Method forward

modelscope/models/nlp/deberta_v2/backbone.py:1093–1222

r""" Args: input_ids (`torch.LongTensor` of shape `('batch_size, sequence_length')`): Indices of input sequence tokens in the vocabulary. attention_mask (`torch.FloatTensor` of shape `('batch_size, sequence_length')`, *optional*): Mask

(
        self,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    )

            'The prune function is not implemented in DeBERTa model.')

    def forward(
        self,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, AttentionBackboneModelOutput]:
        r"""
        Args:
            input_ids (`torch.LongTensor` of shape `('batch_size, sequence_length')`):
                Indices of input sequence tokens in the vocabulary.

            attention_mask (`torch.FloatTensor` of shape `('batch_size, sequence_length')`, *optional*):
                Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

            token_type_ids (`torch.LongTensor` of shape `('batch_size, sequence_length')`, *optional*):
                Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
                1]`:

                - 0 corresponds to a *sentence A* token,
                - 1 corresponds to a *sentence B* token.

            position_ids (`torch.LongTensor` of shape `('batch_size, sequence_length')`, *optional*):
                Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
                `[0,config.max_position_embeddings - 1]`.

            inputs_embeds (`torch.FloatTensor` of shape `('batch_size, sequence_length', hidden_size)`, *optional*):
                Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
                This is useful if you want more control over how to convert *input_ids* indices into associated
                vectors than the model's internal embedding lookup matrix.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
                tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
                more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a dataclass instead of a plain tuple.

        Returns:
            Returns `modelscope.outputs.AttentionBackboneModelOutput`

        Examples:
            >>> from modelscope.models import Model
            >>> from modelscope.preprocessors import Preprocessor
            >>> model = Model.from_pretrained('damo/nlp_debertav2_fill-mask_chinese-lite', task='backbone')
            >>> preprocessor = Preprocessor.from_pretrained('damo/nlp_debertav2_fill-mask_chinese-lite')
            >>> print(model(**preprocessor('这是个测试')))
        """

        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions