tensorflow/models · error · ValueError

StridedTransformerEncoderBlock does not support `output_rang

Error message

StridedTransformerEncoderBlock does not support `output_range` argument.

What it means

Error "StridedTransformerEncoderBlock does not support `output_range` argument." thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/layers/pack_optimization.py:73

        packed_embeddings, input_mask, dtype=tf.bool)

    combined_attention_mask = tf.cast(
        tf.math.logical_and(attention_mask, packing_mask), tf.float32)

    return dict(
        packed_embeddings=packed_embeddings,
        combined_attention_mask=combined_attention_mask)


@tf_keras.utils.register_keras_serializable(package='Text')
class StridedTransformerEncoderBlock(
    transformer_encoder_block.TransformerEncoderBlock):
  """Transformer layer for packing optimization to stride over inputs."""

  def __init__(self, *args, **kwargs):
    super().__init__(*args, **kwargs)
    if self._output_range is not None:
      raise ValueError('StridedTransformerEncoderBlock does not '
                       'support `output_range` argument.')
    # TODO(b/337888023): Support block sparse attention with strided inputs.
    if self._src_block_size is not None:
      raise ValueError('StridedTransformerEncoderBlock does not '
                       'support block sparse attention.')

  def call(self, inputs, stride: tf.Tensor):
    if isinstance(inputs, (list, tuple)):
      if len(inputs) == 2:
        input_tensor, attention_mask = inputs
        key_value = None
      elif len(inputs) == 3:
        input_tensor, key_value, attention_mask = inputs
      else:
        raise ValueError('Unexpected inputs to %s with length at %d' %
                         (self.__class__, len(inputs)))
    else:
      input_tensor, key_value, attention_mask = (inputs, None, None)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/layers/pack_optimization.py:73 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/8a047395701292ec. Report an issue: GitHub.