Class BertForMaskedLM

bert/modeling_bert.py:1005–1110

@add_start_docstrings("""Bert Model with a `language modeling` head on top. """, BERT_START_DOCSTRING)
class BertForMaskedLM(BertPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        assert (
            not config.is_decoder
        ), "If you want to use `BertForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention."

        self.bert = BertModel(config)
        self.cls = BertOnlyMLMHead(config)

        self.init_weights()

    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    @add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
    @add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="bert-base-uncased")
    def forward(
        self,
        input_ids=None,
        attention_mask=None,
        token_type_ids=None,
        position_ids=None,
        head_mask=None,
        inputs_embeds=None,
        labels=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        output_attentions=None,
        output_hidden_states=None,
        **kwargs
    ):
        r"""
        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
            Labels for computing the masked language modeling loss.
            Indices should be in ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)
            Tokens with indices set to ``-100`` are ignored (masked), the loss is only computed for the tokens with labels
            in ``[0, ..., config.vocab_size]``
        kwargs (:obj:`Dict[str, any]`, optional, defaults to `{}`):
            Used to hide legacy arguments that have been deprecated.

    Returns:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
        masked_lm_loss (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
            Masked language modeling loss.
        prediction_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
            Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
            of shape :obj:`(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_attentions=True`` is passed or when ``config.output_attentions=True``):
            Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
            :obj:`(batch_size, num_heads, sequence_length, sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.