Tune a foundation model with the Tuning Studio to guide an AI foundation model to return useful output.

Required permissions

To run tuning experiments, you must have the Admin or Editor role in a project.

The Tuning Studio is not available with all plans or in all data centers. See watsonx.ai Runtime plans and Regional availability for services and features.

Data format

Tabular: JSON, JSONL

Data size

50 to 10,000 input and output example pairs. The maximum file size is 200 MB.

You use the Tuning Studio to create a tuned version of an existing foundation model.

Foundation models are AI models that are pretrained on terabytes of data from across the internet and other public resources. They are unrivaled in their ability to predict the next best word and generate language. While language-generation can be useful for brainstorming and spurring creativity, foundation models typically need to be guided to achieve concrete tasks. Model tuning, and other techniques, such as retrieval-augmented generation, help you to use foundation models in meaningful ways for your business.

With the Tuning Studio, you can tune a smaller foundation model to improve its performance on natural language processing tasks such as classification, summarization, and generation. Tuning can help a smaller foundation model achieve results comparable to larger models in the same model family. By tuning and deploying the smaller model, you can reduce long-term inference costs.

Much like prompt engineering, tuning a foundation model helps you to influence the content and format of the foundation model output. Knowing what to expect from a foundation model is essential if you want to plug the step of inferencing a foundation model into a business workflow.

The following diagram illustrates how tuning a foundation model can help you guide the model to generate useful output. You provide labeled data that can include proprietary information which is unknown to the foundation model and that illustrates the format and type of output that you want the model to return. Your examples give the foundation model a pattern to follow and apply to future output.

Instead of generalizing in traditional tasks such as text translation and text or answer generation, after you tune a foundation model, the output is more tailored to your needs.

• Generated text or answers can follow a specific style
• The tuned model can summarize or extract information in the way you want
• With much smaller prompts, the tuned model can classify text effectively

To learn more about when tuning a model is the right approach, see When to tune a foundation model.