tensorflow/models · error · ValueError

Unknown `output` value "%s". `output` can be either "logits"

Error message

Unknown `output` value "%s". `output` can be either "logits" or "predictions"

What it means

Error "Unknown `output` value "%s". `output` can be either "logits" or "predictions"" thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/layers/masked_lm.py:56

      uniform initializer.
    output: The output style for this layer. Can be either 'logits' or
      'predictions'.
  """

  def __init__(self,
               embedding_table,
               activation=None,
               initializer='glorot_uniform',
               output='logits',
               name=None,
               **kwargs):
    super().__init__(name=name, **kwargs)
    self.embedding_table = embedding_table
    self.activation = activation
    self.initializer = tf_keras.initializers.get(initializer)

    if output not in ('predictions', 'logits'):
      raise ValueError(
          ('Unknown `output` value "%s". `output` can be either "logits" or '
           '"predictions"') % output)
    self._output_type = output

  def build(self, input_shape):
    self._vocab_size, hidden_size = self.embedding_table.shape
    self.dense = tf_keras.layers.Dense(
        hidden_size,
        activation=self.activation,
        kernel_initializer=self.initializer,
        name='transform/dense')
    self.layer_norm = tf_keras.layers.LayerNormalization(
        axis=-1, epsilon=1e-12, name='transform/LayerNorm')
    self.bias = self.add_weight(
        'output_bias/bias',
        shape=(self._vocab_size,),
        initializer='zeros',
        trainable=True)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/layers/masked_lm.py:56 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/f0e8dd841406fab3. Report an issue: GitHub.