update app.py

app.py

@@ -1,3 +1,5 @@
+# app.py
+
 import gradio as gr
 from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 import pandas as pd
@@ -24,7 +26,6 @@ from src.display.utils import (
     Precision
 )
 
-
 from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
 from src.populate import get_evaluation_queue_df, get_leaderboard_df
 from src.submission.submit import add_new_eval
@@ -50,6 +51,8 @@ except Exception:
 
 
 LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
+print("LEADERBOARD_DF Shape:", LEADERBOARD_DF.shape)  # Debug
+print("LEADERBOARD_DF Columns:", LEADERBOARD_DF.columns.tolist())  # Debug
 
 (
     finished_eval_queue_df,
@@ -67,11 +70,19 @@ with demo:
             if LEADERBOARD_DF.empty:
                 gr.Markdown("No evaluations have been performed yet. The leaderboard is currently empty.")
             else:
+                default_selection = [col.name for col in COLUMNS if col.displayed_by_default]
+                print("Default Selection before ensuring 'model':", default_selection)  # Debug
+
+                # Ensure "model" is included
+                if "model" not in default_selection:
+                    default_selection.insert(0, "model")
+                    print("Default Selection after ensuring 'model':", default_selection)  # Debug
+
                 leaderboard = Leaderboard(
                     value=LEADERBOARD_DF,
                     datatype=[col.type for col in COLUMNS],
                     select_columns=SelectColumns(
-                        default_selection=[col.name for col in COLUMNS if col.displayed_by_default],
+                        default_selection=default_selection,
                         cant_deselect=[col.name for col in COLUMNS if col.never_hidden],
                         label="Select Columns to Display:",
                     ),
@@ -116,11 +127,12 @@ with demo:
                         value=None,
                         interactive=True,
                     )
-                    num_examples_input = gr.Number(
-                        label="Number of Examples per Subject (e.g., 10)",
-                        value=10,
-                        precision=0
-                    )
+                    # Removed num_examples_input since we're using a fixed number
+                    # num_examples_input = gr.Number(
+                    #     label="Number of Examples per Subject (e.g., 10)",
+                    #     value=10,
+                    #     precision=0
+                    # )
 
                 with gr.Column():
                     precision = gr.Dropdown(
@@ -150,7 +162,7 @@ with demo:
                     precision,
                     weight_type,
                     model_type,
-                    num_examples_input
+                    # num_examples_input  # Removed
                 ],
                 submission_result,
             )
@@ -168,4 +180,4 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+demo.queue(default_concurrency_limit=40).launch()