optimum/neuron/modeling.py [105:143]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    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)
            # last_hidden_state -> (batch_size, sequencen_len, hidden_size)
            last_hidden_state = self.remove_padding(
                [outputs[0]], dims=[0, 1], indices=[input_ids.shape[0], input_ids.shape[1]]
            )[0]  # Remove padding on batch_size(0), and sequence_length(1)
            if len(outputs) > 1:
                # pooler_output -> (batch_size, hidden_size)
                pooler_output = self.remove_padding([outputs[1]], dims=[0], indices=[input_ids.shape[0]])[
                    0
                ]  # Remove padding on batch_size(0)
            else:
                pooler_output = None

        return BaseModelOutputWithPooling(last_hidden_state=last_hidden_state, pooler_output=pooler_output)


@add_start_docstrings(
    """
    Neuron Model for Sentence Transformers.
    """,
    NEURON_MODEL_START_DOCSTRING,
)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/neuron/models/bert/model.py [72:110]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    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)
            # last_hidden_state -> (batch_size, sequencen_len, hidden_size)
            last_hidden_state = self.remove_padding(
                [outputs[0]], dims=[0, 1], indices=[input_ids.shape[0], input_ids.shape[1]]
            )[0]  # Remove padding on batch_size(0), and sequence_length(1)
            if len(outputs) > 1:
                # pooler_output -> (batch_size, hidden_size)
                pooler_output = self.remove_padding([outputs[1]], dims=[0], indices=[input_ids.shape[0]])[
                    0
                ]  # Remove padding on batch_size(0)
            else:
                pooler_output = None

        return BaseModelOutputWithPooling(last_hidden_state=last_hidden_state, pooler_output=pooler_output)


@add_start_docstrings(
    """
    Masked language Bert Model with a `language modeling` head on top, for masked language modeling tasks on Neuron devices.
    """,
    NEURON_MODEL_START_DOCSTRING,
)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -