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

08/02/2023

∙

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 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.

READ FULL TEXT

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

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Scaling Up Models and Data with and

Memorization for Good: Encryption with Autoregressive Language Models

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language

Mini-Giants: "Small" Language Models and Open Source Win-Win

QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models

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

Related Research

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Scaling Up Models and Data with and

Memorization for Good: Encryption with Autoregressive Language Models

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language

Mini-Giants: "Small" Language Models and Open Source Win-Win

QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models