gordicaleksa/pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

语言：Jupyter Notebook · GitHub 星标：1,119 · Fork：188

话题：attention · attention-is-all-you-need · attention-mechanism · deep-learning · deeplearning · jupyter · original-transformer · python

在 GitHub 上查看原仓库