huggingface-hub

Manage Hugging Face models, datasets, Spaces, and endpoints via the hf CLI.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/musical-basics/hermes-build-2 --skill huggingface-hub-musical-basics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/musical-basics/hermes-build-2/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/musical-basics/hermes-build-2 --skill huggingface-hub-musical-basics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill centralizes and simplifies interaction with the Hugging Face Hub so users can find, download, upload, sync, and deploy models, datasets, Spaces, and buckets without manually navigating web interfaces or combining disparate CLI commands.

Core Features & Use Cases

  • Model and Dataset Management: Search, download, upload, duplicate, move, and inspect models and datasets stored on the Hub.
  • Deployment & Compute: Deploy and manage inference endpoints, run jobs, and monitor compute resources for MLOps workflows.
  • Storage & Automation: Manage S3-like buckets, sync large folders with resumable uploads, manage cache and webhooks, and extend automation via extensions and skills.
  • Use Case: A data scientist can use this Skill to run SQL queries against dataset parquet URLs, sync a large dataset to cloud storage, and deploy a trained model as an inference endpoint for production testing.

Quick Start

Use the huggingface-hub skill to download the model 'username/model-name' to a local folder and list its files.

Frequently Asked Questions about huggingface-hub

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download Hugging Face models and datasets using the command line?

You can download Hugging Face models and datasets by using the hf CLI to search, pull, and inspect repositories directly into your local environment, supporting automation workflows.

Can I sync large folders to Hugging Face buckets with resumable uploads?

Yes, you can sync large folders to Hugging Face buckets using resumable uploads via the hf CLI, ensuring reliable data transfer for massive datasets without restarting interrupted operations.

How do I deploy and manage Hugging Face inference endpoints for MLOps?

Deploy and manage Hugging Face inference endpoints by using the hf CLI to handle the endpoint lifecycle, monitor compute resources, and integrate model deployment directly into MLOps pipelines.

Do I need an HF_TOKEN to automate Hugging Face Hub operations?

Yes, automating Hugging Face Hub operations requires authenticated access via HF_TOKEN or CLI login to securely manage repositories, sync data, and handle endpoint lifecycle tasks.

What is the best way to run SQL queries against Hugging Face parquet datasets?

The best way to run SQL queries against Hugging Face parquet datasets is by using the hf CLI to query dataset parquet URLs directly, returning machine-readable JSON output for pipeline analysis.

Does the huggingface-hub skill support repository branching and tagging?

Yes, the huggingface-hub skill supports repository branching and tagging via the hf CLI, allowing you to manage model versions and dataset snapshots within MLOps automation workflows.