Roman

The same issue deploying [bert_multi_cased_L-12_H-768_A-12](https://tfhub.dev/tensorflow/bert_multi_cased_L-12_H-768_A-12/4) from TF-Hub using the corresponding [bert_multi_cased_preprocess](https://tfhub.dev/tensorflow/bert_multi_cased_preprocess/3), i.e. ```py inp = tf.keras.layers.Input(shape=(), dtype=tf.string, name='input') preprocess = hub.KerasLayer('https://tfhub.dev/tensorflow/bert_multi_cased_preprocess/3', name='preprocessing') encoded_inp = preprocess(inp) bert = hub.KerasLayer('https://tfhub.dev/tensorflow/bert_multi_cased_L-12_H-768_A-12/4', trainable=True, name='bert_encoder')...