Method forward

modelscope/models/nlp/peer/backbone.py:487–556

(
            self,
            hidden_states,
            attention_mask=None,
            head_mask=None,
            encoder_hidden_states=None,
            encoder_attention_mask=None,
            past_key_value=None,
            output_attentions=False,
            side_info_sets=dict(),
    )

        self.output = PeerOutput(config)

    def forward(
            self,
            hidden_states,
            attention_mask=None,
            head_mask=None,
            encoder_hidden_states=None,
            encoder_attention_mask=None,
            past_key_value=None,
            output_attentions=False,
            side_info_sets=dict(),
    ):
        # decoder uni-directional self-attention cached key/values tuple is at positions 1,2
        self_attn_past_key_value = past_key_value[:
                                                  2] if past_key_value is not None else None
        self_attention_outputs = self.attention(
            hidden_states,
            attention_mask,
            head_mask,
            output_attentions=output_attentions,
            past_key_value=self_attn_past_key_value,
            side_info_sets=side_info_sets,
        )
        attention_output = self_attention_outputs[0]

        # if decoder, the last output is tuple of self-attn cache
        if self.is_decoder:
            outputs = self_attention_outputs[1:-1]
            present_key_value = self_attention_outputs[-1]
        else:
            outputs = self_attention_outputs[
                1:]  # add self attentions if we output attention weights

        cross_attn_present_key_value = None
        if self.is_decoder and encoder_hidden_states is not None:
            assert hasattr(
                self, 'crossattention'
            ), f'If `encoder_hidden_states` are passed, {self} has to be instantiated \
                with cross-attention layers by setting `config.add_cross_attention=True`'

            # cross_attn cached key/values tuple is at positions 3,4 of past_key_value tuple
            cross_attn_past_key_value = past_key_value[
                -2:] if past_key_value is not None else None
            cross_attention_outputs = self.crossattention(
                attention_output,
                attention_mask,
                head_mask,
                encoder_hidden_states,
                encoder_attention_mask,
                cross_attn_past_key_value,
                output_attentions,
            )
            attention_output = cross_attention_outputs[0]
            outputs = outputs + cross_attention_outputs[
                1:-1]  # add cross attentions if we output attention weights

            # add cross-attn cache to positions 3,4 of present_key_value tuple
            cross_attn_present_key_value = cross_attention_outputs[-1]
            present_key_value = present_key_value + cross_attn_present_key_value