Class ChatGLMPreTrainedModel

train/patch/modeling_chatglm.py:572–613

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

class ChatGLMPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and
    a simple interface for downloading and loading pretrained models.
    """

    is_parallelizable = False
    supports_gradient_checkpointing = True
    config_class = ChatGLMConfig
    base_model_prefix = "transformer"
    _no_split_modules = ["GLMBlock"]

    def _init_weights(self, module: nn.Module):
        """Initialize the weights."""
        return

    def get_masks(self, input_ids, past_key_values, padding_mask=None):
        batch_size, seq_length = input_ids.shape
        full_attention_mask = torch.ones(batch_size, seq_length, seq_length, device=input_ids.device)
        full_attention_mask.tril_()
        past_length = 0
        if past_key_values:
            past_length = past_key_values[0][0].shape[0]
        if past_length:
            full_attention_mask = torch.cat((torch.ones(batch_size, seq_length, past_length,
                                                        device=input_ids.device), full_attention_mask), dim=-1)
        if padding_mask is not None:
            full_attention_mask = full_attention_mask * padding_mask.unsqueeze(1)
        if not past_length and padding_mask is not None:
            full_attention_mask -= padding_mask.unsqueeze(-1) - 1
        full_attention_mask = (full_attention_mask < 0.5).bool()
        full_attention_mask.unsqueeze_(1)
        return full_attention_mask

    def get_position_ids(self, input_ids, device):
        batch_size, seq_length = input_ids.shape
        position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)
        return position_ids

    def _set_gradient_checkpointing(self, module, value=False):
        if isinstance(module, GLMTransformer):
            module.gradient_checkpointing = value


class Embedding(torch.nn.Module):