minor change

sotopia_space/benchmark.py

@@ -41,7 +41,7 @@ def benchmark_table():
     global original_df, ablation_df
     global LP_original_dfs, LP_MODE
     
-    gr.Markdown(f"**Version**: sotopia (v1.01; 2024.04.22) | **# Examples**: 7200 | **# Models**: {len(MODEL_OPTIONS)} | **# Comparisons**: x", elem_classes="markdown-text")
+    # gr.Markdown(f"**Version**: sotopia (v1.01; 2024.04.22) | **# Examples**: 7200 | **# Models**: {len(MODEL_OPTIONS)} | **# Comparisons**: x", elem_classes="markdown-text")
                 
     with gr.TabItem("BARTScore on 100 samples", elem_id="od-benchmark-tab-table-ablation", id=0, elem_classes="subtab"):
         # original_df, ablation_df = skip_empty_original_df, skip_empty_ablation_df
@@ -52,7 +52,7 @@ def benchmark_table():
         # original_df.insert(0, "Rank", range(1, 1 + len(original_df)))
         with gr.Row():
             with gr.Column(scale=4):
-                gr.Markdown("**Vs GPT3.5**: Models are evaluated using BARTScore") 
+                gr.Markdown("Models are evaluated using BARTScore") 
             # with gr.Column(scale=1):
                 # length_penlty_slider = gr.Slider(minimum=0.1, maximum=1, step=0.1, value=DEFAULT_LP, label="Length Penalty", elem_id="length-penalty-slider") 
         # checkbox_skip_empty = gr.Checkbox(label="Skip empty results", value=False, elem_id="skip-empty-checkbox", scale=2)