case class TransformerEmbedding(embedding: Embedding, addPositionalEmbedding: Boolean, positionalEmbedding: Constant) extends GenericModule[Variable, Variable] with Product with Serializable
A module with positional and token embeddings
Token embeddings are lookup embeddings. Positional embeddings are supplied as a constant. They are supposed to come from a fixed unlearned derivation of the positions.
Token and positional embeddings are summed.
Gradients are not computed for positionalEmbedding
- Alphabetic
- By Inheritance
- TransformerEmbedding
- Serializable
- Product
- Equals
- GenericModule
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
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
- val addPositionalEmbedding: Boolean
- def apply[S](a: Variable)(implicit arg0: Sc[S]): Variable
Alias of forward
Alias of forward
- Definition Classes
- GenericModule
- 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()
- val embedding: Embedding
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def forward[S](x: Variable)(implicit arg0: Sc[S]): Variable
The implementation of the function.
The implementation of the function.
In addition of
xit can also use all thestate to compute its value.- Definition Classes
- TransformerEmbedding → GenericModule
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def gradients(loss: Variable, zeroGrad: Boolean = true): Seq[Option[STen]]
Computes the gradient of loss with respect to the parameters.
Computes the gradient of loss with respect to the parameters.
- Definition Classes
- GenericModule
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- final def learnableParameters: Long
Returns the total number of optimizable parameters.
Returns the total number of optimizable parameters.
- Definition Classes
- GenericModule
- 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 parameters: Seq[(Constant, PTag)]
Returns the state variables which need gradient computation.
Returns the state variables which need gradient computation.
- Definition Classes
- GenericModule
- val positionalEmbedding: Constant
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- def state: List[(Constant, LeafTag with Product with Serializable)]
List of optimizable, or non-optimizable, but stateful parameters
List of optimizable, or non-optimizable, but stateful parameters
Stateful means that the state is carried over the repeated forward calls.
- Definition Classes
- TransformerEmbedding → GenericModule
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- 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])
- final def zeroGrad(): Unit
- Definition Classes
- GenericModule
Deprecated Value Members
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable]) @Deprecated
- Deprecated
(Since version 9)