Hugging Face

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

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

A benchmark for AI-driven CAD generation and editing

The open source codebase powering HuggingChat

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

Place where folks can contribute to 🤗 community events

Let's build better datasets, together!

HuggingFace library to process and filter large amounts of webdata

Scaling Data-Constrained Language Models

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

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

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

Faster generation with text-to-image diffusion models.

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

Durable, searchable memory of your past agent sessions.

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

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

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

Code for instruction-tuning Stable Diffusion.

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

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

Manage scalable open LLM inference endpoints in Slurm clusters

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

[](https://github.com/huggingface/Mongoku/actions/workflows/ci.yml)

✨Fast Coreference Resolution in spaCy with Neural Networks

A Rust NFS Server implementation

Pipeline for pulling and processing online language model pretraining data from the web

Open reproduction of MUSE for fast text2image generation.

An interface library for RL post training with environments.

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

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

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

Training and inference on AWS Trainium and Inferentia chips.

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

Inference and training library for high-quality TTS models.

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

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

A cross-platform browser ML framework.

Turn any repository into an RL environment for training and evaluation.

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

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

Low-latency speech-to-speech pipeline

Easily embed, cluster and semantically label text datasets

A blazing fast inference solution for text embeddings models

Provides an implementation of today's most used tokenizers, with a focus on performances and versatility.

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

Custom Hugging Face components for Visual Blocks

Use Hugging Face with JavaScript

🤗 LeLab: A web UI interface on top of LeRobot

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

🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.

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