Find and Download a ModelKit
For the best experience sign up.
1) Find a ModelKit
We suggest starting with one of our Quick Start ModelKits.
But you can use the search bar at the top of the Hub, or the Browse and Discover links at the top of the page to explore other ModelKits.
2) View the ModelKit
Click the repository's card to see the ModelKit. You can get more information about what's in the ModelKit by clicking "More Details" in the tag info panel.
This brings up the ModelKit's contents view.
3) Copy the Pull Command
In the repository view click the "Pull Tag" link in the upper right and then copy the resulting command.
TIP
A tag is a name for the ModelKit. You can think of it as the ModelKit's filename. Often tags will be used to indicate a version (e.g., latest
or 1.4
), but they can also be used to indicate specifics about what's in the ModelKit - like the quantization of a model (e.g., q8_0
or q4_0
), or the purpose of a dataset (e.g., validation
or training
).
You can change which tag you're viewing by using the drop down beside the repository name.
4) Install the KitOps CLI
In a terminal type:
bash
brew tap jozu-ai/kitops
brew install kitops
kit version
You should see a message in the terminal showing which Kit CLI version you are running.
5) Pull and Unpack the ModelKit
In a terminal create a new empty directory, then paste in the pull command you copied from the repository earlier:
bash
kit pull jozu.ml/jozu-quickstarts/fine-tuning:latest
kit unpack -d . jozu.ml/jozu-quickstarts/fine-tuning:latest
TIP
The size of the ModelKit is inclusive of that package only. If a ModelKit references a base model from a different ModelKit then pulling one will pull both ModelKits. You can learn more about referencing base models in the Model Parts KitOps documentation.
INFO
The Jozu Hub is in beta, so not everything works yet and we would love your feedback: reach us at [email protected].