Models
Computer vision
Language
Multimodal
Fairseq
A sequence modeling toolkit for training custom models for translation, summarization, and other text generation tasks.
VizSeq
A research toolkit for natural language generation (translation, captioning, summarization, and more)
Hateful Memes Dataset
An open source dataset designed for the development of new systems that identify multimodal hate speech.
Reasoning
Libraries
Language
FastText
A lightweight library designed to help build scalable solutions for text representation and classification
MUSE
A Python library that enables faster development and evaluation of cross-lingual word embeddings and NLP
Reasoning
ReAgent
A platform for Large-Scale Reasoning systems (Reinforcement Learning, Contextual Bandits)
PHYRE
Benchmark for PHYsical REasoning that contains a set of simple classical mechanics puzzles in a 2D environment
TorchCraft
Enables AI research on real-time strategy (RTS) games such as StarCraft: Brood War
Frameworks and tools
Sharing our ML frameworks and tools with the community to collaborate and accelerate AI advancement
Datasets
Large-scale datasets and benchmarks for training, evaluating, and testing models to measure and advance AI progress
Demos
Our demos for anyone wanting to experience our latest research breakthroughs first hand
System cards
Multiple machine learning (ML) models that help people understand the intention, impact and limitations of our AI systems
Publications
Our library of published papers to learn about our latest AI breakthroughs and innovations
Latest Work
Our Actions
Newsletter