Method forward

workers/modeling_chatglm_med.py:887–998

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

        config_class=_CONFIG_FOR_DOC,
    )
    def forward(
            self,
            input_ids: Optional[torch.LongTensor] = None,
            position_ids: Optional[torch.LongTensor] = None,
            attention_mask: Optional[torch.Tensor] = None,
            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
            inputs_embeds: Optional[torch.LongTensor] = None,
            use_cache: Optional[bool] = None,
            output_attentions: Optional[bool] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
    ) -> Union[Tuple[torch.Tensor, ...], BaseModelOutputWithPast]:

        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        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:
            batch_size, seq_length = input_ids.shape[:2]
        elif inputs_embeds is not None:
            batch_size, seq_length, _ = inputs_embeds.shape[:2]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        if past_key_values is None:
            past_key_values = tuple([None] * len(self.layers))

            MASK, gMASK = 150000, 150001
            mask_token = MASK if MASK in input_ids else gMASK
            use_gmask = False if MASK in input_ids else gMASK
            seq = input_ids[0].tolist()

            mask_position = seq.index(mask_token)

            if attention_mask is None:
                attention_mask = self.get_masks(
                    seq=seq,
                    device=input_ids.device
                )

            if position_ids is None:
                position_ids = self.get_position_ids(
                    seq=seq,
                    mask_position=mask_position,
                    device=input_ids.device,
                    gmask=use_gmask
                )

        if inputs_embeds is None:
            inputs_embeds = self.word_embeddings(input_ids)

        # [seq_len, batch, hidden_size]
        hidden_states = inputs_embeds.transpose(0, 1)