🤗 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.

🦜🔗 The platform for reliable agents.

A high-throughput and memory-efficient inference and serving engine for LLMs

A natural language interface for computers

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

Streamlit — A faster way to build and share data apps.

aider is AI pair programming in your terminal

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

OpenMMLab Detection Toolbox and Benchmark

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Fast and memory-efficient exact attention

SGLang is a fast serving framework for large language models and vision language models.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Machine Learning Engineering Open Book

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

verl: Volcano Engine Reinforcement Learning for LLMs

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

🦉 Data Versioning and ML Experiments

DALL·E Mini - Generate images from a text prompt

A list of all named GANs!

Structured Outputs

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

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

A collaboration friendly studio for NeRFs

🐍 Geometric Computer Vision Library for Spatial AI