hugging-face-cli

Execute Hugging Face Hub operations via the hf command-line interface for managing models, datasets, and spaces.

Updated Mar 2, 2026
One-click install
npx skills add https://github.com/DMT123/claude-skills-collection --skill hugging-face-cli-dmt123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-cli
Source: https://github.com/DMT123/claude-skills-collection/tree/main/plugins/huggingface/hugging-face-cli
Command: npx skills add https://github.com/DMT123/claude-skills-collection --skill hugging-face-cli-dmt123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides direct command-line access to the Hugging Face Hub, streamlining operations like downloading models, uploading datasets, managing repositories, and executing cloud compute jobs.

Core Features & Use Cases

  • Model & Dataset Management: Download, upload, and manage models, datasets, and Spaces.
  • Repository Operations: Create, delete, list, and update repositories and their contents.
  • Cloud Compute: Run jobs on Hugging Face's infrastructure, including GPU instances.
  • Use Case: You need to download a specific version of a large language model for local fine-tuning, or upload your newly trained model to the Hub for sharing.

Quick Start

Log in to your Hugging Face account using the hf auth login command.

Frequently Asked Questions about hugging-face-cli

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

FAQPage Schema
How do I download a specific version of a model from Hugging Face Hub?

To download a specific model version from Hugging Face Hub, you use the `hf` command-line interface to manage and retrieve repository contents. This streamlines downloading models for local fine-tuning.

What is the best way to upload a dataset to Hugging Face Hub via command line?

Uploading a dataset to Hugging Face Hub is best done using the `hf` CLI for repository operations. It allows you to directly upload and manage your datasets after authenticating with your account.

Can I run cloud compute jobs on Hugging Face GPU instances using the CLI?

Yes, you can run cloud compute jobs on Hugging Face infrastructure, including GPU instances, using the `hf` command-line interface. This facilitates executing jobs directly on Hub cloud resources.

How do I authenticate my Hugging Face account for command line repository management?

To authenticate your Hugging Face account for command line repository management, you execute the `hf auth login` command. This establishes the connection needed for subsequent Hub operations.

Does the Hugging Face CLI support creating and deleting Spaces?

Yes, the Hugging Face CLI supports creating, deleting, listing, and updating repositories, which includes managing Spaces. This provides direct command-line access to Hub repository structures.

Why do I need to understand Hub repository structures when using the Hugging Face CLI?

Understanding Hub repository structures is required because the `hf` command-line interface executes operations based on these structures. This ensures accurate management of models, datasets, and cache.