Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window.

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:

Supervised fine tuning

Supported Models:

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

Model	Version
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" \

http://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

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.

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.
`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-1.0-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 http://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

Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login , or by using Cloud Shell, which automatically logs you into the gcloud CLI . You can check the currently active account by running gcloud auth list.

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 \
     "http://TUNING_JOB_REGION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs"

PowerShell

Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login . You can check the currently active account by running gcloud auth list.

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 "http://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.

Response

{
  "name": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID",
  "createTime": CREATE_TIME,
  "updateTime": UPDATE_TIME,
  "status": "STATUS",
  "supervisedTuningSpec": {
        "training_dataset_uri": "TRAINING_DATASET_URI",
        "validation_dataset_uri": "VALIDATION_DATASET_URI",
        "hyper_parameters": {
            "epoch_count": EPOCH_COUNT,
            "learning_rate_multiplier": LEARNING_RATE_MULTIPLIER
        },
    },
  "tunedModelDisplayName": "TUNED_MODEL_DISPLAYNAME"
}

Python


import time

import vertexai
from vertexai.preview.tuning import sft

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"

vertexai.init(project=project_id, location="us-central1")

sft_tuning_job = sft.train(
    source_model="gemini-1.0-pro-002",
    train_dataset="gs://cloud-samples-data/ai-platform/generative_ai/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)

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

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-1.0-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 epochs to train. Leave it unset to use the recommeded value.
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 http://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",
      "validation_dataset_uri": "VALIDATION_DATASET_URI",
      "hyper_parameters": {
          "epoch_count": EPOCH_COUNT,
          "learning_rate_multiplier": 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 \
     "http://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 "http://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.

Response

{
  "name": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID",
  "createTime": CREATE_TIME,
  "updateTime": UPDATE_TIME,
  "status": "STATUS",
  "supervisedTuningSpec": {
        "training_dataset_uri": "TRAINING_DATASET_URI",
        "validation_dataset_uri": "VALIDATION_DATASET_URI",
        "hyper_parameters": {
            "epoch_count": EPOCH_COUNT,
            "learning_rate_multiplier": LEARNING_RATE_MULTIPLIER
        },
    },
  "tunedModelDisplayName": "TUNED_MODEL_DISPLAYNAME"
}

Python


import time

import vertexai
from vertexai.preview.tuning import sft

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"

vertexai.init(project=project_id, location="us-central1")

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

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

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 http://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)" \
     "http://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 "http://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.

Response

{
  "tuning_jobs": [
    TUNING_JOB_1, TUNING_JOB_2, ...
  ]
}

Python

import vertexai
from vertexai.preview.tuning import sft

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"

vertexai.init(project=project_id, location="us-central1")

responses = sft.SupervisedTuningJob.list()

for response in responses:
    print(response)

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 http://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)" \
     "http://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 "http://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.

Response

{
  "name": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/tuningJobs/TUNING_JOB_ID",
  "tunedModelDisplayName": "TUNED_MODEL_DISPLAYNAME",
  "createTime": CREATE_TIME,
  "endTime": END_TIME,
  "tuned_model": {
      "model": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/models/MODEL_ID",
      "endpoint": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/endpoints/ENDPOINT_ID"
  },
  "experiment": "projects/PROJECT_ID/locations/TUNING_JOB_REGION/metadataStores/default/contexts/EXPERIMENT_ID",
  "tuning_data_statistics": {
      "supervised_tuning_data_stats": {
          "tuning_dataset_example_count": "TUNING_DATASET_EXAMPLE_COUNT",
          "total_tuning_character_count": "TOTAL_TUNING_CHARACTER_COUNT",
          "tuning_step_count": "TUNING_STEP_COUNT"
      }
  },
  "status": "STATUS",
  "supervisedTuningSpec" : {
        "training_dataset_uri": "TRAINING_DATASET_URI",
        "validation_dataset_uri": "VALIDATION_DATASET_URI",
        "hyper_parameters": {
            "epoch_count": EPOCH_COUNT,
            "learning_rate_multiplier": LEARNING_RATE_MULTIPLIER
        }
    }
}

Python

import vertexai
from vertexai.preview.tuning import sft

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"
# tuning_job_id = "TUNING_JOB_ID"

vertexai.init(project=project_id, location="us-central1")

response = sft.SupervisedTuningJob(
    f"projects/{project_id}/locations/{location}/tuningJobs/{tuning_job_id}"
)

print(response)

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 http://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 "" \
     "http://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 "http://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.

Response

{}

Python

import vertexai
from vertexai.preview.tuning import sft

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"
# tuning_job_id = "TUNING_JOB_ID"

vertexai.init(project=project_id, location="us-central1")

job = sft.SupervisedTuningJob(
    f"projects/{project_id}/locations/{location}/tuningJobs/{tuning_job_id}"
)
job.cancel()

What's next

For detailed documentation, see the following: