updating quantization

app.py

@@ -74,9 +74,9 @@ def quantize_model(model_name, quantization_type, group_size=128, auth_token=Non
     else : 
         quantization_config = TorchAoConfig(quantization_type)
     if device == "cuda" : 
-        model = load_model_gpu(model_name, quantization_config, auth_token)
+        model = load_model_gpu(model_name, quantization_config=quantization_config, auth_token=auth_token)
     else : 
-        model = load_model_cpu(model_name, quantization_config, auth_token)
+        model = load_model_cpu(model_name, quantization_config=quantization_config, auth_token=auth_token)
 
     return model