Update app.py

app.py

@@ -34,7 +34,7 @@ def load_model(model_name, quantization):
         model_name,
         return_dict=True,
         load_in_8bit=quantization,
-        device_map='cuda:0',
+        device_map='cpu',
         low_cpu_mem_usage=True,
     )
     return model