File size: 42,152 Bytes
4c65bff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2018 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.
""" Auto Tokenizer class."""

import importlib
import json
import os
import warnings
from collections import OrderedDict
from typing import TYPE_CHECKING, Dict, Optional, Tuple, Union

from ...configuration_utils import PretrainedConfig
from ...dynamic_module_utils import get_class_from_dynamic_module, resolve_trust_remote_code
from ...tokenization_utils import PreTrainedTokenizer
from ...tokenization_utils_base import TOKENIZER_CONFIG_FILE
from ...utils import cached_file, extract_commit_hash, is_sentencepiece_available, is_tokenizers_available, logging
from ..encoder_decoder import EncoderDecoderConfig
from .auto_factory import _LazyAutoMapping
from .configuration_auto import (
    CONFIG_MAPPING_NAMES,
    AutoConfig,
    config_class_to_model_type,
    model_type_to_module_name,
    replace_list_option_in_docstrings,
)


if is_tokenizers_available():
    from ...tokenization_utils_fast import PreTrainedTokenizerFast
else:
    PreTrainedTokenizerFast = None


logger = logging.get_logger(__name__)

if TYPE_CHECKING:
    # This significantly improves completion suggestion performance when
    # the transformers package is used with Microsoft's Pylance language server.
    TOKENIZER_MAPPING_NAMES: OrderedDict[str, Tuple[Optional[str], Optional[str]]] = OrderedDict()
else:
    TOKENIZER_MAPPING_NAMES = OrderedDict(
        [
            (
                "albert",
                (
                    "AlbertTokenizer" if is_sentencepiece_available() else None,
                    "AlbertTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("align", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("bark", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("bart", ("BartTokenizer", "BartTokenizerFast")),
            (
                "barthez",
                (
                    "BarthezTokenizer" if is_sentencepiece_available() else None,
                    "BarthezTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("bartpho", ("BartphoTokenizer", None)),
            ("bert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("bert-generation", ("BertGenerationTokenizer" if is_sentencepiece_available() else None, None)),
            ("bert-japanese", ("BertJapaneseTokenizer", None)),
            ("bertweet", ("BertweetTokenizer", None)),
            (
                "big_bird",
                (
                    "BigBirdTokenizer" if is_sentencepiece_available() else None,
                    "BigBirdTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("bigbird_pegasus", ("PegasusTokenizer", "PegasusTokenizerFast" if is_tokenizers_available() else None)),
            ("biogpt", ("BioGptTokenizer", None)),
            ("blenderbot", ("BlenderbotTokenizer", "BlenderbotTokenizerFast")),
            ("blenderbot-small", ("BlenderbotSmallTokenizer", None)),
            ("blip", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("blip-2", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("bloom", (None, "BloomTokenizerFast" if is_tokenizers_available() else None)),
            ("bridgetower", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            ("bros", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("byt5", ("ByT5Tokenizer", None)),
            (
                "camembert",
                (
                    "CamembertTokenizer" if is_sentencepiece_available() else None,
                    "CamembertTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("canine", ("CanineTokenizer", None)),
            ("chinese_clip", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            (
                "clap",
                (
                    "RobertaTokenizer",
                    "RobertaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "clip",
                (
                    "CLIPTokenizer",
                    "CLIPTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "clipseg",
                (
                    "CLIPTokenizer",
                    "CLIPTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "code_llama",
                (
                    "CodeLlamaTokenizer" if is_sentencepiece_available() else None,
                    "CodeLlamaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("codegen", ("CodeGenTokenizer", "CodeGenTokenizerFast" if is_tokenizers_available() else None)),
            ("convbert", ("ConvBertTokenizer", "ConvBertTokenizerFast" if is_tokenizers_available() else None)),
            (
                "cpm",
                (
                    "CpmTokenizer" if is_sentencepiece_available() else None,
                    "CpmTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("cpmant", ("CpmAntTokenizer", None)),
            ("ctrl", ("CTRLTokenizer", None)),
            ("data2vec-audio", ("Wav2Vec2CTCTokenizer", None)),
            ("data2vec-text", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            ("deberta", ("DebertaTokenizer", "DebertaTokenizerFast" if is_tokenizers_available() else None)),
            (
                "deberta-v2",
                (
                    "DebertaV2Tokenizer" if is_sentencepiece_available() else None,
                    "DebertaV2TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("distilbert", ("DistilBertTokenizer", "DistilBertTokenizerFast" if is_tokenizers_available() else None)),
            (
                "dpr",
                (
                    "DPRQuestionEncoderTokenizer",
                    "DPRQuestionEncoderTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("electra", ("ElectraTokenizer", "ElectraTokenizerFast" if is_tokenizers_available() else None)),
            ("ernie", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("ernie_m", ("ErnieMTokenizer" if is_sentencepiece_available() else None, None)),
            ("esm", ("EsmTokenizer", None)),
            ("flaubert", ("FlaubertTokenizer", None)),
            ("fnet", ("FNetTokenizer", "FNetTokenizerFast" if is_tokenizers_available() else None)),
            ("fsmt", ("FSMTTokenizer", None)),
            ("funnel", ("FunnelTokenizer", "FunnelTokenizerFast" if is_tokenizers_available() else None)),
            ("git", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("gpt-sw3", ("GPTSw3Tokenizer" if is_sentencepiece_available() else None, None)),
            ("gpt2", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("gpt_bigcode", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("gpt_neo", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("gpt_neox", (None, "GPTNeoXTokenizerFast" if is_tokenizers_available() else None)),
            ("gpt_neox_japanese", ("GPTNeoXJapaneseTokenizer", None)),
            ("gptj", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("gptsan-japanese", ("GPTSanJapaneseTokenizer", None)),
            ("groupvit", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
            ("herbert", ("HerbertTokenizer", "HerbertTokenizerFast" if is_tokenizers_available() else None)),
            ("hubert", ("Wav2Vec2CTCTokenizer", None)),
            ("ibert", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            ("idefics", (None, "LlamaTokenizerFast" if is_tokenizers_available() else None)),
            ("instructblip", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("jukebox", ("JukeboxTokenizer", None)),
            ("layoutlm", ("LayoutLMTokenizer", "LayoutLMTokenizerFast" if is_tokenizers_available() else None)),
            ("layoutlmv2", ("LayoutLMv2Tokenizer", "LayoutLMv2TokenizerFast" if is_tokenizers_available() else None)),
            ("layoutlmv3", ("LayoutLMv3Tokenizer", "LayoutLMv3TokenizerFast" if is_tokenizers_available() else None)),
            ("layoutxlm", ("LayoutXLMTokenizer", "LayoutXLMTokenizerFast" if is_tokenizers_available() else None)),
            ("led", ("LEDTokenizer", "LEDTokenizerFast" if is_tokenizers_available() else None)),
            ("lilt", ("LayoutLMv3Tokenizer", "LayoutLMv3TokenizerFast" if is_tokenizers_available() else None)),
            (
                "llama",
                (
                    "LlamaTokenizer" if is_sentencepiece_available() else None,
                    "LlamaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("longformer", ("LongformerTokenizer", "LongformerTokenizerFast" if is_tokenizers_available() else None)),
            (
                "longt5",
                (
                    "T5Tokenizer" if is_sentencepiece_available() else None,
                    "T5TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("luke", ("LukeTokenizer", None)),
            ("lxmert", ("LxmertTokenizer", "LxmertTokenizerFast" if is_tokenizers_available() else None)),
            ("m2m_100", ("M2M100Tokenizer" if is_sentencepiece_available() else None, None)),
            ("marian", ("MarianTokenizer" if is_sentencepiece_available() else None, None)),
            (
                "mbart",
                (
                    "MBartTokenizer" if is_sentencepiece_available() else None,
                    "MBartTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "mbart50",
                (
                    "MBart50Tokenizer" if is_sentencepiece_available() else None,
                    "MBart50TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("mega", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            ("megatron-bert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("mgp-str", ("MgpstrTokenizer", None)),
            (
                "mistral",
                (
                    "LlamaTokenizer" if is_sentencepiece_available() else None,
                    "LlamaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("mluke", ("MLukeTokenizer" if is_sentencepiece_available() else None, None)),
            ("mobilebert", ("MobileBertTokenizer", "MobileBertTokenizerFast" if is_tokenizers_available() else None)),
            ("mpnet", ("MPNetTokenizer", "MPNetTokenizerFast" if is_tokenizers_available() else None)),
            ("mpt", (None, "GPTNeoXTokenizerFast" if is_tokenizers_available() else None)),
            ("mra", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            (
                "mt5",
                (
                    "MT5Tokenizer" if is_sentencepiece_available() else None,
                    "MT5TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("musicgen", ("T5Tokenizer", "T5TokenizerFast" if is_tokenizers_available() else None)),
            ("mvp", ("MvpTokenizer", "MvpTokenizerFast" if is_tokenizers_available() else None)),
            ("nezha", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            (
                "nllb",
                (
                    "NllbTokenizer" if is_sentencepiece_available() else None,
                    "NllbTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "nllb-moe",
                (
                    "NllbTokenizer" if is_sentencepiece_available() else None,
                    "NllbTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "nystromformer",
                (
                    "AlbertTokenizer" if is_sentencepiece_available() else None,
                    "AlbertTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("oneformer", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
            ("openai-gpt", ("OpenAIGPTTokenizer", "OpenAIGPTTokenizerFast" if is_tokenizers_available() else None)),
            ("opt", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
            ("owlvit", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
            (
                "pegasus",
                (
                    "PegasusTokenizer" if is_sentencepiece_available() else None,
                    "PegasusTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "pegasus_x",
                (
                    "PegasusTokenizer" if is_sentencepiece_available() else None,
                    "PegasusTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "perceiver",
                (
                    "PerceiverTokenizer",
                    None,
                ),
            ),
            (
                "persimmon",
                (
                    "LlamaTokenizer" if is_sentencepiece_available() else None,
                    "LlamaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("phobert", ("PhobertTokenizer", None)),
            ("pix2struct", ("T5Tokenizer", "T5TokenizerFast" if is_tokenizers_available() else None)),
            ("plbart", ("PLBartTokenizer" if is_sentencepiece_available() else None, None)),
            ("prophetnet", ("ProphetNetTokenizer", None)),
            ("qdqbert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("rag", ("RagTokenizer", None)),
            ("realm", ("RealmTokenizer", "RealmTokenizerFast" if is_tokenizers_available() else None)),
            (
                "reformer",
                (
                    "ReformerTokenizer" if is_sentencepiece_available() else None,
                    "ReformerTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "rembert",
                (
                    "RemBertTokenizer" if is_sentencepiece_available() else None,
                    "RemBertTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("retribert", ("RetriBertTokenizer", "RetriBertTokenizerFast" if is_tokenizers_available() else None)),
            ("roberta", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
            (
                "roberta-prelayernorm",
                ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None),
            ),
            ("roc_bert", ("RoCBertTokenizer", None)),
            ("roformer", ("RoFormerTokenizer", "RoFormerTokenizerFast" if is_tokenizers_available() else None)),
            ("rwkv", (None, "GPTNeoXTokenizerFast" if is_tokenizers_available() else None)),
            ("speech_to_text", ("Speech2TextTokenizer" if is_sentencepiece_available() else None, None)),
            ("speech_to_text_2", ("Speech2Text2Tokenizer", None)),
            ("speecht5", ("SpeechT5Tokenizer" if is_sentencepiece_available() else None, None)),
            ("splinter", ("SplinterTokenizer", "SplinterTokenizerFast")),
            (
                "squeezebert",
                ("SqueezeBertTokenizer", "SqueezeBertTokenizerFast" if is_tokenizers_available() else None),
            ),
            (
                "switch_transformers",
                (
                    "T5Tokenizer" if is_sentencepiece_available() else None,
                    "T5TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "t5",
                (
                    "T5Tokenizer" if is_sentencepiece_available() else None,
                    "T5TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("tapas", ("TapasTokenizer", None)),
            ("tapex", ("TapexTokenizer", None)),
            ("transfo-xl", ("TransfoXLTokenizer", None)),
            (
                "umt5",
                (
                    "T5Tokenizer" if is_sentencepiece_available() else None,
                    "T5TokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("vilt", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("visual_bert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
            ("vits", ("VitsTokenizer", None)),
            ("wav2vec2", ("Wav2Vec2CTCTokenizer", None)),
            ("wav2vec2-conformer", ("Wav2Vec2CTCTokenizer", None)),
            ("wav2vec2_phoneme", ("Wav2Vec2PhonemeCTCTokenizer", None)),
            ("whisper", ("WhisperTokenizer", "WhisperTokenizerFast" if is_tokenizers_available() else None)),
            ("xclip", ("CLIPTokenizer", "CLIPTokenizerFast" if is_tokenizers_available() else None)),
            (
                "xglm",
                (
                    "XGLMTokenizer" if is_sentencepiece_available() else None,
                    "XGLMTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            ("xlm", ("XLMTokenizer", None)),
            ("xlm-prophetnet", ("XLMProphetNetTokenizer" if is_sentencepiece_available() else None, None)),
            (
                "xlm-roberta",
                (
                    "XLMRobertaTokenizer" if is_sentencepiece_available() else None,
                    "XLMRobertaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "xlm-roberta-xl",
                (
                    "XLMRobertaTokenizer" if is_sentencepiece_available() else None,
                    "XLMRobertaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "xlnet",
                (
                    "XLNetTokenizer" if is_sentencepiece_available() else None,
                    "XLNetTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "xmod",
                (
                    "XLMRobertaTokenizer" if is_sentencepiece_available() else None,
                    "XLMRobertaTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
            (
                "yoso",
                (
                    "AlbertTokenizer" if is_sentencepiece_available() else None,
                    "AlbertTokenizerFast" if is_tokenizers_available() else None,
                ),
            ),
        ]
    )

TOKENIZER_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, TOKENIZER_MAPPING_NAMES)

CONFIG_TO_TYPE = {v: k for k, v in CONFIG_MAPPING_NAMES.items()}


def tokenizer_class_from_name(class_name: str):
    if class_name == "PreTrainedTokenizerFast":
        return PreTrainedTokenizerFast

    for module_name, tokenizers in TOKENIZER_MAPPING_NAMES.items():
        if class_name in tokenizers:
            module_name = model_type_to_module_name(module_name)

            module = importlib.import_module(f".{module_name}", "transformers.models")
            try:
                return getattr(module, class_name)
            except AttributeError:
                continue

    for config, tokenizers in TOKENIZER_MAPPING._extra_content.items():
        for tokenizer in tokenizers:
            if getattr(tokenizer, "__name__", None) == class_name:
                return tokenizer

    # We did not fine the class, but maybe it's because a dep is missing. In that case, the class will be in the main
    # init and we return the proper dummy to get an appropriate error message.
    main_module = importlib.import_module("transformers")
    if hasattr(main_module, class_name):
        return getattr(main_module, class_name)

    return None


def get_tokenizer_config(
    pretrained_model_name_or_path: Union[str, os.PathLike],
    cache_dir: Optional[Union[str, os.PathLike]] = None,
    force_download: bool = False,
    resume_download: bool = False,
    proxies: Optional[Dict[str, str]] = None,
    token: Optional[Union[bool, str]] = None,
    revision: Optional[str] = None,
    local_files_only: bool = False,
    subfolder: str = "",
    **kwargs,
):
    """
    Loads the tokenizer configuration from a pretrained model tokenizer configuration.

    Args:
        pretrained_model_name_or_path (`str` or `os.PathLike`):
            This can be either:

            - a string, the *model id* of a pretrained model configuration hosted inside a model repo on
              huggingface.co. Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced
              under a user or organization name, like `dbmdz/bert-base-german-cased`.
            - a path to a *directory* containing a configuration file saved using the
              [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`.

        cache_dir (`str` or `os.PathLike`, *optional*):
            Path to a directory in which a downloaded pretrained model configuration should be cached if the standard
            cache should not be used.
        force_download (`bool`, *optional*, defaults to `False`):
            Whether or not to force to (re-)download the configuration files and override the cached versions if they
            exist.
        resume_download (`bool`, *optional*, defaults to `False`):
            Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists.
        proxies (`Dict[str, str]`, *optional*):
            A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
            'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
        token (`str` or *bool*, *optional*):
            The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
            when running `huggingface-cli login` (stored in `~/.huggingface`).
        revision (`str`, *optional*, defaults to `"main"`):
            The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
            git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
            identifier allowed by git.
        local_files_only (`bool`, *optional*, defaults to `False`):
            If `True`, will only try to load the tokenizer configuration from local files.
        subfolder (`str`, *optional*, defaults to `""`):
            In case the tokenizer config is located inside a subfolder of the model repo on huggingface.co, you can
            specify the folder name here.

    <Tip>

    Passing `token=True` is required when you want to use a private model.

    </Tip>

    Returns:
        `Dict`: The configuration of the tokenizer.

    Examples:

    ```python
    # Download configuration from huggingface.co and cache.
    tokenizer_config = get_tokenizer_config("bert-base-uncased")
    # This model does not have a tokenizer config so the result will be an empty dict.
    tokenizer_config = get_tokenizer_config("xlm-roberta-base")

    # Save a pretrained tokenizer locally and you can reload its config
    from transformers import AutoTokenizer

    tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
    tokenizer.save_pretrained("tokenizer-test")
    tokenizer_config = get_tokenizer_config("tokenizer-test")
    ```"""
    use_auth_token = kwargs.pop("use_auth_token", None)
    if use_auth_token is not None:
        warnings.warn(
            "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
        )
        if token is not None:
            raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
        token = use_auth_token

    commit_hash = kwargs.get("_commit_hash", None)
    resolved_config_file = cached_file(
        pretrained_model_name_or_path,
        TOKENIZER_CONFIG_FILE,
        cache_dir=cache_dir,
        force_download=force_download,
        resume_download=resume_download,
        proxies=proxies,
        token=token,
        revision=revision,
        local_files_only=local_files_only,
        subfolder=subfolder,
        _raise_exceptions_for_missing_entries=False,
        _raise_exceptions_for_connection_errors=False,
        _commit_hash=commit_hash,
    )
    if resolved_config_file is None:
        logger.info("Could not locate the tokenizer configuration file, will try to use the model config instead.")
        return {}
    commit_hash = extract_commit_hash(resolved_config_file, commit_hash)

    with open(resolved_config_file, encoding="utf-8") as reader:
        result = json.load(reader)
    result["_commit_hash"] = commit_hash
    return result


class AutoTokenizer:
    r"""
    This is a generic tokenizer class that will be instantiated as one of the tokenizer classes of the library when
    created with the [`AutoTokenizer.from_pretrained`] class method.

    This class cannot be instantiated directly using `__init__()` (throws an error).
    """

    def __init__(self):
        raise EnvironmentError(
            "AutoTokenizer is designed to be instantiated "
            "using the `AutoTokenizer.from_pretrained(pretrained_model_name_or_path)` method."
        )

    @classmethod
    @replace_list_option_in_docstrings(TOKENIZER_MAPPING_NAMES)
    def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs):
        r"""
        Instantiate one of the tokenizer classes of the library from a pretrained model vocabulary.

        The tokenizer class to instantiate is selected based on the `model_type` property of the config object (either
        passed as an argument or loaded from `pretrained_model_name_or_path` if possible), or when it's missing, by
        falling back to using pattern matching on `pretrained_model_name_or_path`:

        List options

        Params:
            pretrained_model_name_or_path (`str` or `os.PathLike`):
                Can be either:

                    - A string, the *model id* of a predefined tokenizer hosted inside a model repo on huggingface.co.
                      Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
                      user or organization name, like `dbmdz/bert-base-german-cased`.
                    - A path to a *directory* containing vocabulary files required by the tokenizer, for instance saved
                      using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`.
                    - A path or url to a single saved vocabulary file if and only if the tokenizer only requires a
                      single vocabulary file (like Bert or XLNet), e.g.: `./my_model_directory/vocab.txt`. (Not
                      applicable to all derived classes)
            inputs (additional positional arguments, *optional*):
                Will be passed along to the Tokenizer `__init__()` method.
            config ([`PretrainedConfig`], *optional*)
                The configuration object used to determine the tokenizer class to instantiate.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration should be cached if the
                standard cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force the (re-)download the model weights and configuration files and override the
                cached versions if they exist.
            resume_download (`bool`, *optional*, defaults to `False`):
                Whether or not to delete incompletely received files. Will attempt to resume the download if such a
                file exists.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.
            subfolder (`str`, *optional*):
                In case the relevant files are located inside a subfolder of the model repo on huggingface.co (e.g. for
                facebook/rag-token-base), specify it here.
            use_fast (`bool`, *optional*, defaults to `True`):
                Use a [fast Rust-based tokenizer](https://huggingface.co/docs/tokenizers/index) if it is supported for
                a given model. If a fast tokenizer is not available for a given model, a normal Python-based tokenizer
                is returned instead.
            tokenizer_type (`str`, *optional*):
                Tokenizer type to be loaded.
            trust_remote_code (`bool`, *optional*, defaults to `False`):
                Whether or not to allow for custom models defined on the Hub in their own modeling files. This option
                should only be set to `True` for repositories you trust and in which you have read the code, as it will
                execute code present on the Hub on your local machine.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the Tokenizer `__init__()` method. Can be used to set special tokens like
                `bos_token`, `eos_token`, `unk_token`, `sep_token`, `pad_token`, `cls_token`, `mask_token`,
                `additional_special_tokens`. See parameters in the `__init__()` for more details.

        Examples:

        ```python
        >>> from transformers import AutoTokenizer

        >>> # Download vocabulary from huggingface.co and cache.
        >>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")

        >>> # Download vocabulary from huggingface.co (user-uploaded) and cache.
        >>> tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-german-cased")

        >>> # If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
        >>> # tokenizer = AutoTokenizer.from_pretrained("./test/bert_saved_model/")

        >>> # Download vocabulary from huggingface.co and define model-specific arguments
        >>> tokenizer = AutoTokenizer.from_pretrained("roberta-base", add_prefix_space=True)
        ```"""
        use_auth_token = kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
            )
            if kwargs.get("token", None) is not None:
                raise ValueError(
                    "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
                )
            kwargs["token"] = use_auth_token

        config = kwargs.pop("config", None)
        kwargs["_from_auto"] = True

        use_fast = kwargs.pop("use_fast", True)
        tokenizer_type = kwargs.pop("tokenizer_type", None)
        trust_remote_code = kwargs.pop("trust_remote_code", None)

        # First, let's see whether the tokenizer_type is passed so that we can leverage it
        if tokenizer_type is not None:
            tokenizer_class = None
            tokenizer_class_tuple = TOKENIZER_MAPPING_NAMES.get(tokenizer_type, None)

            if tokenizer_class_tuple is None:
                raise ValueError(
                    f"Passed `tokenizer_type` {tokenizer_type} does not exist. `tokenizer_type` should be one of "
                    f"{', '.join(c for c in TOKENIZER_MAPPING_NAMES.keys())}."
                )

            tokenizer_class_name, tokenizer_fast_class_name = tokenizer_class_tuple

            if use_fast:
                if tokenizer_fast_class_name is not None:
                    tokenizer_class = tokenizer_class_from_name(tokenizer_fast_class_name)
                else:
                    logger.warning(
                        "`use_fast` is set to `True` but the tokenizer class does not have a fast version. "
                        " Falling back to the slow version."
                    )
            if tokenizer_class is None:
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_name)

            if tokenizer_class is None:
                raise ValueError(f"Tokenizer class {tokenizer_class_name} is not currently imported.")

            return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)

        # Next, let's try to use the tokenizer_config file to get the tokenizer class.
        tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
        if "_commit_hash" in tokenizer_config:
            kwargs["_commit_hash"] = tokenizer_config["_commit_hash"]
        config_tokenizer_class = tokenizer_config.get("tokenizer_class")
        tokenizer_auto_map = None
        if "auto_map" in tokenizer_config:
            if isinstance(tokenizer_config["auto_map"], (tuple, list)):
                # Legacy format for dynamic tokenizers
                tokenizer_auto_map = tokenizer_config["auto_map"]
            else:
                tokenizer_auto_map = tokenizer_config["auto_map"].get("AutoTokenizer", None)

        # If that did not work, let's try to use the config.
        if config_tokenizer_class is None:
            if not isinstance(config, PretrainedConfig):
                config = AutoConfig.from_pretrained(
                    pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
                )
            config_tokenizer_class = config.tokenizer_class
            if hasattr(config, "auto_map") and "AutoTokenizer" in config.auto_map:
                tokenizer_auto_map = config.auto_map["AutoTokenizer"]

        has_remote_code = tokenizer_auto_map is not None
        has_local_code = config_tokenizer_class is not None or type(config) in TOKENIZER_MAPPING
        trust_remote_code = resolve_trust_remote_code(
            trust_remote_code, pretrained_model_name_or_path, has_local_code, has_remote_code
        )

        if has_remote_code and trust_remote_code:
            if use_fast and tokenizer_auto_map[1] is not None:
                class_ref = tokenizer_auto_map[1]
            else:
                class_ref = tokenizer_auto_map[0]
            tokenizer_class = get_class_from_dynamic_module(class_ref, pretrained_model_name_or_path, **kwargs)
            _ = kwargs.pop("code_revision", None)
            if os.path.isdir(pretrained_model_name_or_path):
                tokenizer_class.register_for_auto_class()
            return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
        elif config_tokenizer_class is not None:
            tokenizer_class = None
            if use_fast and not config_tokenizer_class.endswith("Fast"):
                tokenizer_class_candidate = f"{config_tokenizer_class}Fast"
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_candidate)
            if tokenizer_class is None:
                tokenizer_class_candidate = config_tokenizer_class
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_candidate)
            if tokenizer_class is None:
                raise ValueError(
                    f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."
                )
            return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)

        # Otherwise we have to be creative.
        # if model is an encoder decoder, the encoder tokenizer class is used by default
        if isinstance(config, EncoderDecoderConfig):
            if type(config.decoder) is not type(config.encoder):  # noqa: E721
                logger.warning(
                    f"The encoder model config class: {config.encoder.__class__} is different from the decoder model "
                    f"config class: {config.decoder.__class__}. It is not recommended to use the "
                    "`AutoTokenizer.from_pretrained()` method in this case. Please use the encoder and decoder "
                    "specific tokenizer classes."
                )
            config = config.encoder

        model_type = config_class_to_model_type(type(config).__name__)
        if model_type is not None:
            tokenizer_class_py, tokenizer_class_fast = TOKENIZER_MAPPING[type(config)]
            if tokenizer_class_fast and (use_fast or tokenizer_class_py is None):
                return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
            else:
                if tokenizer_class_py is not None:
                    return tokenizer_class_py.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
                else:
                    raise ValueError(
                        "This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed "
                        "in order to use this tokenizer."
                    )

        raise ValueError(
            f"Unrecognized configuration class {config.__class__} to build an AutoTokenizer.\n"
            f"Model type should be one of {', '.join(c.__name__ for c in TOKENIZER_MAPPING.keys())}."
        )

    def register(config_class, slow_tokenizer_class=None, fast_tokenizer_class=None, exist_ok=False):
        """
        Register a new tokenizer in this mapping.


        Args:
            config_class ([`PretrainedConfig`]):
                The configuration corresponding to the model to register.
            slow_tokenizer_class ([`PretrainedTokenizer`], *optional*):
                The slow tokenizer to register.
            fast_tokenizer_class ([`PretrainedTokenizerFast`], *optional*):
                The fast tokenizer to register.
        """
        if slow_tokenizer_class is None and fast_tokenizer_class is None:
            raise ValueError("You need to pass either a `slow_tokenizer_class` or a `fast_tokenizer_class")
        if slow_tokenizer_class is not None and issubclass(slow_tokenizer_class, PreTrainedTokenizerFast):
            raise ValueError("You passed a fast tokenizer in the `slow_tokenizer_class`.")
        if fast_tokenizer_class is not None and issubclass(fast_tokenizer_class, PreTrainedTokenizer):
            raise ValueError("You passed a slow tokenizer in the `fast_tokenizer_class`.")

        if (
            slow_tokenizer_class is not None
            and fast_tokenizer_class is not None
            and issubclass(fast_tokenizer_class, PreTrainedTokenizerFast)
            and fast_tokenizer_class.slow_tokenizer_class != slow_tokenizer_class
        ):
            raise ValueError(
                "The fast tokenizer class you are passing has a `slow_tokenizer_class` attribute that is not "
                "consistent with the slow tokenizer class you passed (fast tokenizer has "
                f"{fast_tokenizer_class.slow_tokenizer_class} and you passed {slow_tokenizer_class}. Fix one of those "
                "so they match!"
            )

        # Avoid resetting a set slow/fast tokenizer if we are passing just the other ones.
        if config_class in TOKENIZER_MAPPING._extra_content:
            existing_slow, existing_fast = TOKENIZER_MAPPING[config_class]
            if slow_tokenizer_class is None:
                slow_tokenizer_class = existing_slow
            if fast_tokenizer_class is None:
                fast_tokenizer_class = existing_fast

        TOKENIZER_MAPPING.register(config_class, (slow_tokenizer_class, fast_tokenizer_class), exist_ok=exist_ok)