skills.rest
vivekgoquest
vivekgoquestCOMMUNITY
Explore all skills by this author →
GitHub

huggingface-hub

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

Updated Aug 22, 2026
Search Tags:#models#mlops#HuggingFace#download#datasets#hub#hf cli
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill huggingface-hub-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill huggingface-hub-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Interacting with the Hugging Face Hub through the web UI is slow for repetitive tasks like downloading models, uploading large folders, or managing repositories. This Skill provides a complete reference for the modern hf CLI so an AI agent can perform Hub operations directly from the terminal. ## Core Features & Use Cases - Model & Dataset Operations: Search, download, and upload models and datasets, including SQL queries against dataset parquet files via DuckDB. - Repository & Community Management: Create, duplicate, move, and delete repos, plus manage discussions, pull requests, and collections. - Infrastructure & Automation: Deploy Inference Endpoints, run compute Jobs, manage Spaces, S3-like buckets, caches, and webhooks. - Use Case: Ask the agent to download a specific model revision, then upload a fine-tuned version to your namespace with a single authenticated command. ## Quick Start Ask the agent to use the hf CLI to download the model meta-llama/Llama-3-8B from the Hugging Face Hub using your HF_TOKEN.

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 using the CLI?▼

Use the command `hf download REPO_ID` to fetch model files from the Hub. Authenticate first with the HF_TOKEN environment variable or `hf auth login` for gated or private repositories.

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 should use `hf`, including uploads which now handle large folders and resumable transfers.

How do I upload a large folder to the Hugging Face Hub?▼

Use `hf upload REPO_ID LOCAL_PATH`, which handles single-commit uploads and resumable transfers of large directories. The older `hf upload-large-folder` command is deprecated.

Can I run SQL queries on Hugging Face datasets?▼

Yes, `hf datasets sql SQL` executes raw SQL through DuckDB directly against a dataset's parquet URLs. You can list the parquet URLs first with `hf datasets parquet`.

How do I authenticate the Hugging Face CLI with multiple tokens?▼

Use `hf auth login` with tokens from huggingface.co/settings/tokens, then manage them with `hf auth list` and `hf auth switch`. The `hf auth whoami` command shows the currently active account.

Does the hf CLI support machine-readable output for automation?▼

Yes, pass the global flag `--format json` to produce machine-readable output suitable for scripts and automation pipelines. The `-q` or `--quiet` flag limits output to IDs only.

Related Skills

Explore More Software Engineering Skills→
jasrajtulsijasrajtulsi

transformers

Loads and fine-tunes Hugging Face Transformers models for AI workflows.

Community
Advanced
NVIDIANVIDIA
49

sop-ft-orchestrate

Automate end-to-end fine-tuning of SOP monitoring pipelines with DDM-Net and Cosmos-Reason.

Official
Advanced
apacheapache
79

magpie-release-verify-rc

Verify Apache release candidate artefacts, GPG signatures, checksums, and license headers.

Official
Advanced
iaac-maaiiaac-maai
1

huggingface-deploy

Deploy Python applications to HuggingFace Spaces using Docker containers.

Official
Advanced