skills.rest
MLT-OSS
MLT-OSSOFFICIAL
Explore all skills by this author →
WebsiteGitHub

huggingface-hub

Manage Hugging Face Hub models, datasets, Spaces, and inference endpoints via the hf CLI.

14|5|Updated Apr 9, 2026
Search Tags:#models#mlops#datasets#huggingface#hub#hf cli#inference endpoints
One-click install
npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill huggingface-hub-mlt-oss
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/MLT-OSS/hermes-agent-go/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill huggingface-hub-mlt-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Interacting with the Hugging Face Hub through the web UI is slow and hard to automate. This Skill provides a complete reference for the hf command-line interface so you can search, download, upload, and manage models, datasets, Spaces, and compute resources directly from the terminal. ## Core Features & Use Cases - Repository Operations: Download and upload models and datasets, create or delete repos, manage branches, tags, and discussions/PRs. - Data & Compute: Run SQL queries against dataset parquet files with DuckDB, deploy and scale Inference Endpoints, and launch Jobs on HF infrastructure. - Storage & Automation: Manage S3-like buckets, local caches, webhooks, and collections for automated Hub workflows. - Use Case: You need to download a fine-tuned model, query a dataset with SQL to filter training samples, and deploy the result to an Inference Endpoint — all scripted via hf commands with --format json output for automation. ## Quick Start Install the hf CLI and use it to download a model from the Hugging Face Hub to my local machine.

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 the hf download command followed by the repository ID, for example hf download REPO_ID. Authenticate first with hf auth login or by setting the HF_TOKEN environment variable for gated or private repositories.

How to upload large folders to Hugging Face Hub?▼

Use hf upload-large-folder REPO_ID LOCAL_PATH for resumable uploads of large directories. For smaller single-commit uploads, hf upload REPO_ID is the recommended command.

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

The hf command is the modern CLI for the Hugging Face Hub and replaces the deprecated huggingface-cli command. All new workflows should use hf, which covers repos, datasets, jobs, endpoints, and buckets.

Can I run SQL queries on Hugging Face datasets?▼

Yes, hf datasets sql lets you execute raw SQL via DuckDB directly against dataset parquet URLs. You can also list parquet URLs with hf datasets parquet before querying.

How do I deploy and manage Hugging Face Inference Endpoints from the CLI?▼

Use the hf endpoints commands to deploy, pause, resume, and scale-to-zero Inference Endpoints, and browse available options with the catalog subcommand. Authentication via HF_TOKEN is required.

Why is my hf upload failing or incomplete?▼

Large directory uploads can fail due to network interruptions; use hf upload-large-folder for resumable transfers. Also verify authentication with hf auth whoami and check local storage with hf cache verify for checksum issues.

Related Skills

Explore More Software Engineering Skills→
eliottbusinesseliottbusiness

huggingface-hub

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

Community
Intermediate
shiftreposhiftrepo

huggingface-hub

Manage Hugging Face Hub models, datasets, and Spaces via CLI operations.

Official
Advanced
JamesFincherJamesFincher

huggingface-hub

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

Community
Intermediate
Reimonsk8Reimonsk8

github-auth

Configures GitHub authentication using HTTPS tokens, SSH keys, or gh CLI login.

Community
Intermediate