local models loading

Hi, I am trying to load models from local disk using

--model_paths '["models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors","models/Wan-AI/Wan2.1-T2V-14B/models_t5_umt5-xxl-enc-bf16.pth","models/Wan-AI/Wan2.1-T2V-14B/Wan2.1_VAE.pth"]' 

but I got the error:

Traceback (most recent call last):
[rank2]:   File "train.py", line 1099, in <module>
[rank2]:     main()
[rank2]:   File "train.py", line 1005, in main
[rank2]:     model = VideoTrainingModule(
[rank2]:             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank2]:   File "train.py", line 475, in __init__
[rank2]:     self.pipe = WanVideoPipeline.from_pretrained(
[rank2]:                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank2]:   File "diffsynth/pipelines/wan_video.py", line 147, in from_pretrained
[rank2]:     model_pool = pipe.download_and_load_models(model_configs, vram_limit)
[rank2]:                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank2]:   File "diffsynth/diffusion/base_pipeline.py", line 303, in download_and_load_models
[rank2]:     model_pool.auto_load_model(
[rank2]:   File "diffsynth/models/model_loader.py", line 82, in auto_load_model
[rank2]:     raise ValueError(f"Cannot detect the model type. File: {path}. Model hash: {model_hash}")
[rank2]: ValueError: Cannot detect the model type. File: models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors. Model hash: 7607eaaeb524095268b872e4d5189baf

Start with the failing call chain in train.py, then read WanVideoPipeline.from_pretrained in diffsynth/pipelines/wan_video.py and model loading in diffsynth/diffusion/base_pipeline.py and diffsynth/models/model_loader.py. Reproduce the command with the listed local model files and trace why the first safetensors file cannot be detected. Done means the local Wan model loads without the Cannot detect the model type error.