Update app.py

app.py

@@ -18,6 +18,7 @@ model = AutoGPTQForCausalLM.from_quantized(
     trust_remote_code=True,
     device_map="auto",  # Use auto to ensure compatibility with CPU
     use_safetensors=True,
+    torch_dtype=torch.float32,  # Use float32 for CPU compatibility
     quantize_config=None,
 )