How to use the dnn.pytorch.base.base.__init__ function in dnn

def __init__(self, emb_matrix, args):
        """
        Initilize the model data and layer
        * emb_matrix [np.array]: word embedding matrix
        * args [dict]: all model arguments
        """
        nn.Module.__init__(self)
        base.base.__init__(self, args)

        self.emb_mat = layer.embedding_layer(emb_matrix, self.emb_type)
        self.pos_emb_mat = layer.positional_embedding_layer(self.n_hidden)
        self.drop_out = nn.Dropout(self.drop_prob)
        self.transformer = nn.ModuleList([
            layer.transformer_layer(self.emb_dim, self.n_hidden, self.n_head) for _ in range(self.n_layer)
        ])
        self.predict = layer.softmax_layer(self.emb_dim, self.n_class)

def __init__(self, emb_matrix, args, n_hierarchy=1, mode='classify'):
        """
        Initilize the model data and layer
        * emb_matrix [np.array]: word embedding matrix
        * args [dict]: all model arguments
        * mode [str]: use 'classify'/'sequence' to get the result
        """
        nn.Module.__init__(self)
        base.base.__init__(self, args)

        self.n_hierarchy = n_hierarchy
        self.mode = mode
        self.bi_direction_num = 2 if self.bi_direction else 1

        self.emb_mat = layer.embedding_layer(emb_matrix, self.emb_type)
        self.drop_out = nn.Dropout(self.drop_prob)

        rnn_params = (self.n_hidden, self.n_layer, self.drop_prob, self.bi_direction, self.rnn_type)
        self.rnn = nn.ModuleList([layer.RNN_layer(self.emb_dim, *rnn_params)])
        self.att = nn.ModuleList([layer.self_attention_layer(self.bi_direction_num * self.n_hidden)])
        for _ in range(self.n_hierarchy - 1):
            self.rnn.append(layer.RNN_layer(self.bi_direction_num * self.n_hidden, *rnn_params))
            if self.use_attention:
                self.att.append(layer.self_attention_layer(self.bi_direction_num * self.n_hidden))
        self.predict = layer.softmax_layer(self.n_hidden * self.bi_direction_num, self.n_class)