feat: add API for Managed OSS Fine Tuning

Google APIs · copybara-github · commit 5680805cfb38 · 2025-07-11T15:03:22.000-07:00
docs: A comment for field `model` in message `.google.cloud.aiplatform.v1beta1.TunedModel` is changed
docs: A comment for field `learning_rate_multiplier` in message `.google.cloud.aiplatform.v1beta1.SupervisedHyperParameters` is changed
docs: A comment for field `training_dataset_uri` in message `.google.cloud.aiplatform.v1beta1.SupervisedTuningSpec` is changed
docs: A comment for field `validation_dataset_uri` in message `.google.cloud.aiplatform.v1beta1.SupervisedTuningSpec` is changed

PiperOrigin-RevId: 782121247
diff --git a/google/cloud/aiplatform/v1beta1/tuning_job.proto b/google/cloud/aiplatform/v1beta1/tuning_job.proto
@@ -75,6 +75,14 @@ message TuningJob {
   // [TuningJob][google.cloud.aiplatform.v1.TuningJob].
   string description = 3 [(google.api.field_behavior) = OPTIONAL];
 
+  // Optional. The user-provided path to custom model weights. Set this field
+  // to tune a custom model. The path must be a Cloud Storage directory that
+  // contains the model weights in .safetensors format along with associated
+  // model metadata files. If this field is set, the base_model field must still
+  // be set to indicate which base model the custom model is derived from. This
+  // feature is only available for open source models.
+  string custom_base_model = 26 [(google.api.field_behavior) = OPTIONAL];
+
   // Output only. The detailed state of the job.
   JobState state = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
 
@@ -158,13 +166,26 @@ message TuningJob {
   // Users starting the pipeline must have the `iam.serviceAccounts.actAs`
   // permission on this service account.
   string service_account = 22;
+
+  // Optional. Cloud Storage path to the directory where tuning job outputs are
+  // written to. This field is only available and required for open source
+  // models.
+  string output_uri = 25 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // The Model Registry Model and Online Prediction Endpoint associated with
 // this [TuningJob][google.cloud.aiplatform.v1.TuningJob].
 message TunedModel {
   // Output only. The resource name of the TunedModel. Format:
-  // `projects/{project}/locations/{location}/models/{model}`.
+  //
+  // `projects/{project}/locations/{location}/models/{model}@{version_id}`
+  //
+  // When tuning from a base model, the version_id will be 1.
+  //
+  // For continuous tuning, the version id will be incremented by 1 from the
+  // last version id in the parent model. E.g.,
+  // `projects/{project}/locations/{location}/models/{model}@{last_version_id +
+  // 1}`
   string model = 1 [
     (google.api.field_behavior) = OUTPUT_ONLY,
     (google.api.resource_reference) = {
@@ -412,20 +433,44 @@ message SupervisedHyperParameters {
   int64 epoch_count = 1 [(google.api.field_behavior) = OPTIONAL];
 
   // Optional. Multiplier for adjusting the default learning rate.
+  // Mutually exclusive with `learning_rate`.
   double learning_rate_multiplier = 2 [(google.api.field_behavior) = OPTIONAL];
 
+  // Optional. Learning rate for tuning.
+  // Mutually exclusive with `learning_rate_multiplier`.
+  // This feature is only available for open source models.
+  double learning_rate = 6 [(google.api.field_behavior) = OPTIONAL];
+
   // Optional. Adapter size for tuning.
   AdapterSize adapter_size = 3 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Batch size for tuning.
+  // This feature is only available for open source models.
+  int64 batch_size = 5 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Tuning Spec for Supervised Tuning for first party models.
 message SupervisedTuningSpec {
-  // Required. Cloud Storage path to file containing training dataset for
-  // tuning. The dataset must be formatted as a JSONL file.
+  // Supported tuning modes.
+  enum TuningMode {
+    // Tuning mode is unspecified.
+    TUNING_MODE_UNSPECIFIED = 0;
+
+    // Full fine-tuning mode.
+    TUNING_MODE_FULL = 1;
+
+    // PEFT adapter tuning mode.
+    TUNING_MODE_PEFT_ADAPTER = 2;
+  }
+
+  // Required. Training dataset used for tuning. The dataset can be specified as
+  // either a Cloud Storage path to a JSONL file or as the resource name of a
+  // Vertex Multimodal Dataset.
   string training_dataset_uri = 1 [(google.api.field_behavior) = REQUIRED];
 
-  // Optional. Cloud Storage path to file containing validation dataset for
-  // tuning. The dataset must be formatted as a JSONL file.
+  // Optional. Validation dataset used for tuning. The dataset can be specified
+  // as either a Cloud Storage path to a JSONL file or as the resource name of a
+  // Vertex Multimodal Dataset.
   string validation_dataset_uri = 2 [(google.api.field_behavior) = OPTIONAL];
 
   // Optional. Hyperparameters for SFT.
@@ -436,6 +481,9 @@ message SupervisedTuningSpec {
   // the last checkpoint will be exported. Otherwise, enable intermediate
   // checkpoints for SFT. Default is false.
   bool export_last_checkpoint_only = 6 [(google.api.field_behavior) = OPTIONAL];
+
+  // Tuning mode.
+  TuningMode tuning_mode = 7;
 }
 
 // Tuning Spec for Distillation.
