ing the size
        will add newly initialized weights. Reducing the size will remove weights from the end

        Args:
            num_labels (`int`, *optional*):
                New number of labels in the linear layer weight matrix. Increasing the size will add newly initialized
                weights at the end. Reducing the size will remove weights from the end. If not provided or `None`, just
                returns a pointer to the qa labels ``torch.nn.Linear``` module of the model without doing anything.

        Return:
            `torch.nn.Linear`: Pointer to the resized Linear layer or the old Linear layer
        NŠ