File size: 3,136 Bytes
ea51a3d | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | from __future__ import annotations
import json
import os
from transformers import PreTrainedTokenizer
class TransWaveByteTokenizer(PreTrainedTokenizer):
vocab_files_names = {
"vocab_file": "vocab.json"
}
model_input_names = [
"input_ids"
]
def __init__(
self,
vocab_file=None,
model_max_length=20480,
**kwargs,
):
self.vocab_file = vocab_file
self._id_to_token = [
f"<0x{i:02X}>"
for i in range(256)
]
self._token_to_id = {
token: i
for i, token
in enumerate(self._id_to_token)
}
# Values may already arrive through tokenizer_config.json.
# Never pass the same keyword twice.
kwargs.setdefault(
"model_max_length",
model_max_length,
)
kwargs.setdefault(
"clean_up_tokenization_spaces",
False,
)
super().__init__(**kwargs)
@property
def vocab_size(self):
return 256
def get_vocab(self):
vocab = dict(
self._token_to_id
)
vocab.update(
self.added_tokens_encoder
)
return vocab
def _tokenize(
self,
text,
**kwargs,
):
return [
self._id_to_token[b]
for b in text.encode("utf-8")
]
def _convert_token_to_id(
self,
token,
):
if token not in self._token_to_id:
raise ValueError(
f"Unknown byte token: {token}"
)
return self._token_to_id[token]
def _convert_id_to_token(
self,
index,
):
index = int(index)
if not 0 <= index < 256:
raise ValueError(
f"Byte id out of range: {index}"
)
return self._id_to_token[index]
def convert_tokens_to_string(
self,
tokens,
):
data = bytearray()
for token in tokens:
if token in self._token_to_id:
data.append(
self._token_to_id[token]
)
return bytes(data).decode(
"utf-8",
errors="replace",
)
def save_vocabulary(
self,
save_directory,
filename_prefix=None,
):
os.makedirs(
save_directory,
exist_ok=True,
)
filename = (
(
filename_prefix + "-"
)
if filename_prefix
else ""
) + "vocab.json"
path = os.path.join(
save_directory,
filename,
)
vocab = {
token: i
for i, token
in enumerate(self._id_to_token)
}
with open(
path,
"w",
encoding="utf-8",
) as f:
json.dump(
vocab,
f,
ensure_ascii=False,
indent=2,
)
return (path,)
|