Class ChatGLMForSequenceClassification

workers/chatglm3_modeling.py:1210–1294

class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
    def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
        super().__init__(config)

        self.num_labels = config.num_labels
        self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)

        self.classifier_head = nn.Linear(config.hidden_size, config.num_labels, bias=True, dtype=torch.half)
        if config.classifier_dropout is not None:
            self.dropout = nn.Dropout(config.classifier_dropout)
        else:
            self.dropout = None
        self.config = config

        if self.config.quantization_bit:
            self.quantize(self.config.quantization_bit, empty_init=True)

    def forward(
            self,
            input_ids: Optional[torch.LongTensor] = None,
            position_ids: Optional[torch.LongTensor] = None,
            attention_mask: Optional[torch.Tensor] = None,
            full_attention_mask: Optional[torch.Tensor] = None,
            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
            inputs_embeds: Optional[torch.LongTensor] = None,
            labels: Optional[torch.LongTensor] = None,
            use_cache: Optional[bool] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
    ) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]:
        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,
            full_attention_mask=full_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]
        pooled_hidden_states = hidden_states[-1]
        if self.dropout is not None:
            pooled_hidden_states = self.dropout(pooled_hidden_states)
        logits = self.classifier_head(pooled_hidden_states)

        loss = None
        if labels is not None:
            labels.to(logits)
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
                    self.config.problem_type = "single_label_classification"