Class ScoreModelGrader.SamplingParams
-
- All Implemented Interfaces:
public final class ScoreModelGrader.SamplingParamsThe sampling parameters for the model.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public final classScoreModelGrader.SamplingParams.BuilderA builder for SamplingParams.
-
Method Summary
Modifier and Type Method Description final Optional<Long>maxCompletionsTokens()The maximum number of tokens the grader model may generate in its response. final Optional<ReasoningEffort>reasoningEffort()Constrains effort on reasoning for reasoning models. final Optional<Long>seed()A seed value to initialize the randomness, during sampling. final Optional<Double>temperature()A higher temperature increases randomness in the outputs. final Optional<Double>topP()An alternative to temperature for nucleus sampling; 1.0 includes all tokens. final JsonField<Long>_maxCompletionsTokens()Returns the raw JSON value of maxCompletionsTokens. final JsonField<ReasoningEffort>_reasoningEffort()Returns the raw JSON value of reasoningEffort. final JsonField<Long>_seed()Returns the raw JSON value of seed. final JsonField<Double>_temperature()Returns the raw JSON value of temperature. final JsonField<Double>_topP()Returns the raw JSON value of topP. final Map<String, JsonValue>_additionalProperties()final ScoreModelGrader.SamplingParams.BuildertoBuilder()final ScoreModelGrader.SamplingParamsvalidate()Validates that the types of all values in this object match their expected types recursively. final BooleanisValid()Booleanequals(Object other)IntegerhashCode()StringtoString()final static ScoreModelGrader.SamplingParams.Builderbuilder()Returns a mutable builder for constructing an instance of SamplingParams. -
-
Method Detail
-
maxCompletionsTokens
final Optional<Long> maxCompletionsTokens()
The maximum number of tokens the grader model may generate in its response.
-
reasoningEffort
final Optional<ReasoningEffort> reasoningEffort()
Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high,xhigh, andmax. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.
-
temperature
final Optional<Double> temperature()
A higher temperature increases randomness in the outputs.
-
topP
final Optional<Double> topP()
An alternative to temperature for nucleus sampling; 1.0 includes all tokens.
-
_maxCompletionsTokens
final JsonField<Long> _maxCompletionsTokens()
Returns the raw JSON value of maxCompletionsTokens.
Unlike maxCompletionsTokens, this method doesn't throw if the JSON field has an unexpected type.
-
_reasoningEffort
final JsonField<ReasoningEffort> _reasoningEffort()
Returns the raw JSON value of reasoningEffort.
Unlike reasoningEffort, this method doesn't throw if the JSON field has an unexpected type.
-
_seed
final JsonField<Long> _seed()
Returns the raw JSON value of seed.
Unlike seed, this method doesn't throw if the JSON field has an unexpected type.
-
_temperature
final JsonField<Double> _temperature()
Returns the raw JSON value of temperature.
Unlike temperature, this method doesn't throw if the JSON field has an unexpected type.
-
_topP
final JsonField<Double> _topP()
Returns the raw JSON value of topP.
Unlike topP, this method doesn't throw if the JSON field has an unexpected type.
-
_additionalProperties
final Map<String, JsonValue> _additionalProperties()
-
toBuilder
final ScoreModelGrader.SamplingParams.Builder toBuilder()
-
validate
final ScoreModelGrader.SamplingParams validate()
Validates that the types of all values in this object match their expected types recursively.
This method is not forwards compatible with new types from the API for existing fields.
-
builder
final static ScoreModelGrader.SamplingParams.Builder builder()
Returns a mutable builder for constructing an instance of SamplingParams.
-
-
-
-