Публичный след на GitHub Hugging Face

🤗 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 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

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

This repository contains the Hugging Face Agents Course.

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

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

Fully open reproduction of DeepSeek-R1

🤗 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.

Minimalist ML framework for Rust

Train transformer language models with reinforcement learning.

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

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

Build voice agents with open-source models

Give your agents the power of the Hugging Face ecosystem

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

The open source codebase powering HuggingChat

Large Language Model Text Generation Inference

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

🚀 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 course on aligning smol models.

Robust recipes to align language models with human and AI preferences

A blazing fast inference solution for text embeddings models

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

This repo contains the Hugging Face Deep Reinforcement Learning Course.

Notebooks using the Hugging Face libraries 🤗

The Hugging Face course on Transformers

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

Everything about the SmolLM and SmolVLM family of models

The official CLI and Python client for the Hugging Face Hub.

Public repo for HF blog posts

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

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

✨Fast Coreference Resolution in spaCy with Neural Networks

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

Minimalistic large language model 3D-parallelism training

Efficient few-shot learning with Sentence Transformers

Swift app demonstrating Core ML Stable Diffusion

Open-source AI cookbook

A Python port of Pi’s minimalist coding agent.

An interface library for RL post training with environments.

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

Use Hugging Face with JavaScript

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

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

Making the community's best AI chat models available to everyone.

Swift Package to implement a transformers-like API in Swift

Описание для этого репозитория не предоставлено.

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

Описание для этого репозитория не предоставлено.

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.

Описание для этого репозитория не предоставлено.

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

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

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

A cross-platform browser ML framework.

A Rust NFS Server implementation

Build compute kernels and load them from the Hub.

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

Docs of the Hugging Face Hub

Convert any Repo into an RL Environment

xet client tech, used in huggingface_hub

Описание для этого репозитория не предоставлено.

Описание для этого репозитория не предоставлено.

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

Gemma 2 optimized for your local machine.

Durable, searchable memory of your past agent sessions.

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

Hugging Face MCP Server

Let's build better datasets, together!

Training and inference on AWS Trainium and Inferentia chips.

Описание для этого репозитория не предоставлено.

A lightweight express.js server implementing OpenAI’s Responses API, built on top of Chat Completions, powered by Hugging Face Inference Providers.

The home of Carbon Genomic Foundation Model 🧬

A gym environment for PushT

Описание для этого репозитория не предоставлено.

🤗 LeLab: A web UI interface on top of LeRobot

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

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

🤗 Optimum ExecuTorch

Research projects built on top of Transformers

Web application for visualizing robotics datasets in LeRobot format

A benchmark for AI-driven CAD generation and editing

A Command-Line Interface (CLI) and Skill to interact with Papers with Code. For agents and humans.

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

Testbed for LLM inference with cutile-rs.

Hugging Face's take home challenge for post-training internships, now open for you to try!

Описание для этого репозитория не предоставлено.

Synthetic pretraining data by rephrasing the web

A Command-Line Interface (CLI) and Skill to query Semantic Scholar. For agents and humans.

Github action to connect to tailscale

Описание для этого репозитория не предоставлено.

Run GitHub Actions on Hugging Face Jobs

Run reproducible Harbor benchmarks on Hugging Face infrastructure.

Index a repository's issue and pull-request history and serve it back as searchable project memory for coding agents

Benchmarking Knowledge Transfer in Lifelong Robot Learning

GitHub Actions to scan a container image with the Wiz CLI and register its digest with Wiz image trust