► KerasHub: Pretrained Models / API documentation / KerasHub Modeling Layers

KerasHub Modeling Layers

KerasHub modeling layers are give keras.layers.Layer implementations for building blocks common to pretrained models. They can be used to create a new model from scratch, or to extend a pretrained model.

TransformerEncoder layer

TransformerDecoder layer

FNetEncoder layer

FNetEncoder class

PositionEmbedding layer

PositionEmbedding class

RotaryEmbedding layer

RotaryEmbedding class

SinePositionEncoding layer

SinePositionEncoding class

ReversibleEmbedding layer

ReversibleEmbedding class

TokenAndPositionEmbedding layer

TokenAndPositionEmbedding class

AlibiBias layer

AlibiBias class

MaskedLMHead layer

MaskedLMHead class

CachedMultiHeadAttention layer

CachedMultiHeadAttention class

KerasHub Modeling Layers

TransformerEncoder layer

TransformerDecoder layer

FNetEncoder layer

PositionEmbedding layer

RotaryEmbedding layer

SinePositionEncoding layer

ReversibleEmbedding layer

TokenAndPositionEmbedding layer

AlibiBias layer

MaskedLMHead layer

CachedMultiHeadAttention layer