runtime error

Exit code: 1. Reason: ffbeb78da331fe622/modeling_khmerocr.py:83: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) return nn.TransformerEncoder(enc_layer, num_layers=num_layers) Loading weights: 0%| | 0/137 [00:00<?, ?it/s] Loading weights: 100%|██████████| 137/137 [00:00<00:00, 5078.84it/s] Traceback (most recent call last): File "/app/app.py", line 17, in <module> model = AutoModel.from_pretrained(MODEL_REPO, trust_remote_code=True).to(DEVICE) ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 374, in from_pretrained return model_class.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~^ pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4131, in from_pretrained loading_info = cls._finalize_model_loading(model, load_config, loading_info) File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4273, in _finalize_model_loading model.mark_tied_weights_as_initialized(loading_info) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4613, in mark_tied_weights_as_initialized for tied_param in self.all_tied_weights_keys.keys(): ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1968, in __getattr__ raise AttributeError( f"'{type(self).__name__}' object has no attribute '{name}'" ) AttributeError: 'KhmerOCR' object has no attribute 'all_tied_weights_keys'. Did you mean: '_tied_weights_keys'?

Container logs: