Deploy and Infer on BERT MRPC Model?

Hi all,

Sorry in advance for my naivety. I’ve been following this guide to fine-tune a BERT model for the MRPC dataset:

The training and other steps work flawlessly, with a decent level of accuracy.

However, I can’t seem to find any documentation on how to use my exported model for inference?

I’d like to do something as outlined below (obviously pseudocode)…

from bert.deploy import infer 

model = /path/to/model

sentence1 = "The apple fell from the tree"
sentence2 = "The pear fell from the tree"

result = infer(model, sentence1, sentence2)

print(result) # where 0 = not a paraphrase and 1 = is a paraphrase

What would be the best way to go about this? Thanks in advance!!