NLG using AR models

In the previous section, you learned how it is possible to train an AR model on your own corpus. As a result, you trained a GPT-2 version of your own. But the answer to the question How can I use it? remains. To answer that, let’s proceed as follows:

1. Let’s start generating sentences from the model you have just trained, as follows:

   def generate(start, model):
       input_token_ids = tokenizer_gpt.encode(start,
           return_tensors='tf')
       output = model.generate(
           input_token_ids,
           max_length = 500,
           num_beams = 5,
           temperature = 0.7,
           no_repeat_ngram_size=2,
           num_return_sequences=1
       )
    ...