runtime error

Exit code: 1. Reason: s torch.float16 and torch.bfloat16 dtypes, but the current dype in ShapeOPT is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `torch_dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", torch_dtype=torch.float16)` Flash Attention 2.0 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in ShapeOPTModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `torch_dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", torch_dtype=torch.float16)` Flash Attention 2.0 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in ShapeOPTDecoder is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `torch_dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", torch_dtype=torch.float16)` The BetterTransformer implementation does not support padding during training, as the fused kernels do not support attention masks. Beware that passing padded batched data during training may result in unexpected outputs. Please refer to https://huggingface.co/docs/optimum/bettertransformer/overview for more details. load model over!!! load weights over!!! Model loaded to device Traceback (most recent call last): File "/home/user/app/app.py", line 446, in <module> output_model_obj = gr.Model3D( File "/usr/local/lib/python3.10/site-packages/gradio/component_meta.py", line 159, in wrapper return fn(self, **kwargs) TypeError: Model3D.__init__() got an unexpected keyword argument 'display_mode'

Container logs: