Update app.py

app.py

@@ -12,12 +12,42 @@ import pandas as pd
 
 
 benchmark_data = {
-    'Model': ['IlyaGusev/saiga_llama3_8b', 'Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24', "TinyLlama", 'Google-gemma-2-27b-it', 'mistralai/Mistral-Nemo-Instruct-2407', 'Vikhrmodels/Vikhr-Qwen-2.5-0.5b-Instruct'],
-    'Creativity Score': [78.5, 82.3, 85.7, 83.1, 85.6, 76.5, ],
-    'Coherence Score': [75.2, 80.1, 84.3, 81.9, 88.5, 76.6],
-    'Diversity Score': [25.3, 27.8, 31.2, 29.5, 28.4, 24.6]
+    'Model': [
+        'TheBloke/llama3-13b',              # LLaMA3
+        'Vikhrmodels/Vikhr-Nemo-12B',       # Vikhr
+        'TinyLLaMA/TinyLlama-1.1B',         # TinyLLaMA
+        'mistralai/Mistral-7B-instruct',     # Mistral
+        'Qwen/Qwen-7B'                       # Qwen
+    ],
+    'Creativity Score': [
+        37.75,  # LLaMA3
+        46.00,  # Vikhr
+        6.50,   # TinyLLaMA
+        23.75,  # Mistral
+        8.25    # Qwen
+    ],
+    'Diversity Score': [
+        49.50,  # LLaMA3
+        52.00,  # Vikhr
+        14.50,  # TinyLLaMA
+        38.50,  # Mistral
+        15.55   # Qwen
+    ],
+    'Relevance Score': [
+        79.25,  # LLaMA3
+        87.50,  # Vikhr
+        18.50,  # TinyLLaMA
+        76.75,  # Mistral
+        34.25   # Qwen
+    ],
+    'Average Score': [
+        55.50,  # LLaMA3
+        61.83,  # Vikhr
+        13.17,  # TinyLLaMA
+        46.33,  # Mistral
+        19.35   # Qwen
+    ]
 }
-
 def display_results():
     df = pd.DataFrame(benchmark_data)
     return df
@@ -31,10 +61,6 @@ with gr.Blocks() as demo:
         headers=["Model", "Creativity Score", "Coherence Score", "Diversity Score"],
         interactive=False
     )
-    
-    # Button to refresh/display results
-    refresh_btn = gr.Button("Show Results")
-    refresh_btn.click(fn=display_results, outputs=output)
 
 if __name__ == "__main__":
     demo.launch()