object LanguageModelLoss extends Serializable
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- LanguageModelLoss
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- Protected
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
- def apply[S](maxLength: Int, vocabularySize: Int, numBlocks: Int, embeddingDim: Int, attentionHiddenPerHeadDim: Int, attentionNumHeads: Int, encoderMlpHiddenDim: Int, dropout: Double, padToken: Long, tOpt: STenOptions, linearized: Boolean)(implicit arg0: Sc[S]): LanguageModelLoss
Allocate language model module with negative log likelihood loss
Allocate language model module with negative log likelihood loss
- maxLength
Total sequence length including padding if used. Sometimes called block length or context length.
- vocabularySize
Total vocabulary size.
- numBlocks
Number of transformer blocks (layers).
- embeddingDim
Width of the initial embedding dimension, as well as the output width of each transformer block
- attentionHiddenPerHeadDim
Per head hidden dimension in the multihead attention
- attentionNumHeads
Number of attention heads in the multihead attention
- encoderMlpHiddenDim
Hidden dimension within transformer blocks
- padToken
This token is ignored during loss computation. Not used otherwise.
- tOpt
TensorOption to set device and data type
- linearized
Whether to use linearized self attention
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- implicit val load: Load[LanguageModelLoss]
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toString(): String
- Definition Classes
- AnyRef → Any
- implicit val trainingMode: TrainingMode[LanguageModelLoss]
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
Deprecated Value Members
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable]) @Deprecated
- Deprecated
(Since version 9)