861 lines
25 KiB
YAML
861 lines
25 KiB
YAML
- sections:
|
|
- local: index
|
|
title: 🤗 Transformers
|
|
- local: quicktour
|
|
title: Quick tour
|
|
- local: installation
|
|
title: Installation
|
|
title: Get started
|
|
- sections:
|
|
- local: pipeline_tutorial
|
|
title: Run inference with pipelines
|
|
- local: autoclass_tutorial
|
|
title: Write portable code with AutoClass
|
|
- local: preprocessing
|
|
title: Preprocess data
|
|
- local: training
|
|
title: Fine-tune a pretrained model
|
|
- local: run_scripts
|
|
title: Train with a script
|
|
- local: accelerate
|
|
title: Set up distributed training with 🤗 Accelerate
|
|
- local: peft
|
|
title: Load and train adapters with 🤗 PEFT
|
|
- local: model_sharing
|
|
title: Share your model
|
|
- local: transformers_agents
|
|
title: Agents
|
|
- local: llm_tutorial
|
|
title: Generation with LLMs
|
|
title: Tutorials
|
|
- sections:
|
|
- 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
|
|
title: Natural Language Processing
|
|
- isExpanded: false
|
|
sections:
|
|
- local: tasks/audio_classification
|
|
title: Audio classification
|
|
- local: tasks/asr
|
|
title: Automatic speech recognition
|
|
title: Audio
|
|
- isExpanded: false
|
|
sections:
|
|
- local: tasks/image_classification
|
|
title: Image classification
|
|
- local: tasks/semantic_segmentation
|
|
title: Image segmentation
|
|
- 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
|
|
- local: tasks/image_to_image
|
|
title: Image-to-Image
|
|
- local: tasks/image_feature_extraction
|
|
title: Image Feature Extraction
|
|
- local: tasks/mask_generation
|
|
title: Mask Generation
|
|
- local: tasks/knowledge_distillation_for_image_classification
|
|
title: Knowledge Distillation for Computer Vision
|
|
title: Computer Vision
|
|
- 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
|
|
title: Multimodal
|
|
- isExpanded: false
|
|
sections:
|
|
- local: generation_strategies
|
|
title: Customize the generation strategy
|
|
title: Generation
|
|
- isExpanded: false
|
|
sections:
|
|
- local: tasks/idefics
|
|
title: Image tasks with IDEFICS
|
|
- local: tasks/prompting
|
|
title: LLM prompting guide
|
|
title: Prompting
|
|
title: Task Guides
|
|
- sections:
|
|
- local: fast_tokenizers
|
|
title: Use fast tokenizers from 🤗 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
|
|
- local: chat_templating
|
|
title: Templates for chat models
|
|
- local: trainer
|
|
title: Trainer
|
|
- 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: custom_tools
|
|
title: Custom Tools and Prompts
|
|
- local: troubleshooting
|
|
title: Troubleshoot
|
|
- local: hf_quantizer
|
|
title: Contribute new quantization method
|
|
title: Developer guides
|
|
- sections:
|
|
- local: performance
|
|
title: Overview
|
|
- local: quantization
|
|
title: Quantization
|
|
- 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
|
|
- local: fsdp
|
|
title: Fully Sharded Data Parallel
|
|
- local: deepspeed
|
|
title: DeepSpeed
|
|
- 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
|
|
title: PyTorch training on Apple silicon
|
|
- 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
|
|
title: CPU inference
|
|
- local: perf_infer_gpu_one
|
|
title: GPU inference
|
|
title: Optimizing inference
|
|
- local: big_models
|
|
title: Instantiate a big model
|
|
- local: debugging
|
|
title: Debugging
|
|
- local: tf_xla
|
|
title: XLA Integration for TensorFlow Models
|
|
- local: perf_torch_compile
|
|
title: Optimize inference using `torch.compile()`
|
|
title: Performance and scalability
|
|
- sections:
|
|
- local: contributing
|
|
title: How to contribute to 🤗 Transformers?
|
|
- local: add_new_model
|
|
title: How to add a model to 🤗 Transformers?
|
|
- local: add_tensorflow_model
|
|
title: How to convert a 🤗 Transformers model to TensorFlow?
|
|
- local: add_new_pipeline
|
|
title: How to add a pipeline to 🤗 Transformers?
|
|
- local: testing
|
|
title: Testing
|
|
- local: pr_checks
|
|
title: Checks on a Pull Request
|
|
title: Contribute
|
|
- sections:
|
|
- local: philosophy
|
|
title: Philosophy
|
|
- local: glossary
|
|
title: Glossary
|
|
- local: task_summary
|
|
title: What 🤗 Transformers can do
|
|
- local: tasks_explained
|
|
title: How 🤗 Transformers solve tasks
|
|
- local: model_summary
|
|
title: The Transformer model family
|
|
- local: tokenizer_summary
|
|
title: Summary of the tokenizers
|
|
- local: attention
|
|
title: Attention mechanisms
|
|
- local: pad_truncation
|
|
title: Padding and truncation
|
|
- local: bertology
|
|
title: BERTology
|
|
- local: perplexity
|
|
title: Perplexity of fixed-length models
|
|
- local: pipeline_webserver
|
|
title: Pipelines for webserver inference
|
|
- local: model_memory_anatomy
|
|
title: Model training anatomy
|
|
- local: llm_tutorial_optimization
|
|
title: Getting the most out of LLMs
|
|
title: Conceptual guides
|
|
- sections:
|
|
- sections:
|
|
- local: main_classes/agent
|
|
title: Agents and Tools
|
|
- local: model_doc/auto
|
|
title: Auto Classes
|
|
- local: main_classes/backbones
|
|
title: Backbones
|
|
- 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
|
|
- local: main_classes/text_generation
|
|
title: Text Generation
|
|
- local: main_classes/onnx
|
|
title: ONNX
|
|
- 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
|
|
- local: main_classes/quantization
|
|
title: Quantization
|
|
- local: main_classes/tokenizer
|
|
title: Tokenizer
|
|
- local: main_classes/trainer
|
|
title: Trainer
|
|
- local: main_classes/deepspeed
|
|
title: DeepSpeed
|
|
- local: main_classes/feature_extractor
|
|
title: Feature Extractor
|
|
- local: main_classes/image_processor
|
|
title: Image Processor
|
|
title: Main Classes
|
|
- sections:
|
|
- 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
|
|
- local: model_doc/biogpt
|
|
title: BioGpt
|
|
- 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
|
|
- local: model_doc/code_llama
|
|
title: CodeLlama
|
|
- local: model_doc/cohere
|
|
title: Cohere
|
|
- local: model_doc/convbert
|
|
title: ConvBERT
|
|
- local: model_doc/cpm
|
|
title: CPM
|
|
- local: model_doc/cpmant
|
|
title: CPMANT
|
|
- local: model_doc/ctrl
|
|
title: CTRL
|
|
- local: model_doc/dbrx
|
|
title: DBRX
|
|
- 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
|
|
- local: model_doc/ernie
|
|
title: ERNIE
|
|
- local: model_doc/ernie_m
|
|
title: ErnieM
|
|
- local: model_doc/esm
|
|
title: ESM
|
|
- local: model_doc/falcon
|
|
title: Falcon
|
|
- local: model_doc/fastspeech2_conformer
|
|
title: FastSpeech2Conformer
|
|
- local: model_doc/flan-t5
|
|
title: FLAN-T5
|
|
- local: model_doc/flan-ul2
|
|
title: FLAN-UL2
|
|
- 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
|
|
- local: model_doc/fuyu
|
|
title: Fuyu
|
|
- local: model_doc/gemma
|
|
title: Gemma
|
|
- local: model_doc/openai-gpt
|
|
title: GPT
|
|
- local: model_doc/gpt_neo
|
|
title: GPT Neo
|
|
- local: model_doc/gpt_neox
|
|
title: GPT NeoX
|
|
- local: model_doc/gpt_neox_japanese
|
|
title: GPT NeoX Japanese
|
|
- local: model_doc/gptj
|
|
title: GPT-J
|
|
- local: model_doc/gpt2
|
|
title: GPT2
|
|
- local: model_doc/gpt_bigcode
|
|
title: GPTBigCode
|
|
- local: model_doc/gptsan-japanese
|
|
title: GPTSAN Japanese
|
|
- local: model_doc/gpt-sw3
|
|
title: GPTSw3
|
|
- local: model_doc/herbert
|
|
title: HerBERT
|
|
- local: model_doc/ibert
|
|
title: I-BERT
|
|
- local: model_doc/jamba
|
|
title: Jamba
|
|
- local: model_doc/jukebox
|
|
title: Jukebox
|
|
- local: model_doc/led
|
|
title: LED
|
|
- local: model_doc/llama
|
|
title: LLaMA
|
|
- local: model_doc/llama2
|
|
title: Llama2
|
|
- 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
|
|
- local: model_doc/madlad-400
|
|
title: MADLAD-400
|
|
- local: model_doc/mamba
|
|
title: Mamba
|
|
- local: model_doc/marian
|
|
title: MarianMT
|
|
- local: model_doc/markuplm
|
|
title: MarkupLM
|
|
- local: model_doc/mbart
|
|
title: MBart and MBart-50
|
|
- local: model_doc/mega
|
|
title: MEGA
|
|
- local: model_doc/megatron-bert
|
|
title: MegatronBERT
|
|
- local: model_doc/megatron_gpt2
|
|
title: MegatronGPT2
|
|
- local: model_doc/mistral
|
|
title: Mistral
|
|
- local: model_doc/mixtral
|
|
title: Mixtral
|
|
- local: model_doc/mluke
|
|
title: mLUKE
|
|
- local: model_doc/mobilebert
|
|
title: MobileBERT
|
|
- local: model_doc/mpnet
|
|
title: MPNet
|
|
- local: model_doc/mpt
|
|
title: MPT
|
|
- local: model_doc/mra
|
|
title: MRA
|
|
- local: model_doc/mt5
|
|
title: MT5
|
|
- local: model_doc/mvp
|
|
title: MVP
|
|
- local: model_doc/nezha
|
|
title: NEZHA
|
|
- local: model_doc/nllb
|
|
title: NLLB
|
|
- local: model_doc/nllb-moe
|
|
title: NLLB-MoE
|
|
- local: model_doc/nystromformer
|
|
title: Nyströmformer
|
|
- local: model_doc/olmo
|
|
title: OLMo
|
|
- local: model_doc/open-llama
|
|
title: Open-Llama
|
|
- local: model_doc/opt
|
|
title: OPT
|
|
- local: model_doc/pegasus
|
|
title: Pegasus
|
|
- local: model_doc/pegasus_x
|
|
title: PEGASUS-X
|
|
- local: model_doc/persimmon
|
|
title: Persimmon
|
|
- local: model_doc/phi
|
|
title: Phi
|
|
- local: model_doc/phobert
|
|
title: PhoBERT
|
|
- local: model_doc/plbart
|
|
title: PLBart
|
|
- local: model_doc/prophetnet
|
|
title: ProphetNet
|
|
- local: model_doc/qdqbert
|
|
title: QDQBert
|
|
- local: model_doc/qwen2
|
|
title: Qwen2
|
|
- local: model_doc/qwen2_moe
|
|
title: Qwen2MoE
|
|
- local: model_doc/rag
|
|
title: RAG
|
|
- local: model_doc/realm
|
|
title: REALM
|
|
- local: model_doc/recurrent_gemma
|
|
title: RecurrentGemma
|
|
- local: model_doc/reformer
|
|
title: Reformer
|
|
- local: model_doc/rembert
|
|
title: RemBERT
|
|
- local: model_doc/retribert
|
|
title: RetriBERT
|
|
- local: model_doc/roberta
|
|
title: RoBERTa
|
|
- local: model_doc/roberta-prelayernorm
|
|
title: RoBERTa-PreLayerNorm
|
|
- local: model_doc/roc_bert
|
|
title: RoCBert
|
|
- local: model_doc/roformer
|
|
title: RoFormer
|
|
- local: model_doc/rwkv
|
|
title: RWKV
|
|
- local: model_doc/splinter
|
|
title: Splinter
|
|
- local: model_doc/squeezebert
|
|
title: SqueezeBERT
|
|
- local: model_doc/stablelm
|
|
title: StableLm
|
|
- local: model_doc/starcoder2
|
|
title: Starcoder2
|
|
- local: model_doc/switch_transformers
|
|
title: SwitchTransformers
|
|
- 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
|
|
- local: model_doc/umt5
|
|
title: UMT5
|
|
- local: model_doc/xmod
|
|
title: X-MOD
|
|
- 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
|
|
- local: model_doc/xlm-v
|
|
title: XLM-V
|
|
- local: model_doc/xlnet
|
|
title: XLNet
|
|
- local: model_doc/yoso
|
|
title: YOSO
|
|
title: Text models
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/beit
|
|
title: BEiT
|
|
- local: model_doc/bit
|
|
title: BiT
|
|
- local: model_doc/conditional_detr
|
|
title: Conditional DETR
|
|
- local: model_doc/convnext
|
|
title: ConvNeXT
|
|
- local: model_doc/convnextv2
|
|
title: ConvNeXTV2
|
|
- local: model_doc/cvt
|
|
title: CvT
|
|
- local: model_doc/deformable_detr
|
|
title: Deformable DETR
|
|
- local: model_doc/deit
|
|
title: DeiT
|
|
- local: model_doc/depth_anything
|
|
title: Depth Anything
|
|
- local: model_doc/deta
|
|
title: DETA
|
|
- local: model_doc/detr
|
|
title: DETR
|
|
- local: model_doc/dinat
|
|
title: DiNAT
|
|
- local: model_doc/dinov2
|
|
title: DINOV2
|
|
- local: model_doc/dit
|
|
title: DiT
|
|
- local: model_doc/dpt
|
|
title: DPT
|
|
- local: model_doc/efficientformer
|
|
title: EfficientFormer
|
|
- local: model_doc/efficientnet
|
|
title: EfficientNet
|
|
- local: model_doc/focalnet
|
|
title: FocalNet
|
|
- local: model_doc/glpn
|
|
title: GLPN
|
|
- local: model_doc/imagegpt
|
|
title: ImageGPT
|
|
- local: model_doc/levit
|
|
title: LeViT
|
|
- local: model_doc/mask2former
|
|
title: Mask2Former
|
|
- local: model_doc/maskformer
|
|
title: MaskFormer
|
|
- local: model_doc/mobilenet_v1
|
|
title: MobileNetV1
|
|
- local: model_doc/mobilenet_v2
|
|
title: MobileNetV2
|
|
- local: model_doc/mobilevit
|
|
title: MobileViT
|
|
- local: model_doc/mobilevitv2
|
|
title: MobileViTV2
|
|
- local: model_doc/nat
|
|
title: NAT
|
|
- local: model_doc/poolformer
|
|
title: PoolFormer
|
|
- local: model_doc/pvt
|
|
title: Pyramid Vision Transformer (PVT)
|
|
- local: model_doc/pvt_v2
|
|
title: Pyramid Vision Transformer v2 (PVTv2)
|
|
- local: model_doc/regnet
|
|
title: RegNet
|
|
- local: model_doc/resnet
|
|
title: ResNet
|
|
- local: model_doc/segformer
|
|
title: SegFormer
|
|
- local: model_doc/seggpt
|
|
title: SegGpt
|
|
- local: model_doc/superpoint
|
|
title: SuperPoint
|
|
- local: model_doc/swiftformer
|
|
title: SwiftFormer
|
|
- local: model_doc/swin
|
|
title: Swin Transformer
|
|
- local: model_doc/swinv2
|
|
title: Swin Transformer V2
|
|
- local: model_doc/swin2sr
|
|
title: Swin2SR
|
|
- local: model_doc/table-transformer
|
|
title: Table Transformer
|
|
- local: model_doc/upernet
|
|
title: UperNet
|
|
- local: model_doc/van
|
|
title: VAN
|
|
- local: model_doc/vit
|
|
title: Vision Transformer (ViT)
|
|
- local: model_doc/vit_hybrid
|
|
title: ViT Hybrid
|
|
- local: model_doc/vitdet
|
|
title: ViTDet
|
|
- local: model_doc/vit_mae
|
|
title: ViTMAE
|
|
- local: model_doc/vitmatte
|
|
title: ViTMatte
|
|
- local: model_doc/vit_msn
|
|
title: ViTMSN
|
|
- local: model_doc/yolos
|
|
title: YOLOS
|
|
title: Vision models
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/audio-spectrogram-transformer
|
|
title: Audio Spectrogram Transformer
|
|
- local: model_doc/bark
|
|
title: Bark
|
|
- local: model_doc/clap
|
|
title: CLAP
|
|
- local: model_doc/encodec
|
|
title: EnCodec
|
|
- local: model_doc/hubert
|
|
title: Hubert
|
|
- local: model_doc/mctct
|
|
title: MCTCT
|
|
- local: model_doc/mms
|
|
title: MMS
|
|
- local: model_doc/musicgen
|
|
title: MusicGen
|
|
- local: model_doc/musicgen_melody
|
|
title: MusicGen Melody
|
|
- local: model_doc/pop2piano
|
|
title: Pop2Piano
|
|
- local: model_doc/seamless_m4t
|
|
title: Seamless-M4T
|
|
- local: model_doc/seamless_m4t_v2
|
|
title: SeamlessM4T-v2
|
|
- 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
|
|
- local: model_doc/speecht5
|
|
title: SpeechT5
|
|
- local: model_doc/unispeech
|
|
title: UniSpeech
|
|
- local: model_doc/unispeech-sat
|
|
title: UniSpeech-SAT
|
|
- local: model_doc/univnet
|
|
title: UnivNet
|
|
- local: model_doc/vits
|
|
title: VITS
|
|
- local: model_doc/wav2vec2
|
|
title: Wav2Vec2
|
|
- local: model_doc/wav2vec2-bert
|
|
title: Wav2Vec2-BERT
|
|
- local: model_doc/wav2vec2-conformer
|
|
title: Wav2Vec2-Conformer
|
|
- local: model_doc/wav2vec2_phoneme
|
|
title: Wav2Vec2Phoneme
|
|
- local: model_doc/wavlm
|
|
title: WavLM
|
|
- local: model_doc/whisper
|
|
title: Whisper
|
|
- local: model_doc/xls_r
|
|
title: XLS-R
|
|
- local: model_doc/xlsr_wav2vec2
|
|
title: XLSR-Wav2Vec2
|
|
title: Audio models
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/timesformer
|
|
title: TimeSformer
|
|
- local: model_doc/videomae
|
|
title: VideoMAE
|
|
- local: model_doc/vivit
|
|
title: ViViT
|
|
title: Video models
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/align
|
|
title: ALIGN
|
|
- local: model_doc/altclip
|
|
title: AltCLIP
|
|
- local: model_doc/blip
|
|
title: BLIP
|
|
- local: model_doc/blip-2
|
|
title: BLIP-2
|
|
- local: model_doc/bridgetower
|
|
title: BridgeTower
|
|
- local: model_doc/bros
|
|
title: BROS
|
|
- local: model_doc/chinese_clip
|
|
title: Chinese-CLIP
|
|
- local: model_doc/clip
|
|
title: CLIP
|
|
- local: model_doc/clipseg
|
|
title: CLIPSeg
|
|
- local: model_doc/clvp
|
|
title: CLVP
|
|
- local: model_doc/data2vec
|
|
title: Data2Vec
|
|
- local: model_doc/deplot
|
|
title: DePlot
|
|
- local: model_doc/donut
|
|
title: Donut
|
|
- local: model_doc/flava
|
|
title: FLAVA
|
|
- local: model_doc/git
|
|
title: GIT
|
|
- local: model_doc/grounding-dino
|
|
title: Grounding DINO
|
|
- local: model_doc/groupvit
|
|
title: GroupViT
|
|
- local: model_doc/idefics
|
|
title: IDEFICS
|
|
- local: model_doc/idefics2
|
|
title: Idefics2
|
|
- local: model_doc/instructblip
|
|
title: InstructBLIP
|
|
- local: model_doc/kosmos-2
|
|
title: KOSMOS-2
|
|
- local: model_doc/layoutlm
|
|
title: LayoutLM
|
|
- local: model_doc/layoutlmv2
|
|
title: LayoutLMV2
|
|
- local: model_doc/layoutlmv3
|
|
title: LayoutLMV3
|
|
- local: model_doc/layoutxlm
|
|
title: LayoutXLM
|
|
- local: model_doc/lilt
|
|
title: LiLT
|
|
- local: model_doc/llava
|
|
title: Llava
|
|
- local: model_doc/llava_next
|
|
title: LLaVA-NeXT
|
|
- local: model_doc/lxmert
|
|
title: LXMERT
|
|
- local: model_doc/matcha
|
|
title: MatCha
|
|
- local: model_doc/mgp-str
|
|
title: MGP-STR
|
|
- local: model_doc/nougat
|
|
title: Nougat
|
|
- local: model_doc/oneformer
|
|
title: OneFormer
|
|
- local: model_doc/owlvit
|
|
title: OWL-ViT
|
|
- local: model_doc/owlv2
|
|
title: OWLv2
|
|
- local: model_doc/perceiver
|
|
title: Perceiver
|
|
- local: model_doc/pix2struct
|
|
title: Pix2Struct
|
|
- local: model_doc/sam
|
|
title: Segment Anything
|
|
- local: model_doc/siglip
|
|
title: SigLIP
|
|
- local: model_doc/speech-encoder-decoder
|
|
title: Speech Encoder Decoder Models
|
|
- local: model_doc/tapas
|
|
title: TAPAS
|
|
- local: model_doc/trocr
|
|
title: TrOCR
|
|
- local: model_doc/tvlt
|
|
title: TVLT
|
|
- local: model_doc/tvp
|
|
title: TVP
|
|
- local: model_doc/udop
|
|
title: UDOP
|
|
- local: model_doc/vilt
|
|
title: ViLT
|
|
- local: model_doc/vipllava
|
|
title: VipLlava
|
|
- 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
|
|
- local: model_doc/xclip
|
|
title: X-CLIP
|
|
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
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/autoformer
|
|
title: Autoformer
|
|
- local: model_doc/informer
|
|
title: Informer
|
|
- local: model_doc/patchtsmixer
|
|
title: PatchTSMixer
|
|
- local: model_doc/patchtst
|
|
title: PatchTST
|
|
- local: model_doc/time_series_transformer
|
|
title: Time Series Transformer
|
|
title: Time series models
|
|
- isExpanded: false
|
|
sections:
|
|
- local: model_doc/graphormer
|
|
title: Graphormer
|
|
title: Graph models
|
|
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
|
|
- local: internal/image_processing_utils
|
|
title: Utilities for Image Processors
|
|
- local: internal/audio_utils
|
|
title: Utilities for Audio processing
|
|
- local: internal/file_utils
|
|
title: General Utilities
|
|
- local: internal/time_series_utils
|
|
title: Utilities for Time Series
|
|
title: Internal Helpers
|
|
title: API
|