Package io.github.kirstenali.deepj.layers.transformer.norm

Class RMSNorm1D

java.lang.Object

io.github.kirstenali.deepj.layers.transformer.norm.RMSNorm1D

All Implemented Interfaces:

Layer, NormLayer, Trainable

public final class RMSNorm1D
extends Object
implements NormLayer

Constructor Summary

Constructors

Constructor	Description
RMSNorm1D(int dim)
RMSNorm1D(int dim, ParameterFactory parameters)

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)
List<Parameter>	parameters()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface io.github.kirstenali.deepj.layers.Layer

forward, supportsIncrementalInference

Methods inherited from interface io.github.kirstenali.deepj.training.Trainable

zeroGrad

Constructor Details

RMSNorm1D

public RMSNorm1D(int dim)

RMSNorm1D

public RMSNorm1D(int dim,
 ParameterFactory parameters)

Method Details

forward

public Tensor forward(Tensor input)

Specified by:

forward in interface Layer

parameters

public List<Parameter> parameters()

Specified by:

parameters in interface Trainable