runtime error

Exit code: 1. Reason: module instead of copying them in place?) warnings.warn( Попытка загрузки с токеном не удалась: 'base_model.model.model.model.layers.15.input_layernorm' Пробуем загрузить модели без токена... Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:06<00:13, 6.55s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:14<00:07, 7.35s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:14<00:00, 4.82s/it] Some parameters are on the meta device because they were offloaded to the cpu and disk. Traceback (most recent call last): File "/app/app.py", line 48, in <module> model = PeftModel.from_pretrained( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 568, in from_pretrained load_result = model.load_adapter( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 1427, in load_adapter self._update_offload(offload_index, adapters_weights) File "/usr/local/lib/python3.10/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.layers.15.input_layernorm' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/app/app.py", line 64, in <module> model = PeftModel.from_pretrained(base_model, adapter_id) File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 568, in from_pretrained load_result = model.load_adapter( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 1427, in load_adapter self._update_offload(offload_index, adapters_weights) File "/usr/local/lib/python3.10/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.layers.15.input_layernorm'

Container logs: