Huggingface transformer model returns string instead of logits

Question

I am trying to run this example from huggingface website. https://huggingface.co/transformers/task_summary.html. It seems that the model returns two strings instead of logits! and that leads to an error thrown by torch.argmax()

    from transformers import AutoTokenizer, AutoModelForQuestionAnswering
    import torch
    
    tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
    
    model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad", return_dict=True)
    
    text = r""" Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose
    architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural
    Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between
    TensorFlow 2.0 and PyTorch.
    """
    
    questions = ["How many pretrained models are available in  Transformers?",
    "What does  Transformers provide?",
    " Transformers provides interoperability between which frameworks?"]
    
    for question in questions:
      inputs = tokenizer(question, text, add_special_tokens=True, return_tensors="pt")
      input_ids = inputs["input_ids"].tolist()[0] # the list of all indices of words in question + context
    
      text_tokens = tokenizer.convert_ids_to_tokens(input_ids) # Get the tokens for the question + context
      answer_start_scores, answer_end_scores = model(**inputs)
    
      answer_start = torch.argmax(answer_start_scores)  # Get the most likely beginning of answer with the argmax of the score
      answer_end = torch.argmax(answer_end_scores) + 1  # Get the most likely end of answer with the argmax of the score
    
      answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
    
      print(f"Question: {question}")
      print(f"Answer: {answer}")

Answer 1

Since one of the recent updates, the models return now task-specific output objects (which are dictionaries) instead of plain tuples. The site you used has not been updated to reflect that change. You can either force the model to return a tuple by specifying return_dict=False:

answer_start_scores, answer_end_scores = model(**inputs, return_dict=False)

or you can extract the values from the QuestionAnsweringModelOutput object by calling the values() method:

answer_start_scores, answer_end_scores = model(**inputs).values()

or even utilizing the QuestionAnsweringModelOutput object:

outputs = model(**inputs)
answer_start_scores = outputs.start_logits
answer_end_scores = outputs.end_logits