BERT for TensorFlow Jupyter Notebook

This notebook provides a worked example for utilising the BERT for TensorFlow model scripts.

For convenience, it is launched inside of NVIDIA’s Tensorflow Docker container hosted on NGC to have a reproducible environment that is easy to set up.

View in NGC

To take a look at this, or any other, notebook; follow these steps:

1. Navigate to the File Browser tab of the asset in NGC
2. Select the version you'd like to see
3. Under the actions menu (three dots) for the .ipynb file select "View Jupyter"
4. There you have it! You can read a notebook for documentation and copy code samples without ever leaving NGC.

Quick Start

note - This method will not allow you to run the notebook's contents.

Assuming you have Jupyter installed, to simply read through the notebook and code samples follow these steps:

1. Download the latest version of the notebook from this page
2. Navigate to the downloaded directory
3. Deploy the notebook with this command:

jupyter notebook BERT_Jupyter.ipynb

You'll now be able to view the notebook from your web browser.