runtime error

Exit code: 1. Reason: 11 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 27865.26it/s] Traceback (most recent call last): File "/app/app.py", line 45, in <module> model = AutoModelForCausalLM.from_pretrained( MODEL_ID, device_map="auto", torch_dtype=torch.bfloat16, ) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 394, 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 4211, 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 4377, in _finalize_model_loading model.tie_weights(missing_keys=loading_info.missing_keys, recompute_mapping=False) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 2583, in tie_weights if not torch.equal(self.get_parameter(source_param_name), self.get_parameter(target_param_name)): ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ NotImplementedError: aten::equal: attempted to run this operator with Meta tensors, but there was no fake impl or Meta kernel registered. You may have run into this message while using an operator with PT2 compilation APIs (torch.compile/torch.export); in order to use this operator with those APIs you'll need to add a fake impl. Please see the following for next steps: https://pytorch.org/tutorials/advanced/custom_ops_landing_page.html Download complete: 100%|██████████| 4.06G/4.06G [00:11<00:00, 356MB/s]

Container logs: