Stars
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Label Studio is a multi-type data labeling and annotation tool with standardized output format
NumPy and SciPy on Multi-Node Multi-GPU systems
🤗 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.
Python library for converting Python calculations into rendered latex.
A game theoretic approach to explain the output of any machine learning model.
[TMLR 2025🔥] A survey for the autoregressive models in vision.
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
🐍 Geometric Computer Vision Library for Spatial AI
🧑🚀 全世界最好的LLM资料总结（语音视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Fast and Accurate ML in 3 Lines of Code
跨平台 Python 异步聊天机器人框架 / Asynchronous multi-platform chatbot framework written in Python
✨✨Latest Advances on Multimodal Large Language Models
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Creates standalone executables from Python scripts with the same performance as the original script. It is cross-platform and should work on any platform that Python runs on.
Recipes are a standard, well supported set of blueprints for machine learning engineers to rapidly train models using the latest research techniques without significant engineering overhead.Specifi…
Train your Agent model via our easy and efficient framework
C++ Requests: Curl for People, a spiritual port of Python Requests.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
An elegant PyTorch deep reinforcement learning library.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.