runtime error

Exit code: 1. Reason: _tokens.weight | MISSING | Notes: - MISSING: those params were newly initialized because missing from the checkpoint. Consider training on your downstream task. Traceback (most recent call last): File "/app/app.py", line 12, in <module> model = AutoModelForSeq2SeqLM.from_pretrained( model_id, device_map="auto", dtype=torch.float16 if torch.cuda.is_available() else torch.float32, ) 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 4246, 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 4413, 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 2612, 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

Container logs: