PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Deep Learning for humans

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

Deep universal probabilistic programming with Python and PyTorch

Accessible large language models via k-bit quantization for PyTorch.

The fastai deep learning library

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Deepfakes Software For All

We write your reusable computer vision tools. 💜

💫 Industrial-strength Natural Language Processing (NLP) in Python

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠