public sealed class DistillationSpec : IMessage<DistillationSpec>, IEquatable<DistillationSpec>, IDeepCloneable<DistillationSpec>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class DistillationSpec.
Required. A path in a Cloud Storage bucket, which will be treated as the
root output directory of the distillation pipeline. It is used by the
system to generate the paths of output artifacts.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThis documentation details the \u003ccode\u003eDistillationSpec\u003c/code\u003e class, part of the Vertex AI v1beta1 API, used for tuning specifications in the context of model distillation.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eDistillationSpec\u003c/code\u003e class implements several interfaces, including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, providing functionalities for message handling, equality checks, deep cloning, and buffer message operations.\u003c/p\u003e\n"],["\u003cp\u003eKey properties of \u003ccode\u003eDistillationSpec\u003c/code\u003e include \u003ccode\u003eBaseTeacherModel\u003c/code\u003e, \u003ccode\u003eStudentModel\u003c/code\u003e, \u003ccode\u003eTrainingDatasetUri\u003c/code\u003e, and \u003ccode\u003ePipelineRootDirectory\u003c/code\u003e, which are essential for defining the teacher and student models, the training dataset location, and the output directory of the distillation pipeline.\u003c/p\u003e\n"],["\u003cp\u003eThe class offers constructors for creating a new \u003ccode\u003eDistillationSpec\u003c/code\u003e object, either default or based on an existing \u003ccode\u003eDistillationSpec\u003c/code\u003e instance, and also provides boolean properties, such as \u003ccode\u003eHasBaseTeacherModel\u003c/code\u003e to check whether the specified fields have been set.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eTunedTeacherModelSource\u003c/code\u003e property and its \u003ccode\u003eModelName\u003c/code\u003e-typed view counterpart \u003ccode\u003eTunedTeacherModelSourceAsModelName\u003c/code\u003e allow for detailed specification and interaction with the tuned teacher model resource.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class DistillationSpec (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec) \n\n public sealed class DistillationSpec : IMessage\u003cDistillationSpec\u003e, IEquatable\u003cDistillationSpec\u003e, IDeepCloneable\u003cDistillationSpec\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class DistillationSpec.\n\nTuning Spec for Distillation. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e DistillationSpec \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[DistillationSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[DistillationSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[DistillationSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### DistillationSpec()\n\n public DistillationSpec()\n\n### DistillationSpec(DistillationSpec)\n\n public DistillationSpec(DistillationSpec other)\n\nProperties\n----------\n\n### BaseTeacherModel\n\n public string BaseTeacherModel { get; set; }\n\nThe base teacher model that is being distilled. See [Supported\nmodels](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models).\n\n### HasBaseTeacherModel\n\n public bool HasBaseTeacherModel { get; }\n\nGets whether the \"base_teacher_model\" field is set\n\n### HasTunedTeacherModelSource\n\n public bool HasTunedTeacherModelSource { get; }\n\nGets whether the \"tuned_teacher_model_source\" field is set\n\n### HasValidationDatasetUri\n\n public bool HasValidationDatasetUri { get; }\n\nGets whether the \"validation_dataset_uri\" field is set\n\n### HyperParameters\n\n public DistillationHyperParameters HyperParameters { get; set; }\n\nOptional. Hyperparameters for Distillation.\n\n### PipelineRootDirectory\n\n public string PipelineRootDirectory { get; set; }\n\nRequired. A path in a Cloud Storage bucket, which will be treated as the\nroot output directory of the distillation pipeline. It is used by the\nsystem to generate the paths of output artifacts.\n\n### StudentModel\n\n public string StudentModel { get; set; }\n\nThe student model that is being tuned, e.g., \"google/gemma-2b-1.1-it\".\n\n### TeacherModelCase\n\n public DistillationSpec.TeacherModelOneofCase TeacherModelCase { get; }\n\n### TrainingDatasetUri\n\n public string TrainingDatasetUri { get; set; }\n\nRequired. Cloud Storage path to file containing training dataset for\ntuning. The dataset must be formatted as a JSONL file.\n\n### TunedTeacherModelSource\n\n public string TunedTeacherModelSource { get; set; }\n\nThe resource name of the Tuned teacher model. Format:\n`projects/{project}/locations/{location}/models/{model}`.\n\n### TunedTeacherModelSourceAsModelName\n\n public ModelName TunedTeacherModelSourceAsModelName { get; set; }\n\n[ModelName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ModelName)-typed view over the [TunedTeacherModelSource](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DistillationSpec#Google_Cloud_AIPlatform_V1Beta1_DistillationSpec_TunedTeacherModelSource) resource name property.\n\n### ValidationDatasetUri\n\n public string ValidationDatasetUri { get; set; }\n\nOptional. Cloud Storage path to file containing validation dataset for\ntuning. The dataset must be formatted as a JSONL file."]]
