iwslt

There are 0 repository under iwslt topic.

vineeths96 / Compressed-Transformers
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.
deep-learning edge-ml federated-learning iwslt model-compression pytorch transformer
Language:Python 21
sutd-visual-computing-group / LS-KD-compatibility
[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.
cub200-2011 imagenet iwslt knowledge-distillation label-smoothing machine-translation pytorch systematic-diffusion
Language:Python 11
gugundi / NeuralMachineTranslation
Neural Machine Tranlation using Local Attention
attention attention-mechanism encoder-decoder encoder-decoder-model iwslt local-attention multi30k nmt python python3
Language:Jupyter Notebook 6
vuongdanghuy / nmt_transformer
English-Vietnamese Machine Translation using Transformer
iwslt transformer domain-news machine-translation machine-learning
Language:Jupyter Notebook 2

vineeths96 / Compressed-Transformers