[Add] error messages

app.py

@@ -3,8 +3,10 @@ import gradio as gr
 import numpy as np
 import matplotlib.pyplot as plt
 import seaborn as sns
+import re
 from io import BytesIO
 from PIL import Image
+from datasets import DatasetNotFoundError
 
 print(gr.__version__)
 
@@ -71,12 +73,21 @@ def validate_inputs(selected_models, selected_dataset):
     
 
 def update_datasets_based_on_models(selected_models, current_dataset):
-    available_datasets = get_leaderboard_datasets(selected_models) if selected_models else []
-    valid_dataset = current_dataset if current_dataset in available_datasets else None
-    return gr.update(
-        choices=available_datasets,
-        value=valid_dataset
-    )
+    try:
+        available_datasets = get_leaderboard_datasets(selected_models) if selected_models else []
+        valid_dataset = current_dataset if current_dataset in available_datasets else None
+        return gr.update(
+            choices=available_datasets,
+            value=valid_dataset
+        )
+    except DatasetNotFoundError as e:
+        # Extract model name from error message
+        match = re.search(r"open-llm-leaderboard/([\w\-]+)", str(e))
+        model_name = match.group(1) if match else "Unknown Model"
+        
+        # Display a shorter warning
+        gr.Warning(f"Data for '{model_name}' is gated or unavailable.")
+        return gr.update(choices=[], value=None)
 
 with gr.Blocks(title="LLM Similarity Analyzer") as demo:
     gr.Markdown("## Model Similarity Comparison Tool \n\nAs Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these tasks, which we refer to as AI Oversight. We study how model similarity affects both aspects of AI oversight by proposing a probabilistic metric for LM similarity based on overlap in model mistakes. Using this metric, we first show that LLM-as-a-judge scores favor models similar to the judge, generalizing recent self-preference results. Then, we study training on LM annotations, and find complementary knowledge between the weak supervisor and strong student model plays a crucial role in gains from weak-to-strong generalization. As model capabilities increase, it becomes harder to find their mistakes, and we might defer more to AI oversight. However, we observe a concerning trend -- model mistakes are becoming more similar with increasing capabilities, pointing to risks from correlated failures. Our work underscores the importance of reporting and correcting for model similarity, especially in the emerging paradigm of AI oversight. ")