runtime error

Exit code: 1. Reason: ub/utils/_validators.py", line 88, in _inner_fn return fn(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/hub_mixin.py", line 561, in from_pretrained instance = cls._from_pretrained( File "/usr/local/lib/python3.10/site-packages/huggingface_hub/hub_mixin.py", line 775, in _from_pretrained model = cls(**model_kwargs) File "/usr/local/lib/python3.10/site-packages/stoic/model.py", line 67, in __init__ self.configure_model() File "/usr/local/lib/python3.10/site-packages/stoic/model.py", line 110, in configure_model self._configure_seq_embed_model() File "/usr/local/lib/python3.10/site-packages/stoic/model.py", line 117, in _configure_seq_embed_model self.seq_embed_model = self._seq_embed_model_cls( File "/usr/local/lib/python3.10/site-packages/stoic/seq_emb_models.py", line 120, in __init__ self.model = AutoModel.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 387, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4116, 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: