Add check-auto in repo-consistency and fix sorting

src/transformers/models/auto/auto_mappings.py

@@ -628,210 +628,210 @@
 
 SPECIAL_MODEL_TYPE_TO_MODULE_NAME = OrderedDict(
     [
-        ("nllb-moe", "nllb_moe"),
-        ("dab-detr", "dab_detr"),
-        ("xlm-roberta-xl", "xlm_roberta_xl"),
+        ("aimv2_text_model", "aimv2"),
+        ("aimv2_vision_model", "aimv2"),
+        ("align_text_model", "align"),
+        ("align_vision_model", "align"),
+        ("altclip_text_model", "altclip"),
+        ("altclip_vision_model", "altclip"),
+        ("aria_text", "aria"),
         ("audio-spectrogram-transformer", "audio_spectrogram_transformer"),
-        ("megatron-bert", "megatron_bert"),
-        ("clipseg_text_model", "clipseg"),
-        ("clipseg_vision_model", "clipseg"),
-        ("t5gemma2_text", "t5gemma2"),
-        ("t5gemma2_encoder", "t5gemma2"),
-        ("t5gemma2_decoder", "t5gemma2"),
-        ("llama4_vision_model", "llama4"),
-        ("llama4_text", "llama4"),
-        ("pe_video_encoder", "pe_video"),
+        ("audioflamingo3_encoder", "audioflamingo3"),
+        ("bert-generation", "bert_generation"),
+        ("blenderbot-small", "blenderbot_small"),
+        ("blip-2", "blip_2"),
+        ("blip_2_qformer", "blip_2"),
+        ("blip_2_vision_model", "blip_2"),
+        ("blip_text_model", "blip"),
+        ("blip_vision_model", "blip"),
+        ("blt_global_transformer", "blt"),
+        ("blt_local_decoder", "blt"),
+        ("blt_local_encoder", "blt"),
+        ("blt_patcher", "blt"),
+        ("bridgetower_text_model", "bridgetower"),
+        ("bridgetower_vision_model", "bridgetower"),
         ("chameleon_vqgan", "chameleon"),
-        ("aimv2_vision_model", "aimv2"),
-        ("aimv2_text_model", "aimv2"),
-        ("siglip2_text_model", "siglip2"),
-        ("siglip2_vision_model", "siglip2"),
+        ("chinese_clip_text_model", "chinese_clip"),
+        ("chinese_clip_vision_model", "chinese_clip"),
+        ("clap_audio_model", "clap"),
+        ("clap_text_model", "clap"),
         ("clip_text_model", "clip"),
         ("clip_vision_model", "clip"),
+        ("clipseg_text_model", "clipseg"),
+        ("clipseg_vision_model", "clipseg"),
+        ("clvp_decoder", "clvp"),
+        ("clvp_encoder", "clvp"),
+        ("csm_depth_decoder_model", "csm"),
+        ("dab-detr", "dab_detr"),
+        ("data2vec-audio", "data2vec"),
+        ("data2vec-text", "data2vec"),
+        ("data2vec-vision", "data2vec"),
+        ("deberta-v2", "deberta_v2"),
+        ("detr", "maskformer"),
+        ("dia_decoder", "dia"),
+        ("dia_encoder", "dia"),
+        ("donut-swin", "donut"),
+        ("edgetam_vision_model", "edgetam"),
+        ("emu3_text_model", "emu3"),
+        ("emu3_vqgan", "emu3"),
+        ("encoder-decoder", "encoder_decoder"),
+        ("ernie4_5_vl_moe_text", "ernie4_5_vl_moe"),
+        ("ernie4_5_vl_moe_vision", "ernie4_5_vl_moe"),
         ("fastspeech2_conformer_hifigan", "fastspeech2_conformer"),
         ("fastspeech2_conformer_with_hifigan", "fastspeech2_conformer"),
-        ("rt_detr_resnet", "rt_detr"),
-        ("qwen2_5_vl_vision", "qwen2_5_vl"),
-        ("qwen2_5_vl_text", "qwen2_5_vl"),
-        ("glm4v_vision", "glm4v"),
-        ("glm4v_text", "glm4v"),
-        ("moshi_depth", "moshi"),
-        ("qwen3_5_text", "qwen3_5"),
-        ("qwen3_5_vision", "qwen3_5"),
+        ("flava_image_model", "flava"),
+        ("flava_multimodal_model", "flava"),
+        ("flava_text_model", "flava"),
+        ("florence_vision", "florence2"),
         ("gemma3_text", "gemma3"),
-        ("glmasr_encoder", "glmasr"),
-        ("sam3_vit_model", "sam3"),
-        ("sam3_vision_model", "sam3"),
-        ("sam3_lite_text_geometry_encoder", "sam3_lite_text"),
-        ("sam3_lite_text_detr_encoder", "sam3_lite_text"),
-        ("sam3_lite_text_detr_decoder", "sam3_lite_text"),
-        ("sam3_lite_text_mask_decoder", "sam3_lite_text"),
-        ("sam3_lite_text_text_model", "sam3_lite_text"),
-        ("detr", "maskformer"),
-        ("maskformer-swin", "maskformer"),
-        ("roberta-prelayernorm", "roberta_prelayernorm"),
-        ("glm_image_vqmodel", "glm_image"),
-        ("glm_image_vision", "glm_image"),
-        ("glm_image_text", "glm_image"),
-        ("pix2struct_text_model", "pix2struct"),
-        ("pix2struct_vision_model", "pix2struct"),
-        ("clvp_encoder", "clvp"),
-        ("clvp_decoder", "clvp"),
-        ("idefics_vision", "idefics"),
-        ("idefics_perciever", "idefics"),
-        ("gemma3n_text", "gemma3n"),
         ("gemma3n_audio", "gemma3n"),
+        ("gemma3n_text", "gemma3n"),
         ("gemma3n_vision", "gemma3n"),
-        ("florence_vision", "florence2"),
-        ("bert-generation", "bert_generation"),
-        ("clap_text_model", "clap"),
-        ("clap_audio_model", "clap"),
-        ("vision-text-dual-encoder", "vision_text_dual_encoder"),
-        ("dia_encoder", "dia"),
-        ("dia_decoder", "dia"),
-        ("phi4_multimodal_vision", "phi4_multimodal"),
-        ("phi4_multimodal_audio", "phi4_multimodal"),
-        ("metaclip_2_text_model", "metaclip_2"),
-        ("metaclip_2_vision_model", "metaclip_2"),
-        ("sam_hq_vision_model", "sam_hq"),
-        ("voxtral_realtime_text", "voxtral_realtime"),
-        ("voxtral_realtime_encoder", "voxtral_realtime"),
+        ("gemma4_audio", "gemma4"),
+        ("gemma4_text", "gemma4"),
+        ("gemma4_vision", "gemma4"),
+        ("git_vision_model", "git"),
+        ("glm4v_moe_text", "glm4v_moe"),
+        ("glm4v_moe_vision", "glm4v_moe"),
+        ("glm4v_text", "glm4v"),
+        ("glm4v_vision", "glm4v"),
+        ("glm_image_text", "glm_image"),
+        ("glm_image_vision", "glm_image"),
+        ("glm_image_vqmodel", "glm_image"),
+        ("glm_ocr_text", "glm_ocr"),
+        ("glm_ocr_vision", "glm_ocr"),
+        ("glmasr_encoder", "glmasr"),
+        ("granite_speech_encoder", "granite_speech"),
+        ("grounding-dino", "grounding_dino"),
+        ("groupvit_text_model", "groupvit"),
+        ("groupvit_vision_model", "groupvit"),
+        ("idefics2_perceiver", "idefics2"),
+        ("idefics2_vision", "idefics2"),
+        ("idefics3_vision", "idefics3"),
+        ("idefics_perciever", "idefics"),
+        ("idefics_vision", "idefics"),
+        ("instructblip_qformer", "instructblip"),
+        ("instructblip_vision_model", "instructblip"),
+        ("instructblipvideo_qformer", "instructblipvideo"),
+        ("instructblipvideo_vision_model", "instructblipvideo"),
+        ("internvl_vision", "internvl"),
+        ("janus_vision_model", "janus"),
+        ("janus_vqgan", "janus"),
+        ("kosmos-2", "kosmos2"),
+        ("kosmos-2.5", "kosmos2_5"),
+        ("kosmos_2_5_text_model", "kosmos2_5"),
+        ("kosmos_2_5_vision_model", "kosmos2_5"),
         ("kosmos_2_text_model", "kosmos2"),
         ("kosmos_2_vision_model", "kosmos2"),
-        ("kosmos-2", "kosmos2"),
-        ("voxtral_encoder", "voxtral"),
-        ("grounding-dino", "grounding_dino"),
-        ("t5_gemma_module", "t5gemma"),
-        ("bridgetower_vision_model", "bridgetower"),
-        ("bridgetower_text_model", "bridgetower"),
-        ("qwen2_5_omni_vision_encoder", "qwen2_5_omni"),
+        ("lasr_ctc", "lasr"),
+        ("lasr_encoder", "lasr"),
+        ("llama4_text", "llama4"),
+        ("llama4_vision_model", "llama4"),
+        ("lw_detr_vit", "lw_detr"),
+        ("maskformer-swin", "maskformer"),
+        ("megatron-bert", "megatron_bert"),
+        ("metaclip_2_text_model", "metaclip_2"),
+        ("metaclip_2_vision_model", "metaclip_2"),
+        ("mgp-str", "mgp_str"),
+        ("mlcd_vision_model", "mlcd"),
+        ("mllama_text_model", "mllama"),
+        ("mllama_vision_model", "mllama"),
+        ("mm-grounding-dino", "mm_grounding_dino"),
+        ("modernbert-decoder", "modernbert_decoder"),
+        ("moonshine_streaming_encoder", "moonshine_streaming"),
+        ("moshi_depth", "moshi"),
+        ("musicgen_decoder", "musicgen"),
+        ("musicgen_melody_decoder", "musicgen_melody"),
+        ("nllb-moe", "nllb_moe"),
+        ("omdet-turbo", "omdet_turbo"),
+        ("openai-gpt", "openai"),
+        ("owlv2_text_model", "owlv2"),
+        ("owlv2_vision_model", "owlv2"),
+        ("owlvit_text_model", "owlvit"),
+        ("owlvit_vision_model", "owlvit"),
+        ("paddleocr_vl_text", "paddleocr_vl"),
+        ("paddleocr_vl_vision", "paddleocr_vl"),
+        ("parakeet_ctc", "parakeet"),
+        ("parakeet_encoder", "parakeet"),
+        ("pe_audio_encoder", "pe_audio"),
+        ("pe_audio_video_encoder", "pe_audio_video"),
+        ("pe_video_encoder", "pe_video"),
+        ("phi4_multimodal_audio", "phi4_multimodal"),
+        ("phi4_multimodal_vision", "phi4_multimodal"),
+        ("pix2struct_text_model", "pix2struct"),
+        ("pix2struct_vision_model", "pix2struct"),
         ("qwen2_5_omni_audio_encoder", "qwen2_5_omni"),
+        ("qwen2_5_omni_bigvgan", "qwen2_5_omni"),
+        ("qwen2_5_omni_dit", "qwen2_5_omni"),
+        ("qwen2_5_omni_talker", "qwen2_5_omni"),
         ("qwen2_5_omni_text", "qwen2_5_omni"),
         ("qwen2_5_omni_thinker", "qwen2_5_omni"),
-        ("qwen2_5_omni_talker", "qwen2_5_omni"),
-        ("qwen2_5_omni_dit", "qwen2_5_omni"),
-        ("qwen2_5_omni_bigvgan", "qwen2_5_omni"),
         ("qwen2_5_omni_token2wav", "qwen2_5_omni"),
-        ("speech-encoder-decoder", "speech_encoder_decoder"),
-        ("pe_audio_video_encoder", "pe_audio_video"),
-        ("kosmos_2_5_text_model", "kosmos2_5"),
-        ("kosmos_2_5_vision_model", "kosmos2_5"),
-        ("kosmos-2.5", "kosmos2_5"),
-        ("altclip_text_model", "altclip"),
-        ("altclip_vision_model", "altclip"),
-        ("speecht5_hifigan", "speecht5"),
-        ("pe_audio_encoder", "pe_audio"),
-        ("smolvlm_vision", "smolvlm"),
-        ("blt_local_encoder", "blt"),
-        ("blt_local_decoder", "blt"),
-        ("blt_global_transformer", "blt"),
-        ("blt_patcher", "blt"),
-        ("uvdoc_backbone", "uvdoc"),
+        ("qwen2_5_omni_vision_encoder", "qwen2_5_omni"),
+        ("qwen2_5_vl_text", "qwen2_5_vl"),
+        ("qwen2_5_vl_vision", "qwen2_5_vl"),
         ("qwen2_audio_encoder", "qwen2_audio"),
-        ("vision-encoder-decoder", "vision_encoder_decoder"),
-        ("edgetam_vision_model", "edgetam"),
-        ("qwen2_vl_vision", "qwen2_vl"),
         ("qwen2_vl_text", "qwen2_vl"),
-        ("omdet-turbo", "omdet_turbo"),
-        ("janus_vision_model", "janus"),
-        ("janus_vqgan", "janus"),
-        ("musicgen_decoder", "musicgen"),
-        ("sam_vision_model", "sam"),
-        ("data2vec-vision", "data2vec"),
-        ("data2vec-audio", "data2vec"),
-        ("data2vec-text", "data2vec"),
-        ("idefics2_vision", "idefics2"),
-        ("idefics2_perceiver", "idefics2"),
-        ("aria_text", "aria"),
-        ("qwen3_vl_moe_text", "qwen3_vl_moe"),
-        ("qwen3_vl_moe_vision", "qwen3_vl_moe"),
-        ("blenderbot-small", "blenderbot_small"),
-        ("ernie4_5_vl_moe_vision", "ernie4_5_vl_moe"),
-        ("ernie4_5_vl_moe_text", "ernie4_5_vl_moe"),
-        ("siglip_text_model", "siglip"),
-        ("siglip_vision_model", "siglip"),
-        ("flava_image_model", "flava"),
-        ("flava_text_model", "flava"),
-        ("flava_multimodal_model", "flava"),
-        ("modernbert-decoder", "modernbert_decoder"),
-        ("lasr_encoder", "lasr"),
-        ("lasr_ctc", "lasr"),
-        ("instructblip_vision_model", "instructblip"),
-        ("instructblip_qformer", "instructblip"),
-        ("internvl_vision", "internvl"),
+        ("qwen2_vl_vision", "qwen2_vl"),
+        ("qwen3_5_moe_text", "qwen3_5_moe"),
+        ("qwen3_5_moe_vision", "qwen3_5_moe"),
+        ("qwen3_5_text", "qwen3_5"),
+        ("qwen3_5_vision", "qwen3_5"),
         ("qwen3_omni_moe_audio_encoder", "qwen3_omni_moe"),
-        ("qwen3_omni_moe_vision_encoder", "qwen3_omni_moe"),
-        ("qwen3_omni_moe_text", "qwen3_omni_moe"),
-        ("qwen3_omni_moe_thinker", "qwen3_omni_moe"),
         ("qwen3_omni_moe_talker_code_predictor", "qwen3_omni_moe"),
         ("qwen3_omni_moe_talker_text", "qwen3_omni_moe"),
-        ("xclip_text_model", "x_clip"),
-        ("xclip_vision_model", "x_clip"),
-        ("xclip", "x_clip"),
-        ("audioflamingo3_encoder", "audioflamingo3"),
-        ("wav2vec2-bert", "wav2vec2_bert"),
-        ("encoder-decoder", "encoder_decoder"),
-        ("instructblipvideo_vision_model", "instructblipvideo"),
-        ("instructblipvideo_qformer", "instructblipvideo"),
-        ("emu3_vqgan", "emu3"),
-        ("emu3_text_model", "emu3"),
-        ("chinese_clip_text_model", "chinese_clip"),
-        ("chinese_clip_vision_model", "chinese_clip"),
-        ("owlv2_text_model", "owlv2"),
-        ("owlv2_vision_model", "owlv2"),
-        ("qwen3_5_moe_text", "qwen3_5_moe"),
-        ("qwen3_5_moe_vision", "qwen3_5_moe"),
-        ("lw_detr_vit", "lw_detr"),
-        ("donut-swin", "donut"),
-        ("moonshine_streaming_encoder", "moonshine_streaming"),
-        ("owlvit_text_model", "owlvit"),
-        ("owlvit_vision_model", "owlvit"),
-        ("glm_ocr_vision", "glm_ocr"),
-        ("glm_ocr_text", "glm_ocr"),
-        ("xlm-roberta", "xlm_roberta"),
-        ("unispeech-sat", "unispeech_sat"),
-        ("wav2vec2-conformer", "wav2vec2_conformer"),
-        ("blip_text_model", "blip"),
-        ("blip_vision_model", "blip"),
-        ("sam3_geometry_encoder", "sam3"),
-        ("sam3_detr_encoder", "sam3"),
-        ("sam3_detr_decoder", "sam3"),
-        ("sam3_mask_decoder", "sam3"),
-        ("granite_speech_encoder", "granite_speech"),
-        ("deberta-v2", "deberta_v2"),
+        ("qwen3_omni_moe_text", "qwen3_omni_moe"),
+        ("qwen3_omni_moe_thinker", "qwen3_omni_moe"),
+        ("qwen3_omni_moe_vision_encoder", "qwen3_omni_moe"),
+        ("qwen3_vl_moe_text", "qwen3_vl_moe"),
+        ("qwen3_vl_moe_vision", "qwen3_vl_moe"),
+        ("qwen3_vl_text", "qwen3_vl"),
+        ("qwen3_vl_vision", "qwen3_vl"),
+        ("roberta-prelayernorm", "roberta_prelayernorm"),
+        ("rt_detr_resnet", "rt_detr"),
         ("sam2_hiera_det_model", "sam2"),
         ("sam2_vision_model", "sam2"),
-        ("openai-gpt", "openai"),
-        ("csm_depth_decoder_model", "csm"),
-        ("align_text_model", "align"),
-        ("align_vision_model", "align"),
-        ("groupvit_text_model", "groupvit"),
-        ("groupvit_vision_model", "groupvit"),
-        ("mgp-str", "mgp_str"),
-        ("mm-grounding-dino", "mm_grounding_dino"),
-        ("git_vision_model", "git"),
-        ("musicgen_melody_decoder", "musicgen_melody"),
-        ("mllama_vision_model", "mllama"),
-        ("mllama_text_model", "mllama"),
-        ("mlcd_vision_model", "mlcd"),
+        ("sam3_detr_decoder", "sam3"),
+        ("sam3_detr_encoder", "sam3"),
+        ("sam3_geometry_encoder", "sam3"),
+        ("sam3_lite_text_detr_decoder", "sam3_lite_text"),
+        ("sam3_lite_text_detr_encoder", "sam3_lite_text"),
+        ("sam3_lite_text_geometry_encoder", "sam3_lite_text"),
+        ("sam3_lite_text_mask_decoder", "sam3_lite_text"),
+        ("sam3_lite_text_text_model", "sam3_lite_text"),
+        ("sam3_mask_decoder", "sam3"),
+        ("sam3_vision_model", "sam3"),
+        ("sam3_vit_model", "sam3"),
+        ("sam_hq_vision_model", "sam_hq"),
+        ("sam_vision_model", "sam"),
         ("sew-d", "sew_d"),
-        ("video_llama_3_vision", "video_llama_3"),
-        ("idefics3_vision", "idefics3"),
-        ("gemma4_audio", "gemma4"),
-        ("gemma4_text", "gemma4"),
-        ("gemma4_vision", "gemma4"),
-        ("qwen3_vl_vision", "qwen3_vl"),
-        ("qwen3_vl_text", "qwen3_vl"),
-        ("blip_2_vision_model", "blip_2"),
-        ("blip_2_qformer", "blip_2"),
-        ("blip-2", "blip_2"),
-        ("parakeet_encoder", "parakeet"),
-        ("parakeet_ctc", "parakeet"),
+        ("siglip2_text_model", "siglip2"),
+        ("siglip2_vision_model", "siglip2"),
+        ("siglip_text_model", "siglip"),
+        ("siglip_vision_model", "siglip"),
+        ("smolvlm_vision", "smolvlm"),
+        ("speech-encoder-decoder", "speech_encoder_decoder"),
+        ("speecht5_hifigan", "speecht5"),
+        ("t5_gemma_module", "t5gemma"),
+        ("t5gemma2_decoder", "t5gemma2"),
+        ("t5gemma2_encoder", "t5gemma2"),
+        ("t5gemma2_text", "t5gemma2"),
         ("table-transformer", "table_transformer"),
-        ("glm4v_moe_text", "glm4v_moe"),
-        ("glm4v_moe_vision", "glm4v_moe"),
-        ("paddleocr_vl_vision", "paddleocr_vl"),
-        ("paddleocr_vl_text", "paddleocr_vl"),
+        ("unispeech-sat", "unispeech_sat"),
+        ("uvdoc_backbone", "uvdoc"),
+        ("video_llama_3_vision", "video_llama_3"),
+        ("vision-encoder-decoder", "vision_encoder_decoder"),
+        ("vision-text-dual-encoder", "vision_text_dual_encoder"),
+        ("voxtral_encoder", "voxtral"),
+        ("voxtral_realtime_encoder", "voxtral_realtime"),
+        ("voxtral_realtime_text", "voxtral_realtime"),
+        ("wav2vec2-bert", "wav2vec2_bert"),
+        ("wav2vec2-conformer", "wav2vec2_conformer"),
+        ("xclip", "x_clip"),
+        ("xclip_text_model", "x_clip"),
+        ("xclip_vision_model", "x_clip"),
+        ("xlm-roberta", "xlm_roberta"),
+        ("xlm-roberta-xl", "xlm_roberta_xl"),
     ]
 )