Method resize_token_embeddings

bert/modeling_utils.py:376–401

Resize input token embeddings matrix of the model if new_num_tokens != config.vocab_size. Take care of tying weights embeddings afterwards if the model class has a `tie_weights()` method. Arguments: new_num_tokens: (`optional`) int: New number of tokens

(self, new_num_tokens: Optional[int] = None)

            output_embeddings.out_features = input_embeddings.num_embeddings

    def resize_token_embeddings(self, new_num_tokens: Optional[int] = None):
        """ Resize input token embeddings matrix of the model if new_num_tokens != config.vocab_size.
        Take care of tying weights embeddings afterwards if the model class has a `tie_weights()` method.

        Arguments:

            new_num_tokens: (`optional`) int:
                New number of tokens in the embedding matrix. Increasing the size will add newly initialized vectors at the end. Reducing the size will remove vectors from the end.
                If not provided or None: does nothing and just returns a pointer to the input tokens ``torch.nn.Embeddings`` Module of the model.

        Return: ``torch.nn.Embeddings``
            Pointer to the input tokens Embeddings Module of the model
        """
        base_model = getattr(self, self.base_model_prefix, self)  # get the base model if needed
        model_embeds = base_model._resize_token_embeddings(new_num_tokens)
        if new_num_tokens is None:
            return model_embeds

        # Update base model and current model config
        self.config.vocab_size = new_num_tokens
        base_model.vocab_size = new_num_tokens

        # Tie weights again if needed
        self.tie_weights()

        return model_embeds

    def _resize_token_embeddings(self, new_num_tokens):
        old_embeddings = self.get_input_embeddings()