runtime error

Exit code: 1. Reason: limiter) # type: ignore File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 61, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2525, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 986, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context return func(*args, **kwargs) File "/app/app.py", line 76, in chat_fn load_model() File "/app/app.py", line 44, in load_model base_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 5029, in from_pretrained device_map = _get_device_map(model, device_map, max_memory, hf_quantizer, dtype, keep_in_fp32_regex) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1365, 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 127, 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: