Update app.py

app.py

@@ -69,7 +69,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 model = AutoModelForCausalLM.from_pretrained(
     config.base_model_name_or_path,
-    load_in_8bit=True,
+    load_in_8bit=False,
     torch_dtype=torch.float16,
     device_map=device
 )