Update app.py

app.py

@@ -82,7 +82,7 @@ def main():
 
         # loading local llama model
         llm = CTransformers(#model="models/llama-2-7b-chat.ggmlv3.q8_0.bin",
-                            model="models/llama-2-7b-chat.ggmlv3.q4_0.bin",
+                            model="TheBloke/Llama-2-7B-Chat-GGML",
                             model_type="llama",
                             #callbacks=[StreamingStdOutCallbackHandler()],
                             config={'max_new_tokens': 1024,