pytorch-transformers/pytorch_transformers/modeling_gpt2.py [189:221]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.num_labels = num_labels
            self.summary_type = summary_type
            self.summary_use_proj = summary_use_proj
            self.summary_activation = summary_activation
            self.summary_first_dropout = summary_first_dropout
            self.summary_proj_to_labels = summary_proj_to_labels
        else:
            raise ValueError(
                "First argument must be either a vocabulary size (int)"
                "or the path to a pretrained model config file (str)"
            )

    @property
    def max_position_embeddings(self):
        return self.n_positions

    @property
    def hidden_size(self):
        return self.n_embd

    @property
    def num_attention_heads(self):
        return self.n_head

    @property
    def num_hidden_layers(self):
        return self.n_layer



class Attention(nn.Module):
    def __init__(self, nx, n_ctx, config, scale=False):
        super(Attention, self).__init__()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



pytorch-transformers/pytorch_transformers/modeling_openai.py [206:237]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.num_labels = num_labels
            self.summary_type = summary_type
            self.summary_use_proj = summary_use_proj
            self.summary_activation = summary_activation
            self.summary_first_dropout = summary_first_dropout
            self.summary_proj_to_labels = summary_proj_to_labels
        else:
            raise ValueError(
                "First argument must be either a vocabulary size (int)"
                "or the path to a pretrained model config file (str)"
            )

    @property
    def max_position_embeddings(self):
        return self.n_positions

    @property
    def hidden_size(self):
        return self.n_embd

    @property
    def num_attention_heads(self):
        return self.n_head

    @property
    def num_hidden_layers(self):
        return self.n_layer


class Attention(nn.Module):
    def __init__(self, nx, n_ctx, config, scale=False):
        super(Attention, self).__init__()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -