Better MD messaging

app.py

@@ -92,8 +92,8 @@ You can see the prompt clearly displayed below the chatbot to understand what is
 # Read this if you get an error
 I'm using [Inference Endpoint's](https://huggingface.co/inference-endpoints) 
 [Scale to Zero](https://huggingface.co/docs/inference-endpoints/main/en/autoscaling#scaling-to-0) to save money on GPUs.
-If the staus shows its not "Running" send a click **Wake Up Endpoint** to wake it up. You will get a `500 error` and it will take
- ~4 minutes to wake up.
+If the staus is "scaledToZero" click **Wake Up Endpoint** to wake it up. You will get an `error` and it will take
+ ~4 minutes to wake up. This is expected, if you dont like it please give me a free GPU with enough VRAM. 
 """