optimum/neuron/modeling.py [269:303]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        input_ids: torch.Tensor,
        attention_mask: torch.Tensor,
        token_type_ids: Optional[torch.Tensor] = None,
        **kwargs,
    ):
        neuron_inputs = {
            "input_ids": input_ids,
            "attention_mask": attention_mask,
        }
        if token_type_ids is not None:
            neuron_inputs["token_type_ids"] = token_type_ids

        with self.neuron_padding_manager(neuron_inputs) as inputs:
            outputs = self.model(*inputs)  # shape: [batch_size, sequence_length]
            outputs = self.remove_padding(
                outputs, dims=[0, 1], indices=[input_ids.shape[0], input_ids.shape[1]]
            )  # Remove padding on batch_size(0), and sequence_length(1)

        start_logits = outputs[0]
        end_logits = outputs[1]

        return QuestionAnsweringModelOutput(start_logits=start_logits, end_logits=end_logits)


@add_start_docstrings(
    """
    Neuron Model with a sequence classification/regression head on top (a linear layer on top of the
    pooled output) e.g. for GLUE tasks.
    """,
    NEURON_MODEL_START_DOCSTRING,
)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/neuron/models/bert/model.py [163:197]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        input_ids: torch.Tensor,
        attention_mask: torch.Tensor,
        token_type_ids: Optional[torch.Tensor] = None,
        **kwargs,
    ):
        neuron_inputs = {
            "input_ids": input_ids,
            "attention_mask": attention_mask,
        }
        if token_type_ids is not None:
            neuron_inputs["token_type_ids"] = token_type_ids

        with self.neuron_padding_manager(neuron_inputs) as inputs:
            outputs = self.model(*inputs)  # shape: [batch_size, sequence_length]
            outputs = self.remove_padding(
                outputs, dims=[0, 1], indices=[input_ids.shape[0], input_ids.shape[1]]
            )  # Remove padding on batch_size(0), and sequence_length(1)

        start_logits = outputs[0]
        end_logits = outputs[1]

        return QuestionAnsweringModelOutput(start_logits=start_logits, end_logits=end_logits)


@add_start_docstrings(
    """
    Neuron Model with a sequence classification/regression head on top (a linear layer on top of the
    pooled output) e.g. for GLUE tasks.
    """,
    NEURON_MODEL_START_DOCSTRING,
)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -