There are 0 repository under iwslt topic.
In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization aware training of the linear layers and demonstrate the performance for 8 bits, 4 bits, 2 bits and 1 bit (binary) quantization.
[ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an LS-trained teacher with a low-temperature transfer to render high performance students.
Neural Machine Tranlation using Local Attention
English-Vietnamese Machine Translation using Transformer