runtime error

Exit code: 1. Reason: █| 5.23G/5.23G [00:17<00:00, 642MB/s] model.safetensors: 100%|██████████| 5.23G/5.23G [00:17<00:00, 304MB/s] generation_config.json: 0%| | 0.00/190 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 190/190 [00:00<00:00, 1.30MB/s] adapter_model.safetensors: 0%| | 0.00/166M [00:00<?, ?B/s] adapter_model.safetensors: 19%|█▉ | 32.1M/166M [00:01<00:04, 30.3MB/s] adapter_model.safetensors: 100%|██████████| 166M/166M [00:02<00:00, 62.6MB/s]  adapter_model.safetensors: 100%|██████████| 166M/166M [00:02<00:00, 59.0MB/s] 2026-01-12 10:14:09,061 - ERROR - Failed to load model: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: model.norm, model.rotary_emb, model.layers. Traceback (most recent call last): File "/app/app.py", line 40, in <module> model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 604, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 277, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5148, in from_pretrained model.load_adapter( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 298, in load_adapter self._dispatch_accelerate_model( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 544, in _dispatch_accelerate_model dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 383, 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: model.norm, model.rotary_emb, model.layers.

Container logs: