wip

app.py

@@ -168,7 +168,7 @@ with demo:
                     # base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
 
             logger.info("Submut button")
-            submit_button = gr.Button("Submit Eval")
+            submit_button = gr.Button("Submit")
             submission_result = gr.Markdown()
             submit_button.click(
                 partial(add_new_solutions, lbdb=lbdb),
@@ -195,5 +195,5 @@ scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
 logger.info("Launch")
-demo.queue(default_concurrency_limit=40).launch()
+demo.queue(default_concurrency_limit=40).launch(ssr=False)
 logger.info("Done")

src/about.py

@@ -25,7 +25,7 @@ TITLE = """<h1 align="center" id="space-title">AAI FormulaOne Leaderboard</h1>""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+FormulaOne is a dataset of hard code problems as a benchmark for LLM/LRM potency
 """
 
 # Which evaluations are you running? how can people reproduce what you have?