runtime error

Exit code: 1. Reason: ��██| 2/2 [00:55<00:00, 27.83s/it] Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:04<00:04, 4.50s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:05<00:00, 2.28s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:05<00:00, 2.61s/it] /usr/local/lib/python3.10/site-packages/peft/config.py:162: UserWarning: Unexpected keyword arguments ['corda_config', 'trainable_token_indices'] for class LoraConfig, these are ignored. This probably means that you're loading a configuration file that was saved using a higher version of the library and additional parameters have been introduced since. It is highly recommended to upgrade the PEFT version before continuing (e.g. by running `pip install -U peft`). warnings.warn( g++ (Debian 8.3.0-6) 8.3.0 Copyright (C) 2018 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Traceback (most recent call last): File "//app.py", line 32, in <module> model = PeftModel.from_pretrained(model, adapter_path) File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 581, in from_pretrained load_result = model.load_adapter( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 1293, in load_adapter dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 379, in dispatch_model raise ValueError( ValueError: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: base_model.model.model.layers.27, base_model.model.model.layers.28, base_model.model.model.layers.29, base_model.model.model.layers.30, base_model.model.model.layers.31, base_model.model.model.rotary_emb, base_model.model.model.embed_dropout, base_model.model.model.final_layernorm, base_model.model.lm_head.

Container logs: