# facebookresearch/tribev2

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

Repository: https://github.com/facebookresearch/tribev2
Canonical: https://ross.abutalabs.com/products/tribev2
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2026-06-23T13:23:33+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 11
- inputs: {"age_days": 162, "days_push": 71, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3172, forks 694 (observed 2026-08-28T04:07:47.459252+00:00)

## What it is
TRIBE v2 is a multimodal deep learning model from Meta AI that predicts fMRI brain responses to naturalistic video, audio, and text stimuli. It provides pretrained weights, an inference API, and training pipelines for in-silico neuroscience research.

## Use cases
- predict fMRI brain responses to videos
- model how the brain processes audio and language
- run brain encoding experiments with pretrained models
- visualize predicted activity on a cortical surface
- train a multimodal brain encoding model from scratch

## When to choose
- you need to predict brain activity from multimodal stimuli like video, audio, or text
- you are doing computational neuroscience or neural encoding research
- you want a pretrained brain encoding model with HuggingFace weights and a Colab demo

## When to avoid
- you need a clinically validated tool for medical diagnosis
- you require a permissively licensed model for commercial use (CC BY-NC 4.0)
- you lack GPU resources or fMRI domain context for training

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, nlp, audio-processing, video-processing
- domain: deep-learning, machine-learning, artificial-intelligence
- platform: python
- tags: brain-encoding, fmri, multimodal, transformer, computational-neuroscience, research-code, pytorch, neuroscience, gpu, linux

## Member repositories
- facebookresearch/tribev2 (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.459252+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 2026-08-29T18:45:28.019871+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/tribev2 (fetched 2026-08-28T04:07:47.459252+00:00, sha 1cb263cd0a92)
- Data as of 2026-08-30T08:39:29.467469+00:00.