tensorflow/models · error · ValueError

If `use_type_embeddings` is True, then `token_type_vocab_siz

Error message

If `use_type_embeddings` is True, then `token_type_vocab_size` must be specified.

What it means

Error "If `use_type_embeddings` is True, then `token_type_vocab_size` must be specified." thrown in tensorflow/models.

Source

Thrown at official/projects/nhnet/decoder.py:203

               initializer_range=0.02,
               initializer=None,
               **kwargs):
    super(EmbeddingPostprocessor, self).__init__(**kwargs)
    self.use_type_embeddings = use_type_embeddings
    self.token_type_vocab_size = token_type_vocab_size
    self.use_position_embeddings = use_position_embeddings
    self.max_position_embeddings = max_position_embeddings
    self.dropout_prob = dropout_prob
    self.initializer_range = initializer_range

    if not initializer:
      self.initializer = tf_keras.initializers.TruncatedNormal(
          stddev=initializer_range)
    else:
      self.initializer = initializer

    if self.use_type_embeddings and not self.token_type_vocab_size:
      raise ValueError("If `use_type_embeddings` is True, then "
                       "`token_type_vocab_size` must be specified.")

  def build(self, input_shapes):
    """Implements build() for the layer."""
    (word_embeddings_shape, _) = input_shapes
    width = word_embeddings_shape.as_list()[-1]
    self.type_embeddings = None
    if self.use_type_embeddings:
      self.type_embeddings = self.add_weight(
          "type_embeddings",
          shape=[self.token_type_vocab_size, width],
          initializer=tf_keras.initializers.TruncatedNormal(
              stddev=self.initializer_range),
          dtype=self.dtype)

    self.position_embeddings = None
    if self.use_position_embeddings:
      self.position_embeddings = self.add_weight(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/nhnet/decoder.py:203 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/9033328f66b43854. Report an issue: GitHub.