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

Class GroupedQueryAttention

java.lang.Object

io.github.kirstenali.deepj.layers.transformer.attention.GroupedQueryAttention

All Implemented Interfaces:

Layer, Trainable

public final class GroupedQueryAttention
extends Object
implements Layer

Constructor Summary

Constructors

Constructor	Description
GroupedQueryAttention(DeepJNovaConfig config, Random random)
GroupedQueryAttention(DeepJNovaConfig config, Random random, ParameterFactory parameters)

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)
Tensor	forward(Tensor input, InferenceContext context)
List<Parameter>	parameters()
boolean	supportsIncrementalInference()

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.training.Trainable

zeroGrad

Constructor Details

GroupedQueryAttention

public GroupedQueryAttention(DeepJNovaConfig config,
 Random random)

GroupedQueryAttention

public GroupedQueryAttention(DeepJNovaConfig config,
 Random random,
 ParameterFactory parameters)

Method Details

forward

public Tensor forward(Tensor input)

Specified by:

forward in interface Layer

supportsIncrementalInference

public boolean supportsIncrementalInference()

Specified by:

supportsIncrementalInference in interface Layer

forward

public Tensor forward(Tensor input,
 InferenceContext context)

Specified by:

forward in interface Layer

parameters

public List<Parameter> parameters()

Specified by:

parameters in interface Trainable