Using LongformerForMultipleChoice for processing multiple-choice questions with the 4 options

[h56cho]

Hello,

Suppose that I want to process multiple-choice questions with 4 options with LongformerForMultipleChoice.

so each question has main_question, option1, option2, option3, and option4.

How can I generate input_ids from the LongformerTokenizer, so that the LongformerForMultipleChoice can correctly take each of my multiple-choice question as the ones with 4 options?

Thank you,

[valhalla]

What you are doing here seems correct

Strange error when using the Longformer (HuggingFace developers, please reply)

Hello, I am trying to use LongformerForMultipleChoice model, and the code I am using is the following: # import the pre-trained HuggingFace Longformer tokenizer. longformer_tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096') # get the pre-trained HuggingFace Longformer best_model_longformer = LongformerForMultipleChoice.from_pretrained('allenai/longformer-base-4096', output_hidden_states = True) # my multipl…

just make sure when you are passing labels it’s value should be between [0.. num_choices-1]