tensorflow/models · error · ValueError

mode {} is not valid.

Error message

mode {} is not valid.

What it means

Error "mode {} is not valid." thrown in tensorflow/models.

Source

Thrown at official/legacy/transformer/embedding_layer.py:72

    """Get token embeddings of inputs.

    Args:
      inputs: An int64 tensor with shape [batch_size, length]
      mode: string, a valid value is one of "embedding" and "linear".

    Returns:
      outputs: (1) If mode == "embedding", output embedding tensor, float32 with
        shape [batch_size, length, embedding_size]; (2) mode == "linear", output
        linear tensor, float32 with shape [batch_size, length, vocab_size].
    Raises:
      ValueError: if mode is not valid.
    """
    if mode == "embedding":
      return self._embedding(inputs)
    elif mode == "linear":
      return self._linear(inputs)
    else:
      raise ValueError("mode {} is not valid.".format(mode))

  def _embedding(self, inputs):
    """Applies embedding based on inputs tensor."""
    with tf.name_scope("embedding"):
      # Create binary mask of size [batch_size, length]
      embeddings = tf.gather(self.shared_weights, inputs)
      # mask = tf.cast(tf.not_equal(inputs, 0), embeddings.dtype)
      # embeddings *= tf.expand_dims(mask, -1)
      # Scale embedding by the sqrt of the hidden size
      embeddings *= self.hidden_size**0.5

      return embeddings

  def _linear(self, inputs):
    """Computes logits by running inputs through a linear layer.

    Args:
      inputs: A float32 tensor with shape [batch_size, length, hidden_size]

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/legacy/transformer/embedding_layer.py:72 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/948f091a46ea688d. Report an issue: GitHub.