chunked/nltk_chunking/tasks_multiple_choice/chunk_42.txt

You should also create some labels:

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("my_awesome_swag_model")
inputs = tokenizer([[prompt, candidate1], [prompt, candidate2]], return_tensors="pt", padding=True)
labels = torch.tensor(0).unsqueeze(0)

Pass your inputs and labels to the model and return the logits:

from transformers import AutoModelForMultipleChoice
model = AutoModelForMultipleChoice.from_pretrained("my_awesome_swag_model")
outputs = model(**{k: v.unsqueeze(0) for k, v in inputs.items()}, labels=labels)
logits = outputs.logits

Get the class with the highest probability:

predicted_class = logits.argmax().item()
predicted_class
'0'

Tokenize each prompt and candidate answer pair and return TensorFlow tensors:

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("my_awesome_swag_model")
inputs = tokenizer([[prompt, candidate1], [prompt, candidate2]], return_tensors="tf", padding=True)

Pass your inputs to the model and return the logits:

from transformers import TFAutoModelForMultipleChoice
model = TFAutoModelForMultipleChoice.from_pretrained("my_awesome_swag_model")
inputs = {k: tf.expand_dims(v, 0) for k, v in inputs.items()}
outputs = model(inputs)
logits = outputs.logits

Get the class with the highest probability:

predicted_class = int(tf.math.argmax(logits, axis=-1)[0])
predicted_class
'0'