Tuning API

Model tuning is a crucial process in adapting Gemini to perform specific tasks with greater precision and accuracy. Model tuning works by providing a model with a training dataset that contains a set of examples of specific downstream tasks.

Use the Gemini tuning API for the following use-cases:

Supported Models:

You can use supervised fine-tuning on the following Gemini models:

Model Version
Gemini 1.5 Pro gemini-1.5-pro-002
Gemini 1.5 Flash gemini-1.5-flash-002
Gemini 1.0 Pro gemini-1.0-pro-002

Example syntax

Syntax to tune a model.

curl

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \

https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs \
-d '{
  "baseModel": "...",
  "supervisedTuningSpec" : {
    ...
      "hyper_parameters": {
        ...
      },
  },
  "tunedModelDisplayName": "",
}'

Parameters list

See examples for implementation details.

Request body

The request body contains data with the following parameters:

Parameters

source_model

Optional: string

Name of the foundation model that's being tuned. Supported values are: gemini-1.0-pro-002.

tunedModelDisplayName

string

The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.

supervisedTuningSpec

Parameters

training_dataset

string

Cloud Storage URI of your training dataset. The dataset must be formatted as a JSONL file. For best results, provide at least 100 to 500 examples. For more information, see About supervised tuning datasets.

validation_dataset

Optional: string

Cloud Storage URI of your validation dataset. Your dataset must be formatted as a JSONL file. A dataset can contain up to 256 examples. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. For more information, see About supervised tuning datasets .

epoch_count

Optional: int

Number of complete passes the model makes over the entire training dataset during training. Vertex AI automatically adjusts the default value to your training dataset size. This value is based on benchmarking results to optimize model output quality.

learning_rate_multiplier

Optional: float

Multiplier for adjusting the default learning rate.

adapter_size

Optional: AdapterSize

Adapter size for tuning.

tuned_model_display_name

Optional: string

Display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.

AdapterSize

Adapter size for tuning job.

Parameters

ADAPTER_SIZE_UNSPECIFIED

Unspecified adapter size.

ADAPTER_SIZE_ONE

Adapter size 1.

ADAPTER_SIZE_FOUR

Adapter size 4.

ADAPTER_SIZE_EIGHT

Adapter size 8.

ADAPTER_SIZE_SIXTEEN

Adapter size 16.

Examples

Create a supervised tuning Job

You can create a supervised text model tuning job by using the Vertex AI SDK for Python or by sending a POST request.

Basic use case

The basic use case only sets values for baseModel and training_dataset_uri. All other parameters use the default values.

REST

To create a model tuning job, send a POST request by using the tuningJobs.create method. Note that some of the parameters are not supported by all of the models. Ensure that you only include the applicable parameters for the model that you're tuning.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TUNING_JOB_REGION: The region where the tuning job runs. This is also the default region for where the tuned model is uploaded.
  • BASE_MODEL: Name of the foundation model to tune. Supported values: gemini-1.5-pro-002, gemini-1.5-flash-002, gemini-1.0-pro-002.
  • TRAINING_DATASET_URI: Cloud Storage URI of your training dataset. The dataset must be formatted as a JSONL file. For best results, provide at least 100 to 500 examples. For more information, see About supervised tuning datasets .

HTTP method and URL:

POST https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs

Request JSON body:

{
  "baseModel": "BASE_MODEL",
  "supervisedTuningSpec" : {
      "training_dataset_uri": "TRAINING_DATASET_URI"
  },
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python


import time

import vertexai
from vertexai.tuning import sft

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

sft_tuning_job = sft.train(
    source_model="gemini-1.5-pro-002",
    train_dataset="gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl",
)

# Polling for job completion
while not sft_tuning_job.has_ended:
    time.sleep(60)
    sft_tuning_job.refresh()

print(sft_tuning_job.tuned_model_name)
print(sft_tuning_job.tuned_model_endpoint_name)
print(sft_tuning_job.experiment)
# Example response:
# projects/123456789012/locations/us-central1/models/1234567890@1
# projects/123456789012/locations/us-central1/endpoints/123456789012345
# <google.cloud.aiplatform.metadata.experiment_resources.Experiment object at 0x7b5b4ae07af0>

Advanced use case

The advance use case expands upon the basic use case, but also sets values for optional hyper_parameters, such as epoch_count, learning_rate_multiplier and adapter_size.

REST

To create a model tuning job, send a POST request by using the tuningJobs.create method. Note that some of the parameters are not supported by all of the models. Ensure that you only include the applicable parameters for the model that you're tuning.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TUNING_JOB_REGION: The region where the tuning job runs. This is also the default region for where the tuned model is uploaded.
  • BASE_MODEL: Name of the foundation model to tune. Supported values: gemini-1.5-pro-002, gemini-1.5-flash-002, and gemini-1.0-pro-002.
  • TRAINING_DATASET_URI: Cloud Storage URI of your training dataset. The dataset must be formatted as a JSONL file. For best results, provide at least 100 to 500 examples. For more information, see About supervised tuning datasets .
  • VALIDATION_DATASET_URIOptional: The Cloud Storage URI of your validation dataset file.
  • EPOCH_COUNTOptional: The number of complete passes the model makes over the entire training dataset during training. Leave it unset to use the pre-populated recommended value.
  • ADAPTER_SIZEOptional: The Adapter size to use for the tuning job. The adapter size influences the number of trainable parameters for the tuning job. A larger adapter size implies that the model can learn more complex tasks, but it requires a larger training dataset and longer training times.
  • LEARNING_RATE_MULTIPLIER: Optional: A multiplier to apply to the recommended learning rate. Leave it unset to use the recommended value.
  • TUNED_MODEL_DISPLAYNAMEOptional: A display name for the tuned model. If not set, a random name is generated.

HTTP method and URL:

POST https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs

Request JSON body:

{
  "baseModel": "BASE_MODEL",
  "supervisedTuningSpec" : {
      "trainingDatasetUri": "TRAINING_DATASET_URI",
      "validationDatasetUri": "VALIDATION_DATASET_URI",
      "hyperParameters": {
          "epochCount": EPOCH_COUNT,
          "adapterSize": "ADAPTER_SIZE",
          "learningRateMultiplier": LEARNING_RATE_MULTIPLIER
      },
  },
  "tunedModelDisplayName": "TUNED_MODEL_DISPLAYNAME"
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python


import time

import vertexai
from vertexai.tuning import sft

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

sft_tuning_job = sft.train(
    source_model="gemini-1.5-pro-002",
    train_dataset="gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl",
    # The following parameters are optional
    validation_dataset="gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_validation_data.jsonl",
    epochs=4,
    adapter_size=4,
    learning_rate_multiplier=1.0,
    tuned_model_display_name="tuned_gemini_1_5_pro",
)

# Polling for job completion
while not sft_tuning_job.has_ended:
    time.sleep(60)
    sft_tuning_job.refresh()

print(sft_tuning_job.tuned_model_name)
print(sft_tuning_job.tuned_model_endpoint_name)
print(sft_tuning_job.experiment)
# Example response:
# projects/123456789012/locations/us-central1/models/1234567890@1
# projects/123456789012/locations/us-central1/endpoints/123456789012345
# <google.cloud.aiplatform.metadata.experiment_resources.Experiment object at 0x7b5b4ae07af0>

List tuning Jobs

You can view a list of tuning jobs in your current project by using the Vertex AI SDK for Python or by sending a GET request.

REST

To create a model tuning job, send a POST request by using the tuningJobs.create method. Note that some of the parameters are not supported by all of the models. Ensure that you only include the applicable parameters for the model that you're tuning.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TUNING_JOB_REGION: The region where the tuning job runs. This is also the default region for where the tuned model is uploaded.

HTTP method and URL:

GET https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs

To send your request, choose one of these options:

curl

Execute the following command:

curl -X GET \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs"

PowerShell

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python

import vertexai
from vertexai.tuning import sft

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

responses = sft.SupervisedTuningJob.list()

for response in responses:
    print(response)
# Example response:
# <vertexai.tuning._supervised_tuning.SupervisedTuningJob object at 0x7c85287b2680>
# resource name: projects/12345678/locations/us-central1/tuningJobs/123456789012345

Get details of a tuning job

You can get the details of a tuning job by using the Vertex AI SDK for Python or by sending a GET request.

REST

To view a list of model tuning jobs, send a GET request by using the tuningJobs.get method and specify the TuningJob_ID.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TUNING_JOB_REGION: The region where the tuning job runs. This is also the default region for where the tuned model is uploaded.
  • TUNING_JOB_ID: The ID of the tuning job.

HTTP method and URL:

GET https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID

To send your request, choose one of these options:

curl

Execute the following command:

curl -X GET \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID"

PowerShell

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python

import vertexai
from vertexai.tuning import sft

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# LOCATION = "us-central1"
vertexai.init(project=PROJECT_ID, location=LOCATION)

tuning_job_id = "4982013113894174720"
response = sft.SupervisedTuningJob(
    f"projects/{PROJECT_ID}/locations/{LOCATION}/tuningJobs/{tuning_job_id}"
)

print(response)
# Example response:
# <vertexai.tuning._supervised_tuning.SupervisedTuningJob object at 0x7cc4bb20baf0>
# resource name: projects/1234567890/locations/us-central1/tuningJobs/4982013113894174720

Cancel a tuning job

You can cancel a tuning job by using the Vertex AI SDK for Python or by sending a POST request.

REST

To view a list of model tuning jobs, send a GET request by using the tuningJobs.cancel method and specify the TuningJob_ID.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TUNING_JOB_REGION: The region where the tuning job runs. This is also the default region for where the tuned model is uploaded.
  • TUNING_JOB_ID: The ID of the tuning job.

HTTP method and URL:

POST https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID:cancel

To send your request, choose one of these options:

curl

Execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d "" \
"https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID:cancel"

PowerShell

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-Uri "https://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID:cancel" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python

import vertexai
from vertexai.tuning import sft

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# LOCATION = "us-central1"
vertexai.init(project=PROJECT_ID, location=LOCATION)

tuning_job_id = "4982013113894174720"
job = sft.SupervisedTuningJob(
    f"projects/{PROJECT_ID}/locations/{LOCATION}/tuningJobs/{tuning_job_id}"
)
job.cancel()

What's next

For detailed documentation, see the following: