runtime error

Exit code: 1. Reason: --------------------------------------------------+------------+--+- vision_model.vision_model.embeddings.position_ids | UNEXPECTED | | Notes: - UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch. model.safetensors: 0%| | 0.00/1.22G [00:00<?, ?B/s] preprocessor_config.json: 0%| | 0.00/342 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 342/342 [00:00<00:00, 1.86MB/s] Traceback (most recent call last): File "/app/app.py", line 44, in <module> feature_extractor = AutoFeatureExtractor.from_pretrained(safety_model_id) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/feature_extraction_auto.py", line 367, in from_pretrained raise ValueError( ...<3 lines>... ) ValueError: Unrecognized feature extractor in CompVis/stable-diffusion-safety-checker. Should have a `feature_extractor_type` key in its preprocessor_config.json of config.json, or one of the following `model_type` keys in its config.json: audio-spectrogram-transformer, audioflamingo3, clap, clvp, cohere_asr, csm, dac, data2vec-audio, dia, encodec, gemma3n, gemma4, glmasr, granite_speech, higgs_audio_v2_tokenizer, hubert, kyutai_speech_to_text, lasr_ctc, lasr_encoder, markuplm, mimi, moonshine, moshi, musicgen, musicgen_melody, parakeet_ctc, parakeet_encoder, pe_audio, pe_audio_video, phi4_multimodal, pop2piano, qwen2_5_omni, qwen2_audio, qwen3_omni_moe, seamless_m4t, seamless_m4t_v2, sew, sew-d, speech_to_text, speecht5, unispeech, unispeech-sat, univnet, vibevoice_acoustic_tokenizer, vibevoice_asr, voxtral, voxtral_realtime, wav2vec2, wav2vec2-bert, wav2vec2-conformer, wavlm, whisper, xcodec model.safetensors: 0%| | 0.00/1.22G [00:01<?, ?B/s] model.safetensors: 0%| | 0.00/1.22G [00:02<?, ?B/s] model.safetensors: 55%|█████▌ | 671M/1.22G [00:03<00:00, 560MB/s] model.safetensors: 100%|██████████| 1.22G/1.22G [00:03<00:00, 357MB/s]

Container logs: