FAIR Sequence Modeling Toolkit 2

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Basic PyTorch / Hydra / WandB setup for the NYU SLURM cluster

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Generate embeddings from large-scale graph-structured data.

A Python toolbox for performing gradient-free optimization

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The NetHack Learning Environment

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)

A PyTorch Platform for Distributed RL

An asynchronous RL platform for congestion control in QUIC transport protocol. https://arxiv.org/abs/1910.04054.

Hydra is a framework for elegantly configuring complex applications

FAIR Self-Supervised Learning Integrated Multi-modal Environment (SSLIME)

LAnguage Model Analysis

# ParlAI Agent examples with PyTorch, Chainer and TensorFlow

Reading Wikipedia to Answer Open-Domain Questions

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

Use torch in python for deep learning.