skills.rest
Chia1104
Chia1104COMMUNITY
Explore all skills by this author →
Website𝕏@chia7423GitHub

huggingface-hub

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

1|Updated Aug 11, 2026
Search Tags:#models#mlops#HuggingFace#download#datasets#hub#hf cli
One-click install
npx skills add https://github.com/Chia1104/agent-air --skill huggingface-hub-chia1104
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/Chia1104/agent-air/tree/main/skills/hermes/mlops/huggingface-hub
Command: npx skills add https://github.com/Chia1104/agent-air --skill huggingface-hub-chia1104

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Interacting with the Hugging Face Hub through the browser or raw API calls is slow and hard to automate. This Skill provides a complete reference for the modern hf command-line interface so an agent can search, download, upload, and manage Hub resources directly from the terminal. ## Core Features & Use Cases - Model and Dataset Operations: Search, inspect, download, and upload models and datasets, including SQL queries against dataset parquet files via DuckDB. - Repository and Collaboration Management: Create, duplicate, move, and delete repositories, and manage discussions and pull requests on the Hub. - Infrastructure and Automation: Deploy Inference Endpoints, run compute jobs, manage Spaces, buckets, caches, and webhooks. - Use Case: Ask the agent to download a specific model revision, upload a fine-tuned checkpoint to a new repository, and open a pull request with a comment, all through hf commands. ## Quick Start Ask the agent to download the model 'meta-llama/Llama-3-8B' from the Hugging Face Hub using the hf CLI.

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 Hugging Face Hub using the CLI?▼

Use `hf download REPO_ID` to download files from the Hub. Authenticate first with the HF_TOKEN environment variable or `hf auth login`, and add `--format json` for machine-readable output in automation scripts.

How to upload large folders to Hugging Face Hub?▼

Use `hf upload REPO_ID LOCAL_PATH`, which handles single-commit uploads and resumable uploads of large directories. The older `hf upload-large-folder` command is deprecated and should no longer be used.

What is the difference between hf and huggingface-cli?▼

The `hf` command is the modern CLI for the Hugging Face Hub and fully replaces the deprecated `huggingface-cli` command. All new workflows, including auth, repos, jobs, and endpoints, should use `hf`.

Can I run SQL queries on Hugging Face datasets?▼

Yes, `hf datasets sql SQL` executes raw SQL via DuckDB against dataset parquet URLs. You can also list parquet URLs with `hf datasets parquet` before querying.

Does the hf CLI work on Windows?▼

Yes, the hf CLI supports Linux, macOS, and Windows. Install it with the official install script and authenticate using tokens from huggingface.co/settings/tokens.

Why does hf upload fail with authentication errors?▼

Uploads fail when no valid token is configured or the token lacks write permissions for the target repository. Run `hf auth whoami` to verify the active account and `hf auth login` with a write-enabled token.

Related Skills

Explore More Software Engineering Skills→
ToqsickToqsick

huggingface-hub

Search, download, and upload models and datasets on Hugging Face Hub.

Community
Intermediate
cabeznocabezno

huggingface-hub

Manage Hugging Face Hub repositories via the hf CLI.

Community
Basic
rustykuntzrustykuntz
1

huggingface

Download models and datasets from the Hugging Face Hub.

Community
Intermediate
JasonTang99JasonTang99

hf-cli

Manage models, datasets, and repositories on the Hugging Face Hub.

Community
Intermediate