consolidate

app.py

@@ -36,17 +36,38 @@ def init_leaderboard(dataframe):
         ],
     )
 
+def refresh_leaderboard():
+    """Refresh leaderboard data from disk"""
+    try:
+        # Download latest results
+        snapshot_download(
+            repo_id=RESULTS_REPO,
+            local_dir=EVAL_RESULTS_PATH,
+            repo_type="dataset",
+            tqdm_class=None,
+            etag_timeout=30,
+            token=TOKEN
+        )
+    except Exception as e:
+        print(f"Error refreshing results: {e}")
+    
+    # Get fresh leaderboard data
+    df = get_leaderboard_df(EVAL_RESULTS_PATH, COLS, BENCHMARK_COLS)
+    return init_leaderboard(df)
+
 def run_perplexity_test(model_name, revision, precision):
     """Run perplexity evaluation on demand."""
     if not model_name:
-        return "Please enter a model name."
+        return "Please enter a model name.", None
     
     success, result = run_dynamic_perplexity_eval(model_name, revision, precision)
     
     if success:
-        return f"✅ Perplexity evaluation completed!\nPerplexity: {result:.4f}\n\nResults have been saved and will appear in the leaderboard shortly."
+        # Get updated leaderboard
+        new_leaderboard = refresh_leaderboard()
+        return f"✅ Perplexity evaluation completed!\nPerplexity: {result:.4f}", new_leaderboard
     else:
-        return f"❌ Evaluation failed: {result}"
+        return f"❌ Evaluation failed: {result}", None
 
 # Initialize results repository and directory
 try:
@@ -110,7 +131,7 @@ with demo:
             test_button.click(
                 run_perplexity_test,
                 [model_name, revision, precision],
-                result
+                [result, leaderboard]
             )
 
 demo.queue(default_concurrency_limit=5).launch()