runtime error

Exit code: 1. Reason: █| 2.05G/2.05G [00:05<00:00, 380MB/s] Traceback (most recent call last): File "/app/app.py", line 95, in <module> _get_pipeline() ~~~~~~~~~~~~~^^ File "/app/app.py", line 35, in _get_pipeline model = AutoPeftModelForCausalLM.from_pretrained( MODEL_ID, #torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto", ) File "/usr/local/lib/python3.13/site-packages/peft/auto.py", line 115, in from_pretrained base_model = target_class.from_pretrained(base_model_path, revision=base_model_revision, **kwargs) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 374, in from_pretrained return model_class.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~^ pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4118, in from_pretrained device_map = _get_device_map(model, device_map, max_memory, hf_quantizer) File "/usr/local/lib/python3.13/site-packages/transformers/integrations/accelerate.py", line 359, in _get_device_map hf_quantizer.validate_environment(device_map=device_map) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/quantizers/quantizer_bnb_4bit.py", line 72, in validate_environment raise ValueError( ...<6 lines>... ) 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: