Tuning a foundation model
To prompt tune a foundation model, create a tuning experiment that guides the foundation model to return the output you want in the form you want.
If you don't have a project, create one. From the main menu, expand Projects, and then click All projects.
-
Click New project.
-
Name the project, and then optionally add a description.
For more information about project options, such as reporting or logging, see Creating a project.
-
Click Create.
- Required services
- watsonx.ai
- Required permissions
- To tune a foundation model, you must have the Admin or Editor role in a project.
Before you begin
The foundation model that you want to tune must be installed. For more information, see Adding AI models.
Make decisions about the following tuning options:
- Choose the tuning method to use. See Methods for tuning.
- Find the foundation model that works best for your use case. See Choosing a foundation model to tune.
Create training data to use for fine tuning the foundation model. See Data formats.
Tune a foundation model
-
From the project overview, click the Assets tab, and then click New asset > Tune a foundation model with labeled data.
-
Name the tuning experiment.
-
Optional: Add a description and tags. Add a description as a reminder to yourself and to help collaborators understand the goal of the tuned model. Assigning a tag gives you a way to filter your tuning assets later to show only the assets associated with a tag.
-
Click Create.
-
Click Select a foundation model to choose the foundation model that you want to tune.
Click a tile to see a model card with details about the foundation model. When you find the foundation model that you want to use, click Select.
-
Follow the steps for the method you want to use:
-
Evaluate the results. See Evaluating the tuning experiment.
Learn more
- Creating a fine-tuning experiment
- Creating a prompt-tuning experiment
- Evaluating the tuning experiment
- Deploying a tuned model
Parent topic: Tuning Studio