public sealed class Generator.Types.ModelParameter : IMessage<Generator.Types.ModelParameter>, IEquatable<Generator.Types.ModelParameter>, IDeepCloneable<Generator.Types.ModelParameter>, IBufferMessage, IMessage
Reference documentation and code samples for the Dialogflow v3 API class Generator.Types.ModelParameter.
Parameters to be passed to the LLM. If not set, default values will be used.
Implements
IMessageGeneratorTypesModelParameter, IEquatableGeneratorTypesModelParameter, IDeepCloneableGeneratorTypesModelParameter, IBufferMessage, IMessageNamespace
Google.Cloud.Dialogflow.Cx.V3Assembly
Google.Cloud.Dialogflow.Cx.V3.dll
Constructors
ModelParameter()
public ModelParameter()
ModelParameter(ModelParameter)
public ModelParameter(Generator.Types.ModelParameter other)
Parameter | |
---|---|
Name | Description |
other |
GeneratorTypesModelParameter |
Properties
HasMaxDecodeSteps
public bool HasMaxDecodeSteps { get; }
Gets whether the "max_decode_steps" field is set
Property Value | |
---|---|
Type | Description |
bool |
HasTemperature
public bool HasTemperature { get; }
Gets whether the "temperature" field is set
Property Value | |
---|---|
Type | Description |
bool |
HasTopK
public bool HasTopK { get; }
Gets whether the "top_k" field is set
Property Value | |
---|---|
Type | Description |
bool |
HasTopP
public bool HasTopP { get; }
Gets whether the "top_p" field is set
Property Value | |
---|---|
Type | Description |
bool |
MaxDecodeSteps
public int MaxDecodeSteps { get; set; }
The maximum number of tokens to generate.
Property Value | |
---|---|
Type | Description |
int |
Temperature
public float Temperature { get; set; }
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.
Property Value | |
---|---|
Type | Description |
float |
TopK
public int TopK { get; set; }
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.
Property Value | |
---|---|
Type | Description |
int |
TopP
public float TopP { get; set; }
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.
Property Value | |
---|---|
Type | Description |
float |