CyberZHG
CyberZHG
keras-layer-normalization
Layer normalization implemented in Keras
keras-pos-embd
Position embedding layers in Keras
keras-transformer-xl
Transformer-XL with checkpoint loader
keras-lookahead
Lookahead mechanism for optimizers in Keras.
keras-adaptive-softmax
Adaptive embedding and softmax
keras-drop-block
DropBlock implemented in Keras
keras-gradient-accumulation
Gradient accumulation for Keras