Stars
🤗 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.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Fully open reproduction of DeepSeek-R1
🤗 smolagents: a barebones library for agents that think in code.
Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed.
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Train transformer language models with reinforcement learning.
Large Language Model Text Generation Inference
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
A font family with a great monospaced variant for programmers.
The main repo for NLWeb, implemented in Python.
Simple, safe way to store and distribute tensors
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
The official Python client for the Hugging Face Hub.
🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …
A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗
Export Hugging Face models to Core ML and TensorFlow Lite
skops is a Python library helping you share your scikit-learn based models and put them in production
MOVED - see https://github.com/eventials/django-pjax
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
The Official Model Context Protocol (MCP) server for Kagi search & other tools.
git extension for {collaborative, communal, continual} model development