Update app.py

app.py

@@ -116,7 +116,8 @@ def load_model():
     # )
     llm = CTransformers(
         model = "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
-        model_file = "mistral-7b-instruct-v0.1.Q8_0.gguf",
+        # model_file = "mistral-7b-instruct-v0.1.Q8_0.gguf",
+        model_file = "mistral-7b-instruct-v0.1.Q4_0.gguf",
         # model="TheBloke/Llama-2-70B-chat-GGUF",
         # model = "Deci/DeciLM-6b-instruct",
         callbacks=[StreamingStdOutCallbackHandler()]