…

로드된 config 객체의 model_type 속성에 따라 인스턴스화할 configuration 클래스가 선택되며, 해당 속성이 없는 경우 pretrained_model_name_or_path에 대해 패턴 매칭을 사용하는 방식으로 폴백됩니다:

• EvollaModel — EvollaConfig (EvollaConfig 모델)
• afmoe — AfmoeConfig (AfmoeConfig 모델)
• aimv2 — Aimv2Config (Aimv2Config 모델)
• aimv2_text_model — Aimv2TextConfig (Aimv2TextConfig 모델)
• aimv2_vision_model — Aimv2VisionConfig (Aimv2VisionConfig 모델)
• albert — AlbertConfig (AlbertConfig 모델)
• align — AlignConfig (AlignConfig 모델)
• align_text_model — AlignTextConfig (AlignTextConfig 모델)
• align_vision_model — AlignVisionConfig (AlignVisionConfig 모델)
• altclip — AltCLIPConfig (AltCLIPConfig 모델)
• altclip_text_model — AltCLIPTextConfig (AltCLIPTextConfig 모델)
• altclip_vision_model — AltCLIPVisionConfig (AltCLIPVisionConfig 모델)
• apertus — ApertusConfig (ApertusConfig 모델)
• arcee — ArceeConfig (ArceeConfig 모델)
• aria — AriaConfig (AriaConfig 모델)
• aria_text — AriaTextConfig (AriaTextConfig 모델)
• audio-spectrogram-transformer — ASTConfig (ASTConfig 모델)
• audioflamingo3 — AudioFlamingo3Config (AudioFlamingo3Config 모델)
• audioflamingo3_encoder — AudioFlamingo3EncoderConfig (AudioFlamingo3EncoderConfig 모델)
• autoformer — AutoformerConfig (AutoformerConfig 모델)
• axk1 — AXK1Config (AXK1Config 모델)
• axk2 — AXK2Config (AXK2Config 모델)
• aya_vision — AyaVisionConfig (AyaVisionConfig 모델)
• bailing_hybrid — BailingHybridConfig (BailingHybridConfig 모델)
• bamba — BambaConfig (BambaConfig 모델)
• bark — BarkConfig (BarkConfig 모델)
• bart — BartConfig (BartConfig 모델)
• beam — BeamConfig (BeamConfig 모델)
• beit — BeitConfig (BeitConfig 모델)
• bert — BertConfig (BertConfig 모델)
• bert-generation — BertGenerationConfig (BertGenerationConfig 모델)
• big_bird — BigBirdConfig (BigBirdConfig 모델)
• bigbird_pegasus — BigBirdPegasusConfig (BigBirdPegasusConfig 모델)
• biogpt — BioGptConfig (BioGptConfig 모델)
• bit — BitConfig (BitConfig 모델)
• bitnet — BitNetConfig (BitNetConfig 모델)
• blenderbot — BlenderbotConfig (BlenderbotConfig 모델)
• blenderbot-small — BlenderbotSmallConfig (BlenderbotSmallConfig 모델)
• blip — BlipConfig (BlipConfig 모델)
• blip-2 — Blip2Config (Blip2Config 모델)
• blip_2_qformer — Blip2QFormerConfig (Blip2QFormerConfig 모델)
• blip_2_vision_model — Blip2VisionConfig (Blip2VisionConfig 모델)
• blip_text_model — BlipTextConfig (BlipTextConfig 모델)
• blip_vision_model — BlipVisionConfig (BlipVisionConfig 모델)
• bloom — BloomConfig (BloomConfig 모델)
• blt — BltConfig (BltConfig 모델)
• blt_global_transformer — BltGlobalTransformerConfig (BltGlobalTransformerConfig 모델)
• blt_local_decoder — BltLocalDecoderConfig (BltLocalDecoderConfig 모델)
• blt_local_encoder — BltLocalEncoderConfig (BltLocalEncoderConfig 모델)
• blt_patcher — BltPatcherConfig (BltPatcherConfig 모델)
• bridgetower — BridgeTowerConfig (BridgeTowerConfig 모델)
• bridgetower_text_model — BridgeTowerTextConfig (BridgeTowerTextConfig 모델)
• bridgetower_vision_model — BridgeTowerVisionConfig (BridgeTowerVisionConfig 모델)
• bros — BrosConfig (BrosConfig 모델)
• camembert — CamembertConfig (CamembertConfig 모델)
• canary — CanaryConfig (CanaryConfig 모델)
• canary_decoder — CanaryDecoderConfig (CanaryDecoderConfig 모델)
• canine — CanineConfig (CanineConfig 모델)
• chameleon — ChameleonConfig (ChameleonConfig 모델)
• chameleon_vqgan — ChameleonVQVAEConfig (ChameleonVQVAEConfig 모델)
• chinese_clip — ChineseCLIPConfig (ChineseCLIPConfig 모델)
• chinese_clip_text_model — ChineseCLIPTextConfig (ChineseCLIPTextConfig 모델)
• chinese_clip_vision_model — ChineseCLIPVisionConfig (ChineseCLIPVisionConfig 모델)
• chmv2 — CHMv2Config (CHMv2Config 모델)
• clap — ClapConfig (ClapConfig 모델)
• clap_audio_model — ClapAudioConfig (ClapAudioConfig 모델)
• clap_text_model — ClapTextConfig (ClapTextConfig 모델)
• clip — CLIPConfig (CLIPConfig 모델)
• clip_text_model — CLIPTextConfig (CLIPTextConfig 모델)
• clip_vision_model — CLIPVisionConfig (CLIPVisionConfig 모델)
• clipseg — CLIPSegConfig (CLIPSegConfig 모델)
• clipseg_text_model — CLIPSegTextConfig (CLIPSegTextConfig 모델)
• clipseg_vision_model — CLIPSegVisionConfig (CLIPSegVisionConfig 모델)
• clvp — ClvpConfig (ClvpConfig 모델)
• clvp_decoder — ClvpDecoderConfig (ClvpDecoderConfig 모델)
• clvp_encoder — ClvpEncoderConfig (ClvpEncoderConfig 모델)
• codegen — CodeGenConfig (CodeGenConfig 모델)
• cohere — CohereConfig (CohereConfig 모델)
• cohere2 — Cohere2Config (Cohere2Config 모델)
• cohere2_moe — Cohere2MoeConfig (Cohere2MoeConfig 모델)
• cohere2_vision — Cohere2VisionConfig (Cohere2VisionConfig 모델)
• cohere_asr — CohereAsrConfig (CohereAsrConfig 모델)
• cohere_compass — CohereCompassConfig (CohereCompassConfig 모델)
• cohere_compass_text — CohereCompassTextConfig (CohereCompassTextConfig 모델)
• cohere_compass_vision — CohereCompassVisionConfig (CohereCompassVisionConfig 모델)
• colmodernvbert — ColModernVBertConfig (ColModernVBertConfig 모델)
• colpali — ColPaliConfig (ColPaliConfig 모델)
• colqwen2 — ColQwen2Config (ColQwen2Config 모델)
• conditional_detr — ConditionalDetrConfig (ConditionalDetrConfig 모델)
• convbert — ConvBertConfig (ConvBertConfig 모델)
• convnext — ConvNextConfig (ConvNextConfig 모델)
• convnextv2 — ConvNextV2Config (ConvNextV2Config 모델)
• cosmos3_edge — Cosmos3EdgeConfig (Cosmos3EdgeConfig 모델)
• cosmos3_edge_text — Cosmos3EdgeTextConfig (Cosmos3EdgeTextConfig 모델)
• cosmos3_edge_vision — Cosmos3EdgeVisionConfig (Cosmos3EdgeVisionConfig 모델)
• cosmos3_omni — Cosmos3OmniConfig (Cosmos3OmniConfig 모델)
• cpmant — CpmAntConfig (CpmAntConfig 모델)
• csm — CsmConfig (CsmConfig 모델)
• csm_depth_decoder_model — CsmDepthDecoderConfig (CsmDepthDecoderConfig 모델)
• ctrl — CTRLConfig (CTRLConfig 모델)
• cvt — CvtConfig (CvtConfig 모델)
• cwm — CwmConfig (CwmConfig 모델)
• d_fine — DFineConfig (DFineConfig 모델)
• dab-detr — DabDetrConfig (DabDetrConfig 모델)
• dac — DacConfig (DacConfig 모델)
• data2vec-audio — Data2VecAudioConfig (Data2VecAudioConfig 모델)
• data2vec-text — Data2VecTextConfig (Data2VecTextConfig 모델)
• data2vec-vision — Data2VecVisionConfig (Data2VecVisionConfig 모델)
• dbrx — DbrxConfig (DbrxConfig 모델)
• deberta — DebertaConfig (DebertaConfig 모델)
• deberta-v2 — DebertaV2Config (DebertaV2Config 모델)
• decision_transformer — DecisionTransformerConfig (DecisionTransformerConfig 모델)
• deepseek_ocr2 — DeepseekOcr2Config (DeepseekOcr2Config 모델)
• deepseek_ocr2_encoder — DeepseekOcr2VisionEncoderConfig (DeepseekOcr2VisionEncoderConfig 모델)
• deepseek_ocr2_sam_vision_model — DeepseekOcr2SamVisionConfig (DeepseekOcr2SamVisionConfig 모델)
• deepseek_ocr2_text — DeepseekOcr2TextConfig (DeepseekOcr2TextConfig 모델)
• deepseek_ocr2_vision — DeepseekOcr2VisionConfig (DeepseekOcr2VisionConfig 모델)
• deepseek_v2 — DeepseekV2Config (DeepseekV2Config 모델)
• deepseek_v3 — DeepseekV3Config (DeepseekV3Config 모델)
• deepseek_v32 — DeepseekV32Config (DeepseekV32Config 모델)
• deepseek_v4 — DeepseekV4Config (DeepseekV4Config 모델)
• deepseek_vl — DeepseekVLConfig (DeepseekVLConfig 모델)
• deepseek_vl_hybrid — DeepseekVLHybridConfig (DeepseekVLHybridConfig 모델)
• deformable_detr — DeformableDetrConfig (DeformableDetrConfig 모델)
• deimv2 — Deimv2Config (Deimv2Config 모델)
• deit — DeiTConfig (DeiTConfig 모델)
• depth_anything — DepthAnythingConfig (DepthAnythingConfig 모델)
• depth_pro — DepthProConfig (DepthProConfig 모델)
• detr — DetrConfig (DetrConfig 모델)
• dia — DiaConfig (DiaConfig 모델)
• dia_decoder — DiaDecoderConfig (DiaDecoderConfig 모델)
• dia_encoder — DiaEncoderConfig (DiaEncoderConfig 모델)
• diffllama — DiffLlamaConfig (DiffLlamaConfig 모델)
• diffusion_gemma — DiffusionGemmaConfig (DiffusionGemmaConfig 모델)
• diffusion_gemma_text — DiffusionGemmaTextConfig (DiffusionGemmaTextConfig 모델)
• dinat — DinatConfig (DinatConfig 모델)
• dinov2 — Dinov2Config (Dinov2Config 모델)
• dinov2_with_registers — Dinov2WithRegistersConfig (Dinov2WithRegistersConfig 모델)
• dinov3_convnext — DINOv3ConvNextConfig (DINOv3ConvNextConfig 모델)
• dinov3_vit — DINOv3ViTConfig (DINOv3ViTConfig 모델)
• distilbert — DistilBertConfig (DistilBertConfig 모델)
• doge — DogeConfig (DogeConfig 모델)
• donut-swin — DonutSwinConfig (DonutSwinConfig 모델)
• dots1 — Dots1Config (Dots1Config 모델)
• dots3_note — Dots3NoteConfig (Dots3NoteConfig 모델)
• dots3_note_audio_encoder — Dots3NoteAudioConfig (Dots3NoteAudioConfig 모델)
• dots3_note_text — Dots3NoteTextConfig (Dots3NoteTextConfig 모델)
• dots3_note_vision_encoder — Dots3NoteVisionConfig (Dots3NoteVisionConfig 모델)
• dpr — DPRConfig (DPRConfig 모델)
• dpt — DPTConfig (DPTConfig 모델)
• edgetam — EdgeTamConfig (EdgeTamConfig 모델)
• edgetam_mask_decoder — EdgeTamMaskDecoderConfig (EdgeTamMaskDecoderConfig 모델)
• edgetam_prompt_encoder — EdgeTamPromptEncoderConfig (EdgeTamPromptEncoderConfig 모델)
• edgetam_video — EdgeTamVideoConfig (EdgeTamVideoConfig 모델)
• edgetam_video_mask_decoder — EdgeTamVideoMaskDecoderConfig (EdgeTamVideoMaskDecoderConfig 모델)
• edgetam_video_prompt_encoder — EdgeTamVideoPromptEncoderConfig (EdgeTamVideoPromptEncoderConfig 모델)
• edgetam_vision_model — EdgeTamVisionConfig (EdgeTamVisionConfig 모델)
• efficientloftr — EfficientLoFTRConfig (EfficientLoFTRConfig 모델)
• efficientnet — EfficientNetConfig (EfficientNetConfig 모델)
• electra — ElectraConfig (ElectraConfig 모델)
• embedding_gemma2 — EmbeddingGemma2Config (EmbeddingGemma2Config 모델)
• embedding_gemma2_text — EmbeddingGemma2TextConfig (EmbeddingGemma2TextConfig 모델)
• emu3 — Emu3Config (Emu3Config 모델)
• emu3_text_model — Emu3TextConfig (Emu3TextConfig 모델)
• emu3_vqgan — Emu3VQVAEConfig (Emu3VQVAEConfig 모델)
• encodec — EncodecConfig (EncodecConfig 모델)
• 인코더-디코더 — EncoderDecoderConfig (EncoderDecoderConfig 모델)
• eomt — EomtConfig (EomtConfig 모델)
• eomt_dinov3 — EomtDinov3Config (EomtDinov3Config 모델)
• ernie — ErnieConfig (ErnieConfig 모델)
• ernie4_5 — Ernie4_5Config (Ernie4_5Config 모델)
• ernie4_5_moe — Ernie4_5_MoeConfig (Ernie4_5_MoeConfig 모델)
• ernie4_5_vl_moe — Ernie4_5_VLMoeConfig (Ernie4_5_VLMoeConfig 모델)
• ernie4_5_vl_moe_text — Ernie4_5_VLMoeTextConfig (Ernie4_5_VLMoeTextConfig 모델)
• ernie4_5_vl_moe_vision — Ernie4_5_VLMoeVisionConfig (Ernie4_5_VLMoeVisionConfig 모델)
• esm — EsmConfig (EsmConfig 모델)
• esmc — EsmcConfig (EsmcConfig 모델)
• esmfold2 — EsmFold2Config (EsmFold2Config 모델)
• eurobert — EuroBertConfig (EuroBertConfig 모델)
• evolla — EvollaConfig (EvollaConfig 모델)
• exaone4 — Exaone4Config (Exaone4Config 모델)
• exaone4_5 — Exaone4_5_Config (Exaone4_5_Config 모델)
• exaone4_5_vision — Exaone4_5_VisionConfig (Exaone4_5_VisionConfig 모델)
• exaone_moe — ExaoneMoeConfig (ExaoneMoeConfig 모델)
• falcon — FalconConfig (FalconConfig 모델)
• falcon_h1 — FalconH1Config (FalconH1Config 모델)
• falcon_mamba — FalconMambaConfig (FalconMambaConfig 모델)
• fast_vlm — FastVlmConfig (FastVlmConfig 모델)
• fastspeech2_conformer — FastSpeech2ConformerConfig (FastSpeech2ConformerConfig 모델)
• fastspeech2_conformer_hifigan — FastSpeech2ConformerHifiGanConfig (FastSpeech2ConformerHifiGanConfig 모델)
• fastspeech2_conformer_with_hifigan — FastSpeech2ConformerWithHifiGanConfig (FastSpeech2ConformerWithHifiGanConfig 모델)
• flaubert — FlaubertConfig (FlaubertConfig 모델)
• flava — FlavaConfig (FlavaConfig 모델)
• flava_image_codebook — FlavaImageCodebookConfig (FlavaImageCodebookConfig 모델)
• flava_image_model — FlavaImageConfig (FlavaImageConfig 모델)
• flava_multimodal_model — FlavaMultimodalConfig (FlavaMultimodalConfig 모델)
• flava_text_model — FlavaTextConfig (FlavaTextConfig 모델)
• flex_olmo — FlexOlmoConfig (FlexOlmoConfig 모델)
• flint — FlintConfig (FlintConfig 모델)
• florence2 — Florence2Config (Florence2Config 모델)
• florence_vision — Florence2VisionConfig (Florence2VisionConfig 모델)
• fnet — FNetConfig (FNetConfig 모델)
• focalnet — FocalNetConfig (FocalNetConfig 모델)
• fsmt — FSMTConfig (FSMTConfig 모델)
• fun_asr_nano — FunAsrNanoConfig (FunAsrNanoConfig 모델)
• fun_asr_nano_encoder — FunAsrNanoEncoderConfig (FunAsrNanoEncoderConfig 모델)
• funnel — FunnelConfig (FunnelConfig 모델)
• fuyu — FuyuConfig (FuyuConfig 모델)
• gemma — GemmaConfig (GemmaConfig 모델)
• gemma2 — Gemma2Config (Gemma2Config 모델)
• gemma3 — Gemma3Config (Gemma3Config 모델)
• gemma3_text — Gemma3TextConfig (Gemma3TextConfig 모델)
• gemma3n — Gemma3nConfig (Gemma3nConfig 모델)
• gemma3n_audio — Gemma3nAudioConfig (Gemma3nAudioConfig 모델)
• gemma3n_text — Gemma3nTextConfig (Gemma3nTextConfig 모델)
• gemma3n_vision — Gemma3nVisionConfig (Gemma3nVisionConfig 모델)
• gemma4 — Gemma4Config (Gemma4Config 모델)
• gemma4_assistant — Gemma4AssistantConfig (Gemma4AssistantConfig 모델)
• gemma4_audio — Gemma4AudioConfig (Gemma4AudioConfig 모델)
• gemma4_text — Gemma4TextConfig (Gemma4TextConfig 모델)
• gemma4_unified — Gemma4UnifiedConfig (Gemma4UnifiedConfig 모델)
• gemma4_unified_assistant — Gemma4UnifiedAssistantConfig (Gemma4UnifiedAssistantConfig 모델)
• gemma4_unified_audio — Gemma4UnifiedAudioConfig (Gemma4UnifiedAudioConfig 모델)
• gemma4_unified_text — Gemma4UnifiedTextConfig (Gemma4UnifiedTextConfig 모델)
• gemma4_unified_vision — Gemma4UnifiedVisionConfig (Gemma4UnifiedVisionConfig 모델)
• gemma4_vision — Gemma4VisionConfig (Gemma4VisionConfig 모델)
• git — GitConfig (GitConfig 모델)
• git_vision_model — GitVisionConfig (GitVisionConfig 모델)
• glm — GlmConfig (GlmConfig 모델)
• glm4 — Glm4Config (Glm4Config 모델)
• glm46v — Glm46VConfig (Glm46VConfig 모델)
• glm4_moe — Glm4MoeConfig (Glm4MoeConfig 모델)
• glm4_moe_lite — Glm4MoeLiteConfig (Glm4MoeLiteConfig 모델)
• glm4v — Glm4vConfig (Glm4vConfig 모델)
• glm4v_moe — Glm4vMoeConfig (Glm4vMoeConfig 모델)
• glm4v_moe_text — Glm4vMoeTextConfig (Glm4vMoeTextConfig 모델)
• glm4v_moe_vision — Glm4vMoeVisionConfig (Glm4vMoeVisionConfig 모델)
• glm4v_text — Glm4vTextConfig (Glm4vTextConfig 모델)
• glm4v_vision — Glm4vVisionConfig (Glm4vVisionConfig 모델)
• glm5_next — Glm5NextConfig (Glm5NextConfig 모델)
• glm5_next_text — Glm5NextTextConfig (Glm5NextTextConfig 모델)
• glm5_next_vision — Glm5NextVisionConfig (Glm5NextVisionConfig 모델)
• glm_image — GlmImageConfig (GlmImageConfig 모델)
• glm_image_text — GlmImageTextConfig (GlmImageTextConfig 모델)
• glm_image_vision — GlmImageVisionConfig (GlmImageVisionConfig 모델)
• glm_image_vqmodel — GlmImageVQVAEConfig (GlmImageVQVAEConfig 모델)
• glm_moe_dsa — GlmMoeDsaConfig (GlmMoeDsaConfig 모델)
• glm_ocr — GlmOcrConfig (GlmOcrConfig 모델)
• glm_ocr_text — GlmOcrTextConfig (GlmOcrTextConfig 모델)
• glm_ocr_vision — GlmOcrVisionConfig (GlmOcrVisionConfig 모델)
• glmasr — GlmAsrConfig (GlmAsrConfig 모델)
• glmasr_encoder — GlmAsrEncoderConfig (GlmAsrEncoderConfig 모델)
• glmga — GlmgaConfig (GlmgaConfig 모델)
• glpn — GLPNConfig (GLPNConfig 모델)
• got_ocr2 — GotOcr2Config (GotOcr2Config 모델)
• got_ocr2_vision — GotOcr2VisionConfig (GotOcr2VisionConfig 모델)
• gpt-sw3 — GPT2Config (GPT2Config 모델)
• gpt2 — GPT2Config (GPT2Config 모델)
• gpt_bigcode — GPTBigCodeConfig (GPTBigCodeConfig 모델)
• gpt_neo — GPTNeoConfig (GPTNeoConfig 모델)
• gpt_neox — GPTNeoXConfig (GPTNeoXConfig 모델)
• gpt_neox_japanese — GPTNeoXJapaneseConfig (GPTNeoXJapaneseConfig 모델)
• gpt_oss — GptOssConfig (GptOssConfig 모델)
• gptj — GPTJConfig (GPTJConfig 모델)
• gradium_phonon_tts — GradiumPhononTTSConfig (GradiumPhononTTSConfig 모델)
• granite — GraniteConfig (GraniteConfig 모델)
• granite4_vision — Granite4VisionConfig (Granite4VisionConfig 모델)
• granite4_vision_text — Granite4VisionTextConfig (Granite4VisionTextConfig 모델)
• granite_docling — GraniteDoclingConfig (GraniteDoclingConfig 모델)
• granite_docling_text — GraniteDoclingTextConfig (GraniteDoclingTextConfig 모델)
• granite_docling_vision — GraniteDoclingVisionConfig (GraniteDoclingVisionConfig 모델)
• granite_speech — GraniteSpeechConfig (GraniteSpeechConfig 모델)
• granite_speech5_ctc — GraniteSpeech5CTCConfig (GraniteSpeech5CTCConfig 모델)
• granite_speech5_encoder — GraniteSpeech5EncoderConfig (GraniteSpeech5EncoderConfig 모델)
• granite_speech_encoder — GraniteSpeechEncoderConfig (GraniteSpeechEncoderConfig 모델)
• granite_speech_plus — GraniteSpeechPlusConfig (GraniteSpeechPlusConfig 모델)
• granite_speech_plus_encoder — GraniteSpeechPlusEncoderConfig (GraniteSpeechPlusEncoderConfig 모델)
• granite_swa — GraniteSWAConfig (GraniteSWAConfig 모델)
• granitemoe — GraniteMoeConfig (GraniteMoeConfig 모델)
• granitemoe_swa — GraniteMoeSWAConfig (GraniteMoeSWAConfig 모델)
• granitemoehybrid — GraniteMoeHybridConfig (GraniteMoeHybridConfig 모델)
• granitemoeshared — GraniteMoeSharedConfig (GraniteMoeSharedConfig 모델)
• grounding-dino — GroundingDinoConfig (GroundingDinoConfig 모델)
• groupvit — GroupViTConfig (GroupViTConfig 모델)
• groupvit_text_model — GroupViTTextConfig (GroupViTTextConfig 모델)
• groupvit_vision_model — GroupViTVisionConfig (GroupViTVisionConfig 모델)
• gte — GteConfig (GteConfig 모델)
• helium — HeliumConfig (HeliumConfig 모델)
• hgnet_v2 — HGNetV2Config (HGNetV2Config 모델)
• hiera — HieraConfig (HieraConfig 모델)
• higgs_audio_v2 — HiggsAudioV2Config (HiggsAudioV2Config 모델)
• higgs_audio_v2_tokenizer — HiggsAudioV2TokenizerConfig (HiggsAudioV2TokenizerConfig 모델)
• hrm_text — HrmTextConfig (HrmTextConfig 모델)
• hubert — HubertConfig (HubertConfig 모델)
• hunyuan_v1_dense — HunYuanDenseV1Config (HunYuanDenseV1Config 모델)
• hunyuan_v1_moe — HunYuanMoEV1Config (HunYuanMoEV1Config 모델)
• hunyuan_vl — HunYuanVLConfig (HunYuanVLConfig 모델)
• hunyuan_vl_text — HunYuanVLTextConfig (HunYuanVLTextConfig 모델)
• hunyuan_vl_vision — HunYuanVLVisionConfig (HunYuanVLVisionConfig 모델)
• hy_v3 — HYV3Config (HYV3Config 모델)
• hy_v4 — HYV4Config (HYV4Config 모델)
• hyperclovax — HyperCLOVAXConfig (HyperCLOVAXConfig 모델)
• hyperclovax_vision_v2 — HyperCLOVAXVisionV2Config (HyperCLOVAXVisionV2Config 모델)
• ibert — IBertConfig (IBertConfig 모델)
• idefics — IdeficsConfig (IdeficsConfig 모델)
• idefics2 — Idefics2Config (Idefics2Config 모델)
• idefics2_perceiver — Idefics2PerceiverConfig (Idefics2PerceiverConfig 모델)
• idefics2_vision — Idefics2VisionConfig (Idefics2VisionConfig 모델)
• idefics3 — Idefics3Config (Idefics3Config 모델)
• idefics3_vision — Idefics3VisionConfig (Idefics3VisionConfig 모델)
• idefics_perciever — IdeficsPerceiverConfig (IdeficsPerceiverConfig 모델)
• idefics_vision — IdeficsVisionConfig (IdeficsVisionConfig 모델)
• ijepa — IJepaConfig (IJepaConfig 모델)
• imagegpt — ImageGPTConfig (ImageGPTConfig 모델)
• informer — InformerConfig (InformerConfig 모델)
• inkling2 — Inkling2Config (Inkling2Config 모델)
• inkling2_text — Inkling2TextConfig (Inkling2TextConfig 모델)
• inkling2_vision — Inkling2VisionConfig (Inkling2VisionConfig 모델)
• inkling_audio — InklingAudioConfig (InklingAudioConfig 모델)
• inkling_mm_model — InklingConfig (InklingConfig 모델)
• inkling_text — InklingTextConfig (InklingTextConfig 모델)
• inkling_vision — InklingVisionConfig (InklingVisionConfig 모델)
• instructblip — InstructBlipConfig (InstructBlipConfig 모델)
• instructblip_qformer — InstructBlipQFormerConfig (InstructBlipQFormerConfig 모델)
• instructblip_vision_model — InstructBlipVisionConfig (InstructBlipVisionConfig 모델)
• instructblipvideo — InstructBlipVideoConfig (InstructBlipVideoConfig 모델)
• instructblipvideo_qformer — InstructBlipVideoQFormerConfig (InstructBlipVideoQFormerConfig 모델)
• instructblipvideo_vision_model — InstructBlipVideoVisionConfig (InstructBlipVideoVisionConfig 모델)
• internlm3 — InternLM3Config (InternLM3Config 모델)
• internvl — InternVLConfig (InternVLConfig 모델)
• internvl_vision — InternVLVisionConfig (InternVLVisionConfig 모델)
• iquestcoder — IQuestCoderConfig (IQuestCoderConfig 모델)
• jais2 — Jais2Config (Jais2Config 모델)
• jamba — JambaConfig (JambaConfig 모델)
• janus — JanusConfig (JanusConfig 모델)
• janus_vision_model — JanusVisionConfig (JanusVisionConfig 모델)
• janus_vqgan — JanusVQVAEConfig (JanusVQVAEConfig 모델)
• jetmoe — JetMoeConfig (JetMoeConfig 모델)
• jev — JevConfig (JevConfig 모델)
• jina_embeddings_v3 — JinaEmbeddingsV3Config (JinaEmbeddingsV3Config 모델)
• kimi_k25 — Kimi_K25Config (Kimi_K25Config 모델)
• kimi_k25_vision — Kimi_K25VisionConfig (Kimi_K25VisionConfig 모델)
• kimi_linear — KimiLinearConfig (KimiLinearConfig 모델)
• kolibri1 — Kolibri1Config (Kolibri1Config 모델)
• kosmos-2 — Kosmos2Config (Kosmos2Config 모델)
• kosmos-2.5 — Kosmos2_5Config (Kosmos2_5Config 모델)
• kosmos_2_5_text_model — Kosmos2_5TextConfig (Kosmos2_5TextConfig 모델)
• kosmos_2_5_vision_model — Kosmos2_5VisionConfig (Kosmos2_5VisionConfig 모델)
• kosmos_2_text_model — Kosmos2TextConfig (Kosmos2TextConfig 모델)
• kosmos_2_vision_model — Kosmos2VisionConfig (Kosmos2VisionConfig 모델)
• kyutai_speech_to_text — KyutaiSpeechToTextConfig (KyutaiSpeechToTextConfig 모델)
• laguna — LagunaConfig (LagunaConfig 모델)
• lasr_ctc — LasrCTCConfig (LasrCTCConfig 모델)
• lasr_encoder — LasrEncoderConfig (LasrEncoderConfig 모델)
• layoutlm — LayoutLMConfig (LayoutLMConfig 모델)
• layoutlmv2 — LayoutLMv2Config (LayoutLMv2Config 모델)
• layoutlmv3 — LayoutLMv3Config (LayoutLMv3Config 모델)
• layoutxlm — LayoutXLMConfig (LayoutXLMConfig 모델)
• led — LEDConfig (LEDConfig 모델)
• levit — LevitConfig (LevitConfig 모델)
• lfm2 — Lfm2Config (Lfm2Config 모델)
• lfm2_moe — Lfm2MoeConfig (Lfm2MoeConfig 모델)
• lfm2_vl — Lfm2VlConfig (Lfm2VlConfig 모델)
• lfm3 — Lfm3Config (Lfm3Config 모델)
• lfm3_vl — Lfm3VlConfig (Lfm3VlConfig 모델)
• lfm3_vl_vision — Lfm3VlVisionConfig (Lfm3VlVisionConfig 모델)
• lightglue — LightGlueConfig (LightGlueConfig 모델)
• lighton_ocr — LightOnOcrConfig (LightOnOcrConfig 모델)
• lilt — LiltConfig (LiltConfig 모델)
• llama — LlamaConfig (LlamaConfig 모델)
• llama4 — Llama4Config (Llama4Config 모델)
• llama4_text — Llama4TextConfig (Llama4TextConfig 모델)
• llama4_vision_model — Llama4VisionConfig (Llama4VisionConfig 모델)
• llava — LlavaConfig (LlavaConfig 모델)
• llava_next — LlavaNextConfig (LlavaNextConfig 모델)
• llava_next_video — LlavaNextVideoConfig (LlavaNextVideoConfig 모델)
• llava_onevision — LlavaOnevisionConfig (LlavaOnevisionConfig 모델)
• longcat_flash — LongcatFlashConfig (LongcatFlashConfig 모델)
• longformer — LongformerConfig (LongformerConfig 모델)
• longt5 — LongT5Config (LongT5Config 모델)
• luke — LukeConfig (LukeConfig 모델)
• lw_detr — LwDetrConfig (LwDetrConfig 모델)
• lw_detr_vit — LwDetrViTConfig (LwDetrViTConfig 모델)
• lxmert — LxmertConfig (LxmertConfig 모델)
• m2m_100 — M2M100Config (M2M100Config 모델)
• mamba — MambaConfig (MambaConfig 모델)
• mamba2 — Mamba2Config (Mamba2Config 모델)
• marian — MarianConfig (MarianConfig 모델)
• markuplm — MarkupLMConfig (MarkupLMConfig 모델)
• mask2former — Mask2FormerConfig (Mask2FormerConfig 모델)
• maskformer — MaskFormerConfig (MaskFormerConfig 모델)
• maskformer-swin — MaskFormerSwinConfig (MaskFormerSwinConfig 모델)
• mbart — MBartConfig (MBartConfig 모델)
• megatron-bert — MegatronBertConfig (MegatronBertConfig 모델)
• mellum — MellumConfig (MellumConfig 모델)
• metaclip_2 — MetaClip2Config (MetaClip2Config 모델)
• metaclip_2_text_model — MetaClip2TextConfig (MetaClip2TextConfig 모델)
• metaclip_2_vision_model — MetaClip2VisionConfig (MetaClip2VisionConfig 모델)
• mgp-str — MgpstrConfig (MgpstrConfig 모델)
• mimi — MimiConfig (MimiConfig 모델)
• mimi_decoder — MimiDecoderConfig (MimiDecoderConfig 모델)
• mimi_encoder — MimiEncoderConfig (MimiEncoderConfig 모델)
• mimo_v2_flash — MiMoV2FlashConfig (MiMoV2FlashConfig 모델)
• minicpm3 — MiniCPM3Config (MiniCPM3Config 모델)
• minicpm_ocr — MiniCPMOcrConfig (MiniCPMOcrConfig 모델)
• minicpm_ocr_vision — MiniCPMOcrVisionConfig (MiniCPMOcrVisionConfig 모델)
• minicpmv4_6 — MiniCPMV4_6Config (MiniCPMV4_6Config 모델)
• minicpmv4_6_vision — MiniCPMV4_6VisionConfig (MiniCPMV4_6VisionConfig 모델)
• minicpmv4_7 — MiniCPMV4_7Config (MiniCPMV4_7Config 모델)
• minicpmv4_7_vision — MiniCPMV4_7VisionConfig (MiniCPMV4_7VisionConfig 모델)
• minimax — MiniMaxConfig (MiniMaxConfig 모델)
• minimax_m2 — MiniMaxM2Config (MiniMaxM2Config 모델)
• minimax_m3_vl — MiniMaxM3VLConfig (MiniMaxM3VLConfig 모델)
• minimax_m3_vl_text — MiniMaxM3VLTextConfig (MiniMaxM3VLTextConfig 모델)
• minimax_m3_vl_vision — MiniMaxM3VLVisionConfig (MiniMaxM3VLVisionConfig 모델)
• ministral — MinistralConfig (MinistralConfig 모델)
• ministral3 — Ministral3Config (Ministral3Config 모델)
• mistral — MistralConfig (MistralConfig 모델)
• mistral3 — Mistral3Config (Mistral3Config 모델)
• mistral4 — Mistral4Config (Mistral4Config 모델)
• mistral_large4 — MistralLarge4Config (MistralLarge4Config 모델)
• mistral_large4_text — MistralLarge4TextConfig (MistralLarge4TextConfig 모델)
• mixtral — MixtralConfig (MixtralConfig 모델)
• mlcd — MLCDVisionConfig (MLCDVisionConfig 모델)
• mlcd_vision_model — MLCDVisionConfig (MLCDVisionConfig 모델)
• mllama — MllamaConfig (MllamaConfig 모델)
• mllama_text_model — MllamaTextConfig (MllamaTextConfig 모델)
• mllama_vision_model — MllamaVisionConfig (MllamaVisionConfig 모델)
• mm-grounding-dino — MMGroundingDinoConfig (MMGroundingDinoConfig 모델)
• mobilebert — MobileBertConfig (MobileBertConfig 모델)
• mobilenet_v1 — MobileNetV1Config (MobileNetV1Config 모델)
• mobilenet_v2 — MobileNetV2Config (MobileNetV2Config 모델)
• mobilevit — MobileViTConfig (MobileViTConfig 모델)
• mobilevitv2 — MobileViTV2Config (MobileViTV2Config 모델)
• modernbert — ModernBertConfig (ModernBertConfig 모델)
• modernbert-decoder — ModernBertDecoderConfig (ModernBertDecoderConfig 모델)
• modernvbert — ModernVBertConfig (ModernVBertConfig 모델)
• molmo2 — Molmo2Config (Molmo2Config 모델)
• molmo2_adapter — Molmo2AdapterConfig (Molmo2AdapterConfig 모델)
• molmo2_text — Molmo2TextConfig (Molmo2TextConfig 모델)
• molmo2_vision — Molmo2VisionConfig (Molmo2VisionConfig 모델)
• moonshine — MoonshineConfig (MoonshineConfig 모델)
• moonshine_streaming — MoonshineStreamingConfig (MoonshineStreamingConfig 모델)
• moonshine_streaming_encoder — MoonshineStreamingEncoderConfig (MoonshineStreamingEncoderConfig 모델)
• moshi — MoshiConfig (MoshiConfig 모델)
• moshi_depth — MoshiDepthConfig (MoshiDepthConfig 모델)
• moss_transcribe_diarize — MossTranscribeDiarizeConfig (MossTranscribeDiarizeConfig 모델)
• moss_transcribe_diarize_audio — MossTranscribeDiarizeAudioConfig (MossTranscribeDiarizeAudioConfig 모델)
• mpnet — MPNetConfig (MPNetConfig 모델)
• mpt — MptConfig (MptConfig 모델)
• mra — MraConfig (MraConfig 모델)
• mt5 — MT5Config (MT5Config 모델)
• muse_glimmer — MuseGlimmerConfig (MuseGlimmerConfig 모델)
• muse_glimmer_assistant — MuseGlimmerAssistantConfig (MuseGlimmerAssistantConfig 모델)
• muse_glimmer_text — MuseGlimmerTextConfig (MuseGlimmerTextConfig 모델)
• muse_glimmer_vision — MuseGlimmerVisionConfig (MuseGlimmerVisionConfig 모델)
• muse_spark — MuseSparkConfig (MuseSparkConfig 모델)
• muse_spark_audio — MuseSparkAudioConfig (MuseSparkAudioConfig 모델)
• muse_spark_text — MuseSparkTextConfig (MuseSparkTextConfig 모델)
• muse_spark_vision — MuseSparkVisionConfig (MuseSparkVisionConfig 모델)
• musicflamingo — MusicFlamingoConfig (MusicFlamingoConfig 모델)
• musicgen — MusicgenConfig (MusicgenConfig 모델)
• musicgen_decoder — MusicgenDecoderConfig (MusicgenDecoderConfig 모델)
• musicgen_melody — MusicgenMelodyConfig (MusicgenMelodyConfig 모델)
• musicgen_melody_decoder — MusicgenMelodyDecoderConfig (MusicgenMelodyDecoderConfig 모델)
• mvp — MvpConfig (MvpConfig 모델)
• nanochat — NanoChatConfig (NanoChatConfig 모델)
• nemo_speechlm — Nemotron3_5TranscribeConfig (Nemotron3_5TranscribeConfig 모델)
• nemotron — NemotronConfig (NemotronConfig 모델)
• nemotron3_5_asr — Nemotron3_5AsrConfig (Nemotron3_5AsrConfig 모델)
• nemotron3_5_transcribe_asr_audio — Nemotron3_5TranscribeAsrAudioConfig (Nemotron3_5TranscribeAsrAudioConfig 모델)
• nemotron3_5_transcribe_audio — Nemotron3_5TranscribeAudioConfig (Nemotron3_5TranscribeAudioConfig 모델)
• nemotron3_5_transcribe_word_timestamp — Nemotron3_5TranscribeWordTimestampConfig (Nemotron3_5TranscribeWordTimestampConfig 모델)
• nemotron3_diarization — Nemotron3DiarizationConfig (Nemotron3DiarizationConfig 모델)
• nemotron3_diarization_audio — Nemotron3DiarizationAudioConfig (Nemotron3DiarizationAudioConfig 모델)
• nemotron_asr_streaming — NemotronAsrStreamingConfig (NemotronAsrStreamingConfig 모델)
• nemotron_asr_streaming_encoder — NemotronAsrStreamingEncoderConfig (NemotronAsrStreamingEncoderConfig 모델)
• nemotron_h — NemotronHConfig (NemotronHConfig 모델)
• nemotron_h_omni — NemotronH_Omni_Reasoning_V3_Config (NemotronH_Omni_Reasoning_V3_Config 모델)
• neomme — NeoMMEConfig (NeoMMEConfig 모델)
• neucodec — NeuCodecConfig (NeuCodecConfig 모델)
• nllb-moe — NllbMoeConfig (NllbMoeConfig 모델)
• nomic_bert — NomicBertConfig (NomicBertConfig 모델)
• nougat — NougatConfig (NougatConfig 모델)
• nystromformer — NystromformerConfig (NystromformerConfig 모델)
• olmo — OlmoConfig (OlmoConfig 모델)
• olmo2 — Olmo2Config (Olmo2Config 모델)
• olmo3 — Olmo3Config (Olmo3Config 모델)
• olmo_hybrid — OlmoHybridConfig (OlmoHybridConfig 모델)
• olmoe — OlmoeConfig (OlmoeConfig 모델)
• omdet-turbo — OmDetTurboConfig (OmDetTurboConfig 모델)
• oneformer — OneFormerConfig (OneFormerConfig 모델)
• openai-gpt — OpenAIGPTConfig (OpenAIGPTConfig 모델)
• openai_privacy_filter — OpenAIPrivacyFilterConfig (OpenAIPrivacyFilterConfig 모델)
• opt — OPTConfig (OPTConfig 모델)
• ovis2 — Ovis2Config (Ovis2Config 모델)
• ovis2_vision — Ovis2VisionConfig (Ovis2VisionConfig 모델)
• owlv2 — Owlv2Config (Owlv2Config 모델)
• owlv2_text_model — Owlv2TextConfig (Owlv2TextConfig 모델)
• owlv2_vision_model — Owlv2VisionConfig (Owlv2VisionConfig 모델)
• owlvit — OwlViTConfig (OwlViTConfig 모델)
• owlvit_text_model — OwlViTTextConfig (OwlViTTextConfig 모델)
• owlvit_vision_model — OwlViTVisionConfig (OwlViTVisionConfig 모델)
• paddleocr_vl — PaddleOCRVLConfig (PaddleOCRVLConfig 모델)
• paddleocr_vl_text — PaddleOCRTextConfig (PaddleOCRTextConfig 모델)
• paddleocr_vl_vision — PaddleOCRVisionConfig (PaddleOCRVisionConfig 모델)
• paligemma — PaliGemmaConfig (PaliGemmaConfig 모델)
• parakeet_ctc — ParakeetCTCConfig (ParakeetCTCConfig 모델)
• parakeet_encoder — ParakeetEncoderConfig (ParakeetEncoderConfig 모델)
• parakeet_rnnt — ParakeetRNNTConfig (ParakeetRNNTConfig 모델)
• parakeet_tdt — ParakeetTDTConfig (ParakeetTDTConfig 모델)
• patchtsmixer — PatchTSMixerConfig (PatchTSMixerConfig 모델)
• patchtst — PatchTSTConfig (PatchTSTConfig 모델)
• pe_audio — PeAudioConfig (PeAudioConfig 모델)
• pe_audio_encoder — PeAudioEncoderConfig (PeAudioEncoderConfig 모델)
• pe_audio_video — PeAudioVideoConfig (PeAudioVideoConfig 모델)
• pe_audio_video_encoder — PeAudioVideoEncoderConfig (PeAudioVideoEncoderConfig 모델)
• pe_video — PeVideoConfig (PeVideoConfig 모델)
• pe_video_encoder — PeVideoEncoderConfig (PeVideoEncoderConfig 모델)
• pegasus — PegasusConfig (PegasusConfig 모델)
• pegasus_x — PegasusXConfig (PegasusXConfig 모델)
• perceiver — PerceiverConfig (PerceiverConfig 모델)
• perception_lm — PerceptionLMConfig (PerceptionLMConfig 모델)
• persimmon — PersimmonConfig (PersimmonConfig 모델)
• phi — PhiConfig (PhiConfig 모델)
• phi3 — Phi3Config (Phi3Config 모델)
• phi4_multimodal — Phi4MultimodalConfig (Phi4MultimodalConfig 모델)
• phi4_multimodal_audio — Phi4MultimodalAudioConfig (Phi4MultimodalAudioConfig 모델)
• phi4_multimodal_vision — Phi4MultimodalVisionConfig (Phi4MultimodalVisionConfig 모델)
• phimoe — PhimoeConfig (PhimoeConfig 모델)
• pi0 — PI0Config (PI0Config 모델)
• pix2struct — Pix2StructConfig (Pix2StructConfig 모델)
• pix2struct_text_model — Pix2StructTextConfig (Pix2StructTextConfig 모델)
• pix2struct_vision_model — Pix2StructVisionConfig (Pix2StructVisionConfig 모델)
• pixio — PixioConfig (PixioConfig 모델)
• pixtral — PixtralVisionConfig (PixtralVisionConfig 모델)
• plbart — PLBartConfig (PLBartConfig 모델)
• pocket_tts — PocketTTSConfig (PocketTTSConfig 모델)
• pocket_tts_audio_tokenizer — PocketTTSAudioTokenizerConfig (PocketTTSAudioTokenizerConfig 모델)
• pocket_tts_audio_tokenizer_decoder — PocketTTSAudioTokenizerDecoderConfig (PocketTTSAudioTokenizerDecoderConfig 모델)
• pocket_tts_audio_tokenizer_encoder — PocketTTSAudioTokenizerEncoderConfig (PocketTTSAudioTokenizerEncoderConfig 모델)
• poolformer — PoolFormerConfig (PoolFormerConfig 모델)
• pop2piano — Pop2PianoConfig (Pop2PianoConfig 모델)
• pp_chart2table — PPChart2TableConfig (PPChart2TableConfig 모델)
• pp_chart2table_vision — PPChart2TableVisionConfig (PPChart2TableVisionConfig 모델)
• pp_doclayout_v2 — PPDocLayoutV2Config (PPDocLayoutV2Config 모델)
• pp_doclayout_v3 — PPDocLayoutV3Config (PPDocLayoutV3Config 모델)
• pp_doclayout_v4 — PPDocLayoutV4Config (PPDocLayoutV4Config 모델)
• pp_formulanet — PPFormulaNetConfig (PPFormulaNetConfig 모델)
• pp_formulanet_text — PPFormulaNetTextConfig (PPFormulaNetTextConfig 모델)
• pp_formulanet_vision — PPFormulaNetVisionConfig (PPFormulaNetVisionConfig 모델)
• pp_lcnet — PPLCNetConfig (PPLCNetConfig 모델)
• pp_lcnet_v3 — PPLCNetV3Config (PPLCNetV3Config 모델)
• pp_lcnet_v4 — PPLCNetV4Config (PPLCNetV4Config 모델)
• pp_ocrv5_mobile_det — PPOCRV5MobileDetConfig (PPOCRV5MobileDetConfig 모델)
• pp_ocrv5_mobile_rec — PPOCRV5MobileRecConfig (PPOCRV5MobileRecConfig 모델)
• pp_ocrv5_server_det — PPOCRV5ServerDetConfig (PPOCRV5ServerDetConfig 모델)
• pp_ocrv5_server_rec — PPOCRV5ServerRecConfig (PPOCRV5ServerRecConfig 모델)
• pp_ocrv6_medium_det — PPOCRV6MediumDetConfig (PPOCRV6MediumDetConfig 모델)
• pp_ocrv6_small_det — PPOCRV6SmallDetConfig (PPOCRV6SmallDetConfig 모델)
• pp_ocrv6_small_rec — PPOCRV6SmallRecConfig (PPOCRV6SmallRecConfig 모델)
• pp_ocrv6_tiny_rec — PPOCRV6TinyRecConfig (PPOCRV6TinyRecConfig 모델)
• prompt_depth_anything — PromptDepthAnythingConfig (PromptDepthAnythingConfig 모델)
• prophetnet — ProphetNetConfig (ProphetNetConfig 모델)
• pvt — PvtConfig (PvtConfig 모델)
• pvt_v2 — PvtV2Config (PvtV2Config 모델)
• qianfan_ocr — QianfanOCRConfig (QianfanOCRConfig 모델)
• qianfan_ocr_vision — QianfanOCRVisionConfig (QianfanOCRVisionConfig 모델)
• qwen2 — Qwen2Config (Qwen2Config 모델)
• qwen2_5_omni — Qwen2_5OmniConfig (Qwen2_5OmniConfig 모델)
• qwen2_5_omni_audio_encoder — Qwen2_5OmniAudioEncoderConfig (Qwen2_5OmniAudioEncoderConfig 모델)
• qwen2_5_omni_bigvgan — Qwen2_5OmniBigVGANConfig (Qwen2_5OmniBigVGANConfig 모델)
• qwen2_5_omni_dit — Qwen2_5OmniDiTConfig (Qwen2_5OmniDiTConfig 모델)
• qwen2_5_omni_talker — Qwen2_5OmniTalkerConfig (Qwen2_5OmniTalkerConfig 모델)
• qwen2_5_omni_text — Qwen2_5OmniTextConfig (Qwen2_5OmniTextConfig 모델)
• qwen2_5_omni_thinker — Qwen2_5OmniThinkerConfig (Qwen2_5OmniThinkerConfig 모델)
• qwen2_5_omni_token2wav — Qwen2_5OmniToken2WavConfig (Qwen2_5OmniToken2WavConfig 모델)
• qwen2_5_omni_vision_encoder — Qwen2_5OmniVisionEncoderConfig (Qwen2_5OmniVisionEncoderConfig 모델)
• qwen2_5_vl — Qwen2_5_VLConfig (Qwen2_5_VLConfig 모델)
• qwen2_5_vl_text — Qwen2_5_VLTextConfig (Qwen2_5_VLTextConfig 모델)
• qwen2_5_vl_vision — Qwen2_5_VLVisionConfig (Qwen2_5_VLVisionConfig 모델)
• qwen2_audio — Qwen2AudioConfig (Qwen2AudioConfig 모델)
• qwen2_audio_encoder — Qwen2AudioEncoderConfig (Qwen2AudioEncoderConfig 모델)
• qwen2_moe — Qwen2MoeConfig (Qwen2MoeConfig 모델)
• qwen2_vl — Qwen2VLConfig (Qwen2VLConfig 모델)
• qwen2_vl_text — Qwen2VLTextConfig (Qwen2VLTextConfig 모델)
• qwen2_vl_vision — Qwen2VLVisionConfig (Qwen2VLVisionConfig 모델)
• qwen3 — Qwen3Config (Qwen3Config 모델)
• qwen3_5 — Qwen3_5Config (Qwen3_5Config 모델)
• qwen3_5_moe — Qwen3_5MoeConfig (Qwen3_5MoeConfig 모델)
• qwen3_5_moe_text — Qwen3_5MoeTextConfig (Qwen3_5MoeTextConfig 모델)
• qwen3_5_moe_vision — Qwen3_5MoeVisionConfig (Qwen3_5MoeVisionConfig 모델)
• qwen3_5_text — Qwen3_5TextConfig (Qwen3_5TextConfig 모델)
• qwen3_5_vision — Qwen3_5VisionConfig (Qwen3_5VisionConfig 모델)
• qwen3_asr — Qwen3ASRConfig (Qwen3ASRConfig 모델)
• qwen3_asr_encoder — Qwen3ASREncoderConfig (Qwen3ASREncoderConfig 모델)
• qwen3_moe — Qwen3MoeConfig (Qwen3MoeConfig 모델)
• qwen3_next — Qwen3NextConfig (Qwen3NextConfig 모델)
• qwen3_omni_moe — Qwen3OmniMoeConfig (Qwen3OmniMoeConfig 모델)
• qwen3_omni_moe_audio_encoder — Qwen3OmniMoeAudioEncoderConfig (Qwen3OmniMoeAudioEncoderConfig 모델)
• qwen3_omni_moe_talker_code_predictor — Qwen3OmniMoeTalkerCodePredictorConfig (Qwen3OmniMoeTalkerCodePredictorConfig 모델)
• qwen3_omni_moe_talker_text — Qwen3OmniMoeTalkerTextConfig (Qwen3OmniMoeTalkerTextConfig 모델)
• qwen3_omni_moe_text — Qwen3OmniMoeTextConfig (Qwen3OmniMoeTextConfig 모델)
• qwen3_omni_moe_thinker — Qwen3OmniMoeThinkerConfig (Qwen3OmniMoeThinkerConfig 모델)
• qwen3_omni_moe_vision_encoder — Qwen3OmniMoeVisionEncoderConfig (Qwen3OmniMoeVisionEncoderConfig 모델)
• qwen3_vl — Qwen3VLConfig (Qwen3VLConfig 모델)
• qwen3_vl_moe — Qwen3VLMoeConfig (Qwen3VLMoeConfig 모델)
• qwen3_vl_moe_text — Qwen3VLMoeTextConfig (Qwen3VLMoeTextConfig 모델)
• qwen3_vl_moe_vision — Qwen3VLMoeVisionConfig (Qwen3VLMoeVisionConfig 모델)
• qwen3_vl_text — Qwen3VLTextConfig (Qwen3VLTextConfig 모델)
• qwen3_vl_vision — Qwen3VLVisionConfig (Qwen3VLVisionConfig 모델)
• qwen4_exp — Qwen4ExpConfig (Qwen4ExpConfig 모델)
• qwen4_exp_text — Qwen4ExpTextConfig (Qwen4ExpTextConfig 모델)
• qwen4_exp_vision — Qwen4ExpVisionConfig (Qwen4ExpVisionConfig 모델)
• radio — RadioConfig (RadioConfig 모델)
• rag — RagConfig (RagConfig 모델)
• recurrent_gemma — RecurrentGemmaConfig (RecurrentGemmaConfig 모델)
• reformer — ReformerConfig (ReformerConfig 모델)
• regnet — RegNetConfig (RegNetConfig 모델)
• rembert — RemBertConfig (RemBertConfig 모델)
• resnet — ResNetConfig (ResNetConfig 모델)
• rf_detr — RfDetrConfig (RfDetrConfig 모델)
• rf_detr_dinov2 — RfDetrDinov2Config (RfDetrDinov2Config 모델)
• roberta — RobertaConfig (RobertaConfig 모델)
• roberta-prelayernorm — RobertaPreLayerNormConfig (RobertaPreLayerNormConfig 모델)
• roc_bert — RoCBertConfig (RoCBertConfig 모델)
• roformer — RoFormerConfig (RoFormerConfig 모델)
• rt_detr — RTDetrConfig (RTDetrConfig 모델)
• rt_detr_resnet — RTDetrResNetConfig (RTDetrResNetConfig 모델)
• rt_detr_v2 — RTDetrV2Config (RTDetrV2Config 모델)
• rwkv — RwkvConfig (RwkvConfig 모델)
• sam — SamConfig (SamConfig 모델)
• sam2 — Sam2Config (Sam2Config 모델)
• sam2_hiera_det_model — Sam2HieraDetConfig (Sam2HieraDetConfig 모델)
• sam2_mask_decoder — Sam2MaskDecoderConfig (Sam2MaskDecoderConfig 모델)
• sam2_prompt_encoder — Sam2PromptEncoderConfig (Sam2PromptEncoderConfig 모델)
• sam2_video — Sam2VideoConfig (Sam2VideoConfig 모델)
• sam2_video_mask_decoder — Sam2VideoMaskDecoderConfig (Sam2VideoMaskDecoderConfig 모델)
• sam2_video_prompt_encoder — Sam2VideoPromptEncoderConfig (Sam2VideoPromptEncoderConfig 모델)
• sam2_vision_model — Sam2VisionConfig (Sam2VisionConfig 모델)
• sam3 — Sam3Config (Sam3Config 모델)
• sam3_detr_decoder — Sam3DETRDecoderConfig (Sam3DETRDecoderConfig 모델)
• sam3_detr_encoder — Sam3DETREncoderConfig (Sam3DETREncoderConfig 모델)
• sam3_geometry_encoder — Sam3GeometryEncoderConfig (Sam3GeometryEncoderConfig 모델)
• sam3_lite_text — Sam3LiteTextConfig (Sam3LiteTextConfig 모델)
• sam3_lite_text_detr_decoder — Sam3LiteTextDETRDecoderConfig (Sam3LiteTextDETRDecoderConfig 모델)
• sam3_lite_text_detr_encoder — Sam3LiteTextDETREncoderConfig (Sam3LiteTextDETREncoderConfig 모델)
• sam3_lite_text_geometry_encoder — Sam3LiteTextGeometryEncoderConfig (Sam3LiteTextGeometryEncoderConfig 모델)
• sam3_lite_text_mask_decoder — Sam3LiteTextMaskDecoderConfig (Sam3LiteTextMaskDecoderConfig 모델)
• sam3_lite_text_text_model — Sam3LiteTextTextConfig (Sam3LiteTextTextConfig 모델)
• sam3_mask_decoder — Sam3MaskDecoderConfig (Sam3MaskDecoderConfig 모델)
• sam3_tracker — Sam3TrackerConfig (Sam3TrackerConfig 모델)
• sam3_tracker_mask_decoder — Sam3TrackerMaskDecoderConfig (Sam3TrackerMaskDecoderConfig 모델)
• sam3_tracker_prompt_encoder — Sam3TrackerPromptEncoderConfig (Sam3TrackerPromptEncoderConfig 모델)
• sam3_tracker_video — Sam3TrackerVideoConfig (Sam3TrackerVideoConfig 모델)
• sam3_tracker_video_mask_decoder — Sam3TrackerVideoMaskDecoderConfig (Sam3TrackerVideoMaskDecoderConfig 모델)
• sam3_tracker_video_prompt_encoder — Sam3TrackerVideoPromptEncoderConfig (Sam3TrackerVideoPromptEncoderConfig 모델)
• sam3_video — Sam3VideoConfig (Sam3VideoConfig 모델)
• sam3_vision_model — Sam3VisionConfig (Sam3VisionConfig 모델)
• sam3_vit_model — Sam3ViTConfig (Sam3ViTConfig 모델)
• sam_hq — SamHQConfig (SamHQConfig 모델)
• sam_hq_mask_decoder — SamHQMaskDecoderConfig (SamHQMaskDecoderConfig 모델)
• sam_hq_prompt_encoder — SamHQPromptEncoderConfig (SamHQPromptEncoderConfig 모델)
• sam_hq_vision_model — SamHQVisionConfig (SamHQVisionConfig 모델)
• sam_mask_decoder — SamMaskDecoderConfig (SamMaskDecoderConfig 모델)
• sam_prompt_encoder — SamPromptEncoderConfig (SamPromptEncoderConfig 모델)
• sam_vision_model — SamVisionConfig (SamVisionConfig 모델)
• sapiens2 — Sapiens2Config (Sapiens2Config 모델)
• sapiens2_head — Sapiens2HeadConfig (Sapiens2HeadConfig 모델)
• seamless_m4t — SeamlessM4TConfig (SeamlessM4TConfig 모델)
• seamless_m4t_v2 — SeamlessM4Tv2Config (SeamlessM4Tv2Config 모델)
• seed_oss — SeedOssConfig (SeedOssConfig 모델)
• segformer — SegformerConfig (SegformerConfig 모델)
• seggpt — SegGptConfig (SegGptConfig 모델)
• sew — SEWConfig (SEWConfig 모델)
• sew-d — SEWDConfig (SEWDConfig 모델)
• shieldgemma2 — ShieldGemma2Config (ShieldGemma2Config 모델)
• siglip — SiglipConfig (SiglipConfig 모델)
• siglip2 — Siglip2Config (Siglip2Config 모델)
• siglip2_text_model — Siglip2TextConfig (Siglip2TextConfig 모델)
• siglip2_vision_model — Siglip2VisionConfig (Siglip2VisionConfig 모델)
• siglip_text_model — SiglipTextConfig (SiglipTextConfig 모델)
• siglip_vision_model — SiglipVisionConfig (SiglipVisionConfig 모델)
• slanet — SLANetConfig (SLANetConfig 모델)
• slanext — SLANeXtConfig (SLANeXtConfig 모델)
• slanext_vision — SLANeXtVisionConfig (SLANeXtVisionConfig 모델)
• smollm3 — SmolLM3Config (SmolLM3Config 모델)
• smolvlm — SmolVLMConfig (SmolVLMConfig 모델)
• smolvlm_vision — SmolVLMVisionConfig (SmolVLMVisionConfig 모델)
• solar_open — SolarOpenConfig (SolarOpenConfig 모델)
• speech-encoder-decoder — SpeechEncoderDecoderConfig (SpeechEncoderDecoderConfig 모델)
• speech_to_text — Speech2TextConfig (Speech2TextConfig 모델)
• speecht5 — SpeechT5Config (SpeechT5Config 모델)
• speecht5_hifigan — SpeechT5HifiGanConfig (SpeechT5HifiGanConfig 모델)
• splinter — SplinterConfig (SplinterConfig 모델)
• squeezebert — SqueezeBertConfig (SqueezeBertConfig 모델)
• stablelm — StableLmConfig (StableLmConfig 모델)
• starcoder2 — Starcoder2Config (Starcoder2Config 모델)
• step3p5 — Step3p7TextConfig (Step3p7TextConfig 모델)
• step3p5_vision — Step3p7VisionConfig (Step3p7VisionConfig 모델)
• step3p7 — Step3p7Config (Step3p7Config 모델)
• superglue — SuperGlueConfig (SuperGlueConfig 모델)
• superpoint — SuperPointConfig (SuperPointConfig 모델)
• swiftformer — SwiftFormerConfig (SwiftFormerConfig 모델)
• swin — SwinConfig (SwinConfig 모델)
• swin2sr — Swin2SRConfig (Swin2SRConfig 모델)
• swinv2 — Swinv2Config (Swinv2Config 모델)
• switch_transformers — SwitchTransformersConfig (SwitchTransformersConfig 모델)
• t5 — T5Config (T5Config 모델)
• t5_gemma_module — T5GemmaModuleConfig (T5GemmaModuleConfig 모델)
• t5gemma — T5GemmaConfig (T5GemmaConfig 모델)
• t5gemma2 — T5Gemma2Config (T5Gemma2Config 모델)
• t5gemma2_decoder — T5Gemma2DecoderConfig (T5Gemma2DecoderConfig 모델)
• t5gemma2_encoder — T5Gemma2EncoderConfig (T5Gemma2EncoderConfig 모델)
• t5gemma2_text — T5Gemma2TextConfig (T5Gemma2TextConfig 모델)
• table-transformer — TableTransformerConfig (TableTransformerConfig 모델)
• tapas — TapasConfig (TapasConfig 모델)
• textnet — TextNetConfig (TextNetConfig 모델)
• time_series_transformer — TimeSeriesTransformerConfig (TimeSeriesTransformerConfig 모델)
• timesfm — TimesFmConfig (TimesFmConfig 모델)
• timesfm2_5 — TimesFm2_5Config (TimesFm2_5Config 모델)
• timesformer — TimesformerConfig (TimesformerConfig 모델)
• timm_backbone — TimmBackboneConfig (TimmBackboneConfig 모델)
• timm_wrapper — TimmWrapperConfig (TimmWrapperConfig 모델)
• tipsv2 — Tipsv2Config (Tipsv2Config 모델)
• tipsv2_dpt — Tipsv2DptConfig (Tipsv2DptConfig 모델)
• tipsv2_text_model — Tipsv2TextConfig (Tipsv2TextConfig 모델)
• tipsv2_vision_model — Tipsv2VisionConfig (Tipsv2VisionConfig 모델)
• trocr — TrOCRConfig (TrOCRConfig 모델)
• tvp — TvpConfig (TvpConfig 모델)
• udop — UdopConfig (UdopConfig 모델)
• ultrabert — UltrabertConfig (UltrabertConfig 모델)
• ultravbert — UltraVBertConfig (UltraVBertConfig 모델)
• umt5 — UMT5Config (UMT5Config 모델)
• unispeech — UniSpeechConfig (UniSpeechConfig 모델)
• unispeech-sat — UniSpeechSatConfig (UniSpeechSatConfig 모델)
• univnet — UnivNetConfig (UnivNetConfig 모델)
• unlimited_ocr — UnlimitedOcrConfig (UnlimitedOcrConfig 모델)
• unlimited_ocr_sam_vision_model — UnlimitedOcrSamVisionConfig (UnlimitedOcrSamVisionConfig 모델)
• unlimited_ocr_text — UnlimitedOcrTextConfig (UnlimitedOcrTextConfig 모델)
• unlimited_ocr_vision — UnlimitedOcrVisionConfig (UnlimitedOcrVisionConfig 모델)
• unlimited_ocr_vision_encoder — UnlimitedOcrVisionEncoderConfig (UnlimitedOcrVisionEncoderConfig 모델)
• upernet — UperNetConfig (UperNetConfig 모델)
• uvdoc — UVDocConfig (UVDocConfig 모델)
• uvdoc_backbone — UVDocBackboneConfig (UVDocBackboneConfig 모델)
• vaultgemma — VaultGemmaConfig (VaultGemmaConfig 모델)
• vibevoice — VibeVoiceConfig (VibeVoiceConfig 모델)
• vibevoice_acoustic_tokenizer — VibeVoiceAcousticTokenizerConfig (VibeVoiceAcousticTokenizerConfig 모델)
• vibevoice_acoustic_tokenizer_decoder — VibeVoiceAcousticTokenizerDecoderConfig (VibeVoiceAcousticTokenizerDecoderConfig 모델)
• vibevoice_acoustic_tokenizer_encoder — VibeVoiceAcousticTokenizerEncoderConfig (VibeVoiceAcousticTokenizerEncoderConfig 모델)
• vibevoice_asr — VibeVoiceAsrConfig (VibeVoiceAsrConfig 모델)
• vibevoice_diffusion — VibeVoiceDiffusionHeadConfig (VibeVoiceDiffusionHeadConfig 모델)
• video_llama_3 — VideoLlama3Config (VideoLlama3Config 모델)
• video_llama_3_vision — VideoLlama3VisionConfig (VideoLlama3VisionConfig 모델)
• video_llava — VideoLlavaConfig (VideoLlavaConfig 모델)
• videomae — VideoMAEConfig (VideoMAEConfig 모델)
• videomt — VideomtConfig (VideomtConfig 모델)
• videoprism — VideoPrismConfig (VideoPrismConfig 모델)
• videoprism_text_model — VideoPrismTextConfig (VideoPrismTextConfig 모델)
• videoprism_vision_model — VideoPrismVisionConfig (VideoPrismVisionConfig 모델)
• vilt — ViltConfig (ViltConfig 모델)
• vipllava — VipLlavaConfig (VipLlavaConfig 모델)
• vision-encoder-decoder — VisionEncoderDecoderConfig (VisionEncoderDecoderConfig 모델)
• vision-text-dual-encoder — VisionTextDualEncoderConfig (VisionTextDualEncoderConfig 모델)
• visual_bert — VisualBertConfig (VisualBertConfig 모델)
• vit — ViTConfig (ViTConfig 모델)
• vit_mae — ViTMAEConfig (ViTMAEConfig 모델)
• vit_msn — ViTMSNConfig (ViTMSNConfig 모델)
• vitdet — VitDetConfig (VitDetConfig 모델)
• vitmatte — VitMatteConfig (VitMatteConfig 모델)
• vitpose — VitPoseConfig (VitPoseConfig 모델)
• vitpose_backbone — VitPoseBackboneConfig (VitPoseBackboneConfig 모델)
• vits — VitsConfig (VitsConfig 모델)
• vivit — VivitConfig (VivitConfig 모델)
• vjepa2 — VJEPA2Config (VJEPA2Config 모델)
• voxtral — VoxtralConfig (VoxtralConfig 모델)
• voxtral_encoder — VoxtralEncoderConfig (VoxtralEncoderConfig 모델)
• voxtral_realtime — VoxtralRealtimeConfig (VoxtralRealtimeConfig 모델)
• voxtral_realtime_encoder — VoxtralRealtimeEncoderConfig (VoxtralRealtimeEncoderConfig 모델)
• voxtral_realtime_text — VoxtralRealtimeTextConfig (VoxtralRealtimeTextConfig 모델)
• wav2vec2 — Wav2Vec2Config (Wav2Vec2Config 모델)
• wav2vec2-bert — Wav2Vec2BertConfig (Wav2Vec2BertConfig 모델)
• wav2vec2-conformer — Wav2Vec2ConformerConfig (Wav2Vec2ConformerConfig 모델)
• wavlm — WavLMConfig (WavLMConfig 모델)
• whisper — WhisperConfig (WhisperConfig 모델)
• xclip — XCLIPConfig (XCLIPConfig 모델)
• xclip_text_model — XCLIPTextConfig (XCLIPTextConfig 모델)
• xclip_vision_model — XCLIPVisionConfig (XCLIPVisionConfig 모델)
• xcodec — XcodecConfig (XcodecConfig 모델)
• xcodec2 — Xcodec2Config (Xcodec2Config 모델)
• xglm — XGLMConfig (XGLMConfig 모델)
• xlm — XLMConfig (XLMConfig 모델)
• xlm-roberta — XLMRobertaConfig (XLMRobertaConfig 모델)
• xlm-roberta-xl — XLMRobertaXLConfig (XLMRobertaXLConfig 모델)
• xlnet — XLNetConfig (XLNetConfig 모델)
• xlstm — xLSTMConfig (xLSTMConfig 모델)
• xmod — XmodConfig (XmodConfig 모델)
• yolos — YolosConfig (YolosConfig 모델)
• yoso — YosoConfig (YosoConfig 모델)
• youtu — YoutuConfig (YoutuConfig 모델)
• zamba — ZambaConfig (ZambaConfig 모델)
• zamba2 — Zamba2Config (Zamba2Config 모델)
• zaya — ZayaConfig (ZayaConfig 모델)
• zoedepth — ZoeDepthConfig (ZoeDepthConfig 모델)

>>> from transformers import AutoConfig

>>> # Download configuration from huggingface.co and cache.
>>> config = AutoConfig.from_pretrained("google-bert/bert-base-uncased")

>>> # Download configuration from huggingface.co (user-uploaded) and cache.
>>> config = AutoConfig.from_pretrained("dbmdz/bert-base-german-cased")

>>> # If configuration file is in a directory (e.g., was saved using *save_pretrained('./test/saved_model/')*).
>>> config = AutoConfig.from_pretrained("./test/bert_saved_model/")

>>> # Load a specific configuration file.
>>> config = AutoConfig.from_pretrained("./test/bert_saved_model/my_configuration.json")

>>> # Change some config attributes when loading a pretrained config.
>>> config = AutoConfig.from_pretrained("google-bert/bert-base-uncased", output_attentions=True, foo=False)
>>> config.output_attentions
True

>>> config, unused_kwargs = AutoConfig.from_pretrained(
...     "google-bert/bert-base-uncased", output_attentions=True, foo=False, return_unused_kwargs=True
... )
>>> config.output_attentions
True

>>> unused_kwargs
{'foo': False}

이 클래스에 대한 새 구성을 등록합니다.

pretrained model 어휘에서 라이브러리의 토크나이저 클래스 중 하나를 인스턴스화합니다.

인스턴스화할 토크나이저 클래스는 config 객체의 model_type 속성(인자로 전달되거나, 가능하면 pretrained_model_name_or_path에서 로드된 값)에 따라 선택됩니다. 해당 속성이 없는 경우, pretrained_model_name_or_path에 대해 패턴 매칭을 사용하는 방식으로 폴백합니다.

• EvollaModel — TokenizersBackend (EvollaConfig 모델)
• aimv2 — CLIPTokenizer (Aimv2Config 모델)
• albert — AlbertTokenizer (AlbertConfig 모델)
• align — BertTokenizer (AlignConfig 모델)
• aria — TokenizersBackend (AriaConfig 모델)
• audioflamingo3 — Qwen2Tokenizer (AudioFlamingo3Config 모델)
• aya_vision — CohereTokenizer (AyaVisionConfig 모델)
• bark — BertTokenizer (BarkConfig 모델)
• bart — RobertaTokenizer (BartConfig 모델)
• beam — TokenizersBackend (BeamConfig 모델)
• bert — BertTokenizer (BertConfig 모델)
• bert-generation — BertGenerationTokenizer (BertGenerationConfig 모델)
• big_bird — BigBirdTokenizer (BigBirdConfig 모델)
• bigbird_pegasus — TokenizersBackend (BigBirdPegasusConfig 모델)
• biogpt — BioGptTokenizer (BioGptConfig 모델)
• blenderbot — BlenderbotTokenizer (BlenderbotConfig 모델)
• blenderbot-small — BlenderbotSmallTokenizer (BlenderbotSmallConfig 모델)
• blip — BertTokenizer (BlipConfig 모델)
• blip-2 — GPT2Tokenizer (Blip2Config 모델)
• bridgetower — RobertaTokenizer (BridgeTowerConfig 모델)
• bros — BertTokenizer (BrosConfig 모델)
• camembert — CamembertTokenizer (CamembertConfig 모델)
• canary — TokenizersBackend (CanaryConfig 모델)
• canine — CanineTokenizer (CanineConfig 모델)
• chinese_clip — BertTokenizer (ChineseCLIPConfig 모델)
• clap — RobertaTokenizer (ClapConfig 모델)
• clip — CLIPTokenizer (CLIPConfig 모델)
• clipseg — CLIPTokenizer (CLIPSegConfig 모델)
• clvp — ClvpTokenizer (ClvpConfig 모델)
• codegen — GPT2Tokenizer (CodeGenConfig 모델)
• cohere — CohereTokenizer (CohereConfig 모델)
• cohere2 — CohereTokenizer (Cohere2Config 모델)
• cohere_asr — TokenizersBackend (CohereAsrConfig 모델)
• colqwen2 — Qwen2Tokenizer (ColQwen2Config 모델)
• convbert — BertTokenizer (ConvBertConfig 모델)
• cosmos3_omni — Qwen2Tokenizer (Cosmos3OmniConfig 모델)
• cpmant — CpmAntTokenizer (CpmAntConfig 모델)
• ctrl — CTRLTokenizer (CTRLConfig 모델)
• data2vec-audio — Wav2Vec2CTCTokenizer (Data2VecAudioConfig 모델)
• data2vec-text — RobertaTokenizer (Data2VecTextConfig 모델)
• dbrx — GPT2Tokenizer (DbrxConfig 모델)
• deberta — DebertaTokenizer (DebertaConfig 모델)
• deberta-v2 — DebertaV2Tokenizer (DebertaV2Config 모델)
• dia — DiaTokenizer (DiaConfig 모델)
• diffusion_gemma — GemmaTokenizer (DiffusionGemmaConfig 모델)
• distilbert — BertTokenizer (DistilBertConfig 모델)
• dots3_note — Qwen2Tokenizer (Dots3NoteConfig 모델)
• dpr — DPRQuestionEncoderTokenizer (DPRConfig 모델)
• electra — BertTokenizer (ElectraConfig 모델)
• emu3 — GPT2Tokenizer (Emu3Config 모델)
• ernie — BertTokenizer (ErnieConfig 모델)
• ernie4_5 — TokenizersBackend (Ernie4_5Config 모델)
• ernie4_5_moe — TokenizersBackend (Ernie4_5_MoeConfig 모델)
• esm — EsmTokenizer (EsmConfig 모델)
• esmc — EsmcTokenizer (EsmcConfig 모델)
• esmfold2 — EsmcTokenizer (EsmFold2Config 모델)
• falcon_mamba — GPTNeoXTokenizer (FalconMambaConfig 모델)
• fastspeech2_conformer — None (FastSpeech2ConformerConfig 모델)
• flaubert — FlaubertTokenizer (FlaubertConfig 모델)
• flava — BertTokenizer (FlavaConfig 모델)
• flex_olmo — TokenizersBackend (FlexOlmoConfig 모델)
• florence2 — BartTokenizer (Florence2Config 모델)
• fnet — FNetTokenizer (FNetConfig 모델)
• fsmt — FSMTTokenizer (FSMTConfig 모델)
• fun_asr_nano — Qwen2Tokenizer (FunAsrNanoConfig 모델)
• funnel — FunnelTokenizer (FunnelConfig 모델)
• fuyu — TokenizersBackend (FuyuConfig 모델)
• gemma — GemmaTokenizer (GemmaConfig 모델)
• gemma2 — GemmaTokenizer (Gemma2Config 모델)
• gemma3 — GemmaTokenizer (Gemma3Config 모델)
• gemma3_text — GemmaTokenizer (Gemma3TextConfig 모델)
• gemma3n — GemmaTokenizer (Gemma3nConfig 모델)
• gemma3n_text — GemmaTokenizer (Gemma3nTextConfig 모델)
• git — BertTokenizer (GitConfig 모델)
• glm — TokenizersBackend (GlmConfig 모델)
• glm4 — TokenizersBackend (Glm4Config 모델)
• glm4_moe — TokenizersBackend (Glm4MoeConfig 모델)
• glm4_moe_lite — TokenizersBackend (Glm4MoeLiteConfig 모델)
• glm4v — TokenizersBackend (Glm4vConfig 모델)
• glm4v_moe — TokenizersBackend (Glm4vMoeConfig 모델)
• glm_image — TokenizersBackend (GlmImageConfig 모델)
• glmasr — TokenizersBackend (GlmAsrConfig 모델)
• got_ocr2 — TokenizersBackend (GotOcr2Config 모델)
• gpt-sw3 — GPTSw3Tokenizer (GPT2Config 모델)
• gpt2 — GPT2Tokenizer (GPT2Config 모델)
• gpt_bigcode — TokenizersBackend (GPTBigCodeConfig 모델)
• gpt_neo — GPT2Tokenizer (GPTNeoConfig 모델)
• gpt_neox — GPTNeoXTokenizer (GPTNeoXConfig 모델)
• gpt_neox_japanese — GPTNeoXJapaneseTokenizer (GPTNeoXJapaneseConfig 모델)
• gptj — GPT2Tokenizer (GPTJConfig 모델)
• gradium_phonon_tts — TokenizersBackend (GradiumPhononTTSConfig 모델)
• granite — TokenizersBackend (GraniteConfig 모델)
• granite_speech5_ctc — ParakeetTokenizer (GraniteSpeech5CTCConfig 모델)
• granitemoe — TokenizersBackend (GraniteMoeConfig 모델)
• granitemoehybrid — TokenizersBackend (GraniteMoeHybridConfig 모델)
• granitemoeshared — TokenizersBackend (GraniteMoeSharedConfig 모델)
• grounding-dino — BertTokenizer (GroundingDinoConfig 모델)
• groupvit — CLIPTokenizer (GroupViTConfig 모델)
• gte — XLMRobertaTokenizer (GteConfig 모델)
• hubert — Wav2Vec2CTCTokenizer (HubertConfig 모델)
• hunyuan_vl — Qwen2Tokenizer (HunYuanVLConfig 모델)
• hyperclovax — TokenizersBackend (HyperCLOVAXConfig 모델)
• hyperclovax_vision_v2 — GPT2Tokenizer (HyperCLOVAXVisionV2Config 모델)
• ibert — RobertaTokenizer (IBertConfig 모델)
• idefics — LlamaTokenizer (IdeficsConfig 모델)
• idefics2 — LlamaTokenizer (Idefics2Config 모델)
• instructblip — GPT2Tokenizer (InstructBlipConfig 모델)
• instructblipvideo — GPT2Tokenizer (InstructBlipVideoConfig 모델)
• internlm3 — TokenizersBackend (InternLM3Config 모델)
• internvl — Qwen2Tokenizer (InternVLConfig 모델)
• iquestcoder — TokenizersBackend (IQuestCoderConfig 모델)
• jais2 — GPT2Tokenizer (Jais2Config 모델)
• jamba — TokenizersBackend (JambaConfig 모델)
• jina_embeddings_v3 — XLMRobertaTokenizer (JinaEmbeddingsV3Config 모델)
• kimi_k25 — TokenizersBackend (Kimi_K25Config 모델)
• kimi_linear — TokenizersBackend (KimiLinearConfig 모델)
• kosmos-2 — TokenizersBackend (Kosmos2Config 모델)
• lasr_ctc — LasrTokenizer (LasrCTCConfig 모델)
• lasr_encoder — LasrTokenizer (LasrEncoderConfig 모델)
• layoutlm — BertTokenizer (LayoutLMConfig 모델)
• layoutlmv2 — LayoutLMv2Tokenizer (LayoutLMv2Config 모델)
• layoutlmv3 — LayoutLMv3Tokenizer (LayoutLMv3Config 모델)
• layoutxlm — LayoutXLMTokenizer (LayoutXLMConfig 모델)
• led — LEDTokenizer (LEDConfig 모델)
• lighton_ocr — Qwen2TokenizerFast (LightOnOcrConfig 모델)
• lilt — RobertaTokenizer (LiltConfig 모델)
• llava — TokenizersBackend (LlavaConfig 모델)
• llava_next — TokenizersBackend (LlavaNextConfig 모델)
• longformer — RobertaTokenizer (LongformerConfig 모델)
• luke — LukeTokenizer (LukeConfig 모델)
• lxmert — LxmertTokenizer (LxmertConfig 모델)
• m2m_100 — M2M100Tokenizer (M2M100Config 모델)
• mamba — GPTNeoXTokenizer (MambaConfig 모델)
• mamba2 — GPTNeoXTokenizer (Mamba2Config 모델)
• marian — MarianTokenizer (MarianConfig 모델)
• markuplm — MarkupLMTokenizer (MarkupLMConfig 모델)
• mbart — MBartTokenizer (MBartConfig 모델)
• megatron-bert — BertTokenizer (MegatronBertConfig 모델)
• metaclip_2 — XLMRobertaTokenizer (MetaClip2Config 모델)
• mgp-str — MgpstrTokenizer (MgpstrConfig 모델)
• mimo_v2_flash — TokenizersBackend (MiMoV2FlashConfig 모델)
• minicpm3 — TokenizersBackend (MiniCPM3Config 모델)
• minicpm_ocr — TokenizersBackend (MiniCPMOcrConfig 모델)
• minicpmv4_6 — TokenizersBackend (MiniCPMV4_6Config 모델)
• minicpmv4_7 — TokenizersBackend (MiniCPMV4_7Config 모델)
• minimax_m2 — TokenizersBackend (MiniMaxM2Config 모델)
• ministral — MistralCommonBackend (MinistralConfig 모델)
• ministral3 — MistralCommonBackend (Ministral3Config 모델)
• mistral — MistralCommonBackend (MistralConfig 모델)
• mistral3 — MistralCommonBackend (Mistral3Config 모델)
• mistral_large4 — MistralCommonBackend (MistralLarge4Config 모델)
• mixtral — MistralCommonBackend (MixtralConfig 모델)
• mm-grounding-dino — BertTokenizer (MMGroundingDinoConfig 모델)
• mobilebert — MobileBertTokenizer (MobileBertConfig 모델)
• modernbert — TokenizersBackend (ModernBertConfig 모델)
• modernbert-decoder — TokenizersBackend (ModernBertDecoderConfig 모델)
• molmo2 — TokenizersBackend (Molmo2Config 모델)
• moss_transcribe_diarize — Qwen2Tokenizer (MossTranscribeDiarizeConfig 모델)
• mpnet — MPNetTokenizer (MPNetConfig 모델)
• mpt — GPTNeoXTokenizer (MptConfig 모델)
• mra — RobertaTokenizer (MraConfig 모델)
• mt5 — T5Tokenizer (MT5Config 모델)
• musicgen — T5Tokenizer (MusicgenConfig 모델)
• musicgen_melody — T5Tokenizer (MusicgenMelodyConfig 모델)
• mvp — MvpTokenizer (MvpConfig 모델)
• nemo_speechlm — TokenizersBackend (Nemotron3_5TranscribeConfig 모델)
• nemotron — TokenizersBackend (NemotronConfig 모델)
• nemotron3_5_asr — ParakeetTokenizer (Nemotron3_5AsrConfig 모델)
• nemotron_asr_streaming — ParakeetTokenizer (NemotronAsrStreamingConfig 모델)
• nllb-moe — NllbTokenizer (NllbMoeConfig 모델)
• nomic_bert — BertTokenizer (NomicBertConfig 모델)
• nougat — NougatTokenizer (NougatConfig 모델)
• nystromformer — TokenizersBackend (NystromformerConfig 모델)
• olmo — GPTNeoXTokenizer (OlmoConfig 모델)
• olmo2 — TokenizersBackend (Olmo2Config 모델)
• olmo3 — TokenizersBackend (Olmo3Config 모델)
• olmo_hybrid — TokenizersBackend (OlmoHybridConfig 모델)
• olmoe — GPTNeoXTokenizer (OlmoeConfig 모델)
• omdet-turbo — CLIPTokenizer (OmDetTurboConfig 모델)
• oneformer — CLIPTokenizer (OneFormerConfig 모델)
• openai-gpt — OpenAIGPTTokenizer (OpenAIGPTConfig 모델)
• opt — GPT2Tokenizer (OPTConfig 모델)
• ovis2 — Qwen2Tokenizer (Ovis2Config 모델)
• owlv2 — CLIPTokenizer (Owlv2Config 모델)
• owlvit — CLIPTokenizer (OwlViTConfig 모델)
• paddleocr_vl — TokenizersBackend (PaddleOCRVLConfig 모델)
• parakeet_ctc — ParakeetTokenizer (ParakeetCTCConfig 모델)
• parakeet_rnnt — ParakeetTokenizer (ParakeetRNNTConfig 모델)
• parakeet_tdt — ParakeetTokenizer (ParakeetTDTConfig 모델)
• pegasus — PegasusTokenizer (PegasusConfig 모델)
• pegasus_x — TokenizersBackend (PegasusXConfig 모델)
• perceiver — PerceiverTokenizer (PerceiverConfig 모델)
• persimmon — TokenizersBackend (PersimmonConfig 모델)
• phi — GPT2Tokenizer (PhiConfig 모델)
• phi3 — TokenizersBackend (Phi3Config 모델)
• phimoe — TokenizersBackend (PhimoeConfig 모델)
• pix2struct — TokenizersBackend (Pix2StructConfig 모델)
• pixtral — MistralCommonBackend (PixtralVisionConfig 모델)
• plbart — PLBartTokenizer (PLBartConfig 모델)
• pocket_tts — TokenizersBackend (PocketTTSConfig 모델)
• pp_formulanet — NougatTokenizer (PPFormulaNetConfig 모델)
• prophetnet — ProphetNetTokenizer (ProphetNetConfig 모델)
• qianfan_ocr — Qwen2Tokenizer (QianfanOCRConfig 모델)
• qwen2 — Qwen2Tokenizer (Qwen2Config 모델)
• qwen2_5_omni — Qwen2Tokenizer (Qwen2_5OmniConfig 모델)
• qwen2_5_vl — Qwen2Tokenizer (Qwen2_5_VLConfig 모델)
• qwen2_audio — Qwen2Tokenizer (Qwen2AudioConfig 모델)
• qwen2_moe — Qwen2Tokenizer (Qwen2MoeConfig 모델)
• qwen2_vl — Qwen2Tokenizer (Qwen2VLConfig 모델)
• qwen3 — Qwen2Tokenizer (Qwen3Config 모델)
• qwen3_5 — Qwen3_5Tokenizer (Qwen3_5Config 모델)
• qwen3_5_moe — Qwen3_5Tokenizer (Qwen3_5MoeConfig 모델)
• qwen3_5_moe_text — Qwen3_5Tokenizer (Qwen3_5MoeTextConfig 모델)
• qwen3_5_text — Qwen3_5Tokenizer (Qwen3_5TextConfig 모델)
• qwen3_asr — Qwen2Tokenizer (Qwen3ASRConfig 모델)
• qwen3_moe — Qwen2Tokenizer (Qwen3MoeConfig 모델)
• qwen3_next — Qwen2Tokenizer (Qwen3NextConfig 모델)
• qwen3_omni_moe — Qwen2Tokenizer (Qwen3OmniMoeConfig 모델)
• qwen3_vl — Qwen2Tokenizer (Qwen3VLConfig 모델)
• qwen3_vl_moe — Qwen2Tokenizer (Qwen3VLMoeConfig 모델)
• qwen4_exp — Qwen3_5Tokenizer (Qwen4ExpConfig 모델)
• rag — RagTokenizer (RagConfig 모델)
• recurrent_gemma — GemmaTokenizer (RecurrentGemmaConfig 모델)
• reformer — ReformerTokenizer (ReformerConfig 모델)
• rembert — RemBertTokenizer (RemBertConfig 모델)
• roberta — RobertaTokenizer (RobertaConfig 모델)
• roberta-prelayernorm — RobertaTokenizer (RobertaPreLayerNormConfig 모델)
• roc_bert — RoCBertTokenizer (RoCBertConfig 모델)
• roformer — RoFormerTokenizer (RoFormerConfig 모델)
• rwkv — GPTNeoXTokenizer (RwkvConfig 모델)
• sam3 — CLIPTokenizer (Sam3Config 모델)
• sam3_video — CLIPTokenizer (Sam3VideoConfig 모델)
• seamless_m4t — SeamlessM4TTokenizer (SeamlessM4TConfig 모델)
• seamless_m4t_v2 — SeamlessM4TTokenizer (SeamlessM4Tv2Config 모델)
• shieldgemma2 — GemmaTokenizer (ShieldGemma2Config 모델)
• siglip — SiglipTokenizer (SiglipConfig 모델)
• siglip2 — Siglip2Tokenizer (Siglip2Config 모델)
• smolvlm — TokenizersBackend (SmolVLMConfig 모델)
• speech_to_text — Speech2TextTokenizer (Speech2TextConfig 모델)
• speecht5 — SpeechT5Tokenizer (SpeechT5Config 모델)
• splinter — SplinterTokenizer (SplinterConfig 모델)
• squeezebert — BertTokenizer (SqueezeBertConfig 모델)
• stablelm — TokenizersBackend (StableLmConfig 모델)
• starcoder2 — GPT2Tokenizer (Starcoder2Config 모델)
• switch_transformers — T5Tokenizer (SwitchTransformersConfig 모델)
• t5 — T5Tokenizer (T5Config 모델)
• t5gemma — GemmaTokenizer (T5GemmaConfig 모델)
• tapas — TapasTokenizer (TapasConfig 모델)
• tipsv2 — Tipsv2Tokenizer (Tipsv2Config 모델)
• trocr — XLMRobertaTokenizer (TrOCRConfig 모델)
• tvp — BertTokenizer (TvpConfig 모델)
• udop — UdopTokenizer (UdopConfig 모델)
• umt5 — TokenizersBackend (UMT5Config 모델)
• unispeech — Wav2Vec2CTCTokenizer (UniSpeechConfig 모델)
• unispeech-sat — Wav2Vec2CTCTokenizer (UniSpeechSatConfig 모델)
• vibevoice — Qwen2TokenizerFast (VibeVoiceConfig 모델)
• videoprism — VideoPrismTokenizer (VideoPrismConfig 모델)
• vilt — BertTokenizer (ViltConfig 모델)
• vipllava — TokenizersBackend (VipLlavaConfig 모델)
• visual_bert — BertTokenizer (VisualBertConfig 모델)
• vits — VitsTokenizer (VitsConfig 모델)
• voxtral — MistralCommonBackend (VoxtralConfig 모델)
• voxtral_realtime — MistralCommonBackend (VoxtralRealtimeConfig 모델)
• wav2vec2 — Wav2Vec2CTCTokenizer (Wav2Vec2Config 모델)
• wav2vec2-bert — Wav2Vec2CTCTokenizer (Wav2Vec2BertConfig 모델)
• wav2vec2-conformer — Wav2Vec2CTCTokenizer (Wav2Vec2ConformerConfig 모델)
• whisper — WhisperTokenizer (WhisperConfig 모델)
• xclip — CLIPTokenizer (XCLIPConfig 모델)
• xglm — XGLMTokenizer (XGLMConfig 모델)
• xlm — XLMTokenizer (XLMConfig 모델)
• xlm-roberta — XLMRobertaTokenizer (XLMRobertaConfig 모델)
• xlm-roberta-xl — TokenizersBackend (XLMRobertaXLConfig 모델)
• xlnet — XLNetTokenizer (XLNetConfig 모델)
• xlstm — GPTNeoXTokenizer (xLSTMConfig 모델)
• xmod — XLMRobertaTokenizer (XmodConfig 모델)
• yoso — AlbertTokenizer (YosoConfig 모델)
• zaya — GemmaTokenizer (ZayaConfig 모델)

>>> from transformers import AutoTokenizer

>>> # Download vocabulary from huggingface.co and cache.
>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/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("FacebookAI/roberta-base", add_prefix_space=True)

이 매핑에 새로운 tokenizer를 등록합니다.

…

config 객체의 model_type 속성(인자로 전달되거나, 가능하면 pretrained_model_name_or_path에서 로드된 것)을 기준으로 인스턴스화할 feature extractor 클래스가 선택됩니다. 해당 속성이 없는 경우, pretrained_model_name_or_path에 대해 패턴 매칭을 사용하는 방식으로 폴백합니다.

• audio-spectrogram-transformer — ASTFeatureExtractor (ASTConfig 모델)
• audioflamingo3 — WhisperFeatureExtractor (AudioFlamingo3Config 모델)
• canary — ParakeetFeatureExtractor (CanaryConfig 모델)
• clap — ClapFeatureExtractor (ClapConfig 모델)
• clvp — ClvpFeatureExtractor (ClvpConfig 모델)
• cohere_asr — CohereAsrFeatureExtractor (CohereAsrConfig 모델)
• csm — EncodecFeatureExtractor (CsmConfig 모델)
• dac — DacFeatureExtractor (DacConfig 모델)
• data2vec-audio — Wav2Vec2FeatureExtractor (Data2VecAudioConfig 모델)
• dia — DiaFeatureExtractor (DiaConfig 모델)
• dots3_note — Dots3NoteFeatureExtractor (Dots3NoteConfig 모델)
• embedding_gemma2 — Gemma4AudioFeatureExtractor (EmbeddingGemma2Config 모델)
• encodec — EncodecFeatureExtractor (EncodecConfig 모델)
• fun_asr_nano — FunAsrNanoFeatureExtractor (FunAsrNanoConfig 모델)
• gemma3n — Gemma3nAudioFeatureExtractor (Gemma3nConfig 모델)
• gemma4 — Gemma4AudioFeatureExtractor (Gemma4Config 모델)
• gemma4_unified — Gemma4UnifiedAudioFeatureExtractor (Gemma4UnifiedConfig 모델)
• glmasr — WhisperFeatureExtractor (GlmAsrConfig 모델)
• gradium_phonon_tts — PocketTTSFeatureExtractor (GradiumPhononTTSConfig 모델)
• granite_speech — GraniteSpeechFeatureExtractor (GraniteSpeechConfig 모델)
• granite_speech5_ctc — GraniteSpeech5FeatureExtractor (GraniteSpeech5CTCConfig 모델)
• granite_speech5_encoder — GraniteSpeech5FeatureExtractor (GraniteSpeech5EncoderConfig 모델)
• granite_speech_plus — GraniteSpeechFeatureExtractor (GraniteSpeechPlusConfig 모델)
• higgs_audio_v2_tokenizer — DacFeatureExtractor (HiggsAudioV2TokenizerConfig 모델)
• hubert — Wav2Vec2FeatureExtractor (HubertConfig 모델)
• inkling_mm_model — InklingFeatureExtractor (InklingConfig 모델)
• kyutai_speech_to_text — KyutaiSpeechToTextFeatureExtractor (KyutaiSpeechToTextConfig 모델)
• lasr_ctc — LasrFeatureExtractor (LasrCTCConfig 모델)
• lasr_encoder — LasrFeatureExtractor (LasrEncoderConfig 모델)
• mimi — EncodecFeatureExtractor (MimiConfig 모델)
• moonshine — Wav2Vec2FeatureExtractor (MoonshineConfig 모델)
• moshi — EncodecFeatureExtractor (MoshiConfig 모델)
• moss_transcribe_diarize — MossTranscribeDiarizeFeatureExtractor (MossTranscribeDiarizeConfig 모델)
• muse_spark — MuseSparkFeatureExtractor (MuseSparkConfig 모델)
• musicgen — EncodecFeatureExtractor (MusicgenConfig 모델)
• musicgen_melody — MusicgenMelodyFeatureExtractor (MusicgenMelodyConfig 모델)
• nemo_speechlm — NemotronAsrStreamingFeatureExtractor (Nemotron3_5TranscribeConfig 모델)
• nemotron3_5_asr — NemotronAsrStreamingFeatureExtractor (Nemotron3_5AsrConfig 모델)
• nemotron3_diarization — NemotronAsrStreamingFeatureExtractor (Nemotron3DiarizationConfig 모델)
• nemotron_asr_streaming — NemotronAsrStreamingFeatureExtractor (NemotronAsrStreamingConfig 모델)
• nemotron_asr_streaming_encoder — NemotronAsrStreamingFeatureExtractor (NemotronAsrStreamingEncoderConfig 모델)
• neucodec — NeuCodecFeatureExtractor (NeuCodecConfig 모델)
• parakeet_ctc — ParakeetFeatureExtractor (ParakeetCTCConfig 모델)
• parakeet_encoder — ParakeetFeatureExtractor (ParakeetEncoderConfig 모델)
• parakeet_rnnt — ParakeetFeatureExtractor (ParakeetRNNTConfig 모델)
• parakeet_tdt — ParakeetFeatureExtractor (ParakeetTDTConfig 모델)
• pe_audio — PeAudioFeatureExtractor (PeAudioConfig 모델)
• pe_audio_video — PeAudioFeatureExtractor (PeAudioVideoConfig 모델)
• phi4_multimodal — Phi4MultimodalFeatureExtractor (Phi4MultimodalConfig 모델)
• pocket_tts — PocketTTSFeatureExtractor (PocketTTSConfig 모델)
• pocket_tts_audio_tokenizer — EncodecFeatureExtractor (PocketTTSAudioTokenizerConfig 모델)
• pop2piano — Pop2PianoFeatureExtractor (Pop2PianoConfig 모델)
• qwen2_5_omni — WhisperFeatureExtractor (Qwen2_5OmniConfig 모델)
• qwen2_audio — WhisperFeatureExtractor (Qwen2AudioConfig 모델)
• qwen3_asr — Qwen3ASRFeatureExtractor (Qwen3ASRConfig 모델)
• qwen3_omni_moe — WhisperFeatureExtractor (Qwen3OmniMoeConfig 모델)
• seamless_m4t — SeamlessM4TFeatureExtractor (SeamlessM4TConfig 모델)
• seamless_m4t_v2 — SeamlessM4TFeatureExtractor (SeamlessM4Tv2Config 모델)
• sew — Wav2Vec2FeatureExtractor (SEWConfig 모델)
• sew-d — Wav2Vec2FeatureExtractor (SEWDConfig 모델)
• speech_to_text — Speech2TextFeatureExtractor (Speech2TextConfig 모델)
• speecht5 — SpeechT5FeatureExtractor (SpeechT5Config 모델)
• unispeech — Wav2Vec2FeatureExtractor (UniSpeechConfig 모델)
• unispeech-sat — Wav2Vec2FeatureExtractor (UniSpeechSatConfig 모델)
• univnet — UnivNetFeatureExtractor (UnivNetConfig 모델)
• vibevoice — VibeVoiceAcousticTokenizerFeatureExtractor (VibeVoiceConfig 모델)
• vibevoice_acoustic_tokenizer — VibeVoiceAcousticTokenizerFeatureExtractor (VibeVoiceAcousticTokenizerConfig 모델)
• vibevoice_asr — VibeVoiceAcousticTokenizerFeatureExtractor (VibeVoiceAsrConfig 모델)
• voxtral — WhisperFeatureExtractor (VoxtralConfig 모델)
• voxtral_realtime — VoxtralRealtimeFeatureExtractor (VoxtralRealtimeConfig 모델)
• wav2vec2 — Wav2Vec2FeatureExtractor (Wav2Vec2Config 모델)
• wav2vec2-bert — Wav2Vec2FeatureExtractor (Wav2Vec2BertConfig 모델)
• wav2vec2-conformer — Wav2Vec2FeatureExtractor (Wav2Vec2ConformerConfig 모델)
• wavlm — Wav2Vec2FeatureExtractor (WavLMConfig 모델)
• whisper — WhisperFeatureExtractor (WhisperConfig 모델)
• xcodec — DacFeatureExtractor (XcodecConfig 모델)
• xcodec2 — Xcodec2FeatureExtractor (Xcodec2Config 모델)

비공개 모델을 사용하려면 token=True를 전달해야 합니다.

>>> from transformers import AutoFeatureExtractor

>>> # Download feature extractor from huggingface.co and cache.
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")

>>> # If feature extractor files are in a directory (e.g. feature extractor was saved using *save_pretrained('./test/saved_model/')*)
>>> # feature_extractor = AutoFeatureExtractor.from_pretrained("./test/saved_model/")

이 클래스에 새로운 feature extractor를 등록합니다.

…

model_type 속성에 따라 인스턴스화할 이미지 프로세서 클래스가 선택됩니다. 이 속성은 config 객체의 model_type 속성(인자로 전달되거나, 가능하면 pretrained_model_name_or_path에서 로드된 값)에 기반하여 결정되며, 해당 속성이 없는 경우 pretrained_model_name_or_path에 대해 패턴 매칭을 사용하는 방식으로 폴백됩니다.

• aimv2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (Aimv2Config 모델)
• aimv2_vision_model — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (Aimv2VisionConfig 모델)
• align — {'torchvision': 'EfficientNetImageProcessor', 'pil': 'EfficientNetImageProcessorPil'} (AlignConfig 모델)
• altclip — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (AltCLIPConfig 모델)
• aria — {'pil': 'AriaImageProcessorPil', 'torchvision': 'AriaImageProcessor'} (AriaConfig 모델)
• aya_vision — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (AyaVisionConfig 모델)
• beit — {'pil': 'BeitImageProcessorPil', 'torchvision': 'BeitImageProcessor'} (BeitConfig 모델)
• bit — {'pil': 'BitImageProcessorPil', 'torchvision': 'BitImageProcessor'} (BitConfig 모델)
• blip — {'pil': 'BlipImageProcessorPil', 'torchvision': 'BlipImageProcessor'} (BlipConfig 모델)
• blip-2 — {'torchvision': 'BlipImageProcessor', 'pil': 'BlipImageProcessorPil'} (Blip2Config 모델)
• bridgetower — {'pil': 'BridgeTowerImageProcessorPil', 'torchvision': 'BridgeTowerImageProcessor'} (BridgeTowerConfig 모델)
• chameleon — {'pil': 'ChameleonImageProcessorPil', 'torchvision': 'ChameleonImageProcessor'} (ChameleonConfig 모델)
• chinese_clip — {'pil': 'ChineseCLIPImageProcessorPil', 'torchvision': 'ChineseCLIPImageProcessor'} (ChineseCLIPConfig 모델)
• chmv2 — {'torchvision': 'CHMv2ImageProcessor'} (CHMv2Config 모델)
• clip — {'pil': 'CLIPImageProcessorPil', 'torchvision': 'CLIPImageProcessor'} (CLIPConfig 모델)
• clipseg — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (CLIPSegConfig 모델)
• cohere2_vision — {'torchvision': 'Cohere2VisionImageProcessor'} (Cohere2VisionConfig 모델)
• cohere_compass — {'pil': 'CohereCompassImageProcessorPil', 'torchvision': 'CohereCompassImageProcessor'} (CohereCompassConfig 모델)
• colpali — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (ColPaliConfig 모델)
• colqwen2 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (ColQwen2Config 모델)
• conditional_detr — {'pil': 'ConditionalDetrImageProcessorPil', 'torchvision': 'ConditionalDetrImageProcessor'} (ConditionalDetrConfig 모델)
• convnext — {'pil': 'ConvNextImageProcessorPil', 'torchvision': 'ConvNextImageProcessor'} (ConvNextConfig 모델)
• convnextv2 — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (ConvNextV2Config 모델)
• cosmos3_edge — {'pil': 'Cosmos3EdgeImageProcessorPil', 'torchvision': 'Cosmos3EdgeImageProcessor'} (Cosmos3EdgeConfig 모델)
• cosmos3_omni — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Cosmos3OmniConfig 모델)
• cvt — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (CvtConfig 모델)
• data2vec-vision — {'torchvision': 'BeitImageProcessor', 'pil': 'BeitImageProcessorPil'} (Data2VecVisionConfig 모델)
• deepseek_ocr2 — {'pil': 'DeepseekOcr2ImageProcessorPil', 'torchvision': 'DeepseekOcr2ImageProcessor'} (DeepseekOcr2Config 모델)
• deepseek_vl — {'pil': 'DeepseekVLImageProcessorPil', 'torchvision': 'DeepseekVLImageProcessor'} (DeepseekVLConfig 모델)
• deepseek_vl_hybrid — {'pil': 'DeepseekVLHybridImageProcessorPil', 'torchvision': 'DeepseekVLHybridImageProcessor'} (DeepseekVLHybridConfig 모델)
• deformable_detr — {'pil': 'DeformableDetrImageProcessorPil', 'torchvision': 'DeformableDetrImageProcessor'} (DeformableDetrConfig 모델)
• deimv2 — {'torchvision': 'RTDetrImageProcessor', 'pil': 'RTDetrImageProcessorPil'} (Deimv2Config 모델)
• deit — {'pil': 'DeiTImageProcessorPil', 'torchvision': 'DeiTImageProcessor'} (DeiTConfig 모델)
• depth_anything — {'torchvision': 'DPTImageProcessor', 'pil': 'DPTImageProcessorPil'} (DepthAnythingConfig 모델)
• depth_pro — {'torchvision': 'DepthProImageProcessor'} (DepthProConfig 모델)
• detr — {'pil': 'DetrImageProcessorPil', 'torchvision': 'DetrImageProcessor'} (DetrConfig 모델)
• dinat — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (DinatConfig 모델)
• dinov2 — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (Dinov2Config 모델)
• dinov3_vit — {'torchvision': 'DINOv3ViTImageProcessor'} (DINOv3ViTConfig 모델)
• donut-swin — {'torchvision': 'DonutImageProcessor', 'pil': 'DonutImageProcessorPil'} (DonutSwinConfig 모델)
• dots3_note — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Dots3NoteConfig 모델)
• dpt — {'pil': 'DPTImageProcessorPil', 'torchvision': 'DPTImageProcessor'} (DPTConfig 모델)
• edgetam — {'torchvision': 'Sam2ImageProcessor'} (EdgeTamConfig 모델)
• efficientloftr — {'pil': 'EfficientLoFTRImageProcessorPil', 'torchvision': 'EfficientLoFTRImageProcessor'} (EfficientLoFTRConfig 모델)
• efficientnet — {'pil': 'EfficientNetImageProcessorPil', 'torchvision': 'EfficientNetImageProcessor'} (EfficientNetConfig 모델)
• embedding_gemma2 — {'pil': 'Gemma4ImageProcessorPil', 'torchvision': 'Gemma4ImageProcessor'} (EmbeddingGemma2Config 모델)
• emu3 — {'pil': 'Emu3ImageProcessor'} (Emu3Config 모델)
• eomt — {'pil': 'EomtImageProcessorPil', 'torchvision': 'EomtImageProcessor'} (EomtConfig 모델)
• eomt_dinov3 — {'torchvision': 'EomtImageProcessor', 'pil': 'EomtImageProcessorPil'} (EomtDinov3Config 모델)
• ernie4_5_vl_moe — {'pil': 'Ernie4_5_VLMoeImageProcessorPil', 'torchvision': 'Ernie4_5_VLMoeImageProcessor'} (Ernie4_5_VLMoeConfig 모델)
• exaone4_5 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Exaone4_5_Config 모델)
• flava — {'pil': 'FlavaImageProcessorPil', 'torchvision': 'FlavaImageProcessor'} (FlavaConfig 모델)
• florence2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (Florence2Config 모델)
• focalnet — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (FocalNetConfig 모델)
• fuyu — {'pil': 'FuyuImageProcessorPil', 'torchvision': 'FuyuImageProcessor'} (FuyuConfig 모델)
• gemma3 — {'pil': 'Gemma3ImageProcessorPil', 'torchvision': 'Gemma3ImageProcessor'} (Gemma3Config 모델)
• gemma3n — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (Gemma3nConfig 모델)
• gemma4 — {'pil': 'Gemma4ImageProcessorPil', 'torchvision': 'Gemma4ImageProcessor'} (Gemma4Config 모델)
• gemma4_unified — {'torchvision': 'Gemma4UnifiedImageProcessor'} (Gemma4UnifiedConfig 모델)
• git — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (GitConfig 모델)
• glm46v — {'pil': 'Glm46VImageProcessorPil', 'torchvision': 'Glm46VImageProcessor'} (Glm46VConfig 모델)
• glm4v — {'pil': 'Glm4vImageProcessorPil', 'torchvision': 'Glm4vImageProcessor'} (Glm4vConfig 모델)
• glm5_next — {'pil': 'Glm5NextImageProcessorPil', 'torchvision': 'Glm5NextImageProcessor'} (Glm5NextConfig 모델)
• glm_image — {'pil': 'GlmImageImageProcessorPil', 'torchvision': 'GlmImageImageProcessor'} (GlmImageConfig 모델)
• glmga — {'pil': 'GlmgaImageProcessorPil', 'torchvision': 'GlmgaImageProcessor'} (GlmgaConfig 모델)
• glpn — {'pil': 'GLPNImageProcessorPil', 'torchvision': 'GLPNImageProcessor'} (GLPNConfig 모델)
• got_ocr2 — {'pil': 'GotOcr2ImageProcessorPil', 'torchvision': 'GotOcr2ImageProcessor'} (GotOcr2Config 모델)
• granite4_vision — {'torchvision': 'LlavaNextImageProcessor', 'pil': 'LlavaNextImageProcessorPil'} (Granite4VisionConfig 모델)
• granite_docling — {'pil': 'GraniteDoclingImageProcessorPil', 'torchvision': 'GraniteDoclingImageProcessor'} (GraniteDoclingConfig 모델)
• grounding-dino — {'pil': 'GroundingDinoImageProcessorPil', 'torchvision': 'GroundingDinoImageProcessor'} (GroundingDinoConfig 모델)
• groupvit — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (GroupViTConfig 모델)
• hiera — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (HieraConfig 모델)
• hunyuan_vl — {'pil': 'HunYuanVLImageProcessorPil', 'torchvision': 'HunYuanVLImageProcessor'} (HunYuanVLConfig 모델)
• hyperclovax_vision_v2 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (HyperCLOVAXVisionV2Config 모델)
• idefics — {'pil': 'IdeficsImageProcessorPil', 'torchvision': 'IdeficsImageProcessor'} (IdeficsConfig 모델)
• idefics2 — {'pil': 'Idefics2ImageProcessorPil', 'torchvision': 'Idefics2ImageProcessor'} (Idefics2Config 모델)
• idefics3 — {'pil': 'Idefics3ImageProcessorPil', 'torchvision': 'Idefics3ImageProcessor'} (Idefics3Config 모델)
• ijepa — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (IJepaConfig 모델)
• imagegpt — {'pil': 'ImageGPTImageProcessorPil', 'torchvision': 'ImageGPTImageProcessor'} (ImageGPTConfig 모델)
• inkling2 — {'torchvision': 'Inkling2ImageProcessor'} (Inkling2Config 모델)
• inkling_mm_model — {'torchvision': 'InklingImageProcessor'} (InklingConfig 모델)
• instructblip — {'torchvision': 'BlipImageProcessor', 'pil': 'BlipImageProcessorPil'} (InstructBlipConfig 모델)
• internvl — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (InternVLConfig 모델)
• janus — {'pil': 'JanusImageProcessorPil', 'torchvision': 'JanusImageProcessor'} (JanusConfig 모델)
• kimi_k25 — {'torchvision': 'Kimi_K25ImageProcessor'} (Kimi_K25Config 모델)
• kosmos-2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (Kosmos2Config 모델)
• kosmos-2.5 — {'torchvision': 'Kosmos2_5ImageProcessor', 'pil': 'Kosmos2_5ImageProcessorPil'} (Kosmos2_5Config 모델)
• layoutlmv2 — {'pil': 'LayoutLMv2ImageProcessorPil', 'torchvision': 'LayoutLMv2ImageProcessor'} (LayoutLMv2Config 모델)
• layoutlmv3 — {'pil': 'LayoutLMv3ImageProcessorPil', 'torchvision': 'LayoutLMv3ImageProcessor'} (LayoutLMv3Config 모델)
• layoutxlm — {'torchvision': 'LayoutLMv2ImageProcessor', 'pil': 'LayoutLMv2ImageProcessorPil'} (LayoutXLMConfig 모델)
• levit — {'pil': 'LevitImageProcessorPil', 'torchvision': 'LevitImageProcessor'} (LevitConfig 모델)
• lfm2_vl — {'torchvision': 'Lfm2VlImageProcessor'} (Lfm2VlConfig 모델)
• lfm3_vl — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Lfm3VlConfig 모델)
• lightglue — {'pil': 'LightGlueImageProcessorPil', 'torchvision': 'LightGlueImageProcessor'} (LightGlueConfig 모델)
• lighton_ocr — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (LightOnOcrConfig 모델)
• llama4 — {'torchvision': 'Llama4ImageProcessor'} (Llama4Config 모델)
• llava — {'pil': 'LlavaImageProcessorPil', 'torchvision': 'LlavaImageProcessor'} (LlavaConfig 모델)
• llava_next — {'pil': 'LlavaNextImageProcessorPil', 'torchvision': 'LlavaNextImageProcessor'} (LlavaNextConfig 모델)
• llava_next_video — {'torchvision': 'LlavaNextImageProcessor', 'pil': 'LlavaNextImageProcessorPil'} (LlavaNextVideoConfig 모델)
• llava_onevision — {'pil': 'LlavaOnevisionImageProcessorPil', 'torchvision': 'LlavaOnevisionImageProcessor'} (LlavaOnevisionConfig 모델)
• lw_detr — {'torchvision': 'DeformableDetrImageProcessor', 'pil': 'DeformableDetrImageProcessorPil'} (LwDetrConfig 모델)
• mask2former — {'pil': 'Mask2FormerImageProcessorPil', 'torchvision': 'Mask2FormerImageProcessor'} (Mask2FormerConfig 모델)
• maskformer — {'pil': 'MaskFormerImageProcessorPil', 'torchvision': 'MaskFormerImageProcessor'} (MaskFormerConfig 모델)
• metaclip_2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (MetaClip2Config 모델)
• mgp-str — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (MgpstrConfig 모델)
• minicpm_ocr — {'torchvision': 'MiniCPMOcrImageProcessor'} (MiniCPMOcrConfig 모델)
• minicpmv4_6 — {'pil': 'MiniCPMV4_6ImageProcessorPil', 'torchvision': 'MiniCPMV4_6ImageProcessor'} (MiniCPMV4_6Config 모델)
• minicpmv4_7 — {'pil': 'MiniCPMV4_6ImageProcessorPil', 'torchvision': 'MiniCPMV4_6ImageProcessor'} (MiniCPMV4_7Config 모델)
• minimax_m3_vl — {'torchvision': 'MiniMaxM3VLImageProcessor'} (MiniMaxM3VLConfig 모델)
• mistral3 — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (Mistral3Config 모델)
• mistral_large4 — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (MistralLarge4Config 모델)
• mlcd — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (MLCDVisionConfig 모델)
• mllama — {'pil': 'MllamaImageProcessorPil', 'torchvision': 'MllamaImageProcessor'} (MllamaConfig 모델)
• mm-grounding-dino — {'torchvision': 'GroundingDinoImageProcessor', 'pil': 'GroundingDinoImageProcessorPil'} (MMGroundingDinoConfig 모델)
• mobilenet_v1 — {'pil': 'MobileNetV1ImageProcessorPil', 'torchvision': 'MobileNetV1ImageProcessor'} (MobileNetV1Config 모델)
• mobilenet_v2 — {'pil': 'MobileNetV2ImageProcessorPil', 'torchvision': 'MobileNetV2ImageProcessor'} (MobileNetV2Config 모델)
• mobilevit — {'pil': 'MobileViTImageProcessorPil', 'torchvision': 'MobileViTImageProcessor'} (MobileViTConfig 모델)
• mobilevitv2 — {'torchvision': 'MobileViTImageProcessor', 'pil': 'MobileViTImageProcessorPil'} (MobileViTV2Config 모델)
• molmo2 — {'torchvision': 'Molmo2ImageProcessor'} (Molmo2Config 모델)
• muse_glimmer — {'torchvision': 'MuseGlimmerImageProcessor'} (MuseGlimmerConfig 모델)
• muse_spark — {'torchvision': 'MuseGlimmerImageProcessor'} (MuseSparkConfig 모델)
• nemotron_h_omni — {'torchvision': 'NemotronH_Omni_Reasoning_V3ImageProcessor'} (NemotronH_Omni_Reasoning_V3_Config 모델)
• neomme — {'torchvision': 'NeoMMEImageProcessor'} (NeoMMEConfig 모델)
• nougat — {'pil': 'NougatImageProcessorPil', 'torchvision': 'NougatImageProcessor'} (NougatConfig 모델)
• omdet-turbo — {'torchvision': 'DetrImageProcessor', 'pil': 'DetrImageProcessorPil'} (OmDetTurboConfig 모델)
• oneformer — {'pil': 'OneFormerImageProcessorPil', 'torchvision': 'OneFormerImageProcessor'} (OneFormerConfig 모델)
• ovis2 — {'pil': 'Ovis2ImageProcessorPil', 'torchvision': 'Ovis2ImageProcessor'} (Ovis2Config 모델)
• owlv2 — {'pil': 'Owlv2ImageProcessorPil', 'torchvision': 'Owlv2ImageProcessor'} (Owlv2Config 모델)
• owlvit — {'pil': 'OwlViTImageProcessorPil', 'torchvision': 'OwlViTImageProcessor'} (OwlViTConfig 모델)
• paddleocr_vl — {'pil': 'PaddleOCRVLImageProcessorPil', 'torchvision': 'PaddleOCRVLImageProcessor'} (PaddleOCRVLConfig 모델)
• paligemma — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (PaliGemmaConfig 모델)
• perceiver — {'pil': 'PerceiverImageProcessorPil', 'torchvision': 'PerceiverImageProcessor'} (PerceiverConfig 모델)
• perception_lm — {'torchvision': 'PerceptionLMImageProcessor'} (PerceptionLMConfig 모델)
• phi4_multimodal — {'torchvision': 'Phi4MultimodalImageProcessor'} (Phi4MultimodalConfig 모델)
• pi0 — {'torchvision': 'PI0ImageProcessor'} (PI0Config 모델)
• pix2struct — {'pil': 'Pix2StructImageProcessorPil', 'torchvision': 'Pix2StructImageProcessor'} (Pix2StructConfig 모델)
• pixio — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (PixioConfig 모델)
• pixtral — {'pil': 'PixtralImageProcessorPil', 'torchvision': 'PixtralImageProcessor'} (PixtralVisionConfig 모델)
• poolformer — {'pil': 'PoolFormerImageProcessorPil', 'torchvision': 'PoolFormerImageProcessor'} (PoolFormerConfig 모델)
• pp_chart2table — {'pil': 'PPChart2TableImageProcessorPil', 'torchvision': 'PPChart2TableImageProcessor'} (PPChart2TableConfig 모델)
• pp_doclayout_v2 — {'torchvision': 'PPDocLayoutV2ImageProcessor'} (PPDocLayoutV2Config 모델)
• pp_doclayout_v3 — {'torchvision': 'PPDocLayoutV3ImageProcessor'} (PPDocLayoutV3Config 모델)
• pp_doclayout_v4 — {'torchvision': 'PPDocLayoutV4ImageProcessor'} (PPDocLayoutV4Config 모델)
• pp_formulanet — {'torchvision': 'PPFormulaNetImageProcessor'} (PPFormulaNetConfig 모델)
• pp_lcnet — {'torchvision': 'PPLCNetImageProcessor'} (PPLCNetConfig 모델)
• pp_ocrv5_mobile_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (PPOCRV5MobileDetConfig 모델)
• pp_ocrv5_mobile_rec — {'torchvision': 'PPOCRV5ServerRecImageProcessor'} (PPOCRV5MobileRecConfig 모델)
• pp_ocrv5_server_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (PPOCRV5ServerDetConfig 모델)
• pp_ocrv5_server_rec — {'torchvision': 'PPOCRV5ServerRecImageProcessor'} (PPOCRV5ServerRecConfig 모델)
• pp_ocrv6_medium_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (PPOCRV6MediumDetConfig 모델)
• pp_ocrv6_small_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (PPOCRV6SmallDetConfig 모델)
• pp_ocrv6_small_rec — {'torchvision': 'PPOCRV6SmallRecImageProcessor'} (PPOCRV6SmallRecConfig 모델)
• pp_ocrv6_tiny_rec — {'torchvision': 'PPOCRV6SmallRecImageProcessor'} (PPOCRV6TinyRecConfig 모델)
• prompt_depth_anything — {'pil': 'PromptDepthAnythingImageProcessorPil', 'torchvision': 'PromptDepthAnythingImageProcessor'} (PromptDepthAnythingConfig 모델)
• pvt — {'pil': 'PvtImageProcessorPil', 'torchvision': 'PvtImageProcessor'} (PvtConfig 모델)
• pvt_v2 — {'torchvision': 'PvtImageProcessor', 'pil': 'PvtImageProcessorPil'} (PvtV2Config 모델)
• qianfan_ocr — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (QianfanOCRConfig 모델)
• qwen2_5_omni — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen2_5OmniConfig 모델)
• qwen2_5_vl — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen2_5_VLConfig 모델)
• qwen2_vl — {'pil': 'Qwen2VLImageProcessorPil', 'torchvision': 'Qwen2VLImageProcessor'} (Qwen2VLConfig 모델)
• qwen3_5 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen3_5Config 모델)
• qwen3_5_moe — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen3_5MoeConfig 모델)
• qwen3_omni_moe — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen3OmniMoeConfig 모델)
• qwen3_vl — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen3VLConfig 모델)
• qwen4_exp — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (Qwen4ExpConfig 모델)
• regnet — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (RegNetConfig 모델)
• resnet — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (ResNetConfig 모델)
• rf_detr — {'torchvision': 'RfDetrImageProcessor'} (RfDetrConfig 모델)
• rt_detr — {'pil': 'RTDetrImageProcessorPil', 'torchvision': 'RTDetrImageProcessor'} (RTDetrConfig 모델)
• sam — {'pil': 'SamImageProcessorPil', 'torchvision': 'SamImageProcessor'} (SamConfig 모델)
• sam2 — {'torchvision': 'Sam2ImageProcessor'} (Sam2Config 모델)
• sam2_video — {'torchvision': 'Sam2ImageProcessor'} (Sam2VideoConfig 모델)
• sam3 — {'torchvision': 'Sam3ImageProcessor'} (Sam3Config 모델)
• sam3_lite_text — {'torchvision': 'Sam3ImageProcessor'} (Sam3LiteTextConfig 모델)
• sam3_tracker — {'torchvision': 'Sam3ImageProcessor'} (Sam3TrackerConfig 모델)
• sam3_tracker_video — {'torchvision': 'Sam3ImageProcessor'} (Sam3TrackerVideoConfig 모델)
• sam3_video — {'torchvision': 'Sam3ImageProcessor'} (Sam3VideoConfig 모델)
• sam_hq — {'torchvision': 'SamImageProcessor', 'pil': 'SamImageProcessorPil'} (SamHQConfig 모델)
• sapiens2 — {'torchvision': 'Sapiens2ImageProcessor'} (Sapiens2Config 모델)
• segformer — {'pil': 'SegformerImageProcessorPil', 'torchvision': 'SegformerImageProcessor'} (SegformerConfig 모델)
• seggpt — {'pil': 'SegGptImageProcessorPil', 'torchvision': 'SegGptImageProcessor'} (SegGptConfig 모델)
• shieldgemma2 — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (ShieldGemma2Config 모델)
• siglip — {'pil': 'SiglipImageProcessorPil', 'torchvision': 'SiglipImageProcessor'} (SiglipConfig 모델)
• siglip2 — {'pil': 'Siglip2ImageProcessorPil', 'torchvision': 'Siglip2ImageProcessor'} (Siglip2Config 모델)
• slanet — {'torchvision': 'SLANeXtImageProcessor'} (SLANetConfig 모델)
• slanext — {'torchvision': 'SLANeXtImageProcessor'} (SLANeXtConfig 모델)
• smolvlm — {'pil': 'SmolVLMImageProcessorPil', 'torchvision': 'SmolVLMImageProcessor'} (SmolVLMConfig 모델)
• step3p7 — {'torchvision': 'Step3p7ImageProcessor'} (Step3p7Config 모델)
• superglue — {'pil': 'SuperGlueImageProcessorPil', 'torchvision': 'SuperGlueImageProcessor'} (SuperGlueConfig 모델)
• superpoint — {'pil': 'SuperPointImageProcessorPil', 'torchvision': 'SuperPointImageProcessor'} (SuperPointConfig 모델)
• swiftformer — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (SwiftFormerConfig 모델)
• swin — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (SwinConfig 모델)
• swin2sr — {'pil': 'Swin2SRImageProcessorPil', 'torchvision': 'Swin2SRImageProcessor'} (Swin2SRConfig 모델)
• swinv2 — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (Swinv2Config 모델)
• t5gemma2 — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (T5Gemma2Config 모델)
• t5gemma2_encoder — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (T5Gemma2EncoderConfig 모델)
• table-transformer — {'torchvision': 'DetrImageProcessor', 'pil': 'DetrImageProcessorPil'} (TableTransformerConfig 모델)
• textnet — {'pil': 'TextNetImageProcessorPil', 'torchvision': 'TextNetImageProcessor'} (TextNetConfig 모델)
• timesformer — {'pil': 'VideoMAEImageProcessorPil', 'torchvision': 'VideoMAEImageProcessor'} (TimesformerConfig 모델)
• timm_wrapper — {'pil': 'TimmWrapperImageProcessor'} (TimmWrapperConfig 모델)
• tipsv2 — {'torchvision': 'Tipsv2ImageProcessor'} (Tipsv2Config 모델)
• tipsv2_dpt — {'torchvision': 'Tipsv2DptImageProcessor'} (Tipsv2DptConfig 모델)
• trocr — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (TrOCRConfig 모델)
• tvp — {'pil': 'TvpImageProcessorPil', 'torchvision': 'TvpImageProcessor'} (TvpConfig 모델)
• udop — {'torchvision': 'LayoutLMv3ImageProcessor', 'pil': 'LayoutLMv3ImageProcessorPil'} (UdopConfig 모델)
• ultravbert — {'torchvision': 'UltraVBertImageProcessor'} (UltraVBertConfig 모델)
• unlimited_ocr — {'torchvision': 'UnlimitedOcrImageProcessor'} (UnlimitedOcrConfig 모델)
• upernet — {'torchvision': 'SegformerImageProcessor', 'pil': 'SegformerImageProcessorPil'} (UperNetConfig 모델)
• uvdoc — {'torchvision': 'UVDocImageProcessor'} (UVDocConfig 모델)
• video_llama_3 — {'pil': 'VideoLlama3ImageProcessorPil', 'torchvision': 'VideoLlama3ImageProcessor'} (VideoLlama3Config 모델)
• video_llava — {'pil': 'VideoLlavaImageProcessor'} (VideoLlavaConfig 모델)
• videomae — {'pil': 'VideoMAEImageProcessorPil', 'torchvision': 'VideoMAEImageProcessor'} (VideoMAEConfig 모델)
• vilt — {'pil': 'ViltImageProcessorPil', 'torchvision': 'ViltImageProcessor'} (ViltConfig 모델)
• vipllava — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (VipLlavaConfig 모델)
• vit — {'pil': 'ViTImageProcessorPil', 'torchvision': 'ViTImageProcessor'} (ViTConfig 모델)
• vit_mae — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (ViTMAEConfig 모델)
• vit_msn — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (ViTMSNConfig 모델)
• vitmatte — {'pil': 'VitMatteImageProcessorPil', 'torchvision': 'VitMatteImageProcessor'} (VitMatteConfig 모델)
• vitpose — {'pil': 'VitPoseImageProcessorPil', 'torchvision': 'VitPoseImageProcessor'} (VitPoseConfig 모델)
• vivit — {'torchvision': 'VivitImageProcessor'} (VivitConfig 모델)
• xclip — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (XCLIPConfig 모델)
• yolos — {'pil': 'YolosImageProcessorPil', 'torchvision': 'YolosImageProcessor'} (YolosConfig 모델)
• zoedepth — {'pil': 'ZoeDepthImageProcessorPil', 'torchvision': 'ZoeDepthImageProcessor'} (ZoeDepthConfig 모델)

비공개 모델을 사용하려면 token=True를 전달해야 합니다.

>>> from transformers import AutoImageProcessor

>>> # Download image processor from huggingface.co and cache.
>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")

>>> # If image processor files are in a directory (e.g. image processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # image_processor = AutoImageProcessor.from_pretrained("./test/saved_model/")

이 클래스에 새로운 이미지 프로세서를 등록합니다.

pretrained model 어휘에서 라이브러리의 비디오 프로세서 클래스 중 하나를 인스턴스화합니다.

config 객체의 model_type 속성(인자로 전달되거나, 가능하면 pretrained_model_name_or_path에서 로드된 값)을 기준으로 인스턴스화할 video processor 클래스가 선택됩니다. 해당 속성이 없으면 pretrained_model_name_or_path에 대해 패턴 매칭을 사용하는 방식으로 폴백합니다.

• cohere_compass — {'torchvision': 'CohereCompassVideoProcessor'} (CohereCompassConfig 모델)
• cosmos3_edge — {'torchvision': 'Cosmos3EdgeVideoProcessor'} (Cosmos3EdgeConfig 모델)
• cosmos3_omni — {'torchvision': 'Qwen3VLVideoProcessor'} (Cosmos3OmniConfig 모델)
• dots3_note — {'torchvision': 'Qwen3VLVideoProcessor'} (Dots3NoteConfig 모델)
• embedding_gemma2 — {'torchvision': 'EmbeddingGemma2VideoProcessor'} (EmbeddingGemma2Config 모델)
• ernie4_5_vl_moe — {'torchvision': 'Ernie4_5_VLMoeVideoProcessor'} (Ernie4_5_VLMoeConfig 모델)
• exaone4_5 — {'torchvision': 'Qwen2VLVideoProcessor'} (Exaone4_5_Config 모델)
• gemma4 — {'torchvision': 'Gemma4VideoProcessor'} (Gemma4Config 모델)
• gemma4_unified — {'torchvision': 'Gemma4UnifiedVideoProcessor'} (Gemma4UnifiedConfig 모델)
• glm46v — {'torchvision': 'Glm46VVideoProcessor'} (Glm46VConfig 모델)
• glm4v — {'torchvision': 'Glm4vVideoProcessor'} (Glm4vConfig 모델)
• glm5_next — {'torchvision': 'Glm5NextVideoProcessor'} (Glm5NextConfig 모델)
• glmga — {'torchvision': 'GlmgaVideoProcessor'} (GlmgaConfig 모델)
• hyperclovax_vision_v2 — {'torchvision': 'Qwen2VLVideoProcessor'} (HyperCLOVAXVisionV2Config 모델)
• instructblip — {'torchvision': 'InstructBlipVideoVideoProcessor'} (InstructBlipConfig 모델)
• instructblipvideo — {'torchvision': 'InstructBlipVideoVideoProcessor'} (InstructBlipVideoConfig 모델)
• internvl — {'torchvision': 'InternVLVideoProcessor'} (InternVLConfig 모델)
• kimi_k25 — {'torchvision': 'Kimi_K25VideoProcessor'} (Kimi_K25Config 모델)
• lfm3_vl — {'torchvision': 'Qwen3VLVideoProcessor'} (Lfm3VlConfig 모델)
• llava_next_video — {'torchvision': 'LlavaNextVideoVideoProcessor'} (LlavaNextVideoConfig 모델)
• llava_onevision — {'torchvision': 'LlavaOnevisionVideoProcessor'} (LlavaOnevisionConfig 모델)
• minicpm_ocr — {'torchvision': 'MiniCPMOcrVideoProcessor'} (MiniCPMOcrConfig 모델)
• minicpmv4_6 — {'torchvision': 'MiniCPMV4_6VideoProcessor'} (MiniCPMV4_6Config 모델)
• minicpmv4_7 — {'torchvision': 'MiniCPMV4_6VideoProcessor'} (MiniCPMV4_7Config 모델)
• minimax_m3_vl — {'torchvision': 'MiniMaxM3VLVideoProcessor'} (MiniMaxM3VLConfig 모델)
• molmo2 — {'torchvision': 'Molmo2VideoProcessor'} (Molmo2Config 모델)
• muse_glimmer — {'torchvision': 'MuseGlimmerVideoProcessor'} (MuseGlimmerConfig 모델)
• muse_spark — {'torchvision': 'MuseGlimmerVideoProcessor'} (MuseSparkConfig 모델)
• nemotron_h_omni — {'torchvision': 'NemotronH_Omni_Reasoning_V3VideoProcessor'} (NemotronH_Omni_Reasoning_V3_Config 모델)
• pe_audio_video — {'torchvision': 'PeVideoVideoProcessor'} (PeAudioVideoConfig 모델)
• pe_video — {'torchvision': 'PeVideoVideoProcessor'} (PeVideoConfig 모델)
• perception_lm — {'torchvision': 'PerceptionLMVideoProcessor'} (PerceptionLMConfig 모델)
• qwen2_5_omni — {'torchvision': 'Qwen2VLVideoProcessor'} (Qwen2_5OmniConfig 모델)
• qwen2_5_vl — {'torchvision': 'Qwen2VLVideoProcessor'} (Qwen2_5_VLConfig 모델)
• qwen2_vl — {'torchvision': 'Qwen2VLVideoProcessor'} (Qwen2VLConfig 모델)
• qwen3_5 — {'torchvision': 'Qwen3VLVideoProcessor'} (Qwen3_5Config 모델)
• qwen3_5_moe — {'torchvision': 'Qwen3VLVideoProcessor'} (Qwen3_5MoeConfig 모델)
• qwen3_omni_moe — {'torchvision': 'Qwen2VLVideoProcessor'} (Qwen3OmniMoeConfig 모델)
• qwen3_vl — {'torchvision': 'Qwen3VLVideoProcessor'} (Qwen3VLConfig 모델)
• qwen3_vl_moe — {'torchvision': 'Qwen3VLVideoProcessor'} (Qwen3VLMoeConfig 모델)
• qwen4_exp — {'torchvision': 'Qwen3VLVideoProcessor'} (Qwen4ExpConfig 모델)
• sam2_video — {'torchvision': 'Sam2VideoVideoProcessor'} (Sam2VideoConfig 모델)
• smolvlm — {'torchvision': 'SmolVLMVideoProcessor'} (SmolVLMConfig 모델)
• timesformer — {'torchvision': 'TimesformerVideoProcessor'} (TimesformerConfig 모델)
• video_llama_3 — {'torchvision': 'VideoLlama3VideoProcessor'} (VideoLlama3Config 모델)
• video_llava — {'torchvision': 'VideoLlavaVideoProcessor'} (VideoLlavaConfig 모델)
• videomae — {'torchvision': 'VideoMAEVideoProcessor'} (VideoMAEConfig 모델)
• videomt — {'torchvision': 'VideomtVideoProcessor'} (VideomtConfig 모델)
• videoprism — {'torchvision': 'LlavaOnevisionVideoProcessor'} (VideoPrismConfig 모델)
• vivit — {'torchvision': 'VivitVideoProcessor'} (VivitConfig 모델)
• vjepa2 — {'torchvision': 'VJEPA2VideoProcessor'} (VJEPA2Config 모델)

비공개 모델을 사용하려면 token=True를 전달해야 합니다.

>>> from transformers import AutoVideoProcessor

>>> # Download video processor from huggingface.co and cache.
>>> video_processor = AutoVideoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-0.5b-ov-hf")

>>> # If video processor files are in a directory (e.g. video processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # video_processor = AutoVideoProcessor.from_pretrained("./test/saved_model/")

이 클래스에 새로운 video processor를 등록합니다.

…

인스턴스화할 프로세서 클래스는 config 객체의 model_type 속성(인수로 전달되거나, 가능하면 pretrained_model_name_or_path에서 로드된 값)에 따라 선택됩니다:

• aimv2 — CLIPProcessor (Aimv2Config 모델)
• align — AlignProcessor (AlignConfig 모델)
• altclip — AltCLIPProcessor (AltCLIPConfig 모델)
• aria — AriaProcessor (AriaConfig 모델)
• audioflamingo3 — AudioFlamingo3Processor (AudioFlamingo3Config 모델)
• aya_vision — AyaVisionProcessor (AyaVisionConfig 모델)
• bark — BarkProcessor (BarkConfig 모델)
• blip — BlipProcessor (BlipConfig 모델)
• blip-2 — Blip2Processor (Blip2Config 모델)
• bridgetower — BridgeTowerProcessor (BridgeTowerConfig 모델)
• bros — BrosProcessor (BrosConfig 모델)
• canary — CanaryProcessor (CanaryConfig 모델)
• chameleon — ChameleonProcessor (ChameleonConfig 모델)
• chinese_clip — ChineseCLIPProcessor (ChineseCLIPConfig 모델)
• clap — ClapProcessor (ClapConfig 모델)
• clip — CLIPProcessor (CLIPConfig 모델)
• clipseg — CLIPSegProcessor (CLIPSegConfig 모델)
• clvp — ClvpProcessor (ClvpConfig 모델)
• cohere2_vision — Cohere2VisionProcessor (Cohere2VisionConfig 모델)
• cohere_asr — CohereAsrProcessor (CohereAsrConfig 모델)
• cohere_compass — CohereCompassProcessor (CohereCompassConfig 모델)
• colmodernvbert — ColModernVBertProcessor (ColModernVBertConfig 모델)
• colpali — ColPaliProcessor (ColPaliConfig 모델)
• colqwen2 — ColQwen2Processor (ColQwen2Config 모델)
• cosmos3_edge — Cosmos3EdgeProcessor (Cosmos3EdgeConfig 모델)
• csm — CsmProcessor (CsmConfig 모델)
• deepseek_ocr2 — DeepseekOcr2Processor (DeepseekOcr2Config 모델)
• deepseek_vl — DeepseekVLProcessor (DeepseekVLConfig 모델)
• deepseek_vl_hybrid — DeepseekVLHybridProcessor (DeepseekVLHybridConfig 모델)
• dia — DiaProcessor (DiaConfig 모델)
• diffusion_gemma — Gemma4Processor (DiffusionGemmaConfig 모델)
• dots3_note — Dots3NoteProcessor (Dots3NoteConfig 모델)
• edgetam — Sam2Processor (EdgeTamConfig 모델)
• embedding_gemma2 — EmbeddingGemma2Processor (EmbeddingGemma2Config 모델)
• emu3 — Emu3Processor (Emu3Config 모델)
• ernie4_5_vl_moe — Ernie4_5_VLMoeProcessor (Ernie4_5_VLMoeConfig 모델)
• evolla — EvollaProcessor (EvollaConfig 모델)
• exaone4_5 — Exaone4_5_Processor (Exaone4_5_Config 모델)
• flava — FlavaProcessor (FlavaConfig 모델)
• florence2 — Florence2Processor (Florence2Config 모델)
• fun_asr_nano — FunAsrNanoProcessor (FunAsrNanoConfig 모델)
• fuyu — FuyuProcessor (FuyuConfig 모델)
• gemma3 — Gemma3Processor (Gemma3Config 모델)
• gemma3n — Gemma3nProcessor (Gemma3nConfig 모델)
• gemma4 — Gemma4Processor (Gemma4Config 모델)
• gemma4_unified — Gemma4UnifiedProcessor (Gemma4UnifiedConfig 모델)
• git — GitProcessor (GitConfig 모델)
• glm46v — Glm46VProcessor (Glm46VConfig 모델)
• glm4v — Glm4vProcessor (Glm4vConfig 모델)
• glm4v_moe — Glm4vProcessor (Glm4vMoeConfig 모델)
• glm5_next — Glm5NextProcessor (Glm5NextConfig 모델)
• glm_image — GlmImageProcessor (GlmImageConfig 모델)
• glmasr — GlmAsrProcessor (GlmAsrConfig 모델)
• got_ocr2 — GotOcr2Processor (GotOcr2Config 모델)
• gradium_phonon_tts — PocketTTSProcessor (GradiumPhononTTSConfig 모델)
• granite4_vision — Granite4VisionProcessor (Granite4VisionConfig 모델)
• granite_docling — GraniteDoclingProcessor (GraniteDoclingConfig 모델)
• granite_speech — GraniteSpeechProcessor (GraniteSpeechConfig 모델)
• granite_speech5_ctc — GraniteSpeech5Processor (GraniteSpeech5CTCConfig 모델)
• granite_speech_plus — GraniteSpeechProcessor (GraniteSpeechPlusConfig 모델)
• grounding-dino — GroundingDinoProcessor (GroundingDinoConfig 모델)
• groupvit — CLIPProcessor (GroupViTConfig 모델)
• higgs_audio_v2 — HiggsAudioV2Processor (HiggsAudioV2Config 모델)
• hubert — Wav2Vec2Processor (HubertConfig 모델)
• hunyuan_vl — HunYuanVLProcessor (HunYuanVLConfig 모델)
• hyperclovax_vision_v2 — HyperCLOVAXVisionV2Processor (HyperCLOVAXVisionV2Config 모델)
• idefics — IdeficsProcessor (IdeficsConfig 모델)
• idefics2 — Idefics2Processor (Idefics2Config 모델)
• idefics3 — Idefics3Processor (Idefics3Config 모델)
• inkling2 — Inkling2Processor (Inkling2Config 모델)
• inkling_mm_model — InklingProcessor (InklingConfig 모델)
• instructblip — InstructBlipProcessor (InstructBlipConfig 모델)
• instructblipvideo — InstructBlipVideoProcessor (InstructBlipVideoConfig 모델)
• internvl — InternVLProcessor (InternVLConfig 모델)
• janus — JanusProcessor (JanusConfig 모델)
• kimi_k25 — Kimi_K25Processor (Kimi_K25Config 모델)
• kyutai_speech_to_text — KyutaiSpeechToTextProcessor (KyutaiSpeechToTextConfig 모델)
• lasr_ctc — LasrProcessor (LasrCTCConfig 모델)
• lasr_encoder — LasrProcessor (LasrEncoderConfig 모델)
• layoutlmv2 — LayoutLMv2Processor (LayoutLMv2Config 모델)
• layoutlmv3 — LayoutLMv3Processor (LayoutLMv3Config 모델)
• layoutxlm — LayoutXLMProcessor (LayoutXLMConfig 모델)
• lfm2_vl — Lfm2VlProcessor (Lfm2VlConfig 모델)
• lfm3_vl — Lfm3VlProcessor (Lfm3VlConfig 모델)
• lighton_ocr — LightOnOcrProcessor (LightOnOcrConfig 모델)
• llama4 — Llama4Processor (Llama4Config 모델)
• llava — LlavaProcessor (LlavaConfig 모델)
• llava_next — LlavaNextProcessor (LlavaNextConfig 모델)
• llava_next_video — LlavaNextVideoProcessor (LlavaNextVideoConfig 모델)
• llava_onevision — LlavaOnevisionProcessor (LlavaOnevisionConfig 모델)
• markuplm — MarkupLMProcessor (MarkupLMConfig 모델)
• metaclip_2 — CLIPProcessor (MetaClip2Config 모델)
• mgp-str — MgpstrProcessor (MgpstrConfig 모델)
• minicpm_ocr — MiniCPMOcrProcessor (MiniCPMOcrConfig 모델)
• minicpmv4_6 — MiniCPMV4_6Processor (MiniCPMV4_6Config 모델)
• minicpmv4_7 — MiniCPMV4_7Processor (MiniCPMV4_7Config 모델)
• minimax_m3_vl — MiniMaxM3VLProcessor (MiniMaxM3VLConfig 모델)
• mistral3 — PixtralProcessor (Mistral3Config 모델)
• mistral_large4 — PixtralProcessor (MistralLarge4Config 모델)
• mllama — MllamaProcessor (MllamaConfig 모델)
• mm-grounding-dino — GroundingDinoProcessor (MMGroundingDinoConfig 모델)
• modernvbert — Idefics3Processor (ModernVBertConfig 모델)
• molmo2 — Molmo2Processor (Molmo2Config 모델)
• moonshine — Wav2Vec2Processor (MoonshineConfig 모델)
• moonshine_streaming — MoonshineStreamingProcessor (MoonshineStreamingConfig 모델)
• moss_transcribe_diarize — MossTranscribeDiarizeProcessor (MossTranscribeDiarizeConfig 모델)
• muse_glimmer — MuseGlimmerProcessor (MuseGlimmerConfig 모델)
• muse_spark — MuseSparkProcessor (MuseSparkConfig 모델)
• musicflamingo — MusicFlamingoProcessor (MusicFlamingoConfig 모델)
• musicgen — MusicgenProcessor (MusicgenConfig 모델)
• musicgen_melody — MusicgenMelodyProcessor (MusicgenMelodyConfig 모델)
• nemo_speechlm — Nemotron3_5TranscribeProcessor (Nemotron3_5TranscribeConfig 모델)
• nemotron3_5_asr — Nemotron3_5AsrProcessor (Nemotron3_5AsrConfig 모델)
• nemotron3_diarization — Nemotron3DiarizationProcessor (Nemotron3DiarizationConfig 모델)
• nemotron_asr_streaming — NemotronAsrStreamingProcessor (NemotronAsrStreamingConfig 모델)
• nemotron_h_omni — NemotronH_Omni_Reasoning_V3Processor (NemotronH_Omni_Reasoning_V3_Config 모델)
• neomme — NeoMMEProcessor (NeoMMEConfig 모델)
• nougat — NougatProcessor (NougatConfig 모델)
• omdet-turbo — OmDetTurboProcessor (OmDetTurboConfig 모델)
• oneformer — OneFormerProcessor (OneFormerConfig 모델)
• ovis2 — Ovis2Processor (Ovis2Config 모델)
• owlv2 — Owlv2Processor (Owlv2Config 모델)
• owlvit — OwlViTProcessor (OwlViTConfig 모델)
• paddleocr_vl — PaddleOCRVLProcessor (PaddleOCRVLConfig 모델)
• paligemma — PaliGemmaProcessor (PaliGemmaConfig 모델)
• parakeet_ctc — ParakeetProcessor (ParakeetCTCConfig 모델)
• parakeet_rnnt — ParakeetProcessor (ParakeetRNNTConfig 모델)
• parakeet_tdt — ParakeetProcessor (ParakeetTDTConfig 모델)
• pe_audio — PeAudioProcessor (PeAudioConfig 모델)
• pe_audio_video — PeAudioVideoProcessor (PeAudioVideoConfig 모델)
• pe_video — PeVideoProcessor (PeVideoConfig 모델)
• perception_lm — PerceptionLMProcessor (PerceptionLMConfig 모델)
• phi4_multimodal — Phi4MultimodalProcessor (Phi4MultimodalConfig 모델)
• pi0 — PI0Processor (PI0Config 모델)
• pix2struct — Pix2StructProcessor (Pix2StructConfig 모델)
• pixtral — PixtralProcessor (PixtralVisionConfig 모델)
• pocket_tts — PocketTTSProcessor (PocketTTSConfig 모델)
• pop2piano — Pop2PianoProcessor (Pop2PianoConfig 모델)
• pp_chart2table — PPChart2TableProcessor (PPChart2TableConfig 모델)
• pp_formulanet — PPFormulaNetProcessor (PPFormulaNetConfig 모델)
• qianfan_ocr — QianfanOCRProcessor (QianfanOCRConfig 모델)
• qwen2_5_omni — Qwen2_5OmniProcessor (Qwen2_5OmniConfig 모델)
• qwen2_5_vl — Qwen2_5_VLProcessor (Qwen2_5_VLConfig 모델)
• qwen2_audio — Qwen2AudioProcessor (Qwen2AudioConfig 모델)
• qwen2_vl — Qwen2VLProcessor (Qwen2VLConfig 모델)
• qwen3_5 — Qwen3VLProcessor (Qwen3_5Config 모델)
• qwen3_5_moe — Qwen3VLProcessor (Qwen3_5MoeConfig 모델)
• qwen3_asr — Qwen3ASRProcessor (Qwen3ASRConfig 모델)
• qwen3_omni_moe — Qwen3OmniMoeProcessor (Qwen3OmniMoeConfig 모델)
• qwen3_vl — Qwen3VLProcessor (Qwen3VLConfig 모델)
• qwen3_vl_moe — Qwen3VLProcessor (Qwen3VLMoeConfig 모델)
• qwen4_exp — Qwen3VLProcessor (Qwen4ExpConfig 모델)
• sam — SamProcessor (SamConfig 모델)
• sam2 — Sam2Processor (Sam2Config 모델)
• sam2_video — Sam2VideoProcessor (Sam2VideoConfig 모델)
• sam3 — Sam3Processor (Sam3Config 모델)
• sam3_lite_text — Sam3Processor (Sam3LiteTextConfig 모델)
• sam3_tracker — Sam3TrackerProcessor (Sam3TrackerConfig 모델)
• sam3_tracker_video — Sam3TrackerVideoProcessor (Sam3TrackerVideoConfig 모델)
• sam3_video — Sam3VideoProcessor (Sam3VideoConfig 모델)
• sam_hq — SamHQProcessor (SamHQConfig 모델)
• seamless_m4t — SeamlessM4TProcessor (SeamlessM4TConfig 모델)
• sew — Wav2Vec2Processor (SEWConfig 모델)
• sew-d — Wav2Vec2Processor (SEWDConfig 모델)
• shieldgemma2 — ShieldGemma2Processor (ShieldGemma2Config 모델)
• siglip — SiglipProcessor (SiglipConfig 모델)
• siglip2 — Siglip2Processor (Siglip2Config 모델)
• smolvlm — SmolVLMProcessor (SmolVLMConfig 모델)
• speech_to_text — Speech2TextProcessor (Speech2TextConfig 모델)
• speecht5 — SpeechT5Processor (SpeechT5Config 모델)
• step3p7 — Step3p7Processor (Step3p7Config 모델)
• t5gemma2 — Gemma3Processor (T5Gemma2Config 모델)
• t5gemma2_encoder — Gemma3Processor (T5Gemma2EncoderConfig 모델)
• tipsv2 — Tipsv2Processor (Tipsv2Config 모델)
• trocr — TrOCRProcessor (TrOCRConfig 모델)
• tvp — TvpProcessor (TvpConfig 모델)
• udop — UdopProcessor (UdopConfig 모델)
• ultravbert — Idefics3Processor (UltraVBertConfig 모델)
• unispeech — Wav2Vec2Processor (UniSpeechConfig 모델)
• unispeech-sat — Wav2Vec2Processor (UniSpeechSatConfig 모델)
• unlimited_ocr — UnlimitedOcrProcessor (UnlimitedOcrConfig 모델)
• vibevoice — VibeVoiceProcessor (VibeVoiceConfig 모델)
• vibevoice_asr — VibeVoiceAsrProcessor (VibeVoiceAsrConfig 모델)
• video_llama_3 — VideoLlama3Processor (VideoLlama3Config 모델)
• video_llava — VideoLlavaProcessor (VideoLlavaConfig 모델)
• videoprism — VideoPrismProcessor (VideoPrismConfig 모델)
• vilt — ViltProcessor (ViltConfig 모델)
• vipllava — LlavaProcessor (VipLlavaConfig 모델)
• vision-text-dual-encoder — VisionTextDualEncoderProcessor (VisionTextDualEncoderConfig 모델)
• voxtral — VoxtralProcessor (VoxtralConfig 모델)
• voxtral_realtime — VoxtralRealtimeProcessor (VoxtralRealtimeConfig 모델)
• wav2vec2 — Wav2Vec2Processor (Wav2Vec2Config 모델)
• wav2vec2-bert — Wav2Vec2BertProcessor (Wav2Vec2BertConfig 모델)
• wav2vec2-conformer — Wav2Vec2Processor (Wav2Vec2ConformerConfig 모델)
• wavlm — Wav2Vec2Processor (WavLMConfig 모델)
• whisper — WhisperProcessor (WhisperConfig 모델)

비공개 모델을 사용하려면 token=True를 전달해야 합니다.

>>> from transformers import AutoProcessor

>>> # Download processor from huggingface.co and cache.
>>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h")

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

이 클래스에 새 프로세서를 등록합니다.