Update app

app.py

@@ -8,7 +8,11 @@ df = pd.read_csv(
 )
 
 markdown_text = """
-Hello world
+This space hosts evaluation results for time series forecasting models.
+
+Benchmark definitions, implementations of models, as well as the evaluation results for individual tasks are available under https://github.com/autogluon/fev.
+
+Currently, the results in this space are a minimal proof of concept. Stay tuned for more benchmarks, results for new models and instructions on how to contribute your results.
 """
 
 summary_urls = [
@@ -54,13 +58,21 @@ lb_wql = (
 
 with gr.Blocks() as demo:
     with gr.Tab("Leaderboard"):
-        gr.Markdown("## Point forecast accuracy (measured by MASE)")
+        gr.Markdown("""
+                    ## Chronos zero-shot benchmark results
+
+                    This tab contains results for various forecasting models on the 28 datasets used in Benchmark II (zero-shot evaluation) in the publication [Chronos: Learning the Language of Time Series](https://arxiv.org/abs/2403.07815).
+
+                    Task definitions and the detailed results are available on [GitHub](https://github.com/autogluon/fev/tree/main/benchmarks/chronos_zeroshot).
+                    """)
+        gr.Markdown("""### Point forecast accuracy (measured by MASE)
+                    """)
         gr.Dataframe(
             value=lb_mase,
             interactive=False,
         )
 
-        gr.Markdown("## Probabilistic forecast accuracy (measured by WQL)")
+        gr.Markdown("### Probabilistic forecast accuracy (measured by WQL)")
         gr.Dataframe(
             value=lb_wql,
             interactive=False,