Method forward

train/patch/modeling_chatglm.py:671–720

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

        return self.embedding.word_embeddings

    def forward(
            self,
            input_ids,
            position_ids: Optional[torch.Tensor] = None,
            attention_mask: Optional[torch.BoolTensor] = None,
            full_attention_mask: Optional[torch.BoolTensor] = None,
            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
            inputs_embeds: Optional[torch.Tensor] = None,
            use_cache: Optional[bool] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
    ):
        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

        batch_size, seq_length = input_ids.shape

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

        # if full_attention_mask is None:
        #     if (attention_mask is not None and not attention_mask.all()) or (past_key_values and seq_length != 1):
        #         full_attention_mask = self.get_masks(input_ids, past_key_values, padding_mask=attention_mask)

        # Rotary positional embeddings
        rotary_pos_emb = self.rotary_pos_emb(self.seq_length)
        if position_ids is not None:
            rotary_pos_emb = rotary_pos_emb[position_ids]
        else:
            rotary_pos_emb = rotary_pos_emb[None, :seq_length]
        rotary_pos_emb = rotary_pos_emb.transpose(0, 1).contiguous()

        # Run encoder.
        hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
            inputs_embeds, attention_mask, rotary_pos_emb=rotary_pos_emb,
            kv_caches=past_key_values, use_cache=use_cache, output_hidden_states=output_hidden_states
        )

        if not return_dict:
            return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None)

        return BaseModelOutputWithPast(
            last_hidden_state=hidden_states,
            past_key_values=presents,
            hidden_states=all_hidden_states,
            attentions=all_self_attentions,
        )


class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):