tensorflow/models · error · ValueError

Intermediate_size (%d) isn't a multiple of num_blocks (%d).

Error message

Intermediate_size (%d) isn't a multiple of num_blocks (%d).

What it means

Error "Intermediate_size (%d) isn't a multiple of num_blocks (%d)." thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/layers/block_diag_feedforward.py:70

      num_blocks: int = 1,
      apply_mixing: bool = True,
      kernel_initializer: str = "glorot_uniform",
      bias_initializer: str = "zeros",
      kernel_regularizer: Optional[tf_keras.regularizers.Regularizer] = None,
      bias_regularizer: Optional[tf_keras.regularizers.Regularizer] = None,
      activity_regularizer: Optional[tf_keras.regularizers.Regularizer] = None,
      kernel_constraint: Optional[tf_keras.constraints.Constraint] = None,
      bias_constraint: Optional[tf_keras.constraints.Constraint] = None,
      **kwargs):  # pylint: disable=g-doc-args
    super().__init__(**kwargs)
    self._intermediate_size = intermediate_size
    self._intermediate_activation = intermediate_activation
    self._dropout = dropout
    self._num_blocks = num_blocks
    self._apply_mixing = apply_mixing

    if intermediate_size % num_blocks != 0:
      raise ValueError("Intermediate_size (%d) isn't a multiple of num_blocks "
                       "(%d)." % (intermediate_size, num_blocks))

    self._kernel_initializer = tf_keras.initializers.get(kernel_initializer)
    self._bias_initializer = tf_keras.initializers.get(bias_initializer)
    self._kernel_regularizer = tf_keras.regularizers.get(kernel_regularizer)
    self._bias_regularizer = tf_keras.regularizers.get(bias_regularizer)
    self._activity_regularizer = tf_keras.regularizers.get(activity_regularizer)
    self._kernel_constraint = tf_keras.constraints.get(kernel_constraint)
    self._bias_constraint = tf_keras.constraints.get(bias_constraint)

  def build(self, input_shape):
    hidden_size = input_shape.as_list()[-1]

    common_kwargs = dict(
        kernel_regularizer=self._kernel_regularizer,
        bias_regularizer=self._bias_regularizer,
        activity_regularizer=self._activity_regularizer,
        kernel_constraint=self._kernel_constraint,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/layers/block_diag_feedforward.py:70 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/165b18a9129482aa. Report an issue: GitHub.