File size: 55,891 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 |
# Generated content DO NOT EDIT
class AddedToken:
"""
Represents a token that can be be added to a :class:`~tokenizers.Tokenizer`.
It can have special options that defines the way it should behave.
Args:
content (:obj:`str`): The content of the token
single_word (:obj:`bool`, defaults to :obj:`False`):
Defines whether this token should only match single words. If :obj:`True`, this
token will never match inside of a word. For example the token ``ing`` would match
on ``tokenizing`` if this option is :obj:`False`, but not if it is :obj:`True`.
The notion of "`inside of a word`" is defined by the word boundaries pattern in
regular expressions (ie. the token should start and end with word boundaries).
lstrip (:obj:`bool`, defaults to :obj:`False`):
Defines whether this token should strip all potential whitespaces on its left side.
If :obj:`True`, this token will greedily match any whitespace on its left. For
example if we try to match the token ``[MASK]`` with ``lstrip=True``, in the text
``"I saw a [MASK]"``, we would match on ``" [MASK]"``. (Note the space on the left).
rstrip (:obj:`bool`, defaults to :obj:`False`):
Defines whether this token should strip all potential whitespaces on its right
side. If :obj:`True`, this token will greedily match any whitespace on its right.
It works just like :obj:`lstrip` but on the right.
normalized (:obj:`bool`, defaults to :obj:`True` with :meth:`~tokenizers.Tokenizer.add_tokens` and :obj:`False` with :meth:`~tokenizers.Tokenizer.add_special_tokens`):
Defines whether this token should match against the normalized version of the input
text. For example, with the added token ``"yesterday"``, and a normalizer in charge of
lowercasing the text, the token could be extract from the input ``"I saw a lion
Yesterday"``.
special (:obj:`bool`, defaults to :obj:`False` with :meth:`~tokenizers.Tokenizer.add_tokens` and :obj:`False` with :meth:`~tokenizers.Tokenizer.add_special_tokens`):
Defines whether this token should be skipped when decoding.
"""
def __init__(self, content=None, single_word=False, lstrip=False, rstrip=False, normalized=True, special=False):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
@property
def content(self):
"""
Get the content of this :obj:`AddedToken`
"""
pass
@content.setter
def content(self, value):
"""
Get the content of this :obj:`AddedToken`
"""
pass
@property
def lstrip(self):
"""
Get the value of the :obj:`lstrip` option
"""
pass
@lstrip.setter
def lstrip(self, value):
"""
Get the value of the :obj:`lstrip` option
"""
pass
@property
def normalized(self):
"""
Get the value of the :obj:`normalized` option
"""
pass
@normalized.setter
def normalized(self, value):
"""
Get the value of the :obj:`normalized` option
"""
pass
@property
def rstrip(self):
"""
Get the value of the :obj:`rstrip` option
"""
pass
@rstrip.setter
def rstrip(self, value):
"""
Get the value of the :obj:`rstrip` option
"""
pass
@property
def single_word(self):
"""
Get the value of the :obj:`single_word` option
"""
pass
@single_word.setter
def single_word(self, value):
"""
Get the value of the :obj:`single_word` option
"""
pass
@property
def special(self):
"""
Get the value of the :obj:`special` option
"""
pass
@special.setter
def special(self, value):
"""
Get the value of the :obj:`special` option
"""
pass
class Encoding:
"""
The :class:`~tokenizers.Encoding` represents the output of a :class:`~tokenizers.Tokenizer`.
"""
def __init__(self):
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
@property
def attention_mask(self):
"""
The attention mask
This indicates to the LM which tokens should be attended to, and which should not.
This is especially important when batching sequences, where we need to applying
padding.
Returns:
:obj:`List[int]`: The attention mask
"""
pass
@attention_mask.setter
def attention_mask(self, value):
"""
The attention mask
This indicates to the LM which tokens should be attended to, and which should not.
This is especially important when batching sequences, where we need to applying
padding.
Returns:
:obj:`List[int]`: The attention mask
"""
pass
def char_to_token(self, char_pos, sequence_index=0):
"""
Get the token that contains the char at the given position in the input sequence.
Args:
char_pos (:obj:`int`):
The position of a char in the input string
sequence_index (:obj:`int`, defaults to :obj:`0`):
The index of the sequence that contains the target char
Returns:
:obj:`int`: The index of the token that contains this char in the encoded sequence
"""
pass
def char_to_word(self, char_pos, sequence_index=0):
"""
Get the word that contains the char at the given position in the input sequence.
Args:
char_pos (:obj:`int`):
The position of a char in the input string
sequence_index (:obj:`int`, defaults to :obj:`0`):
The index of the sequence that contains the target char
Returns:
:obj:`int`: The index of the word that contains this char in the input sequence
"""
pass
@property
def ids(self):
"""
The generated IDs
The IDs are the main input to a Language Model. They are the token indices,
the numerical representations that a LM understands.
Returns:
:obj:`List[int]`: The list of IDs
"""
pass
@ids.setter
def ids(self, value):
"""
The generated IDs
The IDs are the main input to a Language Model. They are the token indices,
the numerical representations that a LM understands.
Returns:
:obj:`List[int]`: The list of IDs
"""
pass
@staticmethod
def merge(encodings, growing_offsets=True):
"""
Merge the list of encodings into one final :class:`~tokenizers.Encoding`
Args:
encodings (A :obj:`List` of :class:`~tokenizers.Encoding`):
The list of encodings that should be merged in one
growing_offsets (:obj:`bool`, defaults to :obj:`True`):
Whether the offsets should accumulate while merging
Returns:
:class:`~tokenizers.Encoding`: The resulting Encoding
"""
pass
@property
def n_sequences(self):
"""
The number of sequences represented
Returns:
:obj:`int`: The number of sequences in this :class:`~tokenizers.Encoding`
"""
pass
@n_sequences.setter
def n_sequences(self, value):
"""
The number of sequences represented
Returns:
:obj:`int`: The number of sequences in this :class:`~tokenizers.Encoding`
"""
pass
@property
def offsets(self):
"""
The offsets associated to each token
These offsets let's you slice the input string, and thus retrieve the original
part that led to producing the corresponding token.
Returns:
A :obj:`List` of :obj:`Tuple[int, int]`: The list of offsets
"""
pass
@offsets.setter
def offsets(self, value):
"""
The offsets associated to each token
These offsets let's you slice the input string, and thus retrieve the original
part that led to producing the corresponding token.
Returns:
A :obj:`List` of :obj:`Tuple[int, int]`: The list of offsets
"""
pass
@property
def overflowing(self):
"""
A :obj:`List` of overflowing :class:`~tokenizers.Encoding`
When using truncation, the :class:`~tokenizers.Tokenizer` takes care of splitting
the output into as many pieces as required to match the specified maximum length.
This field lets you retrieve all the subsequent pieces.
When you use pairs of sequences, the overflowing pieces will contain enough
variations to cover all the possible combinations, while respecting the provided
maximum length.
"""
pass
@overflowing.setter
def overflowing(self, value):
"""
A :obj:`List` of overflowing :class:`~tokenizers.Encoding`
When using truncation, the :class:`~tokenizers.Tokenizer` takes care of splitting
the output into as many pieces as required to match the specified maximum length.
This field lets you retrieve all the subsequent pieces.
When you use pairs of sequences, the overflowing pieces will contain enough
variations to cover all the possible combinations, while respecting the provided
maximum length.
"""
pass
def pad(self, length, direction="right", pad_id=0, pad_type_id=0, pad_token="[PAD]"):
"""
Pad the :class:`~tokenizers.Encoding` at the given length
Args:
length (:obj:`int`):
The desired length
direction: (:obj:`str`, defaults to :obj:`right`):
The expected padding direction. Can be either :obj:`right` or :obj:`left`
pad_id (:obj:`int`, defaults to :obj:`0`):
The ID corresponding to the padding token
pad_type_id (:obj:`int`, defaults to :obj:`0`):
The type ID corresponding to the padding token
pad_token (:obj:`str`, defaults to `[PAD]`):
The pad token to use
"""
pass
@property
def sequence_ids(self):
"""
The generated sequence indices.
They represent the index of the input sequence associated to each token.
The sequence id can be None if the token is not related to any input sequence,
like for example with special tokens.
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional sequence index.
"""
pass
@sequence_ids.setter
def sequence_ids(self, value):
"""
The generated sequence indices.
They represent the index of the input sequence associated to each token.
The sequence id can be None if the token is not related to any input sequence,
like for example with special tokens.
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional sequence index.
"""
pass
def set_sequence_id(self, sequence_id):
"""
Set the given sequence index
Set the given sequence index for the whole range of tokens contained in this
:class:`~tokenizers.Encoding`.
"""
pass
@property
def special_tokens_mask(self):
"""
The special token mask
This indicates which tokens are special tokens, and which are not.
Returns:
:obj:`List[int]`: The special tokens mask
"""
pass
@special_tokens_mask.setter
def special_tokens_mask(self, value):
"""
The special token mask
This indicates which tokens are special tokens, and which are not.
Returns:
:obj:`List[int]`: The special tokens mask
"""
pass
def token_to_chars(self, token_index):
"""
Get the offsets of the token at the given index.
The returned offsets are related to the input sequence that contains the
token. In order to determine in which input sequence it belongs, you
must call :meth:`~tokenizers.Encoding.token_to_sequence()`.
Args:
token_index (:obj:`int`):
The index of a token in the encoded sequence.
Returns:
:obj:`Tuple[int, int]`: The token offsets :obj:`(first, last + 1)`
"""
pass
def token_to_sequence(self, token_index):
"""
Get the index of the sequence represented by the given token.
In the general use case, this method returns :obj:`0` for a single sequence or
the first sequence of a pair, and :obj:`1` for the second sequence of a pair
Args:
token_index (:obj:`int`):
The index of a token in the encoded sequence.
Returns:
:obj:`int`: The sequence id of the given token
"""
pass
def token_to_word(self, token_index):
"""
Get the index of the word that contains the token in one of the input sequences.
The returned word index is related to the input sequence that contains
the token. In order to determine in which input sequence it belongs, you
must call :meth:`~tokenizers.Encoding.token_to_sequence()`.
Args:
token_index (:obj:`int`):
The index of a token in the encoded sequence.
Returns:
:obj:`int`: The index of the word in the relevant input sequence.
"""
pass
@property
def tokens(self):
"""
The generated tokens
They are the string representation of the IDs.
Returns:
:obj:`List[str]`: The list of tokens
"""
pass
@tokens.setter
def tokens(self, value):
"""
The generated tokens
They are the string representation of the IDs.
Returns:
:obj:`List[str]`: The list of tokens
"""
pass
def truncate(self, max_length, stride=0, direction="right"):
"""
Truncate the :class:`~tokenizers.Encoding` at the given length
If this :class:`~tokenizers.Encoding` represents multiple sequences, when truncating
this information is lost. It will be considered as representing a single sequence.
Args:
max_length (:obj:`int`):
The desired length
stride (:obj:`int`, defaults to :obj:`0`):
The length of previous content to be included in each overflowing piece
direction (:obj:`str`, defaults to :obj:`right`):
Truncate direction
"""
pass
@property
def type_ids(self):
"""
The generated type IDs
Generally used for tasks like sequence classification or question answering,
these tokens let the LM know which input sequence corresponds to each tokens.
Returns:
:obj:`List[int]`: The list of type ids
"""
pass
@type_ids.setter
def type_ids(self, value):
"""
The generated type IDs
Generally used for tasks like sequence classification or question answering,
these tokens let the LM know which input sequence corresponds to each tokens.
Returns:
:obj:`List[int]`: The list of type ids
"""
pass
@property
def word_ids(self):
"""
The generated word indices.
They represent the index of the word associated to each token.
When the input is pre-tokenized, they correspond to the ID of the given input label,
otherwise they correspond to the words indices as defined by the
:class:`~tokenizers.pre_tokenizers.PreTokenizer` that was used.
For special tokens and such (any token that was generated from something that was
not part of the input), the output is :obj:`None`
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional word index.
"""
pass
@word_ids.setter
def word_ids(self, value):
"""
The generated word indices.
They represent the index of the word associated to each token.
When the input is pre-tokenized, they correspond to the ID of the given input label,
otherwise they correspond to the words indices as defined by the
:class:`~tokenizers.pre_tokenizers.PreTokenizer` that was used.
For special tokens and such (any token that was generated from something that was
not part of the input), the output is :obj:`None`
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional word index.
"""
pass
def word_to_chars(self, word_index, sequence_index=0):
"""
Get the offsets of the word at the given index in one of the input sequences.
Args:
word_index (:obj:`int`):
The index of a word in one of the input sequences.
sequence_index (:obj:`int`, defaults to :obj:`0`):
The index of the sequence that contains the target word
Returns:
:obj:`Tuple[int, int]`: The range of characters (span) :obj:`(first, last + 1)`
"""
pass
def word_to_tokens(self, word_index, sequence_index=0):
"""
Get the encoded tokens corresponding to the word at the given index
in one of the input sequences.
Args:
word_index (:obj:`int`):
The index of a word in one of the input sequences.
sequence_index (:obj:`int`, defaults to :obj:`0`):
The index of the sequence that contains the target word
Returns:
:obj:`Tuple[int, int]`: The range of tokens: :obj:`(first, last + 1)`
"""
pass
@property
def words(self):
"""
The generated word indices.
.. warning::
This is deprecated and will be removed in a future version.
Please use :obj:`~tokenizers.Encoding.word_ids` instead.
They represent the index of the word associated to each token.
When the input is pre-tokenized, they correspond to the ID of the given input label,
otherwise they correspond to the words indices as defined by the
:class:`~tokenizers.pre_tokenizers.PreTokenizer` that was used.
For special tokens and such (any token that was generated from something that was
not part of the input), the output is :obj:`None`
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional word index.
"""
pass
@words.setter
def words(self, value):
"""
The generated word indices.
.. warning::
This is deprecated and will be removed in a future version.
Please use :obj:`~tokenizers.Encoding.word_ids` instead.
They represent the index of the word associated to each token.
When the input is pre-tokenized, they correspond to the ID of the given input label,
otherwise they correspond to the words indices as defined by the
:class:`~tokenizers.pre_tokenizers.PreTokenizer` that was used.
For special tokens and such (any token that was generated from something that was
not part of the input), the output is :obj:`None`
Returns:
A :obj:`List` of :obj:`Optional[int]`: A list of optional word index.
"""
pass
class NormalizedString:
"""
NormalizedString
A NormalizedString takes care of modifying an "original" string, to obtain a "normalized" one.
While making all the requested modifications, it keeps track of the alignment information
between the two versions of the string.
Args:
sequence: str:
The string sequence used to initialize this NormalizedString
"""
def __init__(self, sequence):
pass
def __getitem__(self, key):
"""
Return self[key].
"""
pass
def __getstate__(self, /):
"""
Helper for pickle.
"""
pass
def append(self, s):
"""
Append the given sequence to the string
"""
pass
def clear(self):
"""
Clears the string
"""
pass
def filter(self, func):
"""
Filter each character of the string using the given func
"""
pass
def for_each(self, func):
"""
Calls the given function for each character of the string
"""
pass
def lowercase(self):
"""
Lowercase the string
"""
pass
def lstrip(self):
"""
Strip the left of the string
"""
pass
def map(self, func):
"""
Calls the given function for each character of the string
Replaces each character of the string using the returned value. Each
returned value **must** be a str of length 1 (ie a character).
"""
pass
def nfc(self):
"""
Runs the NFC normalization
"""
pass
def nfd(self):
"""
Runs the NFD normalization
"""
pass
def nfkc(self):
"""
Runs the NFKC normalization
"""
pass
def nfkd(self):
"""
Runs the NFKD normalization
"""
pass
@property
def normalized(self):
"""
The normalized part of the string
"""
pass
@normalized.setter
def normalized(self, value):
"""
The normalized part of the string
"""
pass
@property
def original(self):
""" """
pass
@original.setter
def original(self, value):
""" """
pass
def prepend(self, s):
"""
Prepend the given sequence to the string
"""
pass
def replace(self, pattern, content):
"""
Replace the content of the given pattern with the provided content
Args:
pattern: Pattern:
A pattern used to match the string. Usually a string or a Regex
content: str:
The content to be used as replacement
"""
pass
def rstrip(self):
"""
Strip the right of the string
"""
pass
def slice(self, range):
"""
Slice the string using the given range
"""
pass
def split(self, pattern, behavior):
"""
Split the NormalizedString using the given pattern and the specified behavior
Args:
pattern: Pattern:
A pattern used to split the string. Usually a string or a regex built with `tokenizers.Regex`
behavior: SplitDelimiterBehavior:
The behavior to use when splitting.
Choices: "removed", "isolated", "merged_with_previous", "merged_with_next",
"contiguous"
Returns:
A list of NormalizedString, representing each split
"""
pass
def strip(self):
"""
Strip both ends of the string
"""
pass
def uppercase(self):
"""
Uppercase the string
"""
pass
class PreTokenizedString:
"""
PreTokenizedString
Wrapper over a string, that provides a way to normalize, pre-tokenize, tokenize the
underlying string, while keeping track of the alignment information (offsets).
The PreTokenizedString manages what we call `splits`. Each split represents a substring
which is a subpart of the original string, with the relevant offsets and tokens.
When calling one of the methods used to modify the PreTokenizedString (namely one of
`split`, `normalize` or `tokenize), only the `splits` that don't have any associated
tokens will get modified.
Args:
sequence: str:
The string sequence used to initialize this PreTokenizedString
"""
def __init__(self, sequence):
pass
def __getstate__(self, /):
"""
Helper for pickle.
"""
pass
def get_splits(self, offset_referential="original", offset_type="char"):
"""
Get the splits currently managed by the PreTokenizedString
Args:
offset_referential: :obj:`str`
Whether the returned splits should have offsets expressed relative
to the original string, or the normalized one. choices: "original", "normalized".
offset_type: :obj:`str`
Whether the returned splits should have offsets expressed in bytes or chars.
When slicing an str, we usually want to use chars, which is the default value.
Now in some cases it might be interesting to get these offsets expressed in bytes,
so it is possible to change this here.
choices: "char", "bytes"
Returns
A list of splits
"""
pass
def normalize(self, func):
"""
Normalize each split of the `PreTokenizedString` using the given `func`
Args:
func: Callable[[NormalizedString], None]:
The function used to normalize each underlying split. This function
does not need to return anything, just calling the methods on the provided
NormalizedString allow its modification.
"""
pass
def split(self, func):
"""
Split the PreTokenizedString using the given `func`
Args:
func: Callable[[index, NormalizedString], List[NormalizedString]]:
The function used to split each underlying split.
It is expected to return a list of `NormalizedString`, that represent the new
splits. If the given `NormalizedString` does not need any splitting, we can
just return it directly.
In order for the offsets to be tracked accurately, any returned `NormalizedString`
should come from calling either `.split` or `.slice` on the received one.
"""
pass
def to_encoding(self, type_id=0, word_idx=None):
"""
Return an Encoding generated from this PreTokenizedString
Args:
type_id: int = 0:
The type_id to be used on the generated Encoding.
word_idx: Optional[int] = None:
An optional word index to be used for each token of this Encoding. If provided,
all the word indices in the generated Encoding will use this value, instead
of the one automatically tracked during pre-tokenization.
Returns:
An Encoding
"""
pass
def tokenize(self, func):
"""
Tokenize each split of the `PreTokenizedString` using the given `func`
Args:
func: Callable[[str], List[Token]]:
The function used to tokenize each underlying split. This function must return
a list of Token generated from the input str.
"""
pass
class Regex:
"""
Instantiate a new Regex with the given pattern
"""
def __init__(self, pattern):
pass
def __getstate__(self, /):
"""
Helper for pickle.
"""
pass
class Token:
def __init__(self, id, value, offsets):
pass
def __getstate__(self, /):
"""
Helper for pickle.
"""
pass
def as_tuple(self):
""" """
pass
@property
def id(self):
""" """
pass
@id.setter
def id(self, value):
""" """
pass
@property
def offsets(self):
""" """
pass
@offsets.setter
def offsets(self, value):
""" """
pass
@property
def value(self):
""" """
pass
@value.setter
def value(self, value):
""" """
pass
class Tokenizer:
"""
A :obj:`Tokenizer` works as a pipeline. It processes some raw text as input
and outputs an :class:`~tokenizers.Encoding`.
Args:
model (:class:`~tokenizers.models.Model`):
The core algorithm that this :obj:`Tokenizer` should be using.
"""
def __init__(self, model):
pass
def __getnewargs__(self):
""" """
pass
def __getstate__(self):
""" """
pass
def __setstate__(self, state):
""" """
pass
def add_special_tokens(self, tokens):
"""
Add the given special tokens to the Tokenizer.
If these tokens are already part of the vocabulary, it just let the Tokenizer know about
them. If they don't exist, the Tokenizer creates them, giving them a new id.
These special tokens will never be processed by the model (ie won't be split into
multiple tokens), and they can be removed from the output when decoding.
Args:
tokens (A :obj:`List` of :class:`~tokenizers.AddedToken` or :obj:`str`):
The list of special tokens we want to add to the vocabulary. Each token can either
be a string or an instance of :class:`~tokenizers.AddedToken` for more
customization.
Returns:
:obj:`int`: The number of tokens that were created in the vocabulary
"""
pass
def add_tokens(self, tokens):
"""
Add the given tokens to the vocabulary
The given tokens are added only if they don't already exist in the vocabulary.
Each token then gets a new attributed id.
Args:
tokens (A :obj:`List` of :class:`~tokenizers.AddedToken` or :obj:`str`):
The list of tokens we want to add to the vocabulary. Each token can be either a
string or an instance of :class:`~tokenizers.AddedToken` for more customization.
Returns:
:obj:`int`: The number of tokens that were created in the vocabulary
"""
pass
def async_decode_batch(self, sequences, skip_special_tokens=True):
"""
Decode a batch of ids back to their corresponding string
Args:
sequences (:obj:`List` of :obj:`List[int]`):
The batch of sequences we want to decode
skip_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether the special tokens should be removed from the decoded strings
Returns:
:obj:`List[str]`: A list of decoded strings
"""
pass
def async_encode(self, sequence, pair=None, is_pretokenized=False, add_special_tokens=True):
"""
Asynchronously encode the given input with character offsets.
This is an async version of encode that can be awaited in async Python code.
Example:
Here are some examples of the inputs that are accepted::
await async_encode("A single sequence")
Args:
sequence (:obj:`~tokenizers.InputSequence`):
The main input sequence we want to encode. This sequence can be either raw
text or pre-tokenized, according to the ``is_pretokenized`` argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextInputSequence`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedInputSequence`
pair (:obj:`~tokenizers.InputSequence`, `optional`):
An optional input sequence. The expected format is the same that for ``sequence``.
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
:class:`~tokenizers.Encoding`: The encoded result
"""
pass
def async_encode_batch(self, input, is_pretokenized=False, add_special_tokens=True):
"""
Asynchronously encode the given batch of inputs with character offsets.
This is an async version of encode_batch that can be awaited in async Python code.
Example:
Here are some examples of the inputs that are accepted::
await async_encode_batch([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])
Args:
input (A :obj:`List`/:obj:`Tuple` of :obj:`~tokenizers.EncodeInput`):
A list of single sequences or pair sequences to encode. Each sequence
can be either raw text or pre-tokenized, according to the ``is_pretokenized``
argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextEncodeInput`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedEncodeInput`
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
A :obj:`List` of :class:`~tokenizers.Encoding`: The encoded batch
"""
pass
def async_encode_batch_fast(self, input, is_pretokenized=False, add_special_tokens=True):
"""
Asynchronously encode the given batch of inputs without tracking character offsets.
This is an async version of encode_batch_fast that can be awaited in async Python code.
Example:
Here are some examples of the inputs that are accepted::
await async_encode_batch_fast([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])
Args:
input (A :obj:`List`/:obj:`Tuple` of :obj:`~tokenizers.EncodeInput`):
A list of single sequences or pair sequences to encode. Each sequence
can be either raw text or pre-tokenized, according to the ``is_pretokenized``
argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextEncodeInput`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedEncodeInput`
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
A :obj:`List` of :class:`~tokenizers.Encoding`: The encoded batch
"""
pass
def decode(self, ids, skip_special_tokens=True):
"""
Decode the given list of ids back to a string
This is used to decode anything coming back from a Language Model
Args:
ids (A :obj:`List/Tuple` of :obj:`int`):
The list of ids that we want to decode
skip_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether the special tokens should be removed from the decoded string
Returns:
:obj:`str`: The decoded string
"""
pass
def decode_batch(self, sequences, skip_special_tokens=True):
"""
Decode a batch of ids back to their corresponding string
Args:
sequences (:obj:`List` of :obj:`List[int]`):
The batch of sequences we want to decode
skip_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether the special tokens should be removed from the decoded strings
Returns:
:obj:`List[str]`: A list of decoded strings
"""
pass
@property
def decoder(self):
"""
The `optional` :class:`~tokenizers.decoders.Decoder` in use by the Tokenizer
"""
pass
@decoder.setter
def decoder(self, value):
"""
The `optional` :class:`~tokenizers.decoders.Decoder` in use by the Tokenizer
"""
pass
def enable_padding(
self, direction="right", pad_id=0, pad_type_id=0, pad_token="[PAD]", length=None, pad_to_multiple_of=None
):
"""
Enable the padding
Args:
direction (:obj:`str`, `optional`, defaults to :obj:`right`):
The direction in which to pad. Can be either ``right`` or ``left``
pad_to_multiple_of (:obj:`int`, `optional`):
If specified, the padding length should always snap to the next multiple of the
given value. For example if we were going to pad witha length of 250 but
``pad_to_multiple_of=8`` then we will pad to 256.
pad_id (:obj:`int`, defaults to 0):
The id to be used when padding
pad_type_id (:obj:`int`, defaults to 0):
The type id to be used when padding
pad_token (:obj:`str`, defaults to :obj:`[PAD]`):
The pad token to be used when padding
length (:obj:`int`, `optional`):
If specified, the length at which to pad. If not specified we pad using the size of
the longest sequence in a batch.
"""
pass
def enable_truncation(self, max_length, stride=0, strategy="longest_first", direction="right"):
"""
Enable truncation
Args:
max_length (:obj:`int`):
The max length at which to truncate
stride (:obj:`int`, `optional`):
The length of the previous first sequence to be included in the overflowing
sequence
strategy (:obj:`str`, `optional`, defaults to :obj:`longest_first`):
The strategy used to truncation. Can be one of ``longest_first``, ``only_first`` or
``only_second``.
direction (:obj:`str`, defaults to :obj:`right`):
Truncate direction
"""
pass
def encode(self, sequence, pair=None, is_pretokenized=False, add_special_tokens=True):
"""
Encode the given sequence and pair. This method can process raw text sequences
as well as already pre-tokenized sequences.
Example:
Here are some examples of the inputs that are accepted::
encode("A single sequence")`
encode("A sequence", "And its pair")`
encode([ "A", "pre", "tokenized", "sequence" ], is_pretokenized=True)`
encode(
[ "A", "pre", "tokenized", "sequence" ], [ "And", "its", "pair" ],
is_pretokenized=True
)
Args:
sequence (:obj:`~tokenizers.InputSequence`):
The main input sequence we want to encode. This sequence can be either raw
text or pre-tokenized, according to the ``is_pretokenized`` argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextInputSequence`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedInputSequence`
pair (:obj:`~tokenizers.InputSequence`, `optional`):
An optional input sequence. The expected format is the same that for ``sequence``.
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
:class:`~tokenizers.Encoding`: The encoded result
"""
pass
def encode_batch(self, input, is_pretokenized=False, add_special_tokens=True):
"""
Encode the given batch of inputs. This method accept both raw text sequences
as well as already pre-tokenized sequences. The reason we use `PySequence` is
because it allows type checking with zero-cost (according to PyO3) as we don't
have to convert to check.
Example:
Here are some examples of the inputs that are accepted::
encode_batch([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])
Args:
input (A :obj:`List`/:obj:`Tuple` of :obj:`~tokenizers.EncodeInput`):
A list of single sequences or pair sequences to encode. Each sequence
can be either raw text or pre-tokenized, according to the ``is_pretokenized``
argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextEncodeInput`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedEncodeInput`
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
A :obj:`List` of :class:`~tokenizers.Encoding`: The encoded batch
"""
pass
def encode_batch_fast(self, input, is_pretokenized=False, add_special_tokens=True):
"""
Encode the given batch of inputs. This method is faster than `encode_batch`
because it doesn't keep track of offsets, they will be all zeros.
Example:
Here are some examples of the inputs that are accepted::
encode_batch_fast([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])
Args:
input (A :obj:`List`/:obj:`Tuple` of :obj:`~tokenizers.EncodeInput`):
A list of single sequences or pair sequences to encode. Each sequence
can be either raw text or pre-tokenized, according to the ``is_pretokenized``
argument:
- If ``is_pretokenized=False``: :class:`~tokenizers.TextEncodeInput`
- If ``is_pretokenized=True``: :class:`~tokenizers.PreTokenizedEncodeInput`
is_pretokenized (:obj:`bool`, defaults to :obj:`False`):
Whether the input is already pre-tokenized
add_special_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to add the special tokens
Returns:
A :obj:`List` of :class:`~tokenizers.Encoding`: The encoded batch
"""
pass
@property
def encode_special_tokens(self):
"""
Modifies the tokenizer in order to use or not the special tokens
during encoding.
Args:
value (:obj:`bool`):
Whether to use the special tokens or not
"""
pass
@encode_special_tokens.setter
def encode_special_tokens(self, value):
"""
Modifies the tokenizer in order to use or not the special tokens
during encoding.
Args:
value (:obj:`bool`):
Whether to use the special tokens or not
"""
pass
@staticmethod
def from_buffer(buffer):
"""
Instantiate a new :class:`~tokenizers.Tokenizer` from the given buffer.
Args:
buffer (:obj:`bytes`):
A buffer containing a previously serialized :class:`~tokenizers.Tokenizer`
Returns:
:class:`~tokenizers.Tokenizer`: The new tokenizer
"""
pass
@staticmethod
def from_file(path):
"""
Instantiate a new :class:`~tokenizers.Tokenizer` from the file at the given path.
Args:
path (:obj:`str`):
A path to a local JSON file representing a previously serialized
:class:`~tokenizers.Tokenizer`
Returns:
:class:`~tokenizers.Tokenizer`: The new tokenizer
"""
pass
@staticmethod
def from_pretrained(identifier, revision="main", token=None):
"""
Instantiate a new :class:`~tokenizers.Tokenizer` from an existing file on the
Hugging Face Hub.
Args:
identifier (:obj:`str`):
The identifier of a Model on the Hugging Face Hub, that contains
a tokenizer.json file
revision (:obj:`str`, defaults to `main`):
A branch or commit id
token (:obj:`str`, `optional`, defaults to `None`):
An optional auth token used to access private repositories on the
Hugging Face Hub
Returns:
:class:`~tokenizers.Tokenizer`: The new tokenizer
"""
pass
@staticmethod
def from_str(json):
"""
Instantiate a new :class:`~tokenizers.Tokenizer` from the given JSON string.
Args:
json (:obj:`str`):
A valid JSON string representing a previously serialized
:class:`~tokenizers.Tokenizer`
Returns:
:class:`~tokenizers.Tokenizer`: The new tokenizer
"""
pass
def get_added_tokens_decoder(self):
"""
Get the underlying vocabulary
Returns:
:obj:`Dict[int, AddedToken]`: The vocabulary
"""
pass
def get_vocab(self, with_added_tokens=True):
"""
Get the underlying vocabulary
Args:
with_added_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to include the added tokens
Returns:
:obj:`Dict[str, int]`: The vocabulary
"""
pass
def get_vocab_size(self, with_added_tokens=True):
"""
Get the size of the underlying vocabulary
Args:
with_added_tokens (:obj:`bool`, defaults to :obj:`True`):
Whether to include the added tokens
Returns:
:obj:`int`: The size of the vocabulary
"""
pass
def id_to_token(self, id):
"""
Convert the given id to its corresponding token if it exists
Args:
id (:obj:`int`):
The id to convert
Returns:
:obj:`Optional[str]`: An optional token, :obj:`None` if out of vocabulary
"""
pass
@property
def model(self):
"""
The :class:`~tokenizers.models.Model` in use by the Tokenizer
"""
pass
@model.setter
def model(self, value):
"""
The :class:`~tokenizers.models.Model` in use by the Tokenizer
"""
pass
def no_padding(self):
"""
Disable padding
"""
pass
def no_truncation(self):
"""
Disable truncation
"""
pass
@property
def normalizer(self):
"""
The `optional` :class:`~tokenizers.normalizers.Normalizer` in use by the Tokenizer
"""
pass
@normalizer.setter
def normalizer(self, value):
"""
The `optional` :class:`~tokenizers.normalizers.Normalizer` in use by the Tokenizer
"""
pass
def num_special_tokens_to_add(self, is_pair):
"""
Return the number of special tokens that would be added for single/pair sentences.
:param is_pair: Boolean indicating if the input would be a single sentence or a pair
:return:
"""
pass
@property
def padding(self):
"""
Get the current padding parameters
`Cannot be set, use` :meth:`~tokenizers.Tokenizer.enable_padding` `instead`
Returns:
(:obj:`dict`, `optional`):
A dict with the current padding parameters if padding is enabled
"""
pass
@padding.setter
def padding(self, value):
"""
Get the current padding parameters
`Cannot be set, use` :meth:`~tokenizers.Tokenizer.enable_padding` `instead`
Returns:
(:obj:`dict`, `optional`):
A dict with the current padding parameters if padding is enabled
"""
pass
def post_process(self, encoding, pair=None, add_special_tokens=True):
"""
Apply all the post-processing steps to the given encodings.
The various steps are:
1. Truncate according to the set truncation params (provided with
:meth:`~tokenizers.Tokenizer.enable_truncation`)
2. Apply the :class:`~tokenizers.processors.PostProcessor`
3. Pad according to the set padding params (provided with
:meth:`~tokenizers.Tokenizer.enable_padding`)
Args:
encoding (:class:`~tokenizers.Encoding`):
The :class:`~tokenizers.Encoding` corresponding to the main sequence.
pair (:class:`~tokenizers.Encoding`, `optional`):
An optional :class:`~tokenizers.Encoding` corresponding to the pair sequence.
add_special_tokens (:obj:`bool`):
Whether to add the special tokens
Returns:
:class:`~tokenizers.Encoding`: The final post-processed encoding
"""
pass
@property
def post_processor(self):
"""
The `optional` :class:`~tokenizers.processors.PostProcessor` in use by the Tokenizer
"""
pass
@post_processor.setter
def post_processor(self, value):
"""
The `optional` :class:`~tokenizers.processors.PostProcessor` in use by the Tokenizer
"""
pass
@property
def pre_tokenizer(self):
"""
The `optional` :class:`~tokenizers.pre_tokenizers.PreTokenizer` in use by the Tokenizer
"""
pass
@pre_tokenizer.setter
def pre_tokenizer(self, value):
"""
The `optional` :class:`~tokenizers.pre_tokenizers.PreTokenizer` in use by the Tokenizer
"""
pass
def save(self, path, pretty=True):
"""
Save the :class:`~tokenizers.Tokenizer` to the file at the given path.
Args:
path (:obj:`str`):
A path to a file in which to save the serialized tokenizer.
pretty (:obj:`bool`, defaults to :obj:`True`):
Whether the JSON file should be pretty formatted.
"""
pass
def to_str(self, pretty=False):
"""
Gets a serialized string representing this :class:`~tokenizers.Tokenizer`.
Args:
pretty (:obj:`bool`, defaults to :obj:`False`):
Whether the JSON string should be pretty formatted.
Returns:
:obj:`str`: A string representing the serialized Tokenizer
"""
pass
def token_to_id(self, token):
"""
Convert the given token to its corresponding id if it exists
Args:
token (:obj:`str`):
The token to convert
Returns:
:obj:`Optional[int]`: An optional id, :obj:`None` if out of vocabulary
"""
pass
def train(self, files, trainer=None):
"""
Train the Tokenizer using the given files.
Reads the files line by line, while keeping all the whitespace, even new lines.
If you want to train from data store in-memory, you can check
:meth:`~tokenizers.Tokenizer.train_from_iterator`
Args:
files (:obj:`List[str]`):
A list of path to the files that we should use for training
trainer (:obj:`~tokenizers.trainers.Trainer`, `optional`):
An optional trainer that should be used to train our Model
"""
pass
def train_from_iterator(self, iterator, trainer=None, length=None):
"""
Train the Tokenizer using the provided iterator.
You can provide anything that is a Python Iterator
* A list of sequences :obj:`List[str]`
* A generator that yields :obj:`str` or :obj:`List[str]`
* A Numpy array of strings
* ...
Args:
iterator (:obj:`Iterator`):
Any iterator over strings or list of strings
trainer (:obj:`~tokenizers.trainers.Trainer`, `optional`):
An optional trainer that should be used to train our Model
length (:obj:`int`, `optional`):
The total number of sequences in the iterator. This is used to
provide meaningful progress tracking
"""
pass
@property
def truncation(self):
"""
Get the currently set truncation parameters
`Cannot set, use` :meth:`~tokenizers.Tokenizer.enable_truncation` `instead`
Returns:
(:obj:`dict`, `optional`):
A dict with the current truncation parameters if truncation is enabled
"""
pass
@truncation.setter
def truncation(self, value):
"""
Get the currently set truncation parameters
`Cannot set, use` :meth:`~tokenizers.Tokenizer.enable_truncation` `instead`
Returns:
(:obj:`dict`, `optional`):
A dict with the current truncation parameters if truncation is enabled
"""
pass
from enum import Enum
from typing import List, Tuple, Union, Any
Offsets = Tuple[int, int]
TextInputSequence = str
PreTokenizedInputSequence = Union[List[str], Tuple[str, ...]]
TextEncodeInput = Union[
TextInputSequence,
Tuple[TextInputSequence, TextInputSequence],
List[TextInputSequence],
]
PreTokenizedEncodeInput = Union[
PreTokenizedInputSequence,
Tuple[PreTokenizedInputSequence, PreTokenizedInputSequence],
List[PreTokenizedInputSequence],
]
InputSequence = Union[TextInputSequence, PreTokenizedInputSequence]
EncodeInput = Union[TextEncodeInput, PreTokenizedEncodeInput]
class OffsetReferential(Enum):
ORIGINAL = "original"
NORMALIZED = "normalized"
class OffsetType(Enum):
BYTE = "byte"
CHAR = "char"
class SplitDelimiterBehavior(Enum):
REMOVED = "removed"
ISOLATED = "isolated"
MERGED_WITH_PREVIOUS = "merged_with_previous"
MERGED_WITH_NEXT = "merged_with_next"
CONTIGUOUS = "contiguous"
from .implementations import (
BertWordPieceTokenizer,
ByteLevelBPETokenizer,
CharBPETokenizer,
SentencePieceBPETokenizer,
SentencePieceUnigramTokenizer,
)
def __getattr__(name: str) -> Any: ...
BertWordPieceTokenizer: Any
ByteLevelBPETokenizer: Any
CharBPETokenizer: Any
SentencePieceBPETokenizer: Any
SentencePieceUnigramTokenizer: Any
|