Обнимающееся лицо сделало это для вас: https://github.com/huggingface/pytorch-pretrained-BERT/blob/master/pytorch_pretrained_bert/modeling.py#L854
class BertForNextSentencePrediction(BertPreTrainedModel):
"""BERT model with next sentence prediction head.
This module comprises the BERT model followed by the next sentence classification head.
Params:
config: a BertConfig class instance with the configuration to build a new model.
Inputs:
`input_ids`: a torch.LongTensor of shape [batch_size, sequence_length]
with the word token indices in the vocabulary(see the tokens preprocessing logic in the scripts
`extract_features.py`, `run_classifier.py` and `run_squad.py`)
`token_type_ids`: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token
types indices selected in [0, 1]. Type 0 corresponds to a `sentence A` and type 1 corresponds to
a `sentence B` token (see BERT paper for more details).
`attention_mask`: an optional torch.LongTensor of shape [batch_size, sequence_length] with indices
selected in [0, 1]. It's a mask to be used if the input sequence length is smaller than the max
input sequence length in the current batch. It's the mask that we typically use for attention when
a batch has varying length sentences.
`next_sentence_label`: next sentence classification loss: torch.LongTensor of shape [batch_size]
with indices selected in [0, 1].
0 => next sentence is the continuation, 1 => next sentence is a random sentence.
Outputs:
if `next_sentence_label` is not `None`:
Outputs the total_loss which is the sum of the masked language modeling loss and the next
sentence classification loss.
if `next_sentence_label` is `None`:
Outputs the next sentence classification logits of shape [batch_size, 2].
Example usage:
```python
# Already been converted into WordPiece token ids
input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]])
input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]])
token_type_ids = torch.LongTensor([[0, 0, 1], [0, 1, 0]])
config = BertConfig(vocab_size_or_config_json_file=32000, hidden_size=768,
num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072)
model = BertForNextSentencePrediction(config)
seq_relationship_logits = model(input_ids, token_type_ids, input_mask)
```
"""
def __init__(self, config):
super(BertForNextSentencePrediction, self).__init__(config)
self.bert = BertModel(config)
self.cls = BertOnlyNSPHead(config)
self.apply(self.init_bert_weights)
def forward(self, input_ids, token_type_ids=None, attention_mask=None, next_sentence_label=None):
_, pooled_output = self.bert(input_ids, token_type_ids, attention_mask,
output_all_encoded_layers=False)
seq_relationship_score = self.cls( pooled_output)
if next_sentence_label is not None:
loss_fct = CrossEntropyLoss(ignore_index=-1)
next_sentence_loss = loss_fct(seq_relationship_score.view(-1, 2), next_sentence_label.view(-1))
return next_sentence_loss
else:
return seq_relationship_score