mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-31 02:02:21 +06:00
Remove dependency of Roberta in Blenderbot (#19411)
* Remove dependency of Roberta in Blenderbot * Move Copied from statements to each method of the Roberta classes * Remove copied from line for mask_token.setter * update output from example in docs
This commit is contained in:
Ryan Chan
GitHub
parent
3080bb4754
commit
4824741c4c
@ -14,10 +14,15 @@
|
||||
# limitations under the License.
|
||||
"""Tokenization class for Blenderbot."""
|
||||
|
||||
from typing import TYPE_CHECKING, List, Optional
|
||||
import json
|
||||
import os
|
||||
from functools import lru_cache
|
||||
from typing import TYPE_CHECKING, List, Optional, Tuple
|
||||
|
||||
import regex as re
|
||||
|
||||
from ...tokenization_utils import AddedToken, PreTrainedTokenizer
|
||||
from ...utils import logging
|
||||
from ..roberta.tokenization_roberta import RobertaTokenizer
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@ -43,32 +48,362 @@ PRETRAINED_VOCAB_FILES_MAP = {
|
||||
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot-3B": 128}
|
||||
|
||||
|
||||
class BlenderbotTokenizer(RobertaTokenizer):
|
||||
r"""
|
||||
Construct a Blenderbot tokenizer.
|
||||
|
||||
[`Blenderbot`] is nearly identical to [`RobertaTokenizer`] and runs end-to-end tokenization: punctuation splitting
|
||||
and wordpiece. The only difference is that it doesn't add BOS token to the beginning of sequences.
|
||||
|
||||
Refer to superclass [`RobertaTokenizer`] for usage examples and documentation concerning parameters.
|
||||
@lru_cache()
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.bytes_to_unicode
|
||||
def bytes_to_unicode():
|
||||
"""
|
||||
Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control
|
||||
characters the bpe code barfs on.
|
||||
|
||||
The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab
|
||||
if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for
|
||||
decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup
|
||||
tables between utf-8 bytes and unicode strings.
|
||||
"""
|
||||
bs = (
|
||||
list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
|
||||
)
|
||||
cs = bs[:]
|
||||
n = 0
|
||||
for b in range(2**8):
|
||||
if b not in bs:
|
||||
bs.append(b)
|
||||
cs.append(2**8 + n)
|
||||
n += 1
|
||||
cs = [chr(n) for n in cs]
|
||||
return dict(zip(bs, cs))
|
||||
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.get_pairs
|
||||
def get_pairs(word):
|
||||
"""
|
||||
Return set of symbol pairs in a word.
|
||||
|
||||
Word is represented as tuple of symbols (symbols being variable-length strings).
|
||||
"""
|
||||
pairs = set()
|
||||
prev_char = word[0]
|
||||
for char in word[1:]:
|
||||
pairs.add((prev_char, char))
|
||||
prev_char = char
|
||||
return pairs
|
||||
|
||||
|
||||
class BlenderbotTokenizer(PreTrainedTokenizer):
|
||||
"""
|
||||
Constructs a Blenderbot tokenizer, derived from the GPT-2 tokenizer, using byte-level Byte-Pair-Encoding.
|
||||
|
||||
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
|
||||
be encoded differently whether it is at the beginning of the sentence (without space) or not:
|
||||
|
||||
```
|
||||
>>> from transformers import BlenderbotTokenizer
|
||||
>>> tokenizer = BlenderbotTokenizer.from_pretrained("facebook/blenderbot-3B")
|
||||
>>> tokenizer("Hello world")['input_ids']
|
||||
[6950, 1085, 2]
|
||||
>>> tokenizer(" Hello world")['input_ids']
|
||||
[6950, 1085, 2]
|
||||
```
|
||||
|
||||
You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you
|
||||
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
|
||||
|
||||
<Tip>
|
||||
|
||||
When used with `is_split_into_words=True`, this tokenizer will add a space before each word (even the first one).
|
||||
|
||||
</Tip>
|
||||
|
||||
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.
|
||||
bos_token (`str`, *optional*, defaults to `"<s>"`):
|
||||
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
||||
|
||||
<Tip>
|
||||
|
||||
When building a sequence using special tokens, this is not the token that is used for the beginning of
|
||||
sequence. The token used is the `cls_token`.
|
||||
|
||||
</Tip>
|
||||
|
||||
eos_token (`str`, *optional*, defaults to `"</s>"`):
|
||||
The end of sequence token.
|
||||
|
||||
<Tip>
|
||||
|
||||
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
|
||||
The token used is the `sep_token`.
|
||||
|
||||
</Tip>
|
||||
|
||||
sep_token (`str`, *optional*, defaults to `"</s>"`):
|
||||
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.
|
||||
cls_token (`str`, *optional*, defaults to `"<s>"`):
|
||||
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.
|
||||
unk_token (`str`, *optional*, defaults to `"<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.
|
||||
pad_token (`str`, *optional*, defaults to `"<pad>"`):
|
||||
The token used for padding, for example when batching sequences of different lengths.
|
||||
mask_token (`str`, *optional*, defaults to `"<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.
|
||||
add_prefix_space (`bool`, *optional*, defaults to `False`):
|
||||
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
|
||||
other word. (Blenderbot tokenizer detect beginning of words by the preceding space).
|
||||
"""
|
||||
|
||||
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"]
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.__init__ with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def __init__(
|
||||
self,
|
||||
vocab_file,
|
||||
merges_file,
|
||||
errors="replace",
|
||||
bos_token="<s>",
|
||||
eos_token="</s>",
|
||||
sep_token="</s>",
|
||||
cls_token="<s>",
|
||||
unk_token="<unk>",
|
||||
pad_token="<pad>",
|
||||
mask_token="<mask>",
|
||||
add_prefix_space=False,
|
||||
**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
|
||||
sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token
|
||||
cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token
|
||||
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
|
||||
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
||||
|
||||
# Mask token behave like a normal word, i.e. include the space before it
|
||||
mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
|
||||
|
||||
super().__init__(
|
||||
errors=errors,
|
||||
bos_token=bos_token,
|
||||
eos_token=eos_token,
|
||||
unk_token=unk_token,
|
||||
sep_token=sep_token,
|
||||
cls_token=cls_token,
|
||||
pad_token=pad_token,
|
||||
mask_token=mask_token,
|
||||
add_prefix_space=add_prefix_space,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
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().split("\n")[1:-1]
|
||||
bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
|
||||
self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
|
||||
self.cache = {}
|
||||
self.add_prefix_space = add_prefix_space
|
||||
|
||||
# Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
|
||||
self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
|
||||
|
||||
@property
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.vocab_size with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def vocab_size(self):
|
||||
return len(self.encoder)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.get_vocab with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def get_vocab(self):
|
||||
return dict(self.encoder, **self.added_tokens_encoder)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.bpe with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def bpe(self, token):
|
||||
if token in self.cache:
|
||||
return self.cache[token]
|
||||
word = tuple(token)
|
||||
pairs = get_pairs(word)
|
||||
|
||||
if not pairs:
|
||||
return token
|
||||
|
||||
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
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer._tokenize with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def _tokenize(self, text):
|
||||
"""Tokenize a string."""
|
||||
bpe_tokens = []
|
||||
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
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer._convert_token_to_id with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
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))
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer._convert_id_to_token with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def _convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
return self.decoder.get(index)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.convert_tokens_to_string with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def convert_tokens_to_string(self, tokens):
|
||||
"""Converts a sequence of tokens (string) in a single string."""
|
||||
text = "".join(tokens)
|
||||
text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors)
|
||||
return text
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.save_vocabulary with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
||||
if not os.path.isdir(save_directory):
|
||||
logger.error(f"Vocabulary path ({save_directory}) should be a 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, indent=2, sort_keys=True, ensure_ascii=False) + "\n")
|
||||
|
||||
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(
|
||||
f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive."
|
||||
" Please check that the tokenizer is not corrupted!"
|
||||
)
|
||||
index = token_index
|
||||
writer.write(" ".join(bpe_tokens) + "\n")
|
||||
index += 1
|
||||
|
||||
return vocab_file, merge_file
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.get_special_tokens_mask with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
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]
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.create_token_type_ids_from_sequences with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
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. Blenderbot 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.
|
||||
"""
|
||||
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 + sep + token_ids_1 + sep) * [0]
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta.RobertaTokenizer.prepare_for_tokenization with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
|
||||
add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
|
||||
if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()):
|
||||
text = " " + text
|
||||
return (text, kwargs)
|
||||
|
||||
def build_inputs_with_special_tokens(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None):
|
||||
"""
|
||||
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
||||
adding special tokens. A Blenderbot sequence has the following format:
|
||||
|
||||
- single sequence: ` X </s>`
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs to which the special tokens will be added
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Will be ignored
|
||||
|
||||
Returns:
|
||||
`List[int]`: list of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
||||
"""
|
||||
@ -90,19 +425,3 @@ class BlenderbotTokenizer(RobertaTokenizer):
|
||||
input_ids = input_ids[-self.model_max_length :]
|
||||
logger.warning(f"Trimmed input from conversation as it was longer than {self.model_max_length} tokens.")
|
||||
return input_ids
|
||||
|
||||
|
||||
def get_pairs(word):
|
||||
"""
|
||||
Return set of symbol pairs in a word.
|
||||
|
||||
Word is represented as tuple of symbols (symbols being variable-length strings).
|
||||
"""
|
||||
pairs = set()
|
||||
prev_char = word[0]
|
||||
for char in word[1:]:
|
||||
pairs.add((prev_char, char))
|
||||
prev_char = char
|
||||
|
||||
pairs = set(pairs)
|
||||
return pairs
|
||||
|
||||
@ -13,11 +13,14 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
"""Fast Tokenization class for Blenderbot."""
|
||||
import json
|
||||
from typing import TYPE_CHECKING, List, Optional, Tuple
|
||||
|
||||
from typing import TYPE_CHECKING, List, Optional
|
||||
from tokenizers import pre_tokenizers, processors
|
||||
|
||||
from ...tokenization_utils_base import AddedToken, BatchEncoding
|
||||
from ...tokenization_utils_fast import PreTrainedTokenizerFast
|
||||
from ...utils import logging
|
||||
from ..roberta.tokenization_roberta_fast import RobertaTokenizerFast
|
||||
from .tokenization_blenderbot import BlenderbotTokenizer
|
||||
|
||||
|
||||
@ -44,33 +47,248 @@ PRETRAINED_VOCAB_FILES_MAP = {
|
||||
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot-3B": 128}
|
||||
|
||||
|
||||
class BlenderbotTokenizerFast(RobertaTokenizerFast):
|
||||
r"""
|
||||
Construct a "fast" Blenderbot tokenizer (backed by HuggingFace's *tokenizers* library).
|
||||
|
||||
[`BlenderbotFast`] is nearly identical to [`RobertaTokenizerFast`] and runs end-to-end tokenization: punctuation
|
||||
splitting and wordpiece. The only difference is that it doesn't add BOS token to the beginning of sequences.
|
||||
|
||||
Refer to superclass [`RobertaTokenizerFast`] for usage examples and documentation concerning parameters.
|
||||
class BlenderbotTokenizerFast(PreTrainedTokenizerFast):
|
||||
"""
|
||||
Construct a "fast" Blenderbot tokenizer (backed by HuggingFace's *tokenizers* library), derived from the GPT-2
|
||||
tokenizer, using byte-level Byte-Pair-Encoding.
|
||||
|
||||
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
|
||||
be encoded differently whether it is at the beginning of the sentence (without space) or not:
|
||||
|
||||
```
|
||||
>>> from transformers import BlenderbotTokenizerFast
|
||||
>>> tokenizer = BlenderbotTokenizerFast.from_pretrained("facebook/blenderbot-3B")
|
||||
>>> tokenizer("Hello world")['input_ids']
|
||||
[6950, 1085, 2]
|
||||
>>> tokenizer(" Hello world")['input_ids']
|
||||
[6950, 1085, 2]
|
||||
```
|
||||
|
||||
You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you
|
||||
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
|
||||
|
||||
<Tip>
|
||||
|
||||
When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`.
|
||||
|
||||
</Tip>
|
||||
|
||||
This tokenizer inherits from [`PreTrainedTokenizerFast`] 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.
|
||||
bos_token (`str`, *optional*, defaults to `"<s>"`):
|
||||
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
||||
|
||||
<Tip>
|
||||
|
||||
When building a sequence using special tokens, this is not the token that is used for the beginning of
|
||||
sequence. The token used is the `cls_token`.
|
||||
|
||||
</Tip>
|
||||
|
||||
eos_token (`str`, *optional*, defaults to `"</s>"`):
|
||||
The end of sequence token.
|
||||
|
||||
<Tip>
|
||||
|
||||
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
|
||||
The token used is the `sep_token`.
|
||||
|
||||
</Tip>
|
||||
|
||||
sep_token (`str`, *optional*, defaults to `"</s>"`):
|
||||
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.
|
||||
cls_token (`str`, *optional*, defaults to `"<s>"`):
|
||||
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.
|
||||
unk_token (`str`, *optional*, defaults to `"<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.
|
||||
pad_token (`str`, *optional*, defaults to `"<pad>"`):
|
||||
The token used for padding, for example when batching sequences of different lengths.
|
||||
mask_token (`str`, *optional*, defaults to `"<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.
|
||||
add_prefix_space (`bool`, *optional*, defaults to `False`):
|
||||
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
|
||||
other word. (Blenderbot tokenizer detect beginning of words by the preceding space).
|
||||
trim_offsets (`bool`, *optional*, defaults to `True`):
|
||||
Whether the post processing step should trim offsets to avoid including whitespaces.
|
||||
"""
|
||||
|
||||
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"]
|
||||
slow_tokenizer_class = BlenderbotTokenizer
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast.__init__ with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def __init__(
|
||||
self,
|
||||
vocab_file=None,
|
||||
merges_file=None,
|
||||
tokenizer_file=None,
|
||||
errors="replace",
|
||||
bos_token="<s>",
|
||||
eos_token="</s>",
|
||||
sep_token="</s>",
|
||||
cls_token="<s>",
|
||||
unk_token="<unk>",
|
||||
pad_token="<pad>",
|
||||
mask_token="<mask>",
|
||||
add_prefix_space=False,
|
||||
trim_offsets=True,
|
||||
**kwargs
|
||||
):
|
||||
super().__init__(
|
||||
vocab_file,
|
||||
merges_file,
|
||||
tokenizer_file=tokenizer_file,
|
||||
errors=errors,
|
||||
bos_token=bos_token,
|
||||
eos_token=eos_token,
|
||||
sep_token=sep_token,
|
||||
cls_token=cls_token,
|
||||
unk_token=unk_token,
|
||||
pad_token=pad_token,
|
||||
mask_token=mask_token,
|
||||
add_prefix_space=add_prefix_space,
|
||||
trim_offsets=trim_offsets,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
pre_tok_state = json.loads(self.backend_tokenizer.pre_tokenizer.__getstate__())
|
||||
if pre_tok_state.get("add_prefix_space", add_prefix_space) != add_prefix_space:
|
||||
pre_tok_class = getattr(pre_tokenizers, pre_tok_state.pop("type"))
|
||||
pre_tok_state["add_prefix_space"] = add_prefix_space
|
||||
self.backend_tokenizer.pre_tokenizer = pre_tok_class(**pre_tok_state)
|
||||
|
||||
self.add_prefix_space = add_prefix_space
|
||||
|
||||
tokenizer_component = "post_processor"
|
||||
tokenizer_component_instance = getattr(self.backend_tokenizer, tokenizer_component, None)
|
||||
if tokenizer_component_instance:
|
||||
state = json.loads(tokenizer_component_instance.__getstate__())
|
||||
|
||||
# The lists 'sep' and 'cls' must be cased in tuples for the object `post_processor_class`
|
||||
if "sep" in state:
|
||||
state["sep"] = tuple(state["sep"])
|
||||
if "cls" in state:
|
||||
state["cls"] = tuple(state["cls"])
|
||||
|
||||
changes_to_apply = False
|
||||
|
||||
if state.get("add_prefix_space", add_prefix_space) != add_prefix_space:
|
||||
state["add_prefix_space"] = add_prefix_space
|
||||
changes_to_apply = True
|
||||
|
||||
if state.get("trim_offsets", trim_offsets) != trim_offsets:
|
||||
state["trim_offsets"] = trim_offsets
|
||||
changes_to_apply = True
|
||||
|
||||
if changes_to_apply:
|
||||
component_class = getattr(processors, state.pop("type"))
|
||||
new_value = component_class(**state)
|
||||
setattr(self.backend_tokenizer, tokenizer_component, new_value)
|
||||
|
||||
@property
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast.mask_token with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def mask_token(self) -> str:
|
||||
"""
|
||||
`str`: Mask token, to use when training a model with masked-language modeling. Log an error if used while not
|
||||
having been set.
|
||||
|
||||
Blenderbot tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will
|
||||
greedily comprise the space before the *<mask>*.
|
||||
"""
|
||||
if self._mask_token is None:
|
||||
if self.verbose:
|
||||
logger.error("Using mask_token, but it is not set yet.")
|
||||
return None
|
||||
return str(self._mask_token)
|
||||
|
||||
@mask_token.setter
|
||||
def mask_token(self, value):
|
||||
"""
|
||||
Overriding the default behavior of the mask token to have it eat the space before it.
|
||||
|
||||
This is needed to preserve backward compatibility with all the previously used models based on Roberta.
|
||||
"""
|
||||
# Mask token behave like a normal word, i.e. include the space before it
|
||||
# So we set lstrip to True
|
||||
value = AddedToken(value, lstrip=True, rstrip=False) if isinstance(value, str) else value
|
||||
self._mask_token = value
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast._batch_encode_plus with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def _batch_encode_plus(self, *args, **kwargs) -> BatchEncoding:
|
||||
is_split_into_words = kwargs.get("is_split_into_words", False)
|
||||
assert self.add_prefix_space or not is_split_into_words, (
|
||||
f"You need to instantiate {self.__class__.__name__} with add_prefix_space=True "
|
||||
"to use it with pretokenized inputs."
|
||||
)
|
||||
|
||||
return super()._batch_encode_plus(*args, **kwargs)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast._encode_plus with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def _encode_plus(self, *args, **kwargs) -> BatchEncoding:
|
||||
is_split_into_words = kwargs.get("is_split_into_words", False)
|
||||
|
||||
assert self.add_prefix_space or not is_split_into_words, (
|
||||
f"You need to instantiate {self.__class__.__name__} with add_prefix_space=True "
|
||||
"to use it with pretokenized inputs."
|
||||
)
|
||||
|
||||
return super()._encode_plus(*args, **kwargs)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast.save_vocabulary with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
||||
files = self._tokenizer.model.save(save_directory, name=filename_prefix)
|
||||
return tuple(files)
|
||||
|
||||
# Copied from transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast.create_token_type_ids_from_sequences with Roberta->Blenderbot, RoBERTa->Blenderbot
|
||||
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. Blenderbot 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.
|
||||
"""
|
||||
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 + sep + token_ids_1 + sep) * [0]
|
||||
|
||||
def build_inputs_with_special_tokens(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None):
|
||||
"""
|
||||
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
||||
adding special tokens. A Blenderbot sequence has the following format:
|
||||
|
||||
- single sequence: ` X </s>`
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs to which the special tokens will be added
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Will be ignored
|
||||
|
||||
Returns:
|
||||
`List[int]`: list of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
||||
"""
|
||||
|
||||
Loading…
Reference in New Issue
Block a user