Method forward

src/transformers/modeling_ctrl.py:332–475

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

(
        self,
        input_ids=None,
        past=None,
        attention_mask=None,
        token_type_ids=None,
        position_ids=None,
        head_mask=None,
        inputs_embeds=None,
        use_cache=None,
        output_attentions=None,
        output_hidden_states=None,
    )

    @add_start_docstrings_to_callable(CTRL_INPUTS_DOCSTRING)
    @add_code_sample_docstrings(tokenizer_class=_TOKENIZER_FOR_DOC, checkpoint="ctrl")
    def forward(
        self,
        input_ids=None,
        past=None,
        attention_mask=None,
        token_type_ids=None,
        position_ids=None,
        head_mask=None,
        inputs_embeds=None,
        use_cache=None,
        output_attentions=None,
        output_hidden_states=None,
    ):
        r"""
    Return:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.CTRLConfig`) and inputs:
        last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the last layer of the model.
        past (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers` with each tensor of shape :obj:`(2, batch_size, num_heads, sequence_length, embed_size_per_head)`):
            Contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `past` input) to speed up sequential decoding.
        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
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )

        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_shape = input_ids.size()
            input_ids = input_ids.view(-1, input_shape[-1])
            batch_size = input_ids.shape[0]
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.size()[:-1]
            batch_size = inputs_embeds.shape[0]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        if past is None:
            past_length = 0
            past = [None] * len(self.h)
        else:
            past_length = past[0][0].size(-2)
        if position_ids is None:
            device = input_ids.device if input_ids is not None else inputs_embeds.device