Added some more dropout

tatp22 / linformer-pytorch

My take on a practical implementation of Linformer for Pytorch.

https://arxiv.org/pdf/2006.04768.pdf

MIT License

400 stars 36 forks source link

Closed tatp22 closed 3 years ago

tatp22 commented 3 years ago

The Transformer doesn't have enough normalization. This aims to fix it