Hugging Face

← All terms · Hosting, infrastructure, databases

Also called HF

The central collaborative hub for the machine learning community, hosting hundreds of thousands of open-weight models, datasets, and AI applications.

What it is

Often described as "the GitHub of AI," Hugging Face provides the infrastructure where researchers and developers upload, share, and download models (like Llama or Stable Diffusion) and training datasets. It also offers "Spaces" to easily host and demo machine learning applications and provides serverless inference APIs.

When you would use it

You visit Hugging Face whenever you need to find, download, or benchmark open-weight AI models, datasets, or libraries like the transformers Python package.

Common operations

• Downloading the GGUF weights of a new local model for use in LM Studio.
• Hosting an interactive demo of a newly trained machine learning model.

Related terms

• Llama (model)
• GGUF
• Open-weight

Dashed terms are named in the source but do not have a page here yet.

Where this is taught

• Running Your First Local Model
• Notebook experiments to model assets