update app

app.py

@@ -149,7 +149,14 @@ def clear_prompt():
     return "","",""
 
 with gr.Blocks() as demo:
-    gr.Markdown("Start typing below and then click **Run** to see the output.")
+    gr.Markdown("# <p style='text-align: center;'>BLOOM vs BLOOMZ Comparison</p>")
+    gr.Markdown("")
+    gr.Markdown("Test Inference on the [BLOOM](https://huggingface.co/bigscience/bloom) and [BLOOMZ](https://huggingface.co/bigscience/bloomz) 176 Billion Parameter models using Petals.  \
+        Please consider contributing your unused GPU cycles to the [Petals Swarm](https://github.com/bigscience-workshop/petals) to speed up inference. <br />\n \
+        Due to heavy resource requirements of these large models, token generation can take upwards of 3-5 seconds per token. Try to keep Max Tokens to a minimum.")
+    gr.Markdown("")
+    gr.Markdown("Special thanks to [RFT Capital](https://www.rftcapital.com/) for supporting our experiments with compute time dontations.")
+    gr.Markdown("Type a Prompt and then click **Run** to see the output.")
     with gr.Row():
         with gr.Column():
             prompt = gr.Textbox(lines=17,label="Prompt",placeholder="Enter Prompt", interactive=True)
@@ -173,5 +180,5 @@ with gr.Blocks() as demo:
         btn_stop.click(stop_threads,cancels=click_run)
     gr.Examples(examples, inputs=[prompt, chk_boxes, max_tokens, temperature, top_p, rep_penalty, stop])
 
-demo.queue(concurrency_count=3)
+demo.queue(concurrency_count=1)
 demo.launch()