runtime error

s] model.safetensors: 62%|██████▏ | 5.48G/8.91G [00:50<00:26, 129MB/s] model.safetensors: 68%|██████▊ | 6.04G/8.91G [00:51<00:14, 192MB/s] model.safetensors: 71%|███████ | 6.34G/8.91G [00:55<00:19, 134MB/s] model.safetensors: 74%|███████▍ | 6.59G/8.91G [00:57<00:17, 132MB/s] model.safetensors: 80%|███████▉ | 7.10G/8.91G [00:58<00:09, 187MB/s] model.safetensors: 83%|████████▎ | 7.39G/8.91G [01:02<00:10, 145MB/s] model.safetensors: 86%|████████▌ | 7.62G/8.91G [01:04<00:09, 138MB/s] model.safetensors: 88%|████████▊ | 7.84G/8.91G [01:05<00:07, 151MB/s] model.safetensors: 93%|█████████▎| 8.29G/8.91G [01:06<00:03, 203MB/s] model.safetensors: 96%|█████████▋| 8.59G/8.91G [01:07<00:01, 223MB/s] model.safetensors: 100%|█████████▉| 8.91G/8.91G [01:07<00:00, 132MB/s] GPTBigCodeGPTQForCausalLM hasn't fused attention module yet, will skip inject fused attention. GPTBigCodeGPTQForCausalLM hasn't fused mlp module yet, will skip inject fused mlp. Traceback (most recent call last): File "/home/user/app/app.py", line 22, in <module> model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, File "/home/user/.local/lib/python3.10/site-packages/auto_gptq/modeling/auto.py", line 119, in from_quantized return quant_func( File "/home/user/.local/lib/python3.10/site-packages/auto_gptq/modeling/_base.py", line 1036, in from_quantized model = autogptq_post_init(model, use_act_order=quantize_config.desc_act) File "/home/user/.local/lib/python3.10/site-packages/auto_gptq/modeling/_utils.py", line 380, in autogptq_post_init submodule.post_init(temp_dq = model.device_tensors[device]) File "/home/user/.local/lib/python3.10/site-packages/auto_gptq/nn_modules/qlinear/qlinear_exllamav2.py", line 140, in post_init assert self.qweight.device.type == "cuda" AssertionError

Container logs: