runtime error

g shards: 60%|██████ | 9/15 [01:57<01:22, 13.79s/it] Downloading shards: 67%|██████▋ | 10/15 [02:12<01:11, 14.20s/it] Downloading shards: 73%|███████▎ | 11/15 [02:26<00:57, 14.30s/it] Downloading shards: 80%|████████ | 12/15 [02:43<00:44, 14.94s/it] Downloading shards: 87%|████████▋ | 13/15 [02:57<00:29, 14.71s/it] Downloading shards: 93%|█████████▎| 14/15 [03:12<00:14, 14.87s/it] Downloading shards: 100%|██████████| 15/15 [03:18<00:00, 12.01s/it] Downloading shards: 100%|██████████| 15/15 [03:18<00:00, 13.21s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 282, in <module> caption_generator = Captions() File "/home/user/app/app.py", line 263, in __init__ self.LLM = Social_Media_Captioner(use_finetuned_LLM, temp_LLM) File "/home/user/app/app.py", line 127, in __init__ self._load_model() File "/home/user/app/app.py", line 149, in _load_model self.model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 488, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2842, in from_pretrained 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 `load_in_8bit_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: