Update app.py

app.py

@@ -110,7 +110,7 @@ def alternative(chatbot, history):
 with gr.Blocks(title=title) as demo:
     gr.HTML(f"<div style=\"text-align: center;\">\n<h1>🌍World - {title}</h1>\n</div>")
     with gr.Tab("Instruct mode"):
-        gr.Markdown(f"100% RNN RWKV-LM **trained on 100+ world languages**. Demo limited to ctxlen {ctx_limit}. Finetuned on alpaca, gpt4all, codealpaca and more. For best results, ** keep you prompt short and clear **.</b>.") # <b>UPDATE: now with Chat (see above, as a tab) ==> turn off as of now due to VRAM leak caused by buggy code.
+        gr.Markdown(f"100% RNN RWKV-LM **trained on 100+ world languages**. Demo limited to ctxlen {ctx_limit}. Finetuned on alpaca, gpt4all, codealpaca and more. For best results, ** keep you prompt short and clear **.\n\nIf the generation gets stuck in the preprocessing stage after 10-20 seconds, there's a [connectivity issue with HuggingFace](https://discuss.huggingface.co/t/space-just-stopped-working-connectionerror/62935/13). Restarting the space will most likely result in the same runtime error.")
         with gr.Row():
             with gr.Column():
                 instruction = gr.Textbox(lines=2, label="Instruction", value='東京で訪れるべき素晴らしい場所とその紹介をいくつか挙げてください。')