tfm.nlp.layers.MobileBertMaskedLM

Masked language model network head for BERT modeling.

tfm.nlp.layers.MobileBertMaskedLM(
    embedding_table,
    activation=None,
    initializer='glorot_uniform',
    output='logits',
    output_weights_use_proj=False,
    **kwargs
)

This layer implements a masked language model based on the provided transformer based encoder. It assumes that the encoder network being passed has a "get_embedding_table()" method. Different from canonical BERT's masked LM layer, when the embedding width is smaller than hidden_size, it adds an extra output weights in shape [vocab_size, (hidden_size - embedding_width)].

embedding_table The embedding table from encoder network.
activation The activation, if any, for the dense layer.
initializer The initializer for the dense layer. Defaults to a Glorot uniform initializer.
output The output style for this layer. Can be either logits or predictions.
output_weights_use_proj Use projection instead of concating extra output weights, this may reduce the MLM task accuracy but will reduce the model params as well.
**kwargs keyword arguments.

Methods

call

View source

call(
    sequence_data, masked_positions
)

This is where the layer's logic lives.

The call() method may not create state (except in its first invocation, wrapping the creation of variables or other resources in tf.init_scope()). It is recommended to create state, including tf.Variable instances and nested Layer instances, in __init__(), or in the build() method that is called automatically before call() executes for the first time.

Args
inputs Input tensor, or dict/list/tuple of input tensors. The first positional inputs argument is subject to special rules:

  • inputs must be explicitly passed. A layer cannot have zero arguments, and inputs cannot be provided via the default value of a keyword argument.
  • NumPy array or Python scalar values in inputs get cast as tensors.
  • TF-Keras mask metadata is only collected from inputs.
  • Layers are built (build(input_shape) method) using shape info from inputs only.
  • input_spec compatibility is only checked against inputs.
  • Mixed precision input casting is only applied to inputs. If a layer has tensor arguments in *args or **kwargs, their casting behavior in mixed precision should be handled manually.
  • The SavedModel input specification is generated using inputs only.
  • Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for inputs and not for tensors in positional and keyword arguments.
*args Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.
**kwargs Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved:
  • training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference.
  • mask: Boolean input mask. If the layer's call() method takes a mask argument, its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support).

    • Returns
    A tensor or list/tuple of tensors.