Method forward

src/transformers/modeling_xlnet.py:755–976

r""" Return: :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.XLNetConfig`) and inputs: last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_predict, hidden_size)`): Sequence of hi

(
        self,
        input_ids=None,
        attention_mask=None,
        mems=None,
        perm_mask=None,
        target_mapping=None,
        token_type_ids=None,
        input_mask=None,
        head_mask=None,
        inputs_embeds=None,
        use_cache=True,
        output_attentions=None,
        output_hidden_states=None,
    )

    @add_start_docstrings_to_callable(XLNET_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
    @add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="xlnet-base-cased")
    def forward(
        self,
        input_ids=None,
        attention_mask=None,
        mems=None,
        perm_mask=None,
        target_mapping=None,
        token_type_ids=None,
        input_mask=None,
        head_mask=None,
        inputs_embeds=None,
        use_cache=True,
        output_attentions=None,
        output_hidden_states=None,
    ):
        r"""
    Return:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.XLNetConfig`) and inputs:
        last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_predict, hidden_size)`):
            Sequence of hidden-states at the last layer of the model.
            `num_predict` corresponds to `target_mapping.shape[1]`. If `target_mapping` is `None`, then `num_predict` corresponds to `sequence_length`.
        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
            Contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `mems` input) to speed up sequential decoding. The token ids which have their past given to this model
            should not be passed as input ids as they have already been computed.
        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.
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )

        # the original code for XLNet uses shapes [len, bsz] with the batch dimension at the end
        # but we want a unified interface in the library with the batch size on the first dimension
        # so we move here the first dimension (batch) to the end
        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            input_ids = input_ids.transpose(0, 1).contiguous()
            qlen, bsz = input_ids.shape[0], input_ids.shape[1]
        elif inputs_embeds is not None:
            inputs_embeds = inputs_embeds.transpose(0, 1).contiguous()
            qlen, bsz = inputs_embeds.shape[0], inputs_embeds.shape[1]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        token_type_ids = token_type_ids.transpose(0, 1).contiguous() if token_type_ids is not None else None
        input_mask = input_mask.transpose(0, 1).contiguous() if input_mask is not None else None