CUDA location is probably zero issue

app.py

@@ -11,7 +11,7 @@ model = None
 def loadmodel():
     global tokenizer, model
     tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Meta-Llama-3.1-70B-AQLM-PV-2Bit-1x16")
-    model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Meta-Llama-3.1-70B-AQLM-PV-2Bit-1x16", torch_dtype=torch.float16, device_map= 'auto')
+    model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Meta-Llama-3.1-70B-AQLM-PV-2Bit-1x16", torch_dtype='auto', device_map= 'auto') #torch_dtype=torch.float16
     #model = model.to('cuda')  # Move the model to GPU if available
     pass