trait LLMLoaderInferenceParams[T] extends AnyRef
- Alphabetic
- By Inheritance
- LLMLoaderInferenceParams
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def getSystemPrompt: String
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
val
inferenceParameters: InferenceParameters
- Attributes
- protected
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
loadParamsMap(paramsMap: Map[String, Any]): Unit
- Attributes
- protected
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
val
paramsMap: Map[String, Any]
- Attributes
- protected
-
def
setCachePrompt(cachePrompt: Boolean): T
Whether to remember the prompt to avoid reprocessing it
-
def
setDynamicTemperatureExponent(dynatempExponent: Float): T
Set the dynamic temperature exponent (default: 1.0)
-
def
setDynamicTemperatureRange(dynatempRange: Float): T
Set the dynamic temperature range (default: 0.0, 0.0 = disabled)
-
def
setFrequencyPenalty(frequencyPenalty: Float): T
Set the repetition alpha frequency penalty (default: 0.0, 0.0 = disabled)
-
def
setGrammar(grammar: String): T
Set BNF-like grammar to constrain generations (see samples in grammars/ dir)
-
def
setIgnoreEos(ignoreEos: Boolean): T
Set whether to ignore end of stream token and continue generating (implies --logit-bias 2-inf)
-
def
setInputPrefix(inputPrefix: String): T
Set a prefix for infilling (default: empty)
-
def
setInputSuffix(inputSuffix: String): T
Set a suffix for infilling (default: empty)
-
def
setMinKeep(minKeep: Int): T
Set the amount of tokens the samplers should return at least (0 = disabled)
-
def
setMinP(minP: Float): T
Set min-p sampling (default: 0.1, 0.0 = disabled)
-
def
setMiroStatEta(mirostatEta: Float): T
Set the MiroStat learning rate, parameter eta (default: 0.1)
-
def
setMiroStatTau(mirostatTau: Float): T
Set the MiroStat target entropy, parameter tau (default: 5.0)
-
def
setNKeep(nKeep: Int): T
Set the number of tokens to keep from the initial prompt (default: 0, -1 = all)
-
def
setNPredict(nPredict: Int): T
Set the number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled)
-
def
setNProbs(nProbs: Int): T
Set the amount top tokens probabilities to output if greater than 0.
-
def
setPenalizeNl(penalizeNl: Boolean): T
Whether to penalize newline tokens
- def setPenaltyPrompt(tokens: ArrayList[Int]): T
-
def
setPenaltyPrompt(tokens: Array[Int]): T
Override which tokens to penalize for repetition.
Override which tokens to penalize for repetition. E.g. if original prompt is "Alice: Hello!" and penaltyPrompt corresponds to the token ids of "Hello!", only the latter will be penalized if repeated. See pull request 3727 for more details.
-
def
setPenaltyPrompt(penaltyPrompt: String): T
Override which part of the prompt is penalized for repetition.
Override which part of the prompt is penalized for repetition. E.g. if original prompt is "Alice: Hello!" and penaltyPrompt is "Hello!", only the latter will be penalized if repeated. See pull request 3727 for more details.
-
def
setPresencePenalty(presencePenalty: Float): T
Set the repetition alpha presence penalty (default: 0.0, 0.0 = disabled)
-
def
setRepeatLastN(repeatLastN: Int): T
Set the last n tokens to consider for penalties (default: 64, 0 = disabled, -1 = ctx_size)
-
def
setRepeatPenalty(repeatPenalty: Float): T
Set the penalty of repeated sequences of tokens (default: 1.0, 1.0 = disabled)
-
def
setSeed(seed: Int): T
Set the RNG seed (default: -1, use random seed for < 0)
- def setStopStrings(stopStrings: ArrayList[String]): T
-
def
setStopStrings(stopStrings: Array[String]): T
Set strings upon seeing which token generation is stopped
- def setSystemPrompt(systemPrompt: String): T
-
def
setTemperature(temperature: Float): T
Set the temperature (default: 0.8)
-
def
setTfsZ(tfsZ: Float): T
Set tail free sampling, parameter z (default: 1.0, 1.0 = disabled)
-
def
setTopK(topK: Int): T
Set top-k sampling (default: 40, 0 = disabled)
-
def
setTopP(topP: Float): T
Set top-p sampling (default: 0.9, 1.0 = disabled)
-
def
setTypicalP(typicalP: Float): T
Set locally typical sampling, parameter p (default: 1.0, 1.0 = disabled)
-
def
setUseChatTemplate(useChatTemplate: Boolean): T
Set whether or not generate should apply a chat template (default: false)
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()