← All courses ← Course home

Lesson 01 of 06

The official catalog: recipes and registry

Apple's coreai-models repository is a set of model recipes plus a typed list. That list helps you talk about the job each preset does.

Agent brief (llms.md)

Start with the official source: Apple's official apple/coreai-models repository. It has recipes for working with models and a model_registry.py file that lists named presets. This course uses the typed list from that registry. It does not make up a fourth group or guess model names from a folder.

App jobWhat must the feature do?
Official repoRecipes and registry

Apple groups the published presets as llm, diffusion, and utility. These labels help because they tell you the kind of output to expect. An llm writes language. A diffusion model makes pictures or video from a prompt. A utility model does a smaller, focused job such as labels, speech-to-text, vectors, or segmentation (cutting an object out of a picture).

Typellm: write language
Typediffusion: make media
Typeutility: do one focused task

The type is a starting label. It does not mean every preset has the same speed, memory use, or device support. Many LLM families have separate macOS and iOS compression presets. Those are the same chat job packed differently for a Mac or a phone.

Recipes versus a model you trained

In the PyTorch to Core AI course, you train ClothingCNN yourself on Fashion-MNIST. You own that small classifier and how it was trained. The coreai-models repository is different. It gives you recipes and a list of ready-made model presets. You can study them and use them for the jobs they are meant to do.

Your courseTrain ClothingCNN
Your artifactA custom clothing classifier
Apple repoChoose a typed preset
RecipePrepare and run that job
AppConnect the output to a feature

You may also see folders named vlm and parakeet in the repository. They are extra recipe folders. If they are not in the typed registry presets listed here, do not give them a made-up model name or type. The published list for this course is the typed llm, diffusion, and utility catalog.

The model architectures course explains how language models and image models have different shapes. From the metal to the model reminds you that every chosen shape still becomes work the chip has to run.

Reading rule. First choose the input and output. Then choose the official type. Only after that compare named presets inside that type.

Next, look at the largest group in the registry: language models.

Key concepts

  • Start at https://github.com/apple/coreai-models for recipes and the typed list.
  • model_registry.py is the source of published presets for this course.
  • The three groups are llm, diffusion, and utility.
  • Type tells you the kind of output. It does not promise the same speed or device support.
  • vlm and parakeet folders can appear in the tree. They are not typed catalog presets here.

Takeaways

  • You can name the official repo as the source of recipes and registry types.
  • You can describe llm, diffusion, and utility by output shape.
  • You can choose input and output first, then type, then a named preset.