Small bug in BERT SQUAD tutorial

In this blog post: Question Answering with a Fine-Tuned BERT · Chris McCormick

# Run our example through the model.
start_scores, end_scores = model(torch.tensor([input_ids]), # The tokens representing our input text.
                              token_type_ids=torch.tensor([segment_ids])) # The segment IDs to differentiate question from answer_text

This code is wrong because huggingface changed the API of how they return values. It should be updated to:

output = model(torch.tensor([input_ids]), # The tokens representing our input text.
                                 token_type_ids=torch.tensor([segment_ids])) # The segment IDs to differentiate question from answer_text
start_scores = output.start_logits
end_scores = output.end_logits