bert_model_definition.py

#https://uber.github.io/ludwig/user_guide/#bert-encoder

template="""
input_features:
    -
        name: Questions
        type: text
        encoder: bert
        config_path: uncased_L-12_H-768_A-12/bert_config.json
        checkpoint_path: uncased_L-12_H-768_A-12/bert_model.ckpt
        preprocessing:
          word_tokenizer: bert
          word_vocab_file: uncased_L-12_H-768_A-12/vocab.txt
          padding_symbol: '[PAD]'
          unknown_symbol: '[UNK]'

output_features:
    -
        name: Category0
        type: category
    -
        name: Category2
        type: category
text:
        word_sequence_length_limit: 128
training:
        batch_size: 32
        learning_rate: 0.00002

"""

with open("model_definition.yaml", "w") as f:
  f.write(template)