SYMBOL INDEX (36 symbols across 9 files)

FILE: convert_tf2_ckpt_for_all_frameworks.py
  function load_tf2_weights_in_bert (line 30) | def load_tf2_weights_in_bert(model, tf_checkpoint_path, config):
  function convert_tf2_checkpoint_to_pytorch (line 240) | def convert_tf2_checkpoint_to_pytorch(tf_checkpoint_path, tf_config_path...

FILE: create_pretraining_data.py
  class TrainingInstance (line 89) | class TrainingInstance(object):
    method __init__ (line 92) | def __init__(self, tokens, segment_ids, masked_lm_positions, masked_lm...
    method __str__ (line 100) | def __str__(self):
    method __repr__ (line 112) | def __repr__(self):
  function write_instance_to_example_files (line 116) | def write_instance_to_example_files(instances, tokenizer, max_seq_length,
  function create_int_feature (line 195) | def create_int_feature(values):
  function create_float_feature (line 200) | def create_float_feature(values):
  function create_training_instances (line 205) | def create_training_instances(input_files,
  function create_instances_from_document (line 256) | def create_instances_from_document(
  function create_masked_lm_predictions (line 377) | def create_masked_lm_predictions(tokens, masked_lm_prob,
  function truncate_seq_pair (line 454) | def truncate_seq_pair(tokens_a, tokens_b, max_num_tokens, rng):
  function main (line 472) | def main(_):

FILE: japanese_tokenizers/implementations.py
  class JapaneseWordPieceTokenizer (line 24) | class JapaneseWordPieceTokenizer(BertWordPieceTokenizer):
    method __init__ (line 25) | def __init__(

FILE: japanese_tokenizers/pre_tokenizers.py
  class MeCabPreTokenizer (line 22) | class MeCabPreTokenizer:
    method __init__ (line 23) | def __init__(self, mecab_dic: Optional[str] = None, mecab_option: Opti...
    method mecab_split (line 45) | def mecab_split(self, i: int, normalized_string: NormalizedString) -> ...
    method pre_tokenize (line 56) | def pre_tokenize(self, pretok: PreTokenizedString):

FILE: make_alphabet_from_unidic.py
  function main (line 20) | def main(args):

FILE: make_corpus_wiki.py
  class MeCabSentenceSplitter (line 25) | class MeCabSentenceSplitter:
    method __init__ (line 26) | def __init__(self, mecab_option=None):
    method __call__ (line 36) | def __call__(self, text):
  function filter_text (line 55) | def filter_text(text):
  function preprocess_text (line 63) | def preprocess_text(text, title=None):
  function main (line 87) | def main(args):

FILE: merge_split_corpora.py
  function _open_file (line 31) | def _open_file(filename):
  function main (line 40) | def main(args):

FILE: tokenization.py
  class BertJapaneseTokenizer (line 24) | class BertJapaneseTokenizer(BertJapaneseTokenizerBase):
    method __init__ (line 25) | def __init__(
    method _convert_token_to_id (line 71) | def _convert_token_to_id(self, token):
  class CharacterTokenizer (line 78) | class CharacterTokenizer(CharacterTokenizerBase):
    method __init__ (line 79) | def __init__(self, vocab, unk_token, normalize_text=True):
    method tokenize (line 82) | def tokenize(self, text):

FILE: train_tokenizer.py
  function main (line 27) | def main(args):