runtime error

Exit code: 1. Reason: parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) module._load_from_state_dict( /usr/local/lib/python3.13/site-packages/torch/nn/modules/module.py:2586: UserWarning: for base_model.model.model.layers.15.feed_forward.w2.lora_B.default.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) module._load_from_state_dict( Traceback (most recent call last): File "/app/app.py", line 25, in <module> MODEL, TOKENIZER = load_model() ~~~~~~~~~~^^ File "/app/app.py", line 14, in load_model model = AutoPeftModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype="auto", device_map="auto", ) File "/usr/local/lib/python3.13/site-packages/peft/auto.py", line 142, in from_pretrained return cls._target_peft_class.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^ base_model, ^^^^^^^^^^^ ...<4 lines>... **kwargs, ^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/peft/peft_model.py", line 568, in from_pretrained load_result = model.load_adapter( model_id, ...<5 lines>... **kwargs, ) File "/usr/local/lib/python3.13/site-packages/peft/peft_model.py", line 1427, in load_adapter self._update_offload(offload_index, adapters_weights) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/peft/peft_model.py", line 1236, in _update_offload safe_module = dict(self.named_modules())[extended_prefix] ~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ KeyError: 'base_model.model.model.model.embed_tokens'

Container logs: