Update app.py

app.py

@@ -83,7 +83,7 @@ for model_name in tqdm(initial_list_of_models):
     df = df._append(benchmark_data, ignore_index=True)
 
 # Sort the dataframe by the number of tokens
-df = df.sort_values(by="➕ Total Number of Tokens", ascending=True)
+df = df.sort_values(by="🪺 Fertility Score", ascending=True)
 
 # Save the dataframe to a csv file
 df.to_json(dataframe_path, lines=True, orient="records", force_ascii=False)
@@ -210,9 +210,9 @@ def refresh():
     global df
     df = pd.read_json(dataframe_path, lines=True)
     return (
-        gr.Dataframe(df),
-        gr.BarPlot(df),
-        gr.Dropdown(choices=df["📛 Models"].tolist()),
+        gr.update(df),
+        gr.update(df),
+        gr.update(choices=df["📛 Models"].tolist()),
     )
 
 leaderboard_description = """The `Total Number of Tokens` in this leaderboard is based on the total number of tokens got from the Arabic section of [rasaif-translations](https://huggingface.co/datasets/MohamedRashad/rasaif-translations) dataset (This dataset was chosen because it represents Arabic Fusha text in a small and concentrated manner).
@@ -240,7 +240,7 @@ with gr.Blocks() as demo:
             barplot = gr.BarPlot(
                 df,
                 x="📛 Models",
-                y="➕ Total Number of Tokens",
+                y="🪺 Fertility Score",
                 x_title=" ",
                 y_title=" ",
                 width=1000,
@@ -248,6 +248,7 @@ with gr.Blocks() as demo:
                 tooltip=["📘 Vocab Size", "🪺 Fertility Score"],
                 vertical=False,
                 x_label_angle=30,
+                label="Models Fertility Score (Lower is better)",
             )
         model_name = gr.Textbox(
             label="Model Name from Hugging Face (e.g. Xenova/gpt-4o)"