Update app.py

app.py

@@ -114,7 +114,7 @@ with gr.Blocks(theme=theme) as main:
     with gr.Column():
         gr.Markdown("# 👁️‍🗨️ WizardLM")
         gr.Markdown("⠀⠀• ⚡ A text generation inference for one of the best open-source text models: WizardLM-2-8x22B.")
-        gr.Markdown("⠀⠀• ⚠️ WARNING! The inference is very slow due to the model being HUGE; it takes 10 seconds before it starts generating; please avoid high max token parameters and sending large amounts of text.")
+        gr.Markdown("⠀⠀• ⚠️ WARNING! The inference is very slow due to the model being HUGE; it takes 10 seconds before it starts generating; please avoid high max token parameters and sending large amounts of text; note it uses CPU because I cannot figure out how to run it in GPU without overloading the model.")
         gr.Markdown(f"⠀⠀• 🔗 Link to models: {model_base} (BASE), {model_quant} (QUANT)")
 
     with gr.Column():