Hugging Face ORG

🤗 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.

Transformers is Hugging Face's Python library with ready-to-use definitions of thousands of state-of-the-art AI models for text, images, audio, video, and multimodal tasks, load a pretrained model from the Hub and run it in a few lines of code.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Diffusers is Hugging Face's Python library for running and fine-tuning AI image, video, and audio generation models like Stable Diffusion, with simple pipelines and access to over 30,000 pretrained models.

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

Python library that lets you load thousands of public AI datasets in one line of code and process data that is too large to fit in memory, using Apache Arrow under the hood.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

PEFT is a Python library that lets you fine-tune large AI models cheaply by training only a tiny fraction of their parameters, so you can customize a model on your own data without needing expensive multi-GPU hardware.

🚀 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

Accelerate is a Hugging Face library that lets you run the same PyTorch training code on one CPU, multiple GPUs, or a multi-machine cluster by adding about five lines of setup.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

The largest collection of image recognition AI models in one library, load any of 1,000+ pretrained models with one line of Python code. The go-to toolkit for anyone building computer vision projects with PyTorch.

This repository contains the Hugging Face Agents Course.

Free online course teaching how to build AI agents using large language models and popular frameworks like smolagents, LlamaIndex, and LangGraph.

🤗 smolagents: a barebones library for agents that think in code.

Lightweight Python library for building AI agents that reason about tasks and execute them by writing and running code, with support for custom tools and any language model.

Fully open reproduction of DeepSeek-R1

Open-source training code and datasets to build your own reasoning AI model that shows its thinking step-by-step, inspired by DeepSeek-R1's breakthrough approach.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

An open-source Python library from Hugging Face that gives researchers and hobbyists a common platform to control robots, collect training data, and run AI decision-making models, without rebuilding incompatible plumbing for each robot.

Minimalist ML framework for Rust

A fast, lightweight machine learning framework written in Rust that lets you run AI models directly without Python, with GPU support and pre-built implementations of popular models.

State-of-the-Art Embeddings, Retrieval, and Reranking

Sentence Transformers is a Python library that converts text into numbers capturing meaning, so you can find semantically similar documents, build semantic search, or detect duplicates even with different wording.

Train transformer language models with reinforcement learning.

A Python library for fine-tuning and aligning AI language models after initial training, using techniques like supervised fine-tuning and human preference optimization.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Transformers.js lets you run Hugging Face machine-learning models directly in a browser or Node.js app with no server needed, covering text, image, audio, and multimodal tasks through a simple pipeline API.

Large Language Model Text Generation Inference

Server toolkit for running open-source large language models on your own hardware and serving them as an API. Handles batching and multi-GPU splitting to serve many users efficiently. Now in maintenance mode.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

A fast Rust-based library from Hugging Face that converts text into tokens for AI models, with easy-to-use Python, Node.js, and Ruby wrappers installable in one command.

The open source codebase powering HuggingChat

The open-source web app behind HuggingChat, run your own AI chat interface that connects to any OpenAI-compatible model endpoint, including local models via Ollama or llama.cpp.

Give your agents the power of the Hugging Face ecosystem

Ready-made instruction sets that teach AI coding assistants like Claude Code and Cursor how to train models, explore datasets, and publish work on Hugging Face, install once, then just ask your assistant to use a skill.

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

ML Intern is an open-source command-line AI assistant for machine learning work, give it a task in plain English and it writes and runs the code, with built-in access to Hugging Face models, datasets, and cloud GPU workspaces.

A course on aligning smol models.

Robust recipes to align language models with human and AI preferences

Inference and training library for high-quality TTS models.

This repo contains the Hugging Face Deep Reinforcement Learning Course.

The simplest, fastest repository for training/finetuning small-sized VLMs.

Build local voice agents with open-source models

A blazing fast inference solution for text embeddings models

Notebooks using the Hugging Face libraries 🤗

🤗 AutoTrain Advanced

Materials for the Hugging Face Diffusion Models Course

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

The Hugging Face course on Transformers

Everything about the SmolLM and SmolVLM family of models

The official Python client for the Hugging Face Hub.

Public repo for HF blog posts

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

Swift app demonstrating Core ML Stable Diffusion

Efficient few-shot learning with Sentence Transformers

Minimalistic large language model 3D-parallelism training

Open-source AI cookbook

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

Use Hugging Face with JavaScript

An interface library for RL post training with environments.

Minimalistic 4D-parallelism distributed training framework for education purpose

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

A collection of 🤗 Transformers.js demos and example applications

Papers & presentation materials from Hugging Face's internal science day

🦄 State-of-the-Art Conversational AI with Transfer Learning

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!

JavaScript Gaussian Splatting library.

Build, enrich, and transform datasets using AI models with no code

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

🔥The Web-scale GUI for MongoDB

Scalable and memory-optimized training of diffusion models

Swift Package to implement a transformers-like API in Swift

LLM powered development for VSCode

LLM powered development for Neovim

No description.

Recipes to scale inference-time compute of open models

🤗 A list of wonderful open-source projects & applications integrated with Hugging Face libraries.

A pytorch quantization backend for optimum

No description.

No description.

An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.

Use AI Agents directly in Blender.

LSP server leveraging LLMs for code completion (and more?)

Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

A cross-platform browser ML framework.

Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.

A Rust NFS Server implementation

Build compute kernels and load them from the Hub.

Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

Easily embed, cluster and semantically label text datasets

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

No description.

Docs of the Hugging Face Hub

An open collection of methodologies to help with successful training of large language models.

xet client tech, used in huggingface_hub

Collection of scripts and notebooks for OpenAI's latest GPT OSS models

An open collection of implementation tips, tricks and resources for training large language models

No description.

A powerful Python library for creating and managing isolated desktop environments using Docker containers.

🤗 Benchmark Large Language Models Reliably On Your Data

HF CLI extension to run local coding agent powered by llmfit and llama.cpp

Prune a model while finetuning or training.

Convert any Repo into an RL Environment

No description.

Where GPUs get cooked 👩‍🍳🔥

Gemma 2 optimized for your local machine.

No description.

⏰ AI conference deadline countdowns

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

Inference, Fine Tuning and many more recipes with Gemma family of models

Manage scalable open LLM inference endpoints in Slurm clusters

Training and inference on AWS Trainium and Inferentia chips.

Hugging Face MCP Server

Code for instruction-tuning Stable Diffusion.

No description.

No description.

👷 Build compute kernels

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

No description.

The home of Carbon Genomic Foundation Model 🧬

A Unity plugin for using Transformers models in Unity.

🎢 Creating and sharing simulation environments for embodied and synthetic data research

SmolVLM2 Demo

Codebase for FinePDFs

General multi-task deep RL Agent

A gym environment for PushT

Hugging Face Deep Learning Containers (DLCs) for Google Cloud

No description.

A Swift client for Hugging Face Hub and Inference Providers APIs

Inference server benchmarking tool

Modal-style sandbox API on top of Hugging Face Jobs

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

ScreenSuite - The most comprehensive benchmarking suite for GUI Agents!

The package used to build the documentation of our Hugging Face repos

A course on robotics by Hugging Face using LeRobot.

Kernel sources for https://huggingface.co/kernels-community

Research projects built on top of Transformers

This repository contains the ML For Games Course

AMD related optimizations for transformer models

No description.

🤗 LeLab: A web UI interface on top of LeRobot

Web application for visualizing robotics datasets in LeRobot format

Additional code for Stable-baselines3 to load and upload models from the Hub.

No description.

No description.

LLM powered development for IntelliJ

A VSCode extension to use Hugging Face Inference Providers in Copilot Chat

Set of auxiliary tools to use with image and video generation libaries. Mainly created to be used with diffusers

A benchmark for AI-driven CAD generation and editing

Datasets for Deep learning Personas

M4 experiment logbook

A course on context engineering with code agents.

Testbed for LLM inference with cutile-rs.

🤗 Tokenizers.js: A pure JS/TS implementation of today's most used tokenizers

No description.

Agent Skill to help convert transformer LLMs to mlx-lm

Parse LaTeX math expressions

No description.

A course on Hugging Face land

A framework for few-shot evaluation of language models.

Reviews pull requests with any OpenAI-compatible LLM

Minimal repository to demonstrate fast LoRA inference with Flux family of models.

Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery

A Swift implementation of the Xet protocol

Lightweight web UI for annotating LeRobot datasets

A huge dataset for Document Visual Question Answering

No description.

Synthetic pretraining data by rephrasing the web

Comprehensive Hugging Face Hub Library for rust

Agentic Resource Discovery Client/Server

A course on building Large Language Models

Ongoing research training transformer models at scale

No description.

No description.

Agentic framework for physics

Huggy is a Unity ML-Agents environment showcasing a dog mastering stick-catching through deep reinforcement learning.

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Hugging Face on Microsoft Azure (documentation, examples and more)

Issue bot for transformers

Official Documentation for HUGS

A course on building and sharing AI datasets

Chat Template Playground for testing & debugging

The official Python SDK and CLI for the Dell Enterprise Hub

No description.

No description.

Run GitHub Actions on Hugging Face Jobs

Official Helm Chart for HUGS

CSI driver for mounting HuggingFace Buckets and Repos as FUSE filesystems

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Backend for the llm-perf leaderboard space

Lint modeling, modular, and configuration files for structural conventions

Tools for merging pretrained large language models.

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

LLM Academy

Benchmarks for the HuggingFace Kernel Community kernels

A framework to capture, analyse and export agentic sessions

Lightweight ahead-of-time compilation toolkit for PyTorch. Used heavily in demos with ZeroGPU on HF Spaces.

No description.

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Collection of evals for Inspect AI

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

Accelerating the development of large multimodal models (LMMs) with lmms-eval

labbench2

Additional code for Tianshou to load and upload models from the Hub.

CI tools for Transformers

Scalable toolkit for efficient model reinforcement

Sources for test kernels at https://huggingface.co/kernels-test

🤗 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.

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Asses and details for HUGS on GCP

No description.

A library for training and deploying machine learning models on Amazon SageMaker

Slurm-Mail is a drop in replacement for Slurm's e-mails to give users much more information about their jobs compared to the standard Slurm e-mails.