Class ScoreModelGrader.SamplingParams
-
- All Implemented Interfaces:
public final class ScoreModelGrader.SamplingParams
The sampling parameters for the model.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public final class
ScoreModelGrader.SamplingParams.Builder
A 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.Builder
toBuilder()
final ScoreModelGrader.SamplingParams
validate()
final Boolean
isValid()
Boolean
equals(Object other)
Integer
hashCode()
String
toString()
final static ScoreModelGrader.SamplingParams.Builder
builder()
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
minimal
,low
,medium
, andhigh
. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
-
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()
-
builder
final static ScoreModelGrader.SamplingParams.Builder builder()
Returns a mutable builder for constructing an instance of SamplingParams.
-
-
-
-