def answer():
from transformers import AutoTokenizer, MobileBertForQuestionAnswering, pipeline
modelname = "csarron/mobilebert-uncased-squad-v2"
model = MobileBertForQuestionAnswering.from_pretrained(modelname)
tokenizer = AutoTokenizer.from_pretrained(modelname)
nlp = pipeline("question-answering", model=model, tokenizer=tokenizer)
with open("merkel.txt", "r") as file:
context = file.read()
response_bert = nlp({
"question": request.json["question"],
"context": context
})
answer = response_bert.get("answer", "No answer available.")
confidence = response_bert.get("score", "No confidence available")
response = app.response_class(
response=f"{answer} (Confidence: {confidence:.4f})",
status=200,
mimetype="application/json")
return response
def create_and_check_mobilebert_for_question_answering(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = MobileBertForQuestionAnswering(config=config)
model.to(torch_device)
model.eval()
result = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
start_positions=sequence_labels,
end_positions=sequence_labels,
)
self.parent.assertEqual(result.start_logits.shape, (self.batch_size, self.seq_length))
self.parent.assertEqual(result.end_logits.shape, (self.batch_size, self.seq_length))
def create_and_check_mobilebert_for_question_answering(
self, config, input_ids, token_type_ids, input_mask,
sequence_labels, token_labels, choice_labels):
model = MobileBertForQuestionAnswering(config=config)
model.to(torch_device)
model.eval()
loss, start_logits, end_logits = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
start_positions=sequence_labels,
end_positions=sequence_labels,
)
result = {
"loss": loss,
"start_logits": start_logits,
"end_logits": end_logits,
}
self.parent.assertListEqual(list(result["start_logits"].size()),
[self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["end_logits"].size()),
[self.batch_size, self.seq_length])
self.check_loss_output(result)