Update app.py

app.py

@@ -99,7 +99,7 @@ def loadModel():
                     torch_dtype=torch.float16,
                     cache_dir=cache_dir,
                     device_map="auto",
-                    quantization_config=quantization_config,
+                    #quantization_config=quantization_config,
                     max_memory={
                         0: "20GB",  # GPU 0 with 20GB memory
                         1: "40GB",  # GPU 0 with 20GB memory