# Huggingface Docs Hub

> [!TIP]

## Pages

- [Academia Hub](academia-hub.md): [!TIP]
- [Using _Adapters_ at Hugging Face](adapters.md): Note: _Adapters_ has replaced the`adapter-transformers`library and is fully compatible in terms of model weights. S...
- [Advanced Compute Options](advanced-compute-options.md): [!WARNING]
- [Agents and the `hf` CLI](agents-cli.md): Coding agents like Claude Code, OpenAI Codex, or Open Code are excellent at using the CLI to interact with the Hub th...
- [Hugging Face MCP Server](agents-mcp.md): The Hugging Face MCP (Model Context Protocol) Server connects your MCP‑compatible AI assistant (for example Codex, Cu...
- [Agents on the Hub](agents-overview.md): Hugging Face provides tools and protocols that connect AI agents directly to the Hub. Whether you're chatting with Cl...
- [Agents on the Hub](agents.md): This page compiles all the libraries and tools Hugging Face offers for agentic workflows:
- [Using AllenNLP at Hugging Face](allennlp.md): `allennlp`is a NLP library for developing state-of-the-art models on different linguistic tasks. It provides high-le...
- [Hub API Endpoints](api.md): We have open endpoints that you can use to retrieve information from the Hub as well as perform certain actions such ...
- [Using Asteroid at Hugging Face](asteroid.md): `asteroid`is a Pytorch toolkit for audio source separation. It enables fast experimentation on common datasets with ...
- [Audit Logs](audit-logs.md): [!WARNING]
- [Using BERTopic at Hugging Face](bertopic.md): [BERTopic](https://github.com/MaartenGr/BERTopic) is a topic modeling framework that leverages 🤗 transformers and c-T...
- [Billing](billing.md): At Hugging Face, we build a collaboration platform for the ML community (i.e., the Hub) and monetize by providing adv...
- [Collections](collections.md): Use Collections to group repositories from the Hub (Models, Datasets, Spaces and Papers) on a dedicated page.
- [Data Studio](data-studio.md): Each dataset page includes a table with the contents of the dataset, arranged by pages of 100 rows. You can navigate ...
- [Uploading datasets](datasets-adding.md): The [Hub](https://huggingface.co/datasets) is home to an extensive collection of community-curated and research datas...
- [Argilla](datasets-argilla.md): Argilla is a collaboration tool for AI engineers and domain experts who need to build high quality datasets for their...
- [Audio Dataset](datasets-audio.md): This guide will show you how to configure your dataset repository with audio files. You can find accompanying example...
- [Dataset Cards](datasets-cards.md): Each dataset may be documented by the`README.md`file in the repository. This file is called a **dataset card**, and...
- [Daft](datasets-daft.md): [Daft](https://daft.ai/) is a high-performance data engine providing simple and reliable data processing for any moda...
- [Dask](datasets-dask.md): [Dask](https://www.dask.org/?utm_source=hf-docs) is a parallel and distributed computing library that scales the exis...
- [Data files Configuration](datasets-data-files-configuration.md): There are no constraints on how to structure dataset repositories.
- [Distilabel](datasets-distilabel.md): Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipel...
- [Datasets Download Stats](datasets-download-stats.md): Counting the number of downloads for datasets is not a trivial task, as a single dataset repository might contain mul...
- [Downloading datasets](datasets-downloading.md): If a dataset on the Hub is tied to a [supported library](./datasets-libraries), loading the dataset can be done in ju...
- [Authentication for private and gated datasets](datasets-duckdb-auth.md): To access private or gated datasets, you need to configure your Hugging Face Token in the DuckDB Secrets Manager.
- [Combine datasets and export](datasets-duckdb-combine-and-export.md): In this section, we'll demonstrate how to combine two datasets and export the result. The first dataset is in CSV for...
- [Query datasets](datasets-duckdb-select.md): Querying datasets is a fundamental step in data analysis. Here, we'll guide you through querying datasets using vario...
- [Perform SQL operations](datasets-duckdb-sql.md): Performing SQL operations with DuckDB opens up a world of possibilities for querying datasets efficiently. Let's dive...
- [Perform vector similarity search](datasets-duckdb-vector-similarity-search.md): The Fixed-Length Arrays feature was added in DuckDB version 0.10.0. This lets you use vector embeddings in DuckDB tab...
- [DuckDB](datasets-duckdb.md): [DuckDB](https://github.com/duckdb/duckdb) is an in-process SQL [OLAP](https://en.wikipedia.org/wiki/Online_analytica...
- [Editing datasets](datasets-editing.md): The [Hub](https://huggingface.co/datasets) enables collaborative curation of community and research datasets. We enco...
- [Embedding Atlas](datasets-embedding-atlas.md): [Embedding Atlas](https://apple.github.io/embedding-atlas/) is an interactive visualization tool for exploring large ...
- [fenic](datasets-fenic.md): [fenic](https://github.com/typedef-ai/fenic) is a PySpark-inspired DataFrame framework designed for building producti...
- [FiftyOne](datasets-fiftyone.md): FiftyOne is an open-source toolkit for curating, visualizing, and
- [File names and splits](datasets-file-names-and-splits.md): To host and share your dataset, create a dataset repository on the Hugging Face Hub and upload your data files.
- [Gated datasets](datasets-gated.md): To give more control over how datasets are used, the Hub allows datasets authors to enable **access requests** for th...
- [Image Dataset](datasets-image.md): This guide will show you how to configure your dataset repository with image files. You can find accompanying example...
- [Lance](datasets-lance.md): [Lance](https://lance.org) is an open multimodal lakehouse table format for AI. You can use Hugging Face paths (`hf:/...
- [Libraries](datasets-libraries.md): The Datasets Hub has support for several libraries in the Open Source ecosystem.
- [Manual Configuration](datasets-manual-configuration.md): This guide will show you how to configure a custom structure for your dataset repository. The [companion collection o...
- [Datasets Overview](datasets-overview.md): The Hugging Face Hub hosts a [large number of community-curated datasets](https://huggingface.co/datasets) for a dive...
- [Pandas](datasets-pandas.md): [Pandas](https://github.com/pandas-dev/pandas) is a widely used Python data analysis toolkit.
- [Authentication](datasets-polars-auth.md): In order to access private or gated datasets, you need to authenticate first. Authentication works by providing an ac...
- [File formats](datasets-polars-file-formats.md): Polars supports the following file formats when reading from Hugging Face:
- [Transforming your dataset](datasets-polars-operations.md): On this page we'll guide you through some of the most common operations used when doing data analysis. This is only a...
- [Optimizations](datasets-polars-optimizations.md): We briefly touched upon the difference between lazy and eager evaluation. On this page we will show how the lazy API ...
- [Polars](datasets-polars.md): [Polars](https://pola.rs/) is an in-memory DataFrame library on top of an [OLAP](https://en.wikipedia.org/wiki/Online...
- [PyArrow](datasets-pyarrow.md): [Arrow](https://github.com/apache/arrow) is a columnar format and a toolbox for fast data interchange and in-memory a...
- [Spark](datasets-spark.md): Spark enables real-time, large-scale data processing in a distributed environment.
- [Streaming datasets](datasets-streaming.md): If a dataset on the Hub is compatible with a [supported library](./datasets-libraries) that allows streaming from Hug...
- [Hugging Face Dataset Upload Decision Guide](datasets-upload-guide-llm.md): [!TIP]
- [Using 🤗 Datasets](datasets-usage.md): Once you've found an interesting dataset on the Hugging Face Hub, you can load the dataset using 🤗 Datasets. You can ...
- [Video Dataset](datasets-video.md): This guide will show you how to configure your dataset repository with video files.
- [Configure the Dataset Viewer](datasets-viewer-configure.md): The Dataset Viewer supports many [data files formats](./datasets-adding#file-formats), from text to tabular and from ...
- [Embed the Dataset Viewer in a webpage](datasets-viewer-embed.md): You can embed the Dataset Viewer in your own webpage using an iframe.
- [SQL Console: Query Hugging Face datasets in your browser](datasets-viewer-sql-console.md): You can run SQL queries on the dataset in the browser using the SQL Console. The SQL Console is powered by [DuckDB](h...
- [WebDataset](datasets-webdataset.md): [WebDataset](https://github.com/webdataset/webdataset) is a library for writing I/O pipelines for large datasets.
- [Datasets](datasets.md): The Hugging Face Hub is home to a growing collection of datasets that span a variety of domains and tasks. These docs...
- [DDUF](dduf.md): DDUF (**D**DUF’s **D**iffusion **U**nified **F**ormat) is a single-file format for diffusion models that aims to unif...
- [Deduplication](deduplication.md): Xet-enabled repositories utilize [content-defined chunking (CDC)](https://huggingface.co/blog/from-files-to-chunks) t...
- [Using 🧨 `diffusers` at Hugging Face](diffusers.md): Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and eve...
- [Digital Object Identifier (DOI)](doi.md): The Hugging Face Hub offers the possibility to generate DOI for your models or datasets. DOIs (Digital Object Identif...
- [Advanced Security](enterprise-hub-advanced-security.md): [!WARNING]
- [Advanced Single Sign-On (SSO)](enterprise-hub-advanced-sso.md): [!WARNING]
- [Analytics](enterprise-hub-analytics.md): [!WARNING]
- [Blog Articles for Organizations](enterprise-hub-blog-articles.md): [!WARNING]
- [Datasets](enterprise-hub-datasets.md): [!WARNING]
- [Gating Group Collections](enterprise-hub-gating-group-collections.md): [!WARNING]
- [Network Security](enterprise-hub-network-security.md): [!WARNING]
- [Resource groups](enterprise-hub-resource-groups.md): [!WARNING]
- [User Provisioning (SCIM)](enterprise-hub-scim.md): [!WARNING]
- [Tokens Management](enterprise-hub-tokens-management.md): [!WARNING]
- [Team & Enterprise plans](enterprise-hub.md): [!TIP]
- [Single Sign-On (SSO)](enterprise-sso.md): [!WARNING]
- [Using ESPnet at Hugging Face](espnet.md): `espnet`is an end-to-end toolkit for speech processing, including automatic speech recognition, text to speech, spee...
- [Evaluation Results](eval-results.md): [!WARNING]
- [Using fastai at Hugging Face](fastai.md): `fastai`is an open-source Deep Learning library that leverages PyTorch and Python to provide high-level components t...
- [Using Flair at Hugging Face](flair.md): [Flair](https://github.com/flairNLP/flair) is a very simple framework for state-of-the-art NLP.
- [GGUF usage with GPT4All](gguf-gpt4all.md): [GPT4All](https://gpt4all.io/) is an open-source LLM application developed by [Nomic](https://nomic.ai/). Version 2.7...
- [GGUF usage with llama.cpp](gguf-llamacpp.md): [!TIP]
- [GGUF](gguf.md): Hugging Face Hub supports all file formats, but has built-in features for [GGUF format](https://github.com/ggerganov/...
- [Hugging Face MCP Server](hf-mcp-server.md): The Hugging Face MCP (Model Context Protocol) Server connects your MCP‑compatible AI assistant (for example Codex, Cu...
- [Hugging Face Hub documentation](index.md): The Hugging Face Hub is a platform with over 2M models, 500k datasets, and 1M demo apps (Spaces), all open source and...
- [Configuration](jobs-configuration.md): You need to be authenticated with`hf auth login`to run Jobs, and use a token with the permission to start and manag...
- [Jobs Overview](jobs-overview.md): Run compute jobs on Hugging Face infrastructure with a familiar UV & Docker-like interface!
- [Quickstart](jobs-quickstart.md): In this guide you will run a Job to fine-tune an open source model on Hugging Face infrastructure in only a few minutes.
- [Webhooks Automation](jobs-webhooks.md): Webhooks allow you to listen for new changes on specific repositories or to all repositories belonging to particular ...
- [Using Keras at Hugging Face](keras.md): Keras is an open-source multi-backend deep learning framework, with support for JAX, TensorFlow, and PyTorch. You can...
- [Backward Compatibility with LFS](legacy-git-lfs.md): Uploads from legacy / non‑Xet‑aware clients still follow the standard Git LFS path, even if the repo is already Xet-b...
- [Use AI Models Locally](local-apps.md): You can run AI models from the Hub locally on your machine. This means that you can benefit from these advantages:
- [Using ML-Agents at Hugging Face](ml-agents.md): `ml-agents`is an open-source toolkit that enables games and simulations made with Unity to serve as environments for...
- [Using mlx-image at Hugging Face](mlx-image.md): [`mlx-image`](https://github.com/riccardomusmeci/mlx-image) is an image models library developed by [Riccardo Musmeci...
- [Using MLX at Hugging Face](mlx.md): [MLX](https://github.com/ml-explore/mlx) is a model training and serving framework for Apple silicon made by Apple Ma...
- [Annotated Model Card Template](model-card-annotated.md): Fully filling out a model card requires input from a few different roles. (One person may have more than one role.) ...
- [Appendix](model-card-appendix.md): _Full text responses to key questions_
- [Model Card Guidebook](model-card-guidebook.md): Model cards are an important documentation and transparency framework for machine learning models. We believe that mo...
- [THE LANDSCAPE OF ML DOCUMENTATION TOOLS](model-card-landscape-analysis.md): The development of the model cards framework in 2018 was inspired by the major documentation framework efforts of Dat...
- [Displaying carbon emissions for your model](model-cards-co2.md): Training ML models is often energy-intensive and can produce a substantial carbon footprint, as described by [Strubel...
- [Model Card components](model-cards-components.md): **Model Card Components** are special elements that you can inject directly into your Model Card markdown to display ...
- [User Studies](model-cards-user-studies.md): During our investigation into the landscape of model documentation tools (data cards etc), we noted how different sta...
- [Model Cards](model-cards.md): Model cards are files that accompany the models and provide handy information. Under the hood, model cards are simple...
- [Model(s) Release Checklist](model-release-checklist.md): The [Hugging Face Hub](https://huggingface.co/models) is the go-to platform for sharing machine learning models.
- [Integrate your library with the Hub](models-adding-libraries.md): The Hugging Face Hub aims to facilitate sharing machine learning models, checkpoints, and artifacts. This endeavor in...
- [Advanced Topics](models-advanced.md): - [Integrate your library with the Hub](./models-adding-libraries)
- [Models Download Stats](models-download-stats.md): Counting the number of downloads for models is not a trivial task, as a single model repository might contain multipl...
- [Downloading models](models-downloading.md): If a model on the Hub is tied to a [supported library](./models-libraries), loading the model can be done in just a f...
- [Models Frequently Asked Questions](models-faq.md): It's up to the person who uploaded the model to include the training information! A user can [specify](./model-cards#...
- [Gated models](models-gated.md): To give more control over how models are used, the Hub allows model authors to enable **access requests** for their m...
- [Inference Providers](models-inference.md): Hugging Face's model pages have pay-as-you-go inference for thousands of models, so you can try them all out right in...
- [Libraries](models-libraries.md): The Hub has support for dozens of libraries in the Open Source ecosystem. Thanks to the`huggingface_hub`Python libr...
- [Tasks](models-tasks.md): Tasks, or pipeline types, describe the "shape" of each model's API (inputs and outputs) and are used to determine whi...
- [The Model Hub](models-the-hub.md): The Model Hub is where the members of the Hugging Face community can host all of their model checkpoints for simple s...
- [Uploading models](models-uploading.md): To upload models to the Hub, you'll need to create an account at [Hugging Face](https://huggingface.co/join). Models ...
- [Widget Examples](models-widgets-examples.md): Note that each widget example can also optionally describe the corresponding model output, directly in the`output`p...
- [Widgets](models-widgets.md): Many model repos have a widget that allows anyone to run inferences directly in the browser. These widgets are powere...
- [Models](models.md): The Hugging Face Hub hosts many models for a [variety of machine learning tasks](https://huggingface.co/tasks). Model...
- [Moderation](moderation.md): [!TIP]
- [Jupyter Notebooks on the Hugging Face Hub](notebooks.md): [Jupyter notebooks](https://jupyter.org/) are a very popular format for sharing code and data analysis for machine le...
- [Notifications](notifications.md): Notifications allow you to know when new activities (**Pull Requests or discussions**) happen on models, datasets, an...
- [Sign in with Hugging Face](oauth.md): You can use the HF OAuth / OpenID connect flow to create a **"Sign in with HF"** flow in any website or App.
- [Use Ollama with any GGUF Model on Hugging Face Hub](ollama.md): 🆕 You can now also run private GGUFs from the Hugging Face Hub.
- [Using OpenCLIP at Hugging Face](open-clip.md): [OpenCLIP](https://github.com/mlfoundations/open_clip) is an open-source implementation of OpenAI's CLIP.
- [Organization cards](organizations-cards.md): You can create an organization card to help users learn more about what your organization is working on and how users...
- [Managing organizations](organizations-managing.md): Visit the [New Organization](https://hf.co/organizations/new) form to create an organization.
- [Access control in organizations](organizations-security.md): [!TIP]
- [Organizations](organizations.md): The Hugging Face Hub offers **Organizations**, which can be used to group accounts and manage datasets, models, and S...
- [Organizations, Security, and the Hub API](other.md): - [Organizations](./organizations)
- [Xet History & Overview](overview.md): [In August 2024 Hugging Face acquired XetHub](https://huggingface.co/blog/xethub-joins-hf), a [seed-stage startup bas...
- [Using PaddleNLP at Hugging Face](paddlenlp.md): Leveraging the [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) framework, [`PaddleNLP`](https://github.com/Pad...
- [Paper Pages](paper-pages.md): Paper pages allow people to find artifacts related to a paper such as models, datasets and apps/demos (Spaces). Paper...
- [Using PEFT at Hugging Face](peft.md): 🤗 [Parameter-Efficient Fine-Tuning (PEFT)](https://huggingface.co/docs/peft/index) is a library for efficiently adapt...
- [The HF PRO subscription 🔥](pro.md): The PRO subscription unlocks essential features for serious users, including:
- [Hub Rate limits](rate-limits.md): To protect our platform's integrity and ensure availability to as many AI community members as possible, we enforce r...
- [Getting Started with Repositories](repositories-getting-started.md): This beginner-friendly guide will help you get the basic skills you need to create and manage your repository on the ...
- [Licenses](repositories-licenses.md): You are able to add a license to any repo that you create on the Hugging Face Hub to let other users know about the p...
- [Next Steps](repositories-next-steps.md): These next sections highlight features and additional information that you may find useful to make the most out of th...
- [Pull requests and Discussions](repositories-pull-requests-discussions.md): Hub Pull requests and Discussions allow users to do community contributions to repositories. Pull requests and discus...
- [Repository Settings](repositories-settings.md): You can choose a repository's visibility when you create it, and any repository that you own can have its visibility ...
- [Repositories](repositories.md): Models, Spaces, and Datasets are hosted on the Hugging Face Hub as [Git repositories](https://git-scm.com/about), whi...
- [Using RL-Baselines3-Zoo at Hugging Face](rl-baselines3-zoo.md): `rl-baselines3-zoo`is a training framework for Reinforcement Learning using Stable Baselines3.
- [Using sample-factory at Hugging Face](sample-factory.md): [`sample-factory`](https://github.com/alex-petrenko/sample-factory) is a codebase for high throughput asynchronous re...
- [Search](search.md): You can easily search anything on the Hub with **Full-text search**. We index model cards, dataset cards, and Spaces ...
- [Two-Factor Authentication (2FA)](security-2fa.md): Using two-factor authentication verifies a user's identity with two methods, adding extra security to ensure only aut...
- [Git over SSH](security-git-ssh.md): You can access and write data in repositories on huggingface.co using SSH (Secure Shell Protocol). When you connect v...
- [Signing commits with GPG](security-gpg.md): `git`has an authentication layer to control who can push commits to a repo, but it does not authenticate the actual ...
- [Third-party scanner: JFrog](security-jfrog.md): [JFrog](https://jfrog.com/)'s security scanner detects malicious behavior in machine learning models.
- [Malware Scanning](security-malware.md): We run every file of your repositories through a [malware scanner](https://www.clamav.net/).
- [Pickle Scanning](security-pickle.md): Pickle is a widely used serialization format in ML. Most notably, it is the default format for PyTorch model weights.
- [Third-party scanner: Protect AI](security-protectai.md): [!TIP]
- [Advanced Access Control in Organizations with Resource Groups](security-resource-groups.md): [!WARNING]
- [Secrets Scanning](security-secrets.md): It is important to manage [your secrets (env variables) properly](./spaces-overview#managing-secrets). The most commo...
- [How to configure OIDC SSO with Azure](security-sso-azure-oidc.md): This guide will use Azure as the SSO provider and the Open ID Connect (OIDC) protocol as our preferred identity proto...
- [How to configure SAML SSO with Azure](security-sso-azure-saml.md): In this guide, we will use Azure as the SSO provider and with the Security Assertion Markup Language (SAML) protocol ...
- [How to configure SCIM with Microsoft Entra ID (Azure AD)](security-sso-entra-id-scim.md): This guide explains how to set up automatic user and group provisioning between Microsoft Entra ID and your Hugging F...
- [How to configure OIDC SSO with Google Workspace](security-sso-google-oidc.md): In this guide, we will use Google Workspace as the SSO provider with the OpenID Connect (OIDC) protocol as our prefer...
- [How to configure SAML SSO with Google Workspace](security-sso-google-saml.md): In this guide, we will use Google Workspace as the SSO provider and with the Security Assertion Markup Language (SAML...
- [How to configure OIDC SSO with Okta](security-sso-okta-oidc.md): In this guide, we will use Okta as the SSO provider and with the Open ID Connect (OIDC) protocol as our preferred ide...
- [How to configure SAML SSO with Okta](security-sso-okta-saml.md): In this guide, we will use Okta as the SSO provider and with the Security Assertion Markup Language (SAML) protocol a...
- [How to configure SCIM with Okta](security-sso-okta-scim.md): This guide explains how to set up SCIM user and group provisioning between Okta and your Hugging Face organization us...
- [Single Sign-On (SSO)](security-sso.md): The Hugging Face Hub gives you the ability to implement mandatory Single Sign-On (SSO) for your organization.
- [User access tokens](security-tokens.md): User Access Tokens are the preferred way to authenticate an application or notebook to Hugging Face services. You can...
- [Security](security.md): The Hugging Face Hub offers several security features to ensure that your code and data are secure. Beyond offering [...
- [Using Sentence Transformers at Hugging Face](sentence-transformers.md): `sentence-transformers`is a library that provides easy methods to compute embeddings (dense vector representations) ...
- [Using SetFit with Hugging Face](setfit.md): SetFit is an efficient and prompt-free framework for few-shot fine-tuning of [Sentence Transformers](https://sbert.ne...
- [How to Add a Space to ArXiv](spaces-add-to-arxiv.md): Demos on Hugging Face Spaces allow a wide audience to try out state-of-the-art machine
- [Advanced Topics](spaces-advanced.md): - [Using OpenCV in Spaces](./spaces-using-opencv)
- [Spaces Changelog](spaces-changelog.md): - Streamlit is no longer provided as a default built-in SDK option. Streamlit applications are now created using the ...
- [Managing Spaces with CircleCI Workflows](spaces-circleci.md): You can keep your app in sync with your GitHub repository with a **CircleCI workflow**.
- [Spaces Configuration Reference](spaces-config-reference.md): Spaces are configured through the`YAML`block at the top of the **README.md** file at the root of the repository. Al...
- [Cookie limitations in Spaces](spaces-cookie-limitations.md): In Hugging Face Spaces, applications have certain limitations when using cookies. This is primarily due to the struct...
- [Spaces Custom Domain](spaces-custom-domain.md): [!WARNING]
- [Handling Spaces Dependencies in Gradio Spaces](spaces-dependencies.md): The default Gradio Spaces environment comes with several pre-installed dependencies:
- [Spaces Dev Mode: Seamless development in Spaces](spaces-dev-mode.md): [!WARNING]
- [Embed your Space in another website](spaces-embed.md): Once your Space is up and running you might wish to embed it in a website or in your blog.
- [Featured Spaces](spaces-featured.md): Hugging Face highlights certain Spaces to make it easier for you to discover high-quality demos and examples built by...
- [How to get a user's plan and status in Spaces](spaces-get-user-plan.md): From inside a Space's iframe, you can check if a user is logged in or not on the main site, and if they have a PRO su...
- [Managing Spaces with Github Actions](spaces-github-actions.md): You can keep your app in sync with your GitHub repository with **Github Actions**. Remember that for files larger tha...
- [Using GPU Spaces](spaces-gpus.md): You can upgrade your Space to use a GPU accelerator using the _Settings_ button in the top navigation bar of the Spac...
- [How to handle URL parameters in Spaces](spaces-handle-url-parameters.md): You can use URL query parameters as a data sharing mechanism, for instance to be able to deep-link into an app with a...
- [Spaces as MCP servers](spaces-mcp-servers.md): You can **expose any public Space that has a visible`MCP`badge into a callable tool** that will be available in any...
- [More ways to create Spaces](spaces-more-ways-to-create.md): You can duplicate a Space by clicking the three dots at the top right and selecting **Duplicate this Space**. Learn m...
- [Adding a Sign-In with HF button to your Space](spaces-oauth.md): You can enable a built-in sign-in flow in your Space by seamlessly creating and associating an [OAuth/OpenID connect]...
- [Using Spaces for Organization Cards](spaces-organization-cards.md): Organization cards are a way to describe your organization to other users. They take the form of a`README.md`static...
- [Spaces Overview](spaces-overview.md): Hugging Face Spaces make it easy for you to create and deploy ML-powered demos in minutes. Watch the following video ...
- [Run with Docker](spaces-run-with-docker.md): You can use Docker to run most Spaces locally.
- [Aim on Spaces](spaces-sdks-docker-aim.md): **Aim** is an easy-to-use & supercharged open-source experiment tracker. Aim logs your training runs and enables a be...
- [Argilla on Spaces](spaces-sdks-docker-argilla.md): Argilla is a free and open source tool to build and iterate on data for AI. It can be deployed on the Hub with a few ...
- [ChatUI on Spaces](spaces-sdks-docker-chatui.md): **HuggingChat** is an open-source interface enabling everyone to try open-source large language models such as Falcon...
- [Dash on Spaces](spaces-sdks-docker-dash.md): With Dash Open Source, you can create data apps on your laptop in pure Python, no JavaScript required.
- [Evidence on Spaces](spaces-sdks-docker-evidence.md): **Evidence** is an open-source framework designed for building data-driven applications, reports, and dashboards usin...
- [Docker Spaces Examples](spaces-sdks-docker-examples.md): We gathered some example demos in the [Spaces Examples](https://huggingface.co/SpacesExamples) organization. Please c...
- [Your First Docker Space: Text Generation with T5](spaces-sdks-docker-first-demo.md): In the following sections, you'll learn the basics of creating a Docker Space, configuring it, and deploying your cod...
- [Giskard on Spaces](spaces-sdks-docker-giskard.md): **Giskard** is an AI model quality testing toolkit for LLMs, tabular, and NLP models. It consists of an open-source P...
- [JupyterLab on Spaces](spaces-sdks-docker-jupyter.md): [JupyterLab](https://jupyter.org/) is a web-based interactive development environment for Jupyter notebooks, code, an...
- [🟧 Label Studio on Spaces](spaces-sdks-docker-label-studio.md): [Label Studio](https://labelstud.io) is an [open-source data labeling
- [Langfuse on Spaces](spaces-sdks-docker-langfuse.md): This guide shows you how to deploy Langfuse on Hugging Face Spaces and start instrumenting your LLM application for o...
- [Livebook on Spaces](spaces-sdks-docker-livebook.md): **Livebook** is an open-source tool for writing interactive code notebooks in [Elixir](https://elixir-lang.org/). It'...
- [marimo on Spaces](spaces-sdks-docker-marimo.md): [marimo](https://github.com/marimo-team/marimo) is a reactive notebook for Python that models notebooks as dataflow g...
- [Panel on Spaces](spaces-sdks-docker-panel.md): [Panel](https://panel.holoviz.org/) is an open-source Python library that lets you easily build powerful tools, dashb...
- [Shiny on Spaces](spaces-sdks-docker-shiny.md): [Shiny](https://shiny.posit.co/) is an open-source framework for building simple, beautiful, and performant data appl...
- [Tabby on Spaces](spaces-sdks-docker-tabby.md): [Tabby](https://tabby.tabbyml.com) is an open-source, self-hosted AI coding assistant. With Tabby, every team can set...
- [ZenML on Spaces](spaces-sdks-docker-zenml.md): [ZenML](https://github.com/zenml-io/zenml) is an extensible, open-source MLOps framework for creating portable, produ...
- [Basic Docker SDK Space](spaces-sdks-docker.md): Spaces accommodate custom [Docker containers](https://docs.docker.com/get-started/) for apps outside the scope of Str...
- [Gradio Spaces](spaces-sdks-gradio.md): **Gradio** provides an easy and intuitive interface for running a model from a list of inputs and displaying the outp...
- [Custom Python Spaces](spaces-sdks-python.md): [!TIP]
- [Static HTML Spaces](spaces-sdks-static.md): Spaces also accommodate custom HTML for your app instead of using Streamlit or Gradio. Set`sdk: static`inside the`...
- [Streamlit Spaces](spaces-sdks-streamlit.md): **Streamlit** gives users freedom to build a full-featured web app with Python in a *reactive* way. Your code is reru...
- [Demo Space](spaces-settings.md): You can configure your Space's appearance and other settings inside the`YAML`block at the top of the **README.md** ...
- [Disk usage on Spaces](spaces-storage.md): Every Space comes with a small amount of disk storage. This disk space is ephemeral, meaning its content will be lost...
- [Using OpenCV in Spaces](spaces-using-opencv.md): In order to use OpenCV in your Gradio or Python Spaces, you'll need to make the Space install both the Python and Deb...
- [Spaces ZeroGPU: Dynamic GPU Allocation for Spaces](spaces-zerogpu.md): ZeroGPU is a shared infrastructure that optimizes GPU usage for AI models and demos on Hugging Face Spaces. It dynami...
- [Spaces](spaces.md): [Hugging Face Spaces](https://huggingface.co/spaces) offer a simple way to host ML demo apps directly on your profile...
- [Using spaCy at Hugging Face](spacy.md): `spaCy`is a popular library for advanced Natural Language Processing used widely across industry.`spaCy`makes it e...
- [Using SpanMarker at Hugging Face](span-marker.md): [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) is a framework for training powerful Named Entity Recognitio...
- [Using SpeechBrain at Hugging Face](speechbrain.md): `speechbrain`is an open-source and all-in-one conversational toolkit for audio/speech. The goal is to create a singl...
- [Using Stable-Baselines3 at Hugging Face](stable-baselines3.md): `stable-baselines3`is a set of reliable implementations of reinforcement learning algorithms in PyTorch.
- [Using Stanza at Hugging Face](stanza.md): `stanza`is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Startin...
- [Storage limits](storage-limits.md): At Hugging Face we aim to provide the AI community with significant volumes of **free storage space for public reposi...
- [Storage Regions on the Hub](storage-regions.md): [!WARNING]
- [Using TensorBoard](tensorboard.md): TensorBoard provides tooling for tracking and visualizing metrics as well as visualizing models. All repositories tha...
- [The image is a sunflower!](tf-keras.md): `tf-keras`is the name given to Keras 2.x version. It is now hosted as a separate GitHub repo [here](https://github.c...
- [Using timm at Hugging Face](timm.md): `timm`, also known as [pytorch-image-models](https://github.com/rwightman/pytorch-image-models), is an open-source co...
- [Using `Transformers.js` at Hugging Face](transformers-js.md): Transformers.js is a JavaScript library for running 🤗 Transformers directly in your browser, with no need for a serve...
- [Using 🤗 `transformers` at Hugging Face](transformers.md): 🤗`transformers`is a library maintained by Hugging Face and the community, for state-of-the-art Machine Learning for...
- [Using Unity Sentis Models from Hugging Face](unity-sentis.md): [Unity 3D](https://unity.com/) is one of the most popular game engines in the world. [Unity Sentis](https://unity.com...
- [Using Xet Storage](using-xet-storage.md): To access a Xet-aware version of the`huggingface_hub`, simply install the latest version:
- [Webhook guide: Setup an automatic system to re-train a model when a dataset changes](webhooks-guide-auto-retrain.md): [!TIP]
- [Webhook guide: build a Discussion bot based on BLOOM](webhooks-guide-discussion-bot.md): [!TIP]
- [Webhook guide: Setup an automatic metadata quality review for models and datasets](webhooks-guide-metadata-review.md): [!TIP]
- [Webhooks](webhooks.md): [!TIP]