Tensors and Dynamic neural networks in Python with strong GPU acceleration

Models and examples built with TensorFlow

The simplest, fastest repository for training/finetuning medium-sized GPTs.

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

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

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

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

Let us control diffusion models!

State-of-the-art 2D and 3D Face Analysis Project

Python sample codes and textbook for robotics algorithms.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Graph Neural Network Library for PyTorch

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

Mamba SSM architecture

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

AutoML library for deep learning

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

An elegant PyTorch deep reinforcement learning library.

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

Uniform Manifold Approximation and Projection

Keras code and weights files for popular deep learning models.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

Python Stream Processing

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.