Hugging Face CLI
Independent PiSkill directory guide. The original skill remains hosted by Hugging Face Skills.
What is Hugging Face CLI?
Helps agents use the Hugging Face Hub CLI for authentication, model and dataset transfers, repositories, Spaces, jobs, buckets, papers, webhooks, and other Hub operations.
What does Hugging Face CLI do?
Hugging Face CLI is a skill for using the current `hf` command to manage models, datasets, Spaces, repositories, cache, buckets, jobs, Inference Endpoints, papers, collections and authentication on the Hugging Face Hub. It replaces the older `huggingface-cli` workflow with a much broader command surface.
Who is Hugging Face CLI best for?
- Developers managing Hugging Face resources from the terminal
- ML teams downloading or publishing models and datasets
- Users running jobs or managing Inference Endpoints
- Teams working with Hub repositories, storage or cache
Common use cases
- Log in and switch Hugging Face tokens
- Download or upload model and dataset files
- Run or schedule Hugging Face Jobs
- Deploy, inspect or scale Inference Endpoints
How does Hugging Face CLI work?
The skill uses `hf --help` and the relevant command group for the task, then applies the required repository, authentication, storage or compute options. It covers both local-Hub interactions such as downloads and cache management and remote operations such as jobs, buckets and endpoints.
Key benefits
- One CLI for a large part of the Hugging Face ecosystem
- Supports both repository and cloud operations
- Includes authentication and local-cache management
- Replaces the deprecated `huggingface-cli` command
Things to know
- Commands and supported options can change as the CLI evolves
- Destructive operations such as repo deletion need explicit care
- Private or gated resources require the correct Hugging Face token
Compatible tools
Frequently asked questions
What is the current Hugging Face CLI command?
What can `hf` manage?
Related skills
GitHub Issue Creator
Turns verified work context into a focused GitHub issue with scope, reproduction or rationale, acceptance criteria, dependencies, and actionable next steps.
HF Memory Estimator
Estimates the memory required to load Safetensors or GGUF model weights for inference, helping users judge whether a model fits available hardware before deployment.
Hugging Face Best Model Finder
Helps identify and compare strong Hugging Face models for a task using available benchmark information instead of choosing a model only by name or popularity.
Hugging Face Community Evals
Runs model evaluations with community evaluation tooling such as inspect-ai and lighteval on local hardware, supporting reproducible comparison of Hugging Face models.
Hugging Face Datasets
Guides Dataset Viewer API workflows for discovering subsets and splits, paging through rows, searching and filtering data, retrieving Parquet files, and inspecting dataset statistics.
Serving Image Selection
Helps choose an appropriate serving container for a Hugging Face model deployment on SageMaker and identify the current container image URI for the target setup.