runtime error

Exit code: 1. Reason: 572M/13.8G [00:22<04:53, 45.1MB/s] Downloading (incomplete total...): 11%|โ–ˆ | 1.51G/13.8G [00:23<01:28, 139MB/s] Downloading (incomplete total...): 19%|โ–ˆโ–‰ | 2.63G/13.8G [00:24<00:41, 267MB/s] Downloading (incomplete total...): 27%|โ–ˆโ–ˆโ–‹ | 3.77G/13.8G [00:25<00:25, 402MB/s] Downloading (incomplete total...): 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 4.91G/13.8G [00:26<00:16, 532MB/s] Downloading (incomplete total...): 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 5.84G/13.8G [00:31<00:23, 339MB/s] Downloading (incomplete total...): 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 7.78G/13.8G [00:32<00:10, 560MB/s] Downloading (incomplete total...): 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 10.1G/13.8G [00:33<00:04, 841MB/s] Downloading (incomplete total...): 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 11.5G/13.8G [00:35<00:02, 791MB/s] Downloading (incomplete total...): 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 13.4G/13.8G [00:36<00:00, 987MB/s] Fetching 2 files: 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 1/2 [00:37<00:37, 37.29s/it] Fetching 2 files: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 2/2 [00:37<00:00, 18.65s/it] Download complete: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 13.8G/13.8G [00:37<00:00, 987MB/s]  Download complete: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 13.8G/13.8G [00:37<00:00, 370MB/s] โŒ ๆจกๅž‹่ผ‰ๅ…ฅๅคฑๆ•—: 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. Traceback (most recent call last): File "/app/app.py", line 105, in <module> demo = gr.ChatInterface( fn=math_solver, ...<7 lines>... theme="soft" ) TypeError: ChatInterface.__init__() got an unexpected keyword argument 'theme'

Container logs:

Fetching error logs...