Update app.py

app.py

@@ -8,7 +8,7 @@ from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
 def get_llm():
     callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
-    return Ollama(model='YandexGPT-5-Lite-8B-instruct-GGUF', callback_manager=callback_manager)
+    return Ollama(model='yandex/YandexGPT-5-Lite-8B-instruct-GGUF:latest', callback_manager=callback_manager)
 
 
 # Interface Gradio