BERT model ("Bidirectional Encoder Representations from Transformers"). Example usage: ```python # Already been converted into WordPiece token ids input_ids = tf.constant([[31, 51, 99], [15, 5, 0]]) input_mask = tf.constant([[1, 1, 1], [1, 1, 0]]) token_type_ids = tf.consta
source not stored for this graph (policy: none)