Method get_output_embeddings

bert/modeling_utils.py:338–346

Returns the model's output embeddings. Returns: :obj:`nn.Module`: A torch module mapping hidden states to vocabulary.

(self)

            raise NotImplementedError

    def get_output_embeddings(self):
        """
        Returns the model's output embeddings.

        Returns:
            :obj:`nn.Module`:
                A torch module mapping hidden states to vocabulary.
        """
        return None  # Overwrite for models with output embeddings

    def tie_weights(self):
        """