

Mitchell Wortsman ,

Ludwig Schmidt

Abstract

OpenFlamingo, an open-source family of autoregressive vision-language models, replicates DeepMind's Flamingo performance across multiple datasets.

Generated by Qwen/Qwen2.5-Coder-32B-Instruct

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.