Running BERT in EC2 GPU instance

On 14 January, we will begin with a tutorial on ML in a VM with GPU.

I am pretty happy with the experience that i have had using TensorFlow 2.3 and Hub on a virtual machine. We have talked about the BERT paper and other language models, but I want to do a refresher with a practical demo this time.

I have created a small repo with requirements and some instructions. Try Bert

Also, for reference, here is the BERT paper.