# mlfoundations/open_flamingo

An open-source framework for training large multimodal models.

Repository: https://github.com/mlfoundations/open_flamingo
Canonical: https://ross.abutalabs.com/products/open_flamingo
Language: Python
License: MIT
License Family: permissive
Topics: computer-vision, deep-learning, in-context-learning, language-model, multimodal-learning, pytorch, flamingo
Last push: 2024-08-31T23:11:03+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1414, "days_push": 732, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4118, forks 319 (observed 2026-08-28T04:08:35.906844+00:00)

## What it is
OpenFlamingo is an open-source PyTorch implementation of DeepMind's Flamingo, a large multimodal vision-language model that interleaves images and text. It provides code for training, evaluating, and generating text with multimodal models that adapt to new tasks via in-context learning.

## Use cases
- train a multimodal vision-language model on interleaved image-text data
- generate captions for images conditioned on text
- adapt a large model to new tasks with in-context learning
- reproduce or extend DeepMind's Flamingo architecture
- evaluate vision-language models on multimodal benchmarks
- build a research prototype combining a vision encoder with a language model

## When to choose
- you need an open, trainable alternative to Flamingo for multimodal research
- you want to fine-tune or study vision-language in-context learning in PyTorch
- you need to interleave images and text in a single generative model

## When to avoid
- you need a production-ready multimodal API rather than a research codebase
- you want the latest multimodal models, as development has slowed since 2024
- you lack GPU resources for training large models

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, computer-vision, llm-training
- domain: deep-learning, large-language-models, computer-vision, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: multimodal, vision-language-model, in-context-learning, flamingo, pytorch, open-source-reimplementation, gpu, linux

## Member repositories
- mlfoundations/open_flamingo (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.906844+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:08.489998+00:00, confidence not recorded.
  - readme: https://github.com/mlfoundations/open_flamingo (fetched 2026-08-28T04:08:35.906844+00:00, sha c996a9a13e2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.