jeffreykthomas/roberta-fine-tuned-stanford

Para usar este modelo, puedes utilizar el siguiente código en Python con la biblioteca Transformers:

from transformers import AutoModelForQuestionAnswering, AutoTokenizer
import torch

model_name = 'jeffreykthomas/roberta-fine-tuned-stanford'
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

question = 'Where do I live?'
context = 'My name is Wolfgang and I live in Berlin'
inputs = tokenizer(question, context, return_tensors='pt')
with torch.no_grad():
    outputs = model(**inputs)

answer_start = torch.argmax(outputs.start_logits)
answer_end = torch.argmax(outputs.end_logits) + 1
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs['input_ids'][0][answer_start:answer_end]))
print(f'Answer: {answer}')