tensorflow/models · error · NotImplementedError

Only "no_norm" and "layer_norm" are supported.

Error message

Only "no_norm" and "layer_norm" are supported.

What it means

Error "Only "no_norm" and "layer_norm" are supported." thrown in tensorflow/models.

Source

Thrown at official/projects/qat/nlp/modeling/layers/mobile_bert_layers.py:88

  Args:
      normalization_type: String. The type of normalization_type, only `no_norm`
        and `layer_norm` are supported.
      name: Name for the norm layer.

  Returns:
    layer norm class.
  """
  if normalization_type == 'no_norm':
    layer = NoNormQuantized(name=name)
  elif normalization_type == 'layer_norm':
    layer = tf_keras.layers.LayerNormalization(
        name=name,
        axis=-1,
        epsilon=1e-12,
        dtype=tf.float32)
  else:
    raise NotImplementedError('Only "no_norm" and "layer_norm" are supported.')
  return layer


class MobileBertEmbeddingQuantized(helper.LayerQuantizerHelper,
                                   tf_keras.layers.Layer):
  """Performs an embedding lookup for MobileBERT.

  This layer includes word embedding, token type embedding, position embedding.
  """

  def __init__(self,
               word_vocab_size,
               word_embed_size,
               type_vocab_size,
               output_embed_size,
               max_sequence_length=512,
               normalization_type='no_norm',
               initializer=tf_keras.initializers.TruncatedNormal(stddev=0.02),

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/qat/nlp/modeling/layers/mobile_bert_layers.py:88 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/dd7af1206a24fdb8. Report an issue: GitHub.