Method forward

train/patch/modeling_chatglm.py:786–849

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

        }

    def forward(
            self,
            input_ids: Optional[torch.Tensor] = None,
            position_ids: Optional[torch.Tensor] = None,
            attention_mask: Optional[torch.Tensor] = None,
            past_key_values: Optional[Tuple[torch.FloatTensor]] = None,
            inputs_embeds: Optional[torch.Tensor] = None,
            labels: Optional[Tuple[torch.Tensor]] = None,
            use_cache: Optional[bool] = None,
            output_attentions: Optional[bool] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
            return_last_logit: Optional[bool] = False,
    ):
        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

        transformer_outputs = self.transformer(
            input_ids=input_ids,
            position_ids=position_ids,
            attention_mask=attention_mask,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        hidden_states = transformer_outputs[0]
        if return_last_logit:
            hidden_states = hidden_states[-1:]
        lm_logits = self.transformer.output_layer(hidden_states)
        lm_logits = lm_logits.transpose(0, 1).contiguous()

        loss = None
        if labels is not None:
            lm_logits = lm_logits.to(torch.float32)
            # Shift so that tokens < n predict n
            shift_logits = lm_logits[..., :-1, :].contiguous()
            if isinstance(labels, tuple) or isinstance(labels, list):
                labels, weights = labels
            shift_labels = labels[..., 1:].contiguous()
            if self.pack_loss:
                loss_fct = CrossEntropyLoss(ignore_index=-100)#, reduction='none')
                loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
                loss *= weights
            else:
                loss_fct = CrossEntropyLoss(ignore_index=-100)
                loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))

            lm_logits = lm_logits.to(hidden_states.dtype)
            loss = loss.to(hidden_states.dtype)

        if not return_dict:
            output = (lm_logits,) + transformer_outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return CausalLMOutputWithPast(