huggingface-hub

Manage Hugging Face Hub models, datasets, and repositories via the hf CLI.

3|1|Updated Apr 19, 2024
One-click install
npx skills add https://github.com/guccang/blogclaw --skill huggingface-hub-guccang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/guccang/blogclaw/tree/main/cmd/hermes-agent/vendor/hermes_runtime/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/guccang/blogclaw --skill huggingface-hub-guccang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies the management of Hugging Face Hub resources by providing a clear reference for searching, downloading, uploading, and maintaining machine learning assets through the hf command line interface.

Core Features & Use Cases

  • Model and Dataset Management: Search, inspect, download, upload, and organize models, datasets, and Spaces on the Hugging Face Hub.
  • Hub Operations: Handle authentication, repository management, discussions, jobs, endpoints, storage buckets, caches, and automation workflows.
  • Use Case: A machine learning engineer can use this Skill to publish a trained model, retrieve datasets for experiments, or manage deployment resources directly from the terminal.

Quick Start

Use the huggingface-hub skill to help me download a model from the Hugging Face Hub and explain the required authentication steps.

Frequently Asked Questions about huggingface-hub

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

FAQPage Schema
How do I download a model from the Hugging Face Hub using the command line?

You can download a Hugging Face model using the hf CLI by executing the download command. This requires authenticating your Hub account first to ensure you have the correct access permissions for the repository.

What is the best way to manage Hugging Face Hub repositories from the terminal?

The best way to manage Hugging Face Hub repositories from the terminal is using the hf CLI. It allows you to handle repository creation, updates, and organization for machine learning assets directly in your command line environment.

Can I upload datasets to Hugging Face via command line operations?

Yes, you can upload datasets to Hugging Face via command line operations. The hf CLI supports uploading and maintaining datasets, allowing you to automate dataset publishing workflows directly from your terminal.

Does the Hugging Face CLI require authentication for downloading public models?

Hugging Face CLI authentication is required to manage repositories and access private assets. While some public models may be accessible, authenticating your account ensures full functionality for downloads, uploads, and deployment management.

How do I handle Hugging Face storage buckets and cache management in MLOps?

You handle Hugging Face storage buckets and cache management in MLOps through the hf CLI. It provides specific commands to manage your local cache and interact with cloud storage for your machine learning workflows.

Why use command line interface for Hugging Face Hub automation tasks?

Using the command line interface for Hugging Face Hub automation tasks allows seamless integration into MLOps pipelines. It enables scripted management of model deployments, dataset retrieval, and repository operations without manual web interaction.