Manages Hugging Face Hub models, datasets, spaces, jobs, and repos via the hf CLI.
npx skills add https://github.com/jrp2014/check_models --skill hf-cli-jrp2014
Please help me install this Agent Skill. Skill: hf-cli Source: https://github.com/jrp2014/check_models/tree/main/.agents/skills/hf-cli Command: npx skills add https://github.com/jrp2014/check_models --skill hf-cli-jrp2014
hf CLI command reference so an AI assistant can execute any Hub operation directly and correctly. ## Core Features & Use Cases - Model and Dataset Operations: Download, upload, search, and inspect models and datasets, including SQL queries against dataset parquet files and leaderboard lookups. - Infrastructure Management: Run and schedule Jobs on Hugging Face hardware, deploy Inference Endpoints, manage Spaces (hardware, secrets, logs, SSH), and create sandboxes. - Repo and Collaboration Workflows: Create and configure repos, manage branches and tags, handle discussions and pull requests, organize collections, and set up webhooks. - Use Case: Ask the assistant to download a specific MLX model revision, check local cache usage with hf cache list, then schedule a nightly training job on an A100 with hf jobs scheduled run—all without leaving the conversation. ## Quick Start Ask the assistant to download the model 'mlx-community/Llama-3.2-3B-Instruct-4bit' from the Hugging Face Hub and then show which account is currently authenticated.High-intent search queries and answers about installing and using this skill.
Use `hf download REPO_ID` with optional flags like `--revision`, `--include`, `--exclude`, and `--local-dir` to control what gets fetched and where it is stored. The `hf` command replaces the deprecated `huggingface-cli`.
Run `hf auth login` to log in from your browser or with a token from huggingface.co/settings/tokens. Use `hf auth whoami` to verify the active account and `hf auth switch` to change between stored tokens.
Yes, `hf jobs run IMAGE COMMAND` launches a job on selectable hardware flavors from cpu-basic up to h200x8. You can also schedule recurring jobs with `hf jobs scheduled run` and monitor them via `hf jobs logs` and `hf jobs inspect`.
Use `hf cache list` to inspect cached repositories sorted by size or access time, then `hf cache prune` to remove detached revisions and incomplete downloads, or `hf cache rm` to delete specific repos.
The `hf` command is the current Hugging Face Hub CLI and fully replaces the deprecated `huggingface-cli`. Auth commands moved under `hf auth`, and the new CLI adds buckets, jobs, sandboxes, endpoints, and skills management.
LAF-USManage repositories, models, and Spaces on the Hugging Face Hub via the hf CLI.
Hung-3008Load and use Hugging Face transformer models for inference and fine-tuning.
huggingfaceManages Hugging Face Hub models, datasets, spaces, jobs, and endpoints via the hf CLI.
biomaps-infraIntegrate with the LabArchives API to manage notebooks, entries, and attachments.