DistillationSpec class - aiplatform library

Constructors

DistillationSpec({String? baseTeacherModel, String? tunedTeacherModelSource, required String trainingDatasetUri, String? validationDatasetUri, DistillationHyperParameters? hyperParameters, String studentModel = '', required String pipelineRootDirectory})
DistillationSpec.fromJson(Object? j): factory

baseTeacherModel → String?: The base teacher model that is being distilled. See Supported models.
final
hashCode → int: The hash code for this object.
no setterinherited
hyperParameters → DistillationHyperParameters?: Optional. Hyperparameters for Distillation.
final
pipelineRootDirectory → String: 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.
final
qualifiedName → String: The fully qualified name of this message, i.e., google.protobuf.Duration or google.rpc.ErrorInfo.
finalinherited
runtimeType → Type: A representation of the runtime type of the object.
no setterinherited
studentModel → String: The student model that is being tuned, e.g., "google/gemma-2b-1.1-it".
final
trainingDatasetUri → String: Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.
final
tunedTeacherModelSource → String?: The resource name of the Tuned teacher model. Format: projects/{project}/locations/{location}/models/{model}.
final
validationDatasetUri → String?: Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.
final

noSuchMethod(Invocation invocation) → dynamic: Invoked when a nonexistent method or property is accessed.
inherited
toJson() → Object: override
toString() → String: A string representation of this object.
override