huggingface-hub

Search, download, and upload models and datasets via the Hugging Face Hub command-line interface.

2|Updated May 22, 2026
One-click install
npx skills add https://github.com/519lab/thoth-agent --skill huggingface-hub-519lab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/519lab/thoth-agent/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/519lab/thoth-agent --skill huggingface-hub-519lab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires hf, and includes scripts (resource) components.

What problem does it solve?

This Skill simplifies the process of interacting with the Hugging Face Hub, allowing users to efficiently search, download, upload, and manage models and datasets.

Core Features & Use Cases

  • Model Management: Search for and download models directly from the Hugging Face Hub.
  • Dataset Management: Search, list, and manage datasets from the Hub.
  • Efficient Workflow: Streamline the process of model training and dataset management using a single command-line interface.
  • Use Case: Quickly find and download a pre-trained language model for a new project, or upload your own dataset for collaboration.

Quick Start

Use the huggingface-hub skill to download the 'gpt-3' model.

Frequently Asked Questions about huggingface-hub

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

FAQPage Schema
How do I download models and datasets from the Hugging Face Hub?

To download models and datasets from the Hugging Face Hub, you can use an efficient command-line interface to search and retrieve resources directly. This streamlines the process of acquiring pre-trained machine learning resources for your projects.

Can I search for pre-trained machine learning models on the Hugging Face Hub via command line?

Yes, you can search for pre-trained machine learning models on the Hugging Face Hub via command line. The interface allows you to query and list available models to find the exact architecture needed for your training workflow.

What is the best way to manage Hugging Face Hub datasets for collaboration?

The best way to manage Hugging Face Hub datasets for collaboration is using a command-line interface to search, list, and upload your data. This enables efficient dataset management and sharing within the machine learning ecosystem.

Do I need the hf package to manage Hugging Face models?

Yes, you need the hf package installed to manage Hugging Face models, as it provides the underlying command-line interface required to interact with the Hub for searching, downloading, and uploading resources.

How do I upload my own dataset to the Hugging Face ecosystem?

To upload your own dataset to the Hugging Face ecosystem, use the dedicated command-line interface to push your local data to the Hub. This simplifies dataset management and enables seamless collaboration with other data scientists.