Maybe a dumb question - how does the model which is trained to predict the next words answer questions, as shown in the reading comprehension example? Do you just feed it the question and watch it generate the answer, or is something else going on?
hugging face has a simple implementation that augments bert in this manner and you can see the code there. their bertqa model get like an 84 F1 on squad 1.1 which really strong performance. you can augment the thier gpt2 implementation similarly.