# facebookresearch/multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Repository: https://github.com/facebookresearch/multimodal
Canonical: https://ross.abutalabs.com/products/multimodal
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2026-08-24T15:05:20+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 1679, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1732, forks 174 (observed 2026-08-28T04:05:28.793331+00:00)

## What it is
TorchMultimodal is a PyTorch library from Meta for training state-of-the-art multimodal multi-task models at scale, covering both content understanding and generative models. It provides modular building blocks (fusion layers, losses, datasets), pretrained model classes like CLIP, FLAVA, BLIP-2, and DALL-E 2, and example scripts replicating published research baselines.

## Use cases
- train a multimodal vision-language model at scale
- fine-tune CLIP or FLAVA on my own dataset
- replicate BLIP-2 or CoCa research baselines in PyTorch
- build a text-to-image diffusion model like DALL-E 2
- get pretrained weights for multimodal models
- train an audio MAE model
- compose custom fusion layers and losses for multi-task learning

## When to choose
- you want PyTorch-native implementations of state-of-the-art multimodal models with pretrained weights
- you need modular, composable building blocks for multimodal research
- you want scalable training baselines for vision-language or generative multimodal tasks

## When to avoid
- you need a production inference API rather than a research training library
- you want a framework-agnostic or non-PyTorch solution
- you need a stable, fully supported product rather than a beta research library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, deep-learning, artificial-intelligence, computer-vision
- platform: python
- tags: pytorch, multimodal, vision-language, diffusion-models, pretrained-models, research, natural-language-processing, gpu, linux

## Member repositories
- facebookresearch/multimodal (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.793331+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 2026-08-30T03:31:30.495928+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/multimodal (fetched 2026-08-28T04:05:28.793331+00:00, sha d67eb68a5bde)
- Data as of 2026-08-30T08:39:29.467469+00:00.