runtime error

Exit code: 1. Reason: vicorn/config.py", line 415, in load_app return import_from_string(self.app) File "/usr/local/lib/python3.10/site-packages/uvicorn/importer.py", line 19, in import_from_string module = importlib.import_module(module_str) File "/usr/local/lib/python3.10/importlib/__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 1050, in _gcd_import File "<frozen importlib._bootstrap>", line 1027, in _find_and_load File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 688, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 883, in exec_module File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "/code/main.py", line 26, in <module> model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 406, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4307, in from_pretrained device_map = _get_device_map(model, device_map, max_memory, hf_quantizer) File "/usr/local/lib/python3.10/site-packages/transformers/integrations/accelerate.py", line 373, in _get_device_map hf_quantizer.validate_environment(device_map=device_map) File "/usr/local/lib/python3.10/site-packages/transformers/quantizers/quantizer_bnb_4bit.py", line 74, in validate_environment raise ValueError( ValueError: Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules in 32-bit, you need to set `llm_int8_enable_fp32_cpu_offload=True` and pass a custom `device_map` to `from_pretrained`. Check https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu for more details.

Container logs: