Class GeminiTunedModel

Namespace

Uralstech.UGemini.Models.Tuning

A fine-tuned model created using ModelService.CreateTunedModel.

public class GeminiTunedModel : GeminiModelId

Inheritance

object

GeminiModelId

GeminiTunedModel

Inherited Members

GeminiModelId.DefaultModelResourceLocation

GeminiModelId.Name

GeminiModelId.BaseModelId

Extension Methods

GeminiFieldMaskGenerator.GetFieldMask<T>(T)

Fields

BaseModel

The name of the GeminiModel to tune. Example: models/gemini-1.5-flash-0

public GeminiModelId BaseModel

Field Value

GeminiModelId

CreateTime

The timestamp when this model was created.

public DateTime CreateTime

Field Value

DateTime

Description

A short description of the model.

public string Description

Field Value

string

DisplayName

The name to display for this model in user interfaces.

public string DisplayName

Field Value

string

Remarks

The display name must be up to 40 characters including spaces.

ReaderProjectNumbers

List of project numbers that have read access to the tuned model.

public long[] ReaderProjectNumbers

Field Value

long[]

State

The state of the tuned model.

public GeminiTunedModelState State

Field Value

GeminiTunedModelState

Temperature

Controls the randomness of the output.

public float Temperature

Field Value

float

Remarks

Values can range over [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied, while a value closer
to 0.0 will typically result in less surprising responses from the model. This value specifies default to be the one used by the
base model while creating the model.

TopK

For Top-k sampling.

public int TopK

Field Value

int

Remarks

Top-k sampling considers the set of topK most probable tokens. This value specifies default to be used by the backend while
making the call to the model. This value specifies default to be the one used by the base model while creating the model.

TopP

For Nucleus sampling.

public float TopP

Field Value

float

Remarks

Nucleus sampling considers the smallest set of tokens whose probability sum is at least topP. This value specifies default to be
the one used by the base model while creating the model.

TunedModelSource

TunedModel to use as the starting point for training the new model.

public GeminiTunedModelSource TunedModelSource

Field Value

GeminiTunedModelSource

TuningTask

The tuning task that creates the tuned model.

public GeminiTuningTask TuningTask

Field Value

GeminiTuningTask

UpdateTime

The timestamp when this model was updated.

public DateTime UpdateTime

Field Value

DateTime