tensorflow/models · error · ValueError

The input size (%d) is not a multiple of the number of atten

Error message

The input size (%d) is not a multiple of the number of attention heads (%d)

What it means

Error "The input size (%d) is not a multiple of the number of attention heads (%d)" thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/layers/transformer_xl.py:143

    input_tensor = input_shape[0] if len(input_shape) == 2 else input_shape
    input_tensor_shape = tf.TensorShape(input_tensor)
    if len(input_tensor_shape.as_list()) != 3:
      raise ValueError("TransformerLayer expects a three-dimensional input of "
                       "shape [batch, sequence, width].")
    batch_size, sequence_length, hidden_size = input_tensor_shape

    if len(input_shape) == 2:
      mask_tensor_shape = tf.TensorShape(input_shape[1])
      expected_mask_tensor_shape = tf.TensorShape(
          [batch_size, sequence_length, sequence_length])
      if not expected_mask_tensor_shape.is_compatible_with(mask_tensor_shape):
        raise ValueError("When passing a mask tensor to TransformerXLBlock, "
                         "the mask tensor must be of shape [batch, "
                         "sequence_length, sequence_length] (here %s). Got a "
                         "mask tensor of shape %s." %
                         (expected_mask_tensor_shape, mask_tensor_shape))
    if hidden_size % self._num_heads != 0:
      raise ValueError(
          "The input size (%d) is not a multiple of the number of attention "
          "heads (%d)" % (hidden_size, self._num_heads))
    self._attention_layer = self._attention_layer_type(
        num_heads=self._num_heads,
        key_dim=self._head_size,
        value_dim=self._head_size,
        dropout=self._attention_dropout_rate,
        use_bias=False,
        kernel_initializer=tf_utils.clone_initializer(self._kernel_initializer),
        name="rel_attn")
    self._attention_dropout = tf_keras.layers.Dropout(
        rate=self._attention_dropout_rate)
    self._attention_layer_norm = tf_keras.layers.LayerNormalization(
        name="self_attention_layer_norm",
        axis=-1,
        epsilon=self._norm_epsilon,
        dtype=tf.float32)
    self._inner_dense = tf_keras.layers.EinsumDense(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/layers/transformer_xl.py:143 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/51d28a60725664a7. Report an issue: GitHub.