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.
python deep-learning jupyter transformers pytorch transformer attention deeplearning attention-mechanism attention-is-all-you-need pytorch-transformers pytorch-transformer transformer-tutorial original-transformer
-
Updated
Dec 27, 2020 - Jupyter Notebook