Hi lightseq Team, I notice lightseq' transformer architecture has an extra layer_norm on both encoder and decoder level (outside decoder layers) Due to the architectural difference, I m unable to ...

Initialize the Lightseq Transformer Encoder Layer. Static variable: layer_id: The layer-index counter starting from 0 and incrementing by 1 every time a layer object is instantiated, ...

Neural machine translation models, such as Recurrent Neural Networks, Long Short-Term Memory networks and the Transformer, are widely used in many translation tasks. Neural machine translation models ...