Function _get_generated_ngrams

bert/generation_utils.py:861–865

(hypo_idx)

            generated_ngram[prev_ngram_tuple] = generated_ngram.get(prev_ngram_tuple, []) + [ngram[-1]]

    def _get_generated_ngrams(hypo_idx):
        # Before decoding the next token, prevent decoding of ngrams that have already appeared
        start_idx = cur_len + 1 - no_repeat_ngram_size
        ngram_idx = tuple(prev_input_ids[hypo_idx, start_idx:cur_len].tolist())
        return generated_ngrams[hypo_idx].get(ngram_idx, [])

    banned_tokens = [_get_generated_ngrams(hypo_idx) for hypo_idx in range(num_hypos)]
    return banned_tokens