File size: 19,517 Bytes
2216aae |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 |
# Generated content DO NOT EDIT
class Model:
"""
Base class for all models
The model represents the actual tokenization algorithm. This is the part that
will contain and manage the learned vocabulary.
This class cannot be constructed directly. Please use one of the concrete models.
"""
def __init__(self):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
def get_trainer(self):
"""
Get the associated :class:`~tokenizers.trainers.Trainer`
Retrieve the :class:`~tokenizers.trainers.Trainer` associated to this
:class:`~tokenizers.models.Model`.
Returns:
:class:`~tokenizers.trainers.Trainer`: The Trainer used to train this model
"""
pass
def id_to_token(self, id):
"""
Get the token associated to an ID
Args:
id (:obj:`int`):
An ID to convert to a token
Returns:
:obj:`str`: The token associated to the ID
"""
pass
def save(self, folder, prefix):
"""
Save the current model
Save the current model in the given folder, using the given prefix for the various
files that will get created.
Any file with the same name that already exists in this folder will be overwritten.
Args:
folder (:obj:`str`):
The path to the target folder in which to save the various files
prefix (:obj:`str`, `optional`):
An optional prefix, used to prefix each file name
Returns:
:obj:`List[str]`: The list of saved files
"""
pass
def token_to_id(self, tokens):
"""
Get the ID associated to a token
Args:
token (:obj:`str`):
A token to convert to an ID
Returns:
:obj:`int`: The ID associated to the token
"""
pass
def tokenize(self, sequence):
"""
Tokenize a sequence
Args:
sequence (:obj:`str`):
A sequence to tokenize
Returns:
A :obj:`List` of :class:`~tokenizers.Token`: The generated tokens
"""
pass
class BPE(Model):
"""
An implementation of the BPE (Byte-Pair Encoding) algorithm
Args:
vocab (:obj:`Dict[str, int]`, `optional`):
A dictionary of string keys and their ids :obj:`{"am": 0,...}`
merges (:obj:`List[Tuple[str, str]]`, `optional`):
A list of pairs of tokens (:obj:`Tuple[str, str]`) :obj:`[("a", "b"),...]`
cache_capacity (:obj:`int`, `optional`):
The number of words that the BPE cache can contain. The cache allows
to speed-up the process by keeping the result of the merge operations
for a number of words.
dropout (:obj:`float`, `optional`):
A float between 0 and 1 that represents the BPE dropout to use.
unk_token (:obj:`str`, `optional`):
The unknown token to be used by the model.
continuing_subword_prefix (:obj:`str`, `optional`):
The prefix to attach to subword units that don't represent a beginning of word.
end_of_word_suffix (:obj:`str`, `optional`):
The suffix to attach to subword units that represent an end of word.
fuse_unk (:obj:`bool`, `optional`):
Whether to fuse any subsequent unknown tokens into a single one
byte_fallback (:obj:`bool`, `optional`):
Whether to use spm byte-fallback trick (defaults to False)
ignore_merges (:obj:`bool`, `optional`):
Whether or not to match tokens with the vocab before using merges.
"""
def __init__(
self,
vocab=None,
merges=None,
cache_capacity=None,
dropout=None,
unk_token=None,
continuing_subword_prefix=None,
end_of_word_suffix=None,
fuse_unk=None,
byte_fallback=False,
ignore_merges=False,
):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
@property
def byte_fallback(self):
""" """
pass
@byte_fallback.setter
def byte_fallback(self, value):
""" """
pass
@property
def continuing_subword_prefix(self):
""" """
pass
@continuing_subword_prefix.setter
def continuing_subword_prefix(self, value):
""" """
pass
@property
def dropout(self):
""" """
pass
@dropout.setter
def dropout(self, value):
""" """
pass
@property
def end_of_word_suffix(self):
""" """
pass
@end_of_word_suffix.setter
def end_of_word_suffix(self, value):
""" """
pass
@staticmethod
def from_file(vocab, merges, **kwargs):
"""
Instantiate a BPE model from the given files.
This method is roughly equivalent to doing::
vocab, merges = BPE.read_file(vocab_filename, merges_filename)
bpe = BPE(vocab, merges)
If you don't need to keep the :obj:`vocab, merges` values lying around,
this method is more optimized than manually calling
:meth:`~tokenizers.models.BPE.read_file` to initialize a :class:`~tokenizers.models.BPE`
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.json` file
merges (:obj:`str`):
The path to a :obj:`merges.txt` file
Returns:
:class:`~tokenizers.models.BPE`: An instance of BPE loaded from these files
"""
pass
@property
def fuse_unk(self):
""" """
pass
@fuse_unk.setter
def fuse_unk(self, value):
""" """
pass
def get_trainer(self):
"""
Get the associated :class:`~tokenizers.trainers.Trainer`
Retrieve the :class:`~tokenizers.trainers.Trainer` associated to this
:class:`~tokenizers.models.Model`.
Returns:
:class:`~tokenizers.trainers.Trainer`: The Trainer used to train this model
"""
pass
def id_to_token(self, id):
"""
Get the token associated to an ID
Args:
id (:obj:`int`):
An ID to convert to a token
Returns:
:obj:`str`: The token associated to the ID
"""
pass
@property
def ignore_merges(self):
""" """
pass
@ignore_merges.setter
def ignore_merges(self, value):
""" """
pass
@staticmethod
def read_file(vocab, merges):
"""
Read a :obj:`vocab.json` and a :obj:`merges.txt` files
This method provides a way to read and parse the content of these files,
returning the relevant data structures. If you want to instantiate some BPE models
from memory, this method gives you the expected input from the standard files.
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.json` file
merges (:obj:`str`):
The path to a :obj:`merges.txt` file
Returns:
A :obj:`Tuple` with the vocab and the merges:
The vocabulary and merges loaded into memory
"""
pass
def save(self, folder, prefix):
"""
Save the current model
Save the current model in the given folder, using the given prefix for the various
files that will get created.
Any file with the same name that already exists in this folder will be overwritten.
Args:
folder (:obj:`str`):
The path to the target folder in which to save the various files
prefix (:obj:`str`, `optional`):
An optional prefix, used to prefix each file name
Returns:
:obj:`List[str]`: The list of saved files
"""
pass
def token_to_id(self, tokens):
"""
Get the ID associated to a token
Args:
token (:obj:`str`):
A token to convert to an ID
Returns:
:obj:`int`: The ID associated to the token
"""
pass
def tokenize(self, sequence):
"""
Tokenize a sequence
Args:
sequence (:obj:`str`):
A sequence to tokenize
Returns:
A :obj:`List` of :class:`~tokenizers.Token`: The generated tokens
"""
pass
@property
def unk_token(self):
""" """
pass
@unk_token.setter
def unk_token(self, value):
""" """
pass
class Unigram(Model):
"""
An implementation of the Unigram algorithm
Args:
vocab (:obj:`List[Tuple[str, float]]`, `optional`, `optional`):
A list of vocabulary items and their relative score [("am", -0.2442),...]
"""
def __init__(self, vocab=None, unk_id=None, byte_fallback=None):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
def get_trainer(self):
"""
Get the associated :class:`~tokenizers.trainers.Trainer`
Retrieve the :class:`~tokenizers.trainers.Trainer` associated to this
:class:`~tokenizers.models.Model`.
Returns:
:class:`~tokenizers.trainers.Trainer`: The Trainer used to train this model
"""
pass
def id_to_token(self, id):
"""
Get the token associated to an ID
Args:
id (:obj:`int`):
An ID to convert to a token
Returns:
:obj:`str`: The token associated to the ID
"""
pass
def save(self, folder, prefix):
"""
Save the current model
Save the current model in the given folder, using the given prefix for the various
files that will get created.
Any file with the same name that already exists in this folder will be overwritten.
Args:
folder (:obj:`str`):
The path to the target folder in which to save the various files
prefix (:obj:`str`, `optional`):
An optional prefix, used to prefix each file name
Returns:
:obj:`List[str]`: The list of saved files
"""
pass
def token_to_id(self, tokens):
"""
Get the ID associated to a token
Args:
token (:obj:`str`):
A token to convert to an ID
Returns:
:obj:`int`: The ID associated to the token
"""
pass
def tokenize(self, sequence):
"""
Tokenize a sequence
Args:
sequence (:obj:`str`):
A sequence to tokenize
Returns:
A :obj:`List` of :class:`~tokenizers.Token`: The generated tokens
"""
pass
class WordLevel(Model):
"""
An implementation of the WordLevel algorithm
Most simple tokenizer model based on mapping tokens to their corresponding id.
Args:
vocab (:obj:`str`, `optional`):
A dictionary of string keys and their ids :obj:`{"am": 0,...}`
unk_token (:obj:`str`, `optional`):
The unknown token to be used by the model.
"""
def __init__(self, vocab=None, unk_token=None):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
@staticmethod
def from_file(vocab, unk_token=None):
"""
Instantiate a WordLevel model from the given file
This method is roughly equivalent to doing::
vocab = WordLevel.read_file(vocab_filename)
wordlevel = WordLevel(vocab)
If you don't need to keep the :obj:`vocab` values lying around, this method is
more optimized than manually calling :meth:`~tokenizers.models.WordLevel.read_file` to
initialize a :class:`~tokenizers.models.WordLevel`
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.json` file
Returns:
:class:`~tokenizers.models.WordLevel`: An instance of WordLevel loaded from file
"""
pass
def get_trainer(self):
"""
Get the associated :class:`~tokenizers.trainers.Trainer`
Retrieve the :class:`~tokenizers.trainers.Trainer` associated to this
:class:`~tokenizers.models.Model`.
Returns:
:class:`~tokenizers.trainers.Trainer`: The Trainer used to train this model
"""
pass
def id_to_token(self, id):
"""
Get the token associated to an ID
Args:
id (:obj:`int`):
An ID to convert to a token
Returns:
:obj:`str`: The token associated to the ID
"""
pass
@staticmethod
def read_file(vocab):
"""
Read a :obj:`vocab.json`
This method provides a way to read and parse the content of a vocabulary file,
returning the relevant data structures. If you want to instantiate some WordLevel models
from memory, this method gives you the expected input from the standard files.
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.json` file
Returns:
:obj:`Dict[str, int]`: The vocabulary as a :obj:`dict`
"""
pass
def save(self, folder, prefix):
"""
Save the current model
Save the current model in the given folder, using the given prefix for the various
files that will get created.
Any file with the same name that already exists in this folder will be overwritten.
Args:
folder (:obj:`str`):
The path to the target folder in which to save the various files
prefix (:obj:`str`, `optional`):
An optional prefix, used to prefix each file name
Returns:
:obj:`List[str]`: The list of saved files
"""
pass
def token_to_id(self, tokens):
"""
Get the ID associated to a token
Args:
token (:obj:`str`):
A token to convert to an ID
Returns:
:obj:`int`: The ID associated to the token
"""
pass
def tokenize(self, sequence):
"""
Tokenize a sequence
Args:
sequence (:obj:`str`):
A sequence to tokenize
Returns:
A :obj:`List` of :class:`~tokenizers.Token`: The generated tokens
"""
pass
@property
def unk_token(self):
""" """
pass
@unk_token.setter
def unk_token(self, value):
""" """
pass
class WordPiece(Model):
"""
An implementation of the WordPiece algorithm
Args:
vocab (:obj:`Dict[str, int]`, `optional`):
A dictionary of string keys and their ids :obj:`{"am": 0,...}`
unk_token (:obj:`str`, `optional`):
The unknown token to be used by the model.
max_input_chars_per_word (:obj:`int`, `optional`):
The maximum number of characters to authorize in a single word.
"""
def __init__(self, vocab=None, unk_token="[UNK]", max_input_chars_per_word=100, continuing_subword_prefix="##"):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
@property
def continuing_subword_prefix(self):
""" """
pass
@continuing_subword_prefix.setter
def continuing_subword_prefix(self, value):
""" """
pass
@staticmethod
def from_file(vocab, **kwargs):
"""
Instantiate a WordPiece model from the given file
This method is roughly equivalent to doing::
vocab = WordPiece.read_file(vocab_filename)
wordpiece = WordPiece(vocab)
If you don't need to keep the :obj:`vocab` values lying around, this method is
more optimized than manually calling :meth:`~tokenizers.models.WordPiece.read_file` to
initialize a :class:`~tokenizers.models.WordPiece`
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.txt` file
Returns:
:class:`~tokenizers.models.WordPiece`: An instance of WordPiece loaded from file
"""
pass
def get_trainer(self):
"""
Get the associated :class:`~tokenizers.trainers.Trainer`
Retrieve the :class:`~tokenizers.trainers.Trainer` associated to this
:class:`~tokenizers.models.Model`.
Returns:
:class:`~tokenizers.trainers.Trainer`: The Trainer used to train this model
"""
pass
def id_to_token(self, id):
"""
Get the token associated to an ID
Args:
id (:obj:`int`):
An ID to convert to a token
Returns:
:obj:`str`: The token associated to the ID
"""
pass
@property
def max_input_chars_per_word(self):
""" """
pass
@max_input_chars_per_word.setter
def max_input_chars_per_word(self, value):
""" """
pass
@staticmethod
def read_file(vocab):
"""
Read a :obj:`vocab.txt` file
This method provides a way to read and parse the content of a standard `vocab.txt`
file as used by the WordPiece Model, returning the relevant data structures. If you
want to instantiate some WordPiece models from memory, this method gives you the
expected input from the standard files.
Args:
vocab (:obj:`str`):
The path to a :obj:`vocab.txt` file
Returns:
:obj:`Dict[str, int]`: The vocabulary as a :obj:`dict`
"""
pass
def save(self, folder, prefix):
"""
Save the current model
Save the current model in the given folder, using the given prefix for the various
files that will get created.
Any file with the same name that already exists in this folder will be overwritten.
Args:
folder (:obj:`str`):
The path to the target folder in which to save the various files
prefix (:obj:`str`, `optional`):
An optional prefix, used to prefix each file name
Returns:
:obj:`List[str]`: The list of saved files
"""
pass
def token_to_id(self, tokens):
"""
Get the ID associated to a token
Args:
token (:obj:`str`):
A token to convert to an ID
Returns:
:obj:`int`: The ID associated to the token
"""
pass
def tokenize(self, sequence):
"""
Tokenize a sequence
Args:
sequence (:obj:`str`):
A sequence to tokenize
Returns:
A :obj:`List` of :class:`~tokenizers.Token`: The generated tokens
"""
pass
@property
def unk_token(self):
""" """
pass
@unk_token.setter
def unk_token(self, value):
""" """
pass
|