hugging-face-cli

Manage Hugging Face Hub models, datasets, and cloud compute jobs via CLI.

1|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/yuxia214/-22 --skill hugging-face-cli-yuxia214
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-cli
Source: https://github.com/yuxia214/-22/tree/main/.cursor/skills/hugging-face-cli
Command: npx skills add https://github.com/yuxia214/-22 --skill hugging-face-cli-yuxia214

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes 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 files, managing repositories, and utilizing cloud compute resources.

Core Features & Use Cases

  • Hub Interaction: Download models, datasets, and spaces; upload your own creations.
  • Repository Management: Create, delete, and manage branches and tags for your Hub repositories.
  • Cache Control: Efficiently manage your local Hugging Face cache.
  • Cloud Compute: Run jobs on Hugging Face's GPU infrastructure.
  • Use Case: You need to download a specific version of a large language model for local fine-tuning. Use this Skill to quickly fetch the exact model weights and configuration files.

Quick Start

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

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 models and datasets from the Hugging Face Hub using a command-line interface?

To download models and datasets from the Hugging Face Hub, use the command-line interface to authenticate and execute file transfers directly fetching the required assets for local operations.

Can I manage repository branches and tags for my Hugging Face spaces via CLI?

Yes, you can manage Hugging Face Hub repositories via CLI to create, delete, and manage branches and tags for your models, datasets, and spaces directly from the terminal.

How do I run cloud compute jobs on Hugging Face GPU infrastructure?

Run cloud compute jobs on Hugging Face infrastructure by using CLI commands to authenticate, configure, and execute your tasks on available GPU resources for model training.

What is the best way to manage local Hugging Face cache when downloading large language models?

Managing local Hugging Face cache is handled directly through CLI commands, allowing you to efficiently clear, inspect, and control downloaded model files stored locally.

How do I authenticate to the Hugging Face Hub before downloading model weights?

Authenticate to the Hugging Face Hub by executing the `hf auth login` command in your terminal, establishing the credentials needed for repository operations and file transfers.

Does the Hugging Face CLI require any external dependencies to upload files to the Hub?

No external dependencies are required to upload files to the Hugging Face Hub, as the CLI operates independently to manage file transfers, repository operations, and authentication.