parsbert_question_answering_PQuAD

# Pytorch
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
path = 'pedramyazdipoor/parsbert_question_answering_PQuAD'
tokenizer = AutoTokenizer.from_pretrained(path)
model = AutoModelForQuestionAnswering.from_pretrained(path)

# Tensorflow
from transformers import AutoTokenizer, TFAutoModelForQuestionAnswering
path = 'pedramyazdipoor/parsbert_question_answering_PQuAD'
tokenizer = AutoTokenizer.from_pretrained(path)
model = TFAutoModelForQuestionAnswering.from_pretrained(path)

# Inference para Pytorch
import torch
import numpy as np
def generate_indexes(start_logits, end_logits, N, max_index):
  output_start = start_logits
  output_end = end_logits
  start_indexes = np.arange(len(start_logits))
  start_probs = output_start
  list_start = dict(zip(start_indexes, start_probs.tolist()))
  end_indexes = np.arange(len(end_logits))
  end_probs = output_end
  list_end = dict(zip(end_indexes, end_probs.tolist()))
  sorted_start_list = sorted(list_start.items(), key=lambda x: x[1], reverse=True)
  sorted_end_list = sorted(list_end.items(), key=lambda x: x[1], reverse=True)
  final_start_idx, final_end_idx = [[] for l in range(2)]
  start_idx, end_idx, prob = 0, 0, (start_probs.tolist()[0] + end_probs.tolist()[0])
  for a in range(0,N):
    for b in range(0,N):
      if (sorted_start_list[a][1] + sorted_end_list[b][1]) > prob:
        if (sorted_start_list[a][0] < sorted_end_list[b][0]) and (sorted_end_list[b][0] < max_index):
          prob = sorted_start_list[a][1] + sorted_end_list[b][1]
          start_idx = sorted_start_list[a][0]
          end_idx = sorted_end_list[b][0]
          final_start_idx.append(start_idx)
          final_end_idx.append(end_idx)
  return final_start_idx[0], final_end_idx[0]

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.eval().to(device)
text = 'Saludos, tengo 26 años'
question = '¿Cuántos años tengo?'
encoding = tokenizer(text,question,add_special_tokens=True, return_token_type_ids=True, return_tensors='pt', padding=True, return_offsets_mapping=True, truncation='only_first', max_length=32)
out = model(encoding['input_ids'].to(device),encoding['attention_mask'].to(device), encoding['token_type_ids'].to(device))
answer_start_index, answer_end_index = generate_indexes(out['start_logits'][0][1:], out['end_logits'][0][1:], 5, 0)
print(tokenizer.tokenize(text + question))
print(tokenizer.tokenize(text + question)[answer_start_index : (answer_end_index + 1)])