File size: 7,455 Bytes
06ba6ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
# coding=utf-8
# Copyright 2022 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization classes for Bloom."""
import pickle
from typing import Optional, Tuple
from ...tokenization_utils_base import BatchEncoding
from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"tokenizer_file": "tokenizer.json"}
PRETRAINED_VOCAB_FILES_MAP = {
"tokenizer_file": {
"bigscience/tokenizer": "https://huggingface.co/bigscience/tokenizer/blob/main/tokenizer.json",
"bigscience/bloom-560m": "https://huggingface.co/bigscience/bloom-560m/blob/main/tokenizer.json",
"bigscience/bloom-1b1": "https://huggingface.co/bigscience/bloom-1b1/blob/main/tokenizer.json",
"bigscience/bloom-1b7": "https://huggingface.co/bigscience/bloom-1b7/blob/main/tokenizer.json",
"bigscience/bloom-3b": "https://huggingface.co/bigscience/bloom-3b/blob/main/tokenizer.json",
"bigscience/bloom-7b1": "https://huggingface.co/bigscience/bloom-7b1/blob/main/tokenizer.json",
"bigscience/bloom": "https://huggingface.co/bigscience/bloom/blob/main/tokenizer.json",
},
}
class BloomTokenizerFast(PreTrainedTokenizerFast):
"""
Construct a "fast" Bloom tokenizer (backed by HuggingFace's *tokenizers* library). Based on 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:
```python
>>> from transformers import BloomTokenizerFast
>>> tokenizer = BloomTokenizerFast.from_pretrained("bigscience/bloom")
>>> tokenizer("Hello world")["input_ids"]
[59414, 8876]
>>> tokenizer(" Hello world")["input_ids"]
[86153, 8876]
```
You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer, 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.
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.
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. (Bloom tokenizer detect beginning of words by the preceding space).
trim_offsets (`bool`, *optional*, defaults to `True`):
Whether or not 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
model_input_names = ["input_ids", "attention_mask"]
slow_tokenizer_class = None
# No `max_model_input_sizes` as BLOOM uses ALiBi positional embeddings
def __init__(
self,
vocab_file=None,
merges_file=None,
tokenizer_file=None,
unk_token="<unk>",
bos_token="<s>",
eos_token="</s>",
pad_token="<pad>",
add_prefix_space=False,
clean_up_tokenization_spaces=False,
**kwargs,
):
super().__init__(
vocab_file,
merges_file,
tokenizer_file=tokenizer_file,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
add_prefix_space=add_prefix_space,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
**kwargs,
)
# TODO @ArthurZucker this can only work one way for now, to update later-on. Tests should also properly
# check this as they were green before.
pre_tok_state = pickle.dumps(self.backend_tokenizer.pre_tokenizer)
decoder_state = pickle.dumps(self.backend_tokenizer.decoder)
if add_prefix_space:
pre_tok_state = pre_tok_state.replace(b'"add_prefix_space":false', b'"add_prefix_space": true')
decoder_state = decoder_state.replace(b'"add_prefix_space":false', b'"add_prefix_space": true')
self.backend_tokenizer.pre_tokenizer = pickle.loads(pre_tok_state)
self.backend_tokenizer.decoder = pickle.loads(decoder_state)
self.add_prefix_space = add_prefix_space
def _batch_encode_plus(self, *args, **kwargs) -> BatchEncoding:
is_split_into_words = kwargs.get("is_split_into_words", False)
if not (self.add_prefix_space or not is_split_into_words):
raise Exception(
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)
def _encode_plus(self, *args, **kwargs) -> BatchEncoding:
is_split_into_words = kwargs.get("is_split_into_words", False)
if not (self.add_prefix_space or not is_split_into_words):
raise Exception(
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)
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)
@property
# Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.default_chat_template
def default_chat_template(self):
"""
A simple chat template that ignores role information and just concatenates messages with EOS tokens.
"""
return "{% for message in messages %}" "{{ message.content }}{{ eos_token }}" "{% endfor %}"
|