def __init__(
self,
vocab_file,
merges_file,
errors="replace",
unk_token="<|endoftext|>",
bos_token="<|startoftext|>",
eos_token="<|endoftext|>",
pad_token="<|endoftext|>", # hack to enable padding
**kwargs):
bos_token = AddedToken(bos_token,
lstrip=False, rstrip=False) if isinstance(
bos_token, str) else bos_token
eos_token = AddedToken(eos_token,
lstrip=False, rstrip=False) if isinstance(
eos_token, str) else eos_token
unk_token = AddedToken(unk_token,
lstrip=False, rstrip=False) if isinstance(
unk_token, str) else unk_token
super().__init__(
errors=errors,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
**kwargs,
)
try:
import ftfy
self.fix_text = ftfy.fix_text
except ImportError:
logger.warning(
"ftfy or spacy is not installed using BERT BasicTokenizer instead of ftfy."
)
self.nlp = BasicTokenizer(do_lower_case=True)
self.fix_text = None
with open(vocab_file, encoding="utf-8") as vocab_handle:
self.encoder = json.load(vocab_handle)
self.decoder = {v: k for k, v in self.encoder.items()}
self.errors = errors # how to handle errors in decoding
self.byte_encoder = bytes_to_unicode()
self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
with open(merges_file, encoding="utf-8") as merges_handle:
bpe_merges = merges_handle.read().strip().split("\n")[1:49152 -
256 - 2 + 1]
bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
self.cache = {
"<|startoftext|>": "<|startoftext|>",
"<|endoftext|>": "<|endoftext|>"
}
self.pat = re.compile(
r"""<\|startoftext\|>|<\|endoftext\|>|'s|'t|'re|'ve|'m|'ll|'d|[\p{L}]+|[\p{N}]|[^\s\p{L}\p{N}]+""",
re.IGNORECASE,
)
def test_basic_tokenizer_lower_strip_accents_default(self):
tokenizer = BasicTokenizer(do_lower_case=True)
self.assertListEqual(
tokenizer.tokenize(" \tHäLLo!how \n Are yoU? "), ["hallo", "!", "how", "are", "you", "?"]
)
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["hello"])
def __init__(
self,
vocab_file,
do_lower_case=True,
do_basic_tokenize=True,
never_split=None,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
tokenize_chinese_chars=True,
strip_accents=None,
**kwargs,
):
super().__init__(
do_lower_case=do_lower_case,
do_basic_tokenize=do_basic_tokenize,
never_split=never_split,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
**kwargs,
)
if not os.path.isfile(vocab_file):
raise ValueError(
f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
"model use `tokenizer = AutoTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
)
self.vocab = load_vocab(vocab_file)
self.ids_to_tokens = collections.OrderedDict([
(ids, tok) for tok, ids in self.vocab.items()
])
self.do_basic_tokenize = do_basic_tokenize
if do_basic_tokenize:
self.basic_tokenizer = BasicTokenizer(
do_lower_case=do_lower_case,
never_split=never_split,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
)
self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab,
unk_token=self.unk_token)
try:
import rjieba
except ImportError:
raise ImportError(
"You need to install rjieba to use RoFormerTokenizer. "
"See https://pypi.org/project/rjieba/ for installation.")
self.jieba = rjieba
def __init__(
self,
model: Union["PreTrainedModel", "TFPreTrainedModel"],
tokenizer: PreTrainedTokenizer,
config: PretrainedConfig,
modelcard: Optional[ModelCard] = None,
framework: Optional[str] = None,
args_parser: ArgumentHandler = TokenClassificationArgumentHandler(
),
device: int = -1,
binary_output: bool = False,
ignore_labels=["O"],
task: str = "",
grouped_entities: bool = False,
ignore_subwords: bool = False,
onnx: bool = True,
graph_path: Optional[Path] = None,
optimization_level: str = 'all'):
super().__init__(model=model,
tokenizer=tokenizer,
config=config,
modelcard=modelcard,
framework=framework,
device=device,
binary_output=binary_output,
task=task,
onnx=onnx,
graph_path=graph_path,
optimization_level=optimization_level)
if not onnx:
self.check_model_type(
TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING if self.framework ==
"tf" else MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING)
self._basic_tokenizer = BasicTokenizer(do_lower_case=False)
self._args_parser = args_parser
self.ignore_labels = ignore_labels
self.grouped_entities = grouped_entities
self.ignore_subwords = ignore_subwords
if self.ignore_subwords and not self.tokenizer.is_fast:
raise ValueError(
"Slow tokenizers cannot ignore subwords. Please set the `ignore_subwords` option"
"to `False` or use a fast tokenizer.")
class RoFormerTokenizer(PreTrainedTokenizer):
r"""
Construct a RoFormer tokenizer. Based on `Rust Jieba <https://pypi.org/project/rjieba/>`.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.
Users should refer to this superclass for more information regarding those methods.
Args:
vocab_file (:obj:`str`):
File containing the vocabulary.
do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to lowercase the input when tokenizing.
do_basic_tokenize (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to do basic tokenization before WordPiece.
never_split (:obj:`Iterable`, `optional`):
Collection of tokens which will never be split during tokenization. Only has an effect when
:obj:`do_basic_tokenize=True`
unk_token (:obj:`str`, `optional`, defaults to :obj:`"[UNK]"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
sep_token (:obj:`str`, `optional`, defaults to :obj:`"[SEP]"`):
The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
sequence classification or for a text and a question for question answering. It is also used as the last
token of a sequence built with special tokens.
pad_token (:obj:`str`, `optional`, defaults to :obj:`"[PAD]"`):
The token used for padding, for example when batching sequences of different lengths.
cls_token (:obj:`str`, `optional`, defaults to :obj:`"[CLS]"`):
The classifier token which is used when doing sequence classification (classification of the whole sequence
instead of per-token classification). It is the first token of the sequence when built with special tokens.
mask_token (:obj:`str`, `optional`, defaults to :obj:`"[MASK]"`):
The token used for masking values. This is the token used when training this model with masked language
modeling. This is the token which the model will try to predict.
tokenize_chinese_chars (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to tokenize Chinese characters.
This should likely be deactivated for Japanese (see this `issue
<https://github.com/huggingface/transformers/issues/328>`__).
strip_accents: (:obj:`bool`, `optional`):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for :obj:`lowercase` (as in the original BERT).
Example::
>>> from transformers import RoFormerTokenizer
>>> tokenizer = RoFormerTokenizer.from_pretrained('junnyu/roformer_chinese_base')
>>> tokenizer.tokenize("今天天气非常好。")
# ['今', '天', '天', '气', '非常', '好', '。']
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
def __init__(
self,
vocab_file,
do_lower_case=True,
do_basic_tokenize=True,
never_split=None,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
tokenize_chinese_chars=True,
strip_accents=None,
**kwargs,
):
super().__init__(
do_lower_case=do_lower_case,
do_basic_tokenize=do_basic_tokenize,
never_split=never_split,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
**kwargs,
)
if not os.path.isfile(vocab_file):
raise ValueError(
f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
"model use `tokenizer = AutoTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
)
self.vocab = load_vocab(vocab_file)
self.ids_to_tokens = collections.OrderedDict([
(ids, tok) for tok, ids in self.vocab.items()
])
self.do_basic_tokenize = do_basic_tokenize
if do_basic_tokenize:
self.basic_tokenizer = BasicTokenizer(
do_lower_case=do_lower_case,
never_split=never_split,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
)
self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab,
unk_token=self.unk_token)
try:
import rjieba
except ImportError:
raise ImportError(
"You need to install rjieba to use RoFormerTokenizer. "
"See https://pypi.org/project/rjieba/ for installation.")
self.jieba = rjieba
@property
def do_lower_case(self):
return self.basic_tokenizer.do_lower_case
@property
def vocab_size(self):
return len(self.vocab)
def __getstate__(self):
state = self.__dict__.copy()
state["jieba"] = None
return state
def __setstate__(self, d):
self.__dict__ = d
import rjieba
self.jieba = rjieba
def get_vocab(self):
return dict(self.vocab, **self.added_tokens_encoder)
def _tokenize(self, text, use_jieba=True):
split_tokens = []
if use_jieba:
for wholword in self.jieba.cut(text, False):
if wholword in self.vocab:
split_tokens.append(wholword)
else:
# use bert tokenizer to _tokenize
char_list = self._tokenize(wholword, use_jieba=False)
split_tokens.extend(char_list)
else:
if self.do_basic_tokenize:
for token in self.basic_tokenizer.tokenize(
text, never_split=self.all_special_tokens):
# If the token is part of the never_split set
if token in self.basic_tokenizer.never_split:
split_tokens.append(token)
else:
split_tokens += self.wordpiece_tokenizer.tokenize(
token)
else:
split_tokens = self.wordpiece_tokenizer.tokenize(text)
return split_tokens
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.vocab.get(token, self.vocab.get(self.unk_token))
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.ids_to_tokens.get(index, self.unk_token)
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
out_string = " ".join(tokens).replace(" ##", "").strip()
return out_string
def build_inputs_with_special_tokens(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None) -> List[int]:
"""
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A RoFormer sequence has the following format:
- single sequence: ``[CLS] X [SEP]``
- pair of sequences: ``[CLS] A [SEP] B [SEP]``
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
Returns:
:obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
"""
if token_ids_1 is None:
return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
cls = [self.cls_token_id]
sep = [self.sep_token_id]
return cls + token_ids_0 + sep + token_ids_1 + sep
def get_special_tokens_mask(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None,
already_has_special_tokens: bool = False,
) -> List[int]:
"""
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer ``prepare_for_model`` method.
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
:obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
"""
if already_has_special_tokens:
return super().get_special_tokens_mask(
token_ids_0=token_ids_0,
token_ids_1=token_ids_1,
already_has_special_tokens=True,
)
if token_ids_1 is not None:
return [1] + ([0] * len(token_ids_0)) + [1] + (
[0] * len(token_ids_1)) + [1]
return [1] + ([0] * len(token_ids_0)) + [1]
def create_token_type_ids_from_sequences(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None) -> List[int]:
"""
Create a mask from the two sequences passed to be used in a sequence-pair classification task. A RoFormer
sequence pair mask has the following format:
::
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
| first sequence | second sequence |
If :obj:`token_ids_1` is :obj:`None`, this method only returns the first portion of the mask (0s).
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
Returns:
:obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
sequence(s).
"""
sep = [self.sep_token_id]
cls = [self.cls_token_id]
if token_ids_1 is None:
return len(cls + token_ids_0 + sep) * [0]
return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 +
sep) * [1]
def save_vocabulary(self,
save_directory: str,
filename_prefix: Optional[str] = None) -> Tuple[str]:
index = 0
if os.path.isdir(save_directory):
vocab_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") +
VOCAB_FILES_NAMES["vocab_file"],
)
else:
vocab_file = (filename_prefix +
"-" if filename_prefix else "") + save_directory
with open(vocab_file, "w", encoding="utf-8") as writer:
for token, token_index in sorted(self.vocab.items(),
key=lambda kv: kv[1]):
if index != token_index:
logger.warning(
f"Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive."
" Please check that the vocabulary is not corrupted!")
index = token_index
writer.write(token + "\n")
index += 1
return (vocab_file, )
def test_basic_tokenizer_respects_never_split_tokens(self):
tokenizer = BasicTokenizer(do_lower_case=False, never_split=["[UNK]"])
self.assertListEqual(
tokenizer.tokenize(" \tHeLLo!how \n Are yoU? [UNK]"), ["HeLLo", "!", "how", "Are", "yoU", "?", "[UNK]"]
)
def test_basic_tokenizer_no_lower_strip_accents_true(self):
tokenizer = BasicTokenizer(do_lower_case=False, strip_accents=True)
self.assertListEqual(
tokenizer.tokenize(" \tHäLLo!how \n Are yoU? "), ["HaLLo", "!", "how", "Are", "yoU", "?"]
)
def test_basic_tokenizer_no_lower(self):
tokenizer = BasicTokenizer(do_lower_case=False)
self.assertListEqual(
tokenizer.tokenize(" \tHeLLo!how \n Are yoU? "), ["HeLLo", "!", "how", "Are", "yoU", "?"]
)
def test_chinese(self):
tokenizer = BasicTokenizer()
self.assertListEqual(tokenizer.tokenize("ah\u535A\u63A8zz"), ["ah", "\u535A", "\u63A8", "zz"])
def get_final_text(pred_text, orig_text, do_lower_case):
"""Project the tokenized prediction back to the original text."""
# When we created the data, we kept track of the alignment between original
# (whitespace tokenized) tokens and our WordPiece tokenized tokens. So
# now `orig_text` contains the span of our original text corresponding to the
# span that we predicted.
#
# However, `orig_text` may contain extra characters that we don't want in
# our prediction.
#
# For example, let's say:
# pred_text = steve smith
# orig_text = Steve Smith's
#
# We don't want to return `orig_text` because it contains the extra "'s".
#
# We don't want to return `pred_text` because it's already been normalized
# (the SQuAD eval script also does punctuation stripping/lower casing but
# our tokenizer does additional normalization like stripping accent
# characters).
#
# What we really want to return is "Steve Smith".
#
# Therefore, we have to apply a semi-complicated alignment heuristic between
# `pred_text` and `orig_text` to get a character-to-character alignment. This
# can fail in certain cases in which case we just return `orig_text`.
def _strip_spaces(text):
ns_chars = []
ns_to_s_map = collections.OrderedDict()
for idx, c in enumerate(text):
if c == " ":
continue
ns_to_s_map[len(ns_chars)] = idx
ns_chars.append(c)
ns_text = "".join(ns_chars)
return ns_text, ns_to_s_map
# We first tokenize `orig_text`, strip whitespace from the result
# and `pred_text`, and check if they are the same length. If they are
# NOT the same length, the heuristic has failed. If they are the same
# length, we assume the characters are one-to-one aligned.
tokenizer = BasicTokenizer(do_lower_case=do_lower_case)
tok_text = " ".join(tokenizer.tokenize(orig_text))
start_position = tok_text.find(pred_text)
if start_position == -1:
return orig_text
end_position = start_position + len(pred_text) - 1
(orig_ns_text, orig_ns_to_s_map) = _strip_spaces(orig_text)
(tok_ns_text, tok_ns_to_s_map) = _strip_spaces(tok_text)
if len(orig_ns_text) != len(tok_ns_text):
return orig_text
# We then project the characters in `pred_text` back to `orig_text` using
# the character-to-character alignment.
tok_s_to_ns_map = {}
for (i, tok_index) in tok_ns_to_s_map.items():
tok_s_to_ns_map[tok_index] = i
orig_start_position = None
if start_position in tok_s_to_ns_map:
ns_start_position = tok_s_to_ns_map[start_position]
if ns_start_position in orig_ns_to_s_map:
orig_start_position = orig_ns_to_s_map[ns_start_position]
if orig_start_position is None:
return orig_text
orig_end_position = None
if end_position in tok_s_to_ns_map:
ns_end_position = tok_s_to_ns_map[end_position]
if ns_end_position in orig_ns_to_s_map:
orig_end_position = orig_ns_to_s_map[ns_end_position]
if orig_end_position is None:
return orig_text
output_text = orig_text[orig_start_position:(orig_end_position + 1)]
return output_text
def _get_final_text(pred_text,
orig_text,
do_lower_case,
verbose_logging=False):
def _strip_spaces(text):
ns_chars = []
ns_to_s_map = collections.OrderedDict()
for (i, c) in enumerate(text):
if c == " ":
continue
ns_to_s_map[len(ns_chars)] = i
ns_chars.append(c)
ns_text = "".join(ns_chars)
return ns_text, ns_to_s_map
# We first tokenize `orig_text`, strip whitespace from the result
# and `pred_text`, and check if they are the same length. If they are
# NOT the same length, the heuristic has failed. If they are the same
# length, we assume the characters are one-to-one aligned.
tokenizer = BasicTokenizer(do_lower_case=do_lower_case)
tok_text = " ".join(tokenizer.tokenize(orig_text))
start_position = tok_text.find(pred_text)
if start_position == -1:
if verbose_logging:
logger.info("Unable to find text: '%s' in '%s'" %
(pred_text, orig_text))
return orig_text
end_position = start_position + len(pred_text) - 1
(orig_ns_text, orig_ns_to_s_map) = _strip_spaces(orig_text)
(tok_ns_text, tok_ns_to_s_map) = _strip_spaces(tok_text)
if len(orig_ns_text) != len(tok_ns_text):
if verbose_logging:
logger.info(
"Length not equal after stripping spaces: '%s' vs '%s'",
orig_ns_text, tok_ns_text)
return orig_text
# We then project the characters in `pred_text` back to `orig_text` using
# the character-to-character alignment.
tok_s_to_ns_map = {}
for (i, tok_index) in tok_ns_to_s_map.items():
tok_s_to_ns_map[tok_index] = i
orig_start_position = None
if start_position in tok_s_to_ns_map:
ns_start_position = tok_s_to_ns_map[start_position]
if ns_start_position in orig_ns_to_s_map:
orig_start_position = orig_ns_to_s_map[ns_start_position]
if orig_start_position is None:
if verbose_logging:
logger.info("Couldn't map start position")
return orig_text
orig_end_position = None
if end_position in tok_s_to_ns_map:
ns_end_position = tok_s_to_ns_map[end_position]
if ns_end_position in orig_ns_to_s_map:
orig_end_position = orig_ns_to_s_map[ns_end_position]
if orig_end_position is None:
if verbose_logging:
logger.info("Couldn't map end position")
return orig_text
output_text = orig_text[orig_start_position:(orig_end_position + 1)]
return output_text
class CLIPTokenizer(PreTrainedTokenizer):
"""
Construct a CLIP tokenizer. Based on byte-level Byte-Pair-Encoding.
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
Args:
vocab_file (`str`):
Path to the vocabulary file.
merges_file (`str`):
Path to the merges file.
errors (`str`, *optional*, defaults to `"replace"`):
Paradigm to follow when decoding bytes to UTF-8. See
[bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
bos_token (`str`, *optional*, defaults to `<|endoftext|>`):
The beginning of sequence token.
eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
The end of sequence token.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
model_input_names = ["input_ids", "attention_mask"]
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
unk_token="<|endoftext|>",
bos_token="<|startoftext|>",
eos_token="<|endoftext|>",
pad_token="<|endoftext|>", # hack to enable padding
**kwargs):
bos_token = AddedToken(bos_token,
lstrip=False, rstrip=False) if isinstance(
bos_token, str) else bos_token
eos_token = AddedToken(eos_token,
lstrip=False, rstrip=False) if isinstance(
eos_token, str) else eos_token
unk_token = AddedToken(unk_token,
lstrip=False, rstrip=False) if isinstance(
unk_token, str) else unk_token
super().__init__(
errors=errors,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
**kwargs,
)
try:
import ftfy
self.fix_text = ftfy.fix_text
except ImportError:
logger.warning(
"ftfy or spacy is not installed using BERT BasicTokenizer instead of ftfy."
)
self.nlp = BasicTokenizer(do_lower_case=True)
self.fix_text = None
with open(vocab_file, encoding="utf-8") as vocab_handle:
self.encoder = json.load(vocab_handle)
self.decoder = {v: k for k, v in self.encoder.items()}
self.errors = errors # how to handle errors in decoding
self.byte_encoder = bytes_to_unicode()
self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
with open(merges_file, encoding="utf-8") as merges_handle:
bpe_merges = merges_handle.read().strip().split("\n")[1:49152 -
256 - 2 + 1]
bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
self.cache = {
"<|startoftext|>": "<|startoftext|>",
"<|endoftext|>": "<|endoftext|>"
}
self.pat = re.compile(
r"""<\|startoftext\|>|<\|endoftext\|>|'s|'t|'re|'ve|'m|'ll|'d|[\p{L}]+|[\p{N}]|[^\s\p{L}\p{N}]+""",
re.IGNORECASE,
)
@property
def vocab_size(self):
return len(self.encoder)
def get_vocab(self):
return dict(self.encoder, **self.added_tokens_encoder)
def build_inputs_with_special_tokens(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None) -> List[int]:
"""
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A CLIP sequence has the following format:
- single sequence: `<|startoftext|> X <|endoftext|>`
Pairs of sequences are not the expected use case, but they will be handled without a separator.
Args:
token_ids_0 (`List[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
"""
bos_token = [self.bos_token_id]
eos_token = [self.eos_token_id]
if token_ids_1 is None:
return bos_token + token_ids_0 + eos_token
return bos_token + token_ids_0 + eos_token + eos_token + token_ids_1 + eos_token
def get_special_tokens_mask(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None,
already_has_special_tokens: bool = False) -> List[int]:
"""
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
"""
if already_has_special_tokens:
return super().get_special_tokens_mask(
token_ids_0=token_ids_0,
token_ids_1=token_ids_1,
already_has_special_tokens=True)
if token_ids_1 is None:
return [1] + ([0] * len(token_ids_0)) + [1]
return [1] + ([0] * len(token_ids_0)) + [1] + [1] + (
[0] * len(token_ids_1)) + [1]
def create_token_type_ids_from_sequences(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None) -> List[int]:
"""
Create a mask from the two sequences passed. CLIP does not make use of token type ids, therefore a list of
zeros is returned.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of zeros.
"""
bos_token = [self.bos_token_id]
eos_token = [self.eos_token_id]
if token_ids_1 is None:
return len(bos_token + token_ids_0 + eos_token) * [0]
return len(bos_token + token_ids_0 + eos_token + eos_token +
token_ids_1 + eos_token) * [0]
def bpe(self, token):
if token in self.cache:
return self.cache[token]
word = tuple(token[:-1]) + (token[-1] + "</w>", )
pairs = get_pairs(word)
if not pairs:
return token + "</w>"
while True:
bigram = min(
pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
if bigram not in self.bpe_ranks:
break
first, second = bigram
new_word = []
i = 0
while i < len(word):
try:
j = word.index(first, i)
except ValueError:
new_word.extend(word[i:])
break
else:
new_word.extend(word[i:j])
i = j
if word[i] == first and i < len(word) - 1 and word[
i + 1] == second:
new_word.append(first + second)
i += 2
else:
new_word.append(word[i])
i += 1
new_word = tuple(new_word)
word = new_word
if len(word) == 1:
break
else:
pairs = get_pairs(word)
word = " ".join(word)
self.cache[token] = word
return word
def _tokenize(self, text):
"""Tokenize a string."""
bpe_tokens = []
if self.fix_text is None:
text = " ".join(self.nlp.tokenize(text))
else:
text = whitespace_clean(self.fix_text(text)).lower()
for token in re.findall(self.pat, text):
token = "".join(
self.byte_encoder[b] for b in token.encode("utf-8")
) # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case)
bpe_tokens.extend(bpe_token
for bpe_token in self.bpe(token).split(" "))
return bpe_tokens
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.encoder.get(token, self.encoder.get(self.unk_token))
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.decoder.get(index)
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
text = "".join(tokens)
byte_array = bytearray([self.byte_decoder[c] for c in text])
text = byte_array.decode("utf-8",
errors=self.errors).replace("</w>",
" ").strip()
return text
def save_vocabulary(self,
save_directory: str,
filename_prefix: Optional[str] = None) -> Tuple[str]:
if not os.path.isdir(save_directory):
logger.error("Vocabulary path ({}) should be a directory".format(
save_directory))
return
vocab_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") +
VOCAB_FILES_NAMES["vocab_file"])
merge_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") +
VOCAB_FILES_NAMES["merges_file"])
with open(vocab_file, "w", encoding="utf-8") as f:
f.write(json.dumps(self.encoder, ensure_ascii=False))
index = 0
with open(merge_file, "w", encoding="utf-8") as writer:
writer.write("#version: 0.2\n")
for bpe_tokens, token_index in sorted(self.bpe_ranks.items(),
key=lambda kv: kv[1]):
if index != token_index:
logger.warning(
"Saving vocabulary to {}: BPE merge indices are not consecutive."
" Please check that the tokenizer is not corrupted!".
format(merge_file))
index = token_index
writer.write(" ".join(bpe_tokens) + "\n")
index += 1
return vocab_file, merge_file
