Skip to main content
In this guide, we’ll walk through creating a domain-specific AI assistant by extending one of Ollama’s base models. We’ll customize Gromo’s assistant—named Harris—so it:
  • Knows its own name
  • Understands Gromo’s investment context
  • Defaults to Indian Rupees (INR) when no currency is specified

​
1. Define Your Modelfile

First, create a Modelfile that builds on Llama 3.2, lowers creativity for financial precision, and sets up a system prompt:
The image contains text that explains how to use a Modelfile to create a custom model from a base model. It is set against a dark background.
Using PARAMETER temperature 0.3 ensures more accurate, fact-driven responses—crucial for financial applications.

​
2. Build the Custom Model

With your Modelfile ready, run:
The image shows a screen titled "Creating a New Model" with a focus on "llama3.2" and an icon labeled "Base Model."
Next, verify the model list:

​
3. Verify Assistant Behavior

Run Harris to confirm its name recognition, context awareness, and INR default:
Notice Harris automatically interprets contributions in ₹, courtesy of the SYSTEM prompt.

​
4. Next Steps: Share Your Model

Once you’re satisfied, push Harris to a registry so colleagues can pull it:
The image outlines two next steps: uploading custom models and enabling access via the "ollama pull" command.
Ensure your registry credentials are configured before pushing or pulling custom models to avoid authentication errors.

​
Further Reading

Watch Video