new

app.py

@@ -2193,7 +2193,6 @@ MRPC_FIVE_SHOT = get_data_mrpc(eval_mode="five_shot")
 # =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =
 # =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =  =
 
-# block = gr.Blocks(theme=gr.themes.Soft())
 
 theme = gr.themes.Soft().set(
     background_fill_primary='*secondary_50'
@@ -2204,13 +2203,13 @@ block = gr.Blocks(theme='rottenlittlecreature/Moon_Goblin')
 
 with block:
     gr.Markdown(f"""
-    ## SeaEval Leaderboard. To submit, refer to the <a href="https://seaeval.github.io/" target="_blank" style="text-decoration: underline">SeaEval Website</a>.  Refer to the [SeaEval paper](https://arxiv.org/abs/2309.04766) for details on metrics, tasks and models.
+    ### SeaEval Leaderboard. To submit, refer to the <a href="https://seaeval.github.io/" target="_blank" style="text-decoration: underline">SeaEval Website</a>.  Refer to the [SeaEval paper](https://arxiv.org/abs/2309.04766) for details on metrics, tasks and models.
     - **Number of Datasets**: > 30
     - **Number of Languages**: > 8
     - **Number of Models**: {NUM_MODELS}
     - **Mode of Evaluation**: Zero-Shot, Five-Shot
 
-    ## Know Issues:
+    ### Know Issues:
     - For base models, the output of base model is not truncated as no EOS detected. Evaluation could be affected, especially with length-aware metrics.
     
     ### The following table shows the performance of the models on the SeaEval benchmark.
@@ -2220,11 +2219,7 @@ with block:
 
     """)
 
-
-
     with gr.Tabs():
-
-
         with gr.TabItem("Cross-Lingual Consistency"):
 
             # dataset 1: cross-mmlu
@@ -3225,8 +3220,8 @@ with block:
                     """)
 
 
-    gr.Markdown(f"""
-    ## If our datasets and leaderboard are useful, please consider cite:
+    gr.Markdown(r"""
+    ### If our datasets and leaderboard are useful, please consider cite:
     ```bibtex
         @article{SeaEval,
         title={SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning},
@@ -3237,25 +3232,6 @@ with block:
     """)
 
 
-    # Running the functions on page load in addition to when the button is clicked
-    # This is optional - If deactivated the data loaded at "Build time" is shown like for Overall tab
-    """
-    block.load(get_mteb_data, inputs=[task_bitext_mining], outputs=data_bitext_mining)
-    """
-
-
-
-
-
 block.queue(max_size=10)
-block.launch(server_name="0.0.0.0", share=False)
-
-
-# Possible changes:
-# Could add graphs / other visual content
-# Could add verification marks
-
-# Sources:
-# https://huggingface.co/spaces/gradio/leaderboard
-# https://huggingface.co/spaces/huggingface-projects/Deep-Reinforcement-Learning-Leaderboard
-# https://getemoji.com/
+# block.launch(server_name="0.0.0.0", share=False)
+block.launch(server_name="0.0.0.0", share=True)