in pytorch-transformers/pytorch_transformers/tokenization_utils.py [0:0]
def _from_pretrained(cls, pretrained_model_name_or_path, *init_inputs, **kwargs):
cache_dir = kwargs.pop('cache_dir', None)
force_download = kwargs.pop('force_download', False)
proxies = kwargs.pop('proxies', None)
s3_models = list(cls.max_model_input_sizes.keys())
vocab_files = {}
init_configuration = {}
if pretrained_model_name_or_path in s3_models:
# Get the vocabulary from AWS S3 bucket
for file_id, map_list in cls.pretrained_vocab_files_map.items():
vocab_files[file_id] = map_list[pretrained_model_name_or_path]
if cls.pretrained_init_configuration and pretrained_model_name_or_path in cls.pretrained_init_configuration:
init_configuration = cls.pretrained_init_configuration[pretrained_model_name_or_path]
else:
# Get the vocabulary from local files
logger.info(
"Model name '{}' not found in model shortcut name list ({}). "
"Assuming '{}' is a path or url to a directory containing tokenizer files.".format(
pretrained_model_name_or_path, ', '.join(s3_models),
pretrained_model_name_or_path))
# Look for the tokenizer main vocabulary files
for file_id, file_name in cls.vocab_files_names.items():
if os.path.isdir(pretrained_model_name_or_path):
# If a directory is provided we look for the standard filenames
full_file_name = os.path.join(pretrained_model_name_or_path, file_name)
else:
# If a path to a file is provided we use it (will only work for non-BPE tokenizer using a single vocabulary file)
full_file_name = pretrained_model_name_or_path
if not os.path.exists(full_file_name):
logger.info("Didn't find file {}. We won't load it.".format(full_file_name))
full_file_name = None
vocab_files[file_id] = full_file_name
# Look for the additional tokens files
additional_files_names = {'added_tokens_file': ADDED_TOKENS_FILE,
'special_tokens_map_file': SPECIAL_TOKENS_MAP_FILE,
'tokenizer_config_file': TOKENIZER_CONFIG_FILE,
}
# If a path to a file was provided, get the parent directory
saved_directory = pretrained_model_name_or_path
if os.path.exists(saved_directory) and not os.path.isdir(saved_directory):
saved_directory = os.path.dirname(saved_directory)
for file_id, file_name in additional_files_names.items():
full_file_name = os.path.join(saved_directory, file_name)
if not os.path.exists(full_file_name):
logger.info("Didn't find file {}. We won't load it.".format(full_file_name))
full_file_name = None
vocab_files[file_id] = full_file_name
if all(full_file_name is None for full_file_name in vocab_files.values()):
logger.error(
"Model name '{}' was not found in model name list ({}). "
"We assumed '{}' was a path or url but couldn't find tokenizer files"
"at this path or url.".format(
pretrained_model_name_or_path, ', '.join(s3_models),
pretrained_model_name_or_path, ))
return None
# Get files from url, cache, or disk depending on the case
try:
resolved_vocab_files = {}
for file_id, file_path in vocab_files.items():
if file_path is None:
resolved_vocab_files[file_id] = None
else:
resolved_vocab_files[file_id] = cached_path(file_path, cache_dir=cache_dir, force_download=force_download, proxies=proxies)
except EnvironmentError as e:
if pretrained_model_name_or_path in s3_models:
logger.error("Couldn't reach server to download vocabulary.")
else:
logger.error(
"Model name '{}' was not found in model name list ({}). "
"We assumed '{}' was a path or url but couldn't find files {} "
"at this path or url.".format(
pretrained_model_name_or_path, ', '.join(s3_models),
pretrained_model_name_or_path, str(vocab_files.keys())))
raise e
for file_id, file_path in vocab_files.items():
if file_path == resolved_vocab_files[file_id]:
logger.info("loading file {}".format(file_path))
else:
logger.info("loading file {} from cache at {}".format(
file_path, resolved_vocab_files[file_id]))
# Prepare tokenizer initialization kwargs
# Did we saved some inputs and kwargs to reload ?
tokenizer_config_file = resolved_vocab_files.pop('tokenizer_config_file', None)
if tokenizer_config_file is not None:
init_kwargs = json.load(open(tokenizer_config_file, encoding="utf-8"))
saved_init_inputs = init_kwargs.pop('init_inputs', ())
if not init_inputs:
init_inputs = saved_init_inputs
else:
init_kwargs = init_configuration
# Update with newly provided kwargs
init_kwargs.update(kwargs)
# Set max length if needed
if pretrained_model_name_or_path in cls.max_model_input_sizes:
# if we're using a pretrained model, ensure the tokenizer
# wont index sequences longer than the number of positional embeddings
max_len = cls.max_model_input_sizes[pretrained_model_name_or_path]
if max_len is not None and isinstance(max_len, (int, float)):
init_kwargs['max_len'] = min(init_kwargs.get('max_len', int(1e12)), max_len)
# Merge resolved_vocab_files arguments in init_kwargs.
added_tokens_file = resolved_vocab_files.pop('added_tokens_file', None)
special_tokens_map_file = resolved_vocab_files.pop('special_tokens_map_file', None)
for args_name, file_path in resolved_vocab_files.items():
if args_name not in init_kwargs:
init_kwargs[args_name] = file_path
if special_tokens_map_file is not None:
special_tokens_map = json.load(open(special_tokens_map_file, encoding="utf-8"))
for key, value in special_tokens_map.items():
if key not in init_kwargs:
init_kwargs[key] = value
# Instantiate tokenizer.
tokenizer = cls(*init_inputs, **init_kwargs)
# Save inputs and kwargs for saving and re-loading with ``save_pretrained``
tokenizer.init_inputs = init_inputs
tokenizer.init_kwargs = init_kwargs
# Add supplementary tokens.
if added_tokens_file is not None:
added_tok_encoder = json.load(open(added_tokens_file, encoding="utf-8"))
added_tok_decoder = {v:k for k, v in added_tok_encoder.items()}
tokenizer.added_tokens_encoder.update(added_tok_encoder)
tokenizer.added_tokens_decoder.update(added_tok_decoder)
return tokenizer