About supervised fine-tuning for Gemini models

Supervised fine-tuning is a good option when you have a well-defined task with available labeled data. It's particularly effective for domain-specific applications where the language or content significantly differs from the data the large model was originally trained on.

Supervised fine-tuning adapts model behavior with a labeled dataset. This process adjusts the model's weights to minimize the difference between its predictions and the actual labels. For example, it can improve model performance for the following types of tasks:

  • Classification
  • Summarization
  • Extractive question answering
  • Chat

Supported models

The following Gemini text models support supervised tuning:

  • gemini-1.0-pro-002.

Use cases for using supervised fine-tuning on text models

Foundation text models work well when the expected output or task can be clearly and concisely defined in a prompt and the prompt consistently produces the expected output. If you want a model to learn something niche or specific that deviates from general language patterns, then you might want to consider tuning that model. For example, you can use model tuning to teach the model the following:

  • Specific structures or formats for generating output.
  • Specific behaviors such as when to provide a terse or verbose output.
  • Specific customized outputs for specific types of inputs.

The following examples are use cases that are difficult to capture with only prompt instructions:

  • Classification: The expected response is a specific word or phrase.

    Tuning the model can help prevent the model from generating verbose responses.

  • Summarization: The summary follows a specific format. For example, you might need to remove personally identifiable information (PII) in a chat summary.

    This formatting of replacing the names of the speakers with #Person1 and #Person2 is difficult to describe and the foundation model might not naturally produce such a response.

  • Extractive question answering: The question is about a context and the answer is a substring of the context.

    The response "Last Glacial Maximum" is a specific phrase from the context.

  • Chat: You need to customize model response to follow a persona, role, or character.

You can also tune a model in the following situations:

  • Prompts are not producing the expected results consistently enough.
  • The task is too complicated to define in a prompt. For example, you want the model to do behavior cloning for a behavior that's hard to articulate in a prompt.
  • You have complex intuitions about a task that are easy to elicit but difficult to formalize in a prompt.
  • You want to reduce the context length by removing the few-shot examples.


Quota is enforced on the number of concurrent tuning jobs. Every project comes with a default quota to run at least one tuning job. This is a global quota, shared across all available regions. If you want to run more jobs concurrently, you need to request additional quota for Global concurrent tuning jobs.


Supervised fine-tuning for gemini-1.0-pro-002 is in Preview.

  • While tuning is in Preview, there is no charge to tune a model.
  • After tuning a model, inference costs for the tuned model still apply. Inference pricing is the same for each stable version of Gemini 1.0 Pro.

For more information, see Vertex AI pricing and Available Gemini stable model versions.

What's next