PyTorch, LLaMA, Detectron2, fairseq, and more
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Training Large Language Model to Reason in a Continuous Latent Space
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
An open-source tool for LLM prompt optimization.
This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).
Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Hackable and optimized Transformers building blocks, supporting a composable construction.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
A PyTorch native platform for training generative AI models
Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
Data manipulation and transformation for audio signal processing, powered by PyTorch
Reinforcement learning environments for compiler and program optimization tasks
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
On-device AI across mobile, embedded and edge for PyTorch
An implementation of a deep learning recommendation model (DLRM)
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
FAIR Chemistry's library of machine learning methods for chemistry
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Large Concept Models: Language modeling in a sentence representation space
End-to-End Object Detection with Transformers
SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"
A method to increase the speed and lower the memory footprint of existing vision transformers.
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
Datasets, Transforms and Models specific to Computer Vision
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
A flexible, high-performance 3D simulator for Embodied AI research.
Set of tools to assess and improve LLM security.
PyTorch native quantization and sparsity for training and inference
Models, data loaders and abstractions for language processing, powered by PyTorch
Hiera: A fast, powerful, and simple hierarchical vision transformer.
FAIR Sequence Modeling Toolkit 2
FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.
Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo
A deep learning library for video understanding research.
LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference
Proposes neural networks that can generate animation of virtual characters for different actions.
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Collection of common code that's shared among different research projects in FAIR computer vision team.
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
Compiler for Neural Network hardware accelerators
Code release for "Learning Video Representations from Large Language Models"
Official code Cross-Covariance Image Transformer (XCiT)
Code release for "Avatars Grow Legs Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model", CVPR 2023
Code for the Convolutional Vision Transformer (ConViT)
Deep Learning for Symbolic Mathematics
LAnguage Model Analysis
Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.
A framework for Privacy Preserving Machine Learning
A library for differentiable nonlinear optimization
Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators
Transformer training code for sequential tasks
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
A simple and effective method for detecting out-of-distribution images in neural networks.
Serve, optimize and scale PyTorch models in production
An End-To-End, Lightweight and Flexible Platform for Game Research
Translate - a PyTorch Language Library
Code for: "And the bit goes down: Revisiting the quantization of neural networks"
[ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
a Lightweight library for sequential learning agents, including reinforcement learning
PyTorch original implementation of Cross-lingual Language Model Pretraining.
Non-local Neural Networks for Video Classification
New and extensible file format for storage of large columnar datasets.
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
Library for Model Based RL
Run PyTorch LLMs locally on servers, desktop and mobile
Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.
A natural language modeling framework based on PyTorch
D2Go is a toolkit for efficient deep learning
A domain specific language to express machine learning workloads.
[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
DrQ-v2: Improved Data-Augmented Reinforcement Learning