"examples/pytorch/image-pretraining/run_mae.py" did not exist on "dc193c906dfb3b9663f8963735c46e030a15b914"
_toctree.yml 25.1 KB
Newer Older
1
- sections:
Sylvain Gugger's avatar
Sylvain Gugger committed
2
3
4
5
6
7
8
9
  - local: index
    title: 馃 Transformers
  - local: quicktour
    title: Quick tour
  - local: installation
    title: Installation
  title: Get started
- sections:
Steven Liu's avatar
Steven Liu committed
10
  - local: pipeline_tutorial
11
    title: Run inference with pipelines
Steven Liu's avatar
Steven Liu committed
12
  - local: autoclass_tutorial
13
    title: Write portable code with AutoClass
Steven Liu's avatar
Steven Liu committed
14
  - local: preprocessing
15
    title: Preprocess data
Sylvain Gugger's avatar
Sylvain Gugger committed
16
  - local: training
17
    title: Fine-tune a pretrained model
18
19
  - local: run_scripts
    title: Train with a script
20
  - local: accelerate
21
    title: Set up distributed training with 馃 Accelerate
22
23
  - local: peft
    title: Load and train adapters with 馃 PEFT
Sylvain Gugger's avatar
Sylvain Gugger committed
24
  - local: model_sharing
25
    title: Share your model
Aymeric Roucher's avatar
Aymeric Roucher committed
26
  - local: agents
Sylvain Gugger's avatar
Sylvain Gugger committed
27
    title: Agents
28
29
  - local: llm_tutorial
    title: Generation with LLMs
30
31
  - local: conversations
    title: Chatting with Transformers
Steven Liu's avatar
Steven Liu committed
32
  title: Tutorials
Sylvain Gugger's avatar
Sylvain Gugger committed
33
- sections:
Yih-Dar's avatar
Yih-Dar committed
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
  - isExpanded: false
    sections:
    - local: tasks/sequence_classification
      title: Text classification
    - local: tasks/token_classification
      title: Token classification
    - local: tasks/question_answering
      title: Question answering
    - local: tasks/language_modeling
      title: Causal language modeling
    - local: tasks/masked_language_modeling
      title: Masked language modeling
    - local: tasks/translation
      title: Translation
    - local: tasks/summarization
      title: Summarization
    - local: tasks/multiple_choice
      title: Multiple choice
Steven Liu's avatar
Steven Liu committed
52
    title: Natural Language Processing
Yih-Dar's avatar
Yih-Dar committed
53
54
55
56
57
58
  - isExpanded: false
    sections:
    - local: tasks/audio_classification
      title: Audio classification
    - local: tasks/asr
      title: Automatic speech recognition
Steven Liu's avatar
Steven Liu committed
59
    title: Audio
Yih-Dar's avatar
Yih-Dar committed
60
61
62
63
64
  - isExpanded: false
    sections:
    - local: tasks/image_classification
      title: Image classification
    - local: tasks/semantic_segmentation
65
      title: Image segmentation
Yih-Dar's avatar
Yih-Dar committed
66
67
68
69
70
71
72
73
74
75
    - local: tasks/video_classification
      title: Video classification
    - local: tasks/object_detection
      title: Object detection
    - local: tasks/zero_shot_object_detection
      title: Zero-shot object detection
    - local: tasks/zero_shot_image_classification
      title: Zero-shot image classification
    - local: tasks/monocular_depth_estimation
      title: Depth estimation
76
77
    - local: tasks/image_to_image
      title: Image-to-Image
78
79
    - local: tasks/image_feature_extraction
      title: Image Feature Extraction
80
81
    - local: tasks/mask_generation
      title: Mask Generation
82
83
    - local: tasks/knowledge_distillation_for_image_classification
      title: Knowledge Distillation for Computer Vision
Steven Liu's avatar
Steven Liu committed
84
    title: Computer Vision
Yih-Dar's avatar
Yih-Dar committed
85
86
87
88
89
90
91
92
93
94
  - isExpanded: false
    sections:
    - local: tasks/image_captioning
      title: Image captioning
    - local: tasks/document_question_answering
      title: Document Question Answering
    - local: tasks/visual_question_answering
      title: Visual Question Answering
    - local: tasks/text-to-speech
      title: Text to speech
95
    title: Multimodal
Yih-Dar's avatar
Yih-Dar committed
96
97
98
99
  - isExpanded: false
    sections:
    - local: generation_strategies
      title: Customize the generation strategy
100
    title: Generation
101
102
103
104
  - isExpanded: false
    sections:
    - local: tasks/idefics
      title: Image tasks with IDEFICS
105
106
    - local: tasks/prompting
      title: LLM prompting guide
107
    title: Prompting
108
109
  title: Task Guides
- sections:
Yih-Dar's avatar
Yih-Dar committed
110
111
112
113
114
115
116
117
  - local: fast_tokenizers
    title: Use fast tokenizers from 馃 Tokenizers
  - local: multilingual
    title: Run inference with multilingual models
  - local: create_a_model
    title: Use model-specific APIs
  - local: custom_models
    title: Share a custom model
118
119
  - local: chat_templating
    title: Templates for chat models
Steven Liu's avatar
Steven Liu committed
120
121
  - local: trainer
    title: Trainer
Yih-Dar's avatar
Yih-Dar committed
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
  - local: sagemaker
    title: Run training on Amazon SageMaker
  - local: serialization
    title: Export to ONNX
  - local: tflite
    title: Export to TFLite
  - local: torchscript
    title: Export to TorchScript
  - local: benchmarks
    title: Benchmarks
  - local: notebooks
    title: Notebooks with examples
  - local: community
    title: Community resources
  - local: troubleshooting
NielsRogge's avatar
NielsRogge committed
137
    title: Troubleshoot
138
139
  - local: hf_quantizer
    title: Contribute new quantization method
140
141
  - local: gguf
    title: Interoperability with GGUF files
142
143
  title: Developer guides
- sections:
Yih-Dar's avatar
Yih-Dar committed
144
145
  - local: performance
    title: Overview
Steven Liu's avatar
Steven Liu committed
146
147
  - local: llm_optims
    title: LLM inference optimization
Steven Liu's avatar
Steven Liu committed
148
149
  - local: quantization
    title: Quantization
Yih-Dar's avatar
Yih-Dar committed
150
151
152
153
154
  - sections:
    - local: perf_train_gpu_one
      title: Methods and tools for efficient training on a single GPU
    - local: perf_train_gpu_many
      title: Multiple GPUs and parallelism
Steven Liu's avatar
Steven Liu committed
155
156
    - local: fsdp
      title: Fully Sharded Data Parallel
Steven Liu's avatar
Steven Liu committed
157
158
    - local: deepspeed
      title: DeepSpeed
Yih-Dar's avatar
Yih-Dar committed
159
160
161
162
163
164
165
    - local: perf_train_cpu
      title: Efficient training on CPU
    - local: perf_train_cpu_many
      title: Distributed CPU training
    - local: perf_train_tpu_tf
      title: Training on TPU with TensorFlow
    - local: perf_train_special
Steven Liu's avatar
Steven Liu committed
166
      title: PyTorch training on Apple silicon
Yih-Dar's avatar
Yih-Dar committed
167
168
169
170
171
172
173
    - local: perf_hardware
      title: Custom hardware for training
    - local: hpo_train
      title: Hyperparameter Search using Trainer API
    title: Efficient training techniques
  - sections:
    - local: perf_infer_cpu
174
      title: CPU inference
Yih-Dar's avatar
Yih-Dar committed
175
    - local: perf_infer_gpu_one
176
      title: GPU inference
Yih-Dar's avatar
Yih-Dar committed
177
178
    title: Optimizing inference
  - local: big_models
Steven Liu's avatar
Steven Liu committed
179
    title: Instantiate a big model
Yih-Dar's avatar
Yih-Dar committed
180
  - local: debugging
Steven Liu's avatar
Steven Liu committed
181
    title: Debugging
Yih-Dar's avatar
Yih-Dar committed
182
183
184
185
  - local: tf_xla
    title: XLA Integration for TensorFlow Models
  - local: perf_torch_compile
    title: Optimize inference using `torch.compile()`
186
187
  title: Performance and scalability
- sections:
Yih-Dar's avatar
Yih-Dar committed
188
  - local: contributing
189
    title: How to contribute to 馃 Transformers?
Yih-Dar's avatar
Yih-Dar committed
190
191
192
193
194
195
196
197
  - local: add_new_model
    title: How to add a model to 馃 Transformers?
  - local: add_new_pipeline
    title: How to add a pipeline to 馃 Transformers?
  - local: testing
    title: Testing
  - local: pr_checks
    title: Checks on a Pull Request
198
  title: Contribute
Sylvain Gugger's avatar
Sylvain Gugger committed
199
- sections:
200
201
202
203
204
  - local: philosophy
    title: Philosophy
  - local: glossary
    title: Glossary
  - local: task_summary
205
    title: What 馃 Transformers can do
Steven Liu's avatar
Steven Liu committed
206
207
  - local: tasks_explained
    title: How 馃 Transformers solve tasks
208
  - local: model_summary
Steven Liu's avatar
Steven Liu committed
209
    title: The Transformer model family
210
211
  - local: tokenizer_summary
    title: Summary of the tokenizers
Steven Liu's avatar
Steven Liu committed
212
213
  - local: attention
    title: Attention mechanisms
214
215
  - local: pad_truncation
    title: Padding and truncation
Sylvain Gugger's avatar
Sylvain Gugger committed
216
217
218
219
  - local: bertology
    title: BERTology
  - local: perplexity
    title: Perplexity of fixed-length models
220
221
  - local: pipeline_webserver
    title: Pipelines for webserver inference
222
223
  - local: model_memory_anatomy
    title: Model training anatomy
Patrick von Platen's avatar
Patrick von Platen committed
224
225
  - local: llm_tutorial_optimization
    title: Getting the most out of LLMs
226
  title: Conceptual guides
Sylvain Gugger's avatar
Sylvain Gugger committed
227
228
- sections:
  - sections:
Sylvain Gugger's avatar
Sylvain Gugger committed
229
230
    - local: main_classes/agent
      title: Agents and Tools
231
232
    - local: model_doc/auto
      title: Auto Classes
233
234
    - local: main_classes/backbones
      title: Backbones
Sylvain Gugger's avatar
Sylvain Gugger committed
235
236
237
238
239
240
241
242
243
244
245
246
    - local: main_classes/callback
      title: Callbacks
    - local: main_classes/configuration
      title: Configuration
    - local: main_classes/data_collator
      title: Data Collator
    - local: main_classes/keras_callbacks
      title: Keras callbacks
    - local: main_classes/logging
      title: Logging
    - local: main_classes/model
      title: Models
247
248
    - local: main_classes/text_generation
      title: Text Generation
249
250
    - local: main_classes/onnx
      title: ONNX
Sylvain Gugger's avatar
Sylvain Gugger committed
251
252
253
254
255
256
257
258
    - local: main_classes/optimizer_schedules
      title: Optimization
    - local: main_classes/output
      title: Model outputs
    - local: main_classes/pipelines
      title: Pipelines
    - local: main_classes/processors
      title: Processors
259
260
    - local: main_classes/quantization
      title: Quantization
Sylvain Gugger's avatar
Sylvain Gugger committed
261
262
263
264
265
    - local: main_classes/tokenizer
      title: Tokenizer
    - local: main_classes/trainer
      title: Trainer
    - local: main_classes/deepspeed
Steven Liu's avatar
Steven Liu committed
266
      title: DeepSpeed
Sylvain Gugger's avatar
Sylvain Gugger committed
267
268
    - local: main_classes/feature_extractor
      title: Feature Extractor
amyeroberts's avatar
amyeroberts committed
269
270
    - local: main_classes/image_processor
      title: Image Processor
Sylvain Gugger's avatar
Sylvain Gugger committed
271
272
    title: Main Classes
  - sections:
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
    - isExpanded: false
      sections:
      - local: model_doc/albert
        title: ALBERT
      - local: model_doc/bart
        title: BART
      - local: model_doc/barthez
        title: BARThez
      - local: model_doc/bartpho
        title: BARTpho
      - local: model_doc/bert
        title: BERT
      - local: model_doc/bert-generation
        title: BertGeneration
      - local: model_doc/bert-japanese
        title: BertJapanese
      - local: model_doc/bertweet
        title: Bertweet
      - local: model_doc/big_bird
        title: BigBird
      - local: model_doc/bigbird_pegasus
        title: BigBirdPegasus
Kamal Raj Kanakarajan's avatar
Kamal Raj Kanakarajan committed
295
296
      - local: model_doc/biogpt
        title: BioGpt
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
      - local: model_doc/blenderbot
        title: Blenderbot
      - local: model_doc/blenderbot-small
        title: Blenderbot Small
      - local: model_doc/bloom
        title: BLOOM
      - local: model_doc/bort
        title: BORT
      - local: model_doc/byt5
        title: ByT5
      - local: model_doc/camembert
        title: CamemBERT
      - local: model_doc/canine
        title: CANINE
      - local: model_doc/codegen
        title: CodeGen
313
314
      - local: model_doc/code_llama
        title: CodeLlama
Saurabh Dash's avatar
Saurabh Dash committed
315
316
      - local: model_doc/cohere
        title: Cohere
317
318
319
320
      - local: model_doc/convbert
        title: ConvBERT
      - local: model_doc/cpm
        title: CPM
321
322
      - local: model_doc/cpmant
        title: CPMANT
323
324
      - local: model_doc/ctrl
        title: CTRL
Abhi Venigalla's avatar
Abhi Venigalla committed
325
326
      - local: model_doc/dbrx
        title: DBRX
327
328
329
330
331
332
333
334
335
336
337
338
339
340
      - local: model_doc/deberta
        title: DeBERTa
      - local: model_doc/deberta-v2
        title: DeBERTa-v2
      - local: model_doc/dialogpt
        title: DialoGPT
      - local: model_doc/distilbert
        title: DistilBERT
      - local: model_doc/dpr
        title: DPR
      - local: model_doc/electra
        title: ELECTRA
      - local: model_doc/encoder-decoder
        title: Encoder Decoder Models
341
342
      - local: model_doc/ernie
        title: ERNIE
343
344
      - local: model_doc/ernie_m
        title: ErnieM
345
346
      - local: model_doc/esm
        title: ESM
347
348
      - local: model_doc/falcon
        title: Falcon
349
350
      - local: model_doc/fastspeech2_conformer
        title: FastSpeech2Conformer
351
352
      - local: model_doc/flan-t5
        title: FLAN-T5
Arthur's avatar
Arthur committed
353
354
      - local: model_doc/flan-ul2
        title: FLAN-UL2
355
356
357
358
359
360
361
362
      - local: model_doc/flaubert
        title: FlauBERT
      - local: model_doc/fnet
        title: FNet
      - local: model_doc/fsmt
        title: FSMT
      - local: model_doc/funnel
        title: Funnel Transformer
Pablo Montalvo's avatar
Pablo Montalvo committed
363
364
      - local: model_doc/fuyu
        title: Fuyu
365
366
      - local: model_doc/gemma
        title: Gemma
367
368
369
370
371
372
      - local: model_doc/openai-gpt
        title: GPT
      - local: model_doc/gpt_neo
        title: GPT Neo
      - local: model_doc/gpt_neox
        title: GPT NeoX
373
374
      - local: model_doc/gpt_neox_japanese
        title: GPT NeoX Japanese
375
376
377
378
      - local: model_doc/gptj
        title: GPT-J
      - local: model_doc/gpt2
        title: GPT2
379
380
      - local: model_doc/gpt_bigcode
        title: GPTBigCode
381
382
      - local: model_doc/gptsan-japanese
        title: GPTSAN Japanese
383
384
      - local: model_doc/gpt-sw3
        title: GPTSw3
385
386
387
388
      - local: model_doc/herbert
        title: HerBERT
      - local: model_doc/ibert
        title: I-BERT
tomeras91's avatar
tomeras91 committed
389
390
      - local: model_doc/jamba
        title: Jamba
Yikang Shen's avatar
Yikang Shen committed
391
392
      - local: model_doc/jetmoe
        title: JetMoe
393
394
      - local: model_doc/jukebox
        title: Jukebox
395
396
      - local: model_doc/led
        title: LED
Jason Phang's avatar
Jason Phang committed
397
398
      - local: model_doc/llama
        title: LLaMA
399
400
      - local: model_doc/llama2
        title: Llama2
Arthur's avatar
Arthur committed
401
402
      - local: model_doc/llama3
        title: Llama3
403
404
405
406
407
408
409
410
      - local: model_doc/longformer
        title: Longformer
      - local: model_doc/longt5
        title: LongT5
      - local: model_doc/luke
        title: LUKE
      - local: model_doc/m2m_100
        title: M2M100
411
412
      - local: model_doc/madlad-400
        title: MADLAD-400
413
414
      - local: model_doc/mamba
        title: Mamba
415
416
      - local: model_doc/marian
        title: MarianMT
NielsRogge's avatar
NielsRogge committed
417
418
      - local: model_doc/markuplm
        title: MarkupLM
419
420
      - local: model_doc/mbart
        title: MBart and MBart-50
421
422
      - local: model_doc/mega
        title: MEGA
423
424
425
426
      - local: model_doc/megatron-bert
        title: MegatronBERT
      - local: model_doc/megatron_gpt2
        title: MegatronGPT2
427
428
      - local: model_doc/mistral
        title: Mistral
429
430
      - local: model_doc/mixtral
        title: Mixtral
431
432
433
434
435
436
      - local: model_doc/mluke
        title: mLUKE
      - local: model_doc/mobilebert
        title: MobileBERT
      - local: model_doc/mpnet
        title: MPNet
437
438
      - local: model_doc/mpt
        title: MPT
439
440
      - local: model_doc/mra
        title: MRA
441
442
443
444
445
446
447
448
      - local: model_doc/mt5
        title: MT5
      - local: model_doc/mvp
        title: MVP
      - local: model_doc/nezha
        title: NEZHA
      - local: model_doc/nllb
        title: NLLB
449
450
      - local: model_doc/nllb-moe
        title: NLLB-MoE
451
452
      - local: model_doc/nystromformer
        title: Nystr枚mformer
Shane A's avatar
Shane A committed
453
454
      - local: model_doc/olmo
        title: OLMo
455
456
      - local: model_doc/open-llama
        title: Open-Llama
457
458
459
460
      - local: model_doc/opt
        title: OPT
      - local: model_doc/pegasus
        title: Pegasus
Jason Phang's avatar
Jason Phang committed
461
462
      - local: model_doc/pegasus_x
        title: PEGASUS-X
463
464
      - local: model_doc/persimmon
        title: Persimmon
Susnato Dhar's avatar
Susnato Dhar committed
465
466
      - local: model_doc/phi
        title: Phi
Gustavo de Rosa's avatar
Gustavo de Rosa committed
467
468
      - local: model_doc/phi3
        title: Phi-3
469
470
471
472
473
474
475
476
      - local: model_doc/phobert
        title: PhoBERT
      - local: model_doc/plbart
        title: PLBart
      - local: model_doc/prophetnet
        title: ProphetNet
      - local: model_doc/qdqbert
        title: QDQBert
Junyang Lin's avatar
Junyang Lin committed
477
478
      - local: model_doc/qwen2
        title: Qwen2
Bo Zheng's avatar
Bo Zheng committed
479
480
      - local: model_doc/qwen2_moe
        title: Qwen2MoE
481
482
483
484
      - local: model_doc/rag
        title: RAG
      - local: model_doc/realm
        title: REALM
Arthur's avatar
Arthur committed
485
486
      - local: model_doc/recurrent_gemma
        title: RecurrentGemma
487
488
489
490
491
492
493
494
      - local: model_doc/reformer
        title: Reformer
      - local: model_doc/rembert
        title: RemBERT
      - local: model_doc/retribert
        title: RetriBERT
      - local: model_doc/roberta
        title: RoBERTa
495
496
      - local: model_doc/roberta-prelayernorm
        title: RoBERTa-PreLayerNorm
Weiwe Shi's avatar
Weiwe Shi committed
497
498
      - local: model_doc/roc_bert
        title: RoCBert
499
500
      - local: model_doc/roformer
        title: RoFormer
Sylvain Gugger's avatar
Sylvain Gugger committed
501
502
      - local: model_doc/rwkv
        title: RWKV
503
504
505
506
      - local: model_doc/splinter
        title: Splinter
      - local: model_doc/squeezebert
        title: SqueezeBERT
Jonathan Tow's avatar
Jonathan Tow committed
507
508
      - local: model_doc/stablelm
        title: StableLm
RaymondLi0's avatar
RaymondLi0 committed
509
510
      - local: model_doc/starcoder2
        title: Starcoder2
511
512
      - local: model_doc/switch_transformers
        title: SwitchTransformers
513
514
515
516
517
518
519
520
521
522
      - local: model_doc/t5
        title: T5
      - local: model_doc/t5v1.1
        title: T5v1.1
      - local: model_doc/tapex
        title: TAPEX
      - local: model_doc/transfo-xl
        title: Transformer XL
      - local: model_doc/ul2
        title: UL2
523
524
      - local: model_doc/umt5
        title: UMT5
Jannis Vamvas's avatar
Jannis Vamvas committed
525
526
      - local: model_doc/xmod
        title: X-MOD
527
528
529
530
531
532
533
534
535
536
      - local: model_doc/xglm
        title: XGLM
      - local: model_doc/xlm
        title: XLM
      - local: model_doc/xlm-prophetnet
        title: XLM-ProphetNet
      - local: model_doc/xlm-roberta
        title: XLM-RoBERTa
      - local: model_doc/xlm-roberta-xl
        title: XLM-RoBERTa-XL
537
538
      - local: model_doc/xlm-v
        title: XLM-V
539
540
541
542
543
544
545
546
547
      - local: model_doc/xlnet
        title: XLNet
      - local: model_doc/yoso
        title: YOSO
      title: Text models
    - isExpanded: false
      sections:
      - local: model_doc/beit
        title: BEiT
NielsRogge's avatar
NielsRogge committed
548
549
      - local: model_doc/bit
        title: BiT
550
551
      - local: model_doc/conditional_detr
        title: Conditional DETR
552
553
      - local: model_doc/convnext
        title: ConvNeXT
Alara Dirik's avatar
Alara Dirik committed
554
555
      - local: model_doc/convnextv2
        title: ConvNeXTV2
556
557
      - local: model_doc/cvt
        title: CvT
NielsRogge's avatar
NielsRogge committed
558
559
      - local: model_doc/deformable_detr
        title: Deformable DETR
560
561
      - local: model_doc/deit
        title: DeiT
NielsRogge's avatar
NielsRogge committed
562
563
      - local: model_doc/depth_anything
        title: Depth Anything
NielsRogge's avatar
NielsRogge committed
564
565
      - local: model_doc/deta
        title: DETA
566
567
      - local: model_doc/detr
        title: DETR
568
569
      - local: model_doc/dinat
        title: DiNAT
NielsRogge's avatar
NielsRogge committed
570
      - local: model_doc/dinov2
571
        title: DINOV2
572
573
574
575
      - local: model_doc/dit
        title: DiT
      - local: model_doc/dpt
        title: DPT
576
577
      - local: model_doc/efficientformer
        title: EfficientFormer
Alara Dirik's avatar
Alara Dirik committed
578
579
      - local: model_doc/efficientnet
        title: EfficientNet
NielsRogge's avatar
NielsRogge committed
580
581
      - local: model_doc/focalnet
        title: FocalNet
582
583
584
585
586
587
      - local: model_doc/glpn
        title: GLPN
      - local: model_doc/imagegpt
        title: ImageGPT
      - local: model_doc/levit
        title: LeViT
Alara Dirik's avatar
Alara Dirik committed
588
589
      - local: model_doc/mask2former
        title: Mask2Former
590
591
      - local: model_doc/maskformer
        title: MaskFormer
592
593
      - local: model_doc/mobilenet_v1
        title: MobileNetV1
594
595
      - local: model_doc/mobilenet_v2
        title: MobileNetV2
596
597
      - local: model_doc/mobilevit
        title: MobileViT
Shehan Munasinghe's avatar
Shehan Munasinghe committed
598
599
      - local: model_doc/mobilevitv2
        title: MobileViTV2
600
601
      - local: model_doc/nat
        title: NAT
602
603
      - local: model_doc/poolformer
        title: PoolFormer
Rinat's avatar
Rinat committed
604
605
      - local: model_doc/pvt
        title: Pyramid Vision Transformer (PVT)
Nate Cibik's avatar
Nate Cibik committed
606
607
      - local: model_doc/pvt_v2
        title: Pyramid Vision Transformer v2 (PVTv2)
608
609
610
611
612
613
      - local: model_doc/regnet
        title: RegNet
      - local: model_doc/resnet
        title: ResNet
      - local: model_doc/segformer
        title: SegFormer
Eduardo Pacheco's avatar
Eduardo Pacheco committed
614
615
      - local: model_doc/seggpt
        title: SegGpt
616
617
      - local: model_doc/superpoint
        title: SuperPoint
Shehan Munasinghe's avatar
Shehan Munasinghe committed
618
619
      - local: model_doc/swiftformer
        title: SwiftFormer
620
621
622
623
      - local: model_doc/swin
        title: Swin Transformer
      - local: model_doc/swinv2
        title: Swin Transformer V2
NielsRogge's avatar
NielsRogge committed
624
625
      - local: model_doc/swin2sr
        title: Swin2SR
626
627
      - local: model_doc/table-transformer
        title: Table Transformer
NielsRogge's avatar
NielsRogge committed
628
629
      - local: model_doc/upernet
        title: UperNet
630
631
632
633
      - local: model_doc/van
        title: VAN
      - local: model_doc/vit
        title: Vision Transformer (ViT)
NielsRogge's avatar
NielsRogge committed
634
635
      - local: model_doc/vit_hybrid
        title: ViT Hybrid
NielsRogge's avatar
NielsRogge committed
636
637
      - local: model_doc/vitdet
        title: ViTDet
638
639
      - local: model_doc/vit_mae
        title: ViTMAE
NielsRogge's avatar
NielsRogge committed
640
641
      - local: model_doc/vitmatte
        title: ViTMatte
642
643
      - local: model_doc/vit_msn
        title: ViTMSN
644
645
646
647
648
      - local: model_doc/yolos
        title: YOLOS
      title: Vision models
    - isExpanded: false
      sections:
649
650
      - local: model_doc/audio-spectrogram-transformer
        title: Audio Spectrogram Transformer
Yoach Lacombe's avatar
Yoach Lacombe committed
651
652
      - local: model_doc/bark
        title: Bark
653
654
      - local: model_doc/clap
        title: CLAP
655
656
      - local: model_doc/encodec
        title: EnCodec
657
658
659
660
      - local: model_doc/hubert
        title: Hubert
      - local: model_doc/mctct
        title: MCTCT
661
662
      - local: model_doc/mms
        title: MMS
Sanchit Gandhi's avatar
Sanchit Gandhi committed
663
664
      - local: model_doc/musicgen
        title: MusicGen
Yoach Lacombe's avatar
Yoach Lacombe committed
665
666
      - local: model_doc/musicgen_melody
        title: MusicGen Melody
Susnato Dhar's avatar
Susnato Dhar committed
667
668
      - local: model_doc/pop2piano
        title: Pop2Piano
669
670
      - local: model_doc/seamless_m4t
        title: Seamless-M4T
Yoach Lacombe's avatar
Yoach Lacombe committed
671
672
      - local: model_doc/seamless_m4t_v2
        title: SeamlessM4T-v2
673
674
675
676
677
678
679
680
      - local: model_doc/sew
        title: SEW
      - local: model_doc/sew-d
        title: SEW-D
      - local: model_doc/speech_to_text
        title: Speech2Text
      - local: model_doc/speech_to_text_2
        title: Speech2Text2
681
682
      - local: model_doc/speecht5
        title: SpeechT5
683
684
685
686
      - local: model_doc/unispeech
        title: UniSpeech
      - local: model_doc/unispeech-sat
        title: UniSpeech-SAT
687
688
      - local: model_doc/univnet
        title: UnivNet
Matthijs Hollemans's avatar
Matthijs Hollemans committed
689
690
      - local: model_doc/vits
        title: VITS
691
692
      - local: model_doc/wav2vec2
        title: Wav2Vec2
693
694
      - local: model_doc/wav2vec2-bert
        title: Wav2Vec2-BERT
695
696
697
698
699
700
      - local: model_doc/wav2vec2-conformer
        title: Wav2Vec2-Conformer
      - local: model_doc/wav2vec2_phoneme
        title: Wav2Vec2Phoneme
      - local: model_doc/wavlm
        title: WavLM
701
702
      - local: model_doc/whisper
        title: Whisper
703
704
705
706
707
      - local: model_doc/xls_r
        title: XLS-R
      - local: model_doc/xlsr_wav2vec2
        title: XLSR-Wav2Vec2
      title: Audio models
NielsRogge's avatar
NielsRogge committed
708
709
710
711
712
713
714
715
    - isExpanded: false
      sections:
      - local: model_doc/timesformer
        title: TimeSformer
      - local: model_doc/videomae
        title: VideoMAE
      - local: model_doc/vivit
        title: ViViT
NielsRogge's avatar
NielsRogge committed
716
      title: Video models
717
718
    - isExpanded: false
      sections:
719
720
      - local: model_doc/align
        title: ALIGN
Jongjyh's avatar
Jongjyh committed
721
722
      - local: model_doc/altclip
        title: AltCLIP
Younes Belkada's avatar
Younes Belkada committed
723
724
      - local: model_doc/blip
        title: BLIP
NielsRogge's avatar
NielsRogge committed
725
726
      - local: model_doc/blip-2
        title: BLIP-2
727
728
      - local: model_doc/bridgetower
        title: BridgeTower
Jinho Park's avatar
Jinho Park committed
729
730
      - local: model_doc/bros
        title: BROS
731
732
      - local: model_doc/chinese_clip
        title: Chinese-CLIP
733
734
      - local: model_doc/clip
        title: CLIP
NielsRogge's avatar
NielsRogge committed
735
736
      - local: model_doc/clipseg
        title: CLIPSeg
Susnato Dhar's avatar
Susnato Dhar committed
737
738
      - local: model_doc/clvp
        title: CLVP
739
740
      - local: model_doc/data2vec
        title: Data2Vec
741
742
      - local: model_doc/deplot
        title: DePlot
NielsRogge's avatar
NielsRogge committed
743
744
      - local: model_doc/donut
        title: Donut
745
746
      - local: model_doc/flava
        title: FLAVA
747
748
      - local: model_doc/git
        title: GIT
749
750
      - local: model_doc/grounding-dino
        title: Grounding DINO
Steven Liu's avatar
Steven Liu committed
751
752
      - local: model_doc/groupvit
        title: GroupViT
753
754
      - local: model_doc/idefics
        title: IDEFICS
amyeroberts's avatar
amyeroberts committed
755
756
      - local: model_doc/idefics2
        title: Idefics2
NielsRogge's avatar
NielsRogge committed
757
758
      - local: model_doc/instructblip
        title: InstructBLIP
NielsRogge's avatar
NielsRogge committed
759
760
      - local: model_doc/kosmos-2
        title: KOSMOS-2
NielsRogge's avatar
NielsRogge committed
761
762
      - local: model_doc/layoutlm
        title: LayoutLM
763
764
765
766
767
768
      - local: model_doc/layoutlmv2
        title: LayoutLMV2
      - local: model_doc/layoutlmv3
        title: LayoutLMV3
      - local: model_doc/layoutxlm
        title: LayoutXLM
769
770
      - local: model_doc/lilt
        title: LiLT
771
772
      - local: model_doc/llava
        title: Llava
NielsRogge's avatar
NielsRogge committed
773
774
      - local: model_doc/llava_next
        title: LLaVA-NeXT
Steven Liu's avatar
Steven Liu committed
775
776
      - local: model_doc/lxmert
        title: LXMERT
777
778
      - local: model_doc/matcha
        title: MatCha
wangpeng's avatar
wangpeng committed
779
780
      - local: model_doc/mgp-str
        title: MGP-STR
NielsRogge's avatar
NielsRogge committed
781
782
      - local: model_doc/nougat
        title: Nougat
Jitesh Jain's avatar
Jitesh Jain committed
783
784
      - local: model_doc/oneformer
        title: OneFormer
785
786
      - local: model_doc/owlvit
        title: OWL-ViT
NielsRogge's avatar
NielsRogge committed
787
788
      - local: model_doc/owlv2
        title: OWLv2
Pablo Montalvo's avatar
Pablo Montalvo committed
789
790
      - local: model_doc/paligemma
        title: PaliGemma
791
792
      - local: model_doc/perceiver
        title: Perceiver
Younes Belkada's avatar
Younes Belkada committed
793
794
      - local: model_doc/pix2struct
        title: Pix2Struct
795
796
      - local: model_doc/sam
        title: Segment Anything
NielsRogge's avatar
NielsRogge committed
797
798
      - local: model_doc/siglip
        title: SigLIP
799
800
      - local: model_doc/speech-encoder-decoder
        title: Speech Encoder Decoder Models
NielsRogge's avatar
NielsRogge committed
801
802
      - local: model_doc/tapas
        title: TAPAS
803
804
      - local: model_doc/trocr
        title: TrOCR
Zineng Tang's avatar
Zineng Tang committed
805
806
      - local: model_doc/tvlt
        title: TVLT
jiqing-feng's avatar
jiqing-feng committed
807
808
      - local: model_doc/tvp
        title: TVP
NielsRogge's avatar
NielsRogge committed
809
810
      - local: model_doc/udop
        title: UDOP
Raushan Turganbay's avatar
Raushan Turganbay committed
811
812
      - local: model_doc/video_llava
        title: VideoLlava
813
814
      - local: model_doc/vilt
        title: ViLT
815
816
      - local: model_doc/vipllava
        title: VipLlava
817
818
819
820
821
822
      - local: model_doc/vision-encoder-decoder
        title: Vision Encoder Decoder Models
      - local: model_doc/vision-text-dual-encoder
        title: Vision Text Dual Encoder
      - local: model_doc/visual_bert
        title: VisualBERT
NielsRogge's avatar
NielsRogge committed
823
824
      - local: model_doc/xclip
        title: X-CLIP
825
826
827
828
829
830
831
832
      title: Multimodal models
    - isExpanded: false
      sections:
      - local: model_doc/decision_transformer
        title: Decision Transformer
      - local: model_doc/trajectory_transformer
        title: Trajectory Transformer
      title: Reinforcement learning models
833
834
    - isExpanded: false
      sections:
835
836
      - local: model_doc/autoformer
        title: Autoformer
837
838
      - local: model_doc/informer
        title: Informer
839
840
      - local: model_doc/patchtsmixer
        title: PatchTSMixer
841
842
      - local: model_doc/patchtst
        title: PatchTST
843
844
845
      - local: model_doc/time_series_transformer
        title: Time Series Transformer
      title: Time series models
846
847
848
849
850
    - isExpanded: false
      sections:
      - local: model_doc/graphormer
        title: Graphormer
      title: Graph models
Sylvain Gugger's avatar
Sylvain Gugger committed
851
852
853
854
855
856
857
858
859
860
861
862
    title: Models
  - sections:
    - local: internal/modeling_utils
      title: Custom Layers and Utilities
    - local: internal/pipelines_utils
      title: Utilities for pipelines
    - local: internal/tokenization_utils
      title: Utilities for Tokenizers
    - local: internal/trainer_utils
      title: Utilities for Trainer
    - local: internal/generation_utils
      title: Utilities for Generation
863
864
    - local: internal/image_processing_utils
      title: Utilities for Image Processors
865
866
    - local: internal/audio_utils
      title: Utilities for Audio processing
Sylvain Gugger's avatar
Sylvain Gugger committed
867
868
    - local: internal/file_utils
      title: General Utilities
869
870
    - local: internal/time_series_utils
      title: Utilities for Time Series
Sylvain Gugger's avatar
Sylvain Gugger committed
871
    title: Internal Helpers
872
  title: API