Interface Generator.ModelParameterOrBuilder
- All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder,com.google.protobuf.MessageOrBuilder
- All Known Implementing Classes:
Generator.ModelParameter,Generator.ModelParameter.Builder
- Enclosing class:
- Generator
public static interface Generator.ModelParameterOrBuilder
extends com.google.protobuf.MessageOrBuilder
-
Method Summary
Modifier and TypeMethodDescriptionintThe maximum number of tokens to generate.floatThe temperature used for sampling.intgetTopK()If set, the sampling process in each step is limited to the top_k tokens with highest probabilities.floatgetTopP()If set, only the tokens comprising the top top_p probability mass are considered.booleanThe maximum number of tokens to generate.booleanThe temperature used for sampling.booleanhasTopK()If set, the sampling process in each step is limited to the top_k tokens with highest probabilities.booleanhasTopP()If set, only the tokens comprising the top top_p probability mass are considered.Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder
isInitializedMethods inherited from interface com.google.protobuf.MessageOrBuilder
findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof
-
Method Details
-
hasTemperature
boolean hasTemperature()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.
optional float temperature = 1;- Returns:
- Whether the temperature field is set.
-
getTemperature
float getTemperature()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.
optional float temperature = 1;- Returns:
- The temperature.
-
hasMaxDecodeSteps
boolean hasMaxDecodeSteps()The maximum number of tokens to generate.
optional int32 max_decode_steps = 2;- Returns:
- Whether the maxDecodeSteps field is set.
-
getMaxDecodeSteps
int getMaxDecodeSteps()The maximum number of tokens to generate.
optional int32 max_decode_steps = 2;- Returns:
- The maxDecodeSteps.
-
hasTopP
boolean hasTopP()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.
optional float top_p = 3;- Returns:
- Whether the topP field is set.
-
getTopP
float getTopP()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.
optional float top_p = 3;- Returns:
- The topP.
-
hasTopK
boolean hasTopK()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.
optional int32 top_k = 4;- Returns:
- Whether the topK field is set.
-
getTopK
int getTopK()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.
optional int32 top_k = 4;- Returns:
- The topK.
-