new

app.py

@@ -2204,12 +2204,9 @@ 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.
-    - **Number of Datasets**: > 30
-    - **Number of Languages**: > 8
-    - **Number of Models**: {NUM_MODELS}
-    - **Mode of Evaluation**: Zero-Shot, Five-Shot
+    - **Number of Datasets**: > 30, **Number of Languages**: > 8, **Number of Models**: {NUM_MODELS}, **Mode of Evaluation**: Zero-Shot, Five-Shot
 
-    ### Know Issues:
+    ### Possible 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.
@@ -2261,7 +2258,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **Cross-XQUAD Leaderboard** 🔮
-                    
                     - **Metric:** Cross-Lingual Consistency, Accuracy, AC3
                     - **Languages:** English, Chinese, Spanish, Vietnamese
                     """)
@@ -2305,7 +2301,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **Cross-MMLU Leaderboard** 🔮
-                    
                     - **Metric:** Cross-Lingual Consistency, Accuracy, AC3
                     - **Languages:** English, Chinese, Malay, Indonesian, Spanish, Vietnamese, Filipino
                     """)
@@ -2347,7 +2342,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **Cross-LogiQA Leaderboard** 🔮
-                    
                     - **Metric:** Cross-Lingual Consistency, Accuracy, AC3
                     - **Languages:** English, Chinese, Malay, Indonesian, Spanish, Vietnamese, Filipino
                     """)
@@ -2377,7 +2371,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **SG_EVAL Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy
                     - **Languages:** English
                     """)
@@ -2406,7 +2399,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **US_EVAL Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy
                     - **Languages:** English
                     """)
@@ -2434,7 +2426,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **CN_EVAL Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy
                     - **Languages:** Chinese
                     """)
@@ -2461,7 +2452,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **PH_EVAL Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy
                     - **Languages:** English
                     """)
@@ -2488,7 +2478,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **SING2ENG Leaderboard** 🔮
-                    
                     - **Metric:** BLEU Avg.
                     - **Languages:** English
                     """)
@@ -2518,7 +2507,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **MMLU Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -2546,7 +2534,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **MMLU Full Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -2574,7 +2561,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **C_EVAL Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -2602,7 +2588,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **C_EVAL Full Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -2629,7 +2614,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **CMMLU Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -2657,7 +2641,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **CMMLU Full Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -2684,7 +2667,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **ZBench Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -2710,7 +2692,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **IndoMMLU Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Bahasa Indonesian
                     """)
@@ -2740,7 +2721,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **flores_ind2eng Leaderboard** 🔮
-                    
                     - **Metric:** BLEU Avg.
                     - **Languages:** English
                     """)
@@ -2767,7 +2747,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **flores_vie2eng Leaderboard** 🔮
-                    
                     - **Metric:** BLEU Avg.
                     - **Languages:** English
                     """)
@@ -2795,7 +2774,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **flores_zho2eng Leaderboard** 🔮
-                    
                     - **Metric:** BLEU Avg.
                     - **Languages:** English
                     """)
@@ -2822,7 +2800,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **flores_zsm2eng Leaderboard** 🔮
-                    
                     - **Metric:** BLEU Avg.
                     - **Languages:** English
                     """)
@@ -2850,8 +2827,7 @@ with block:
                             )
                 with gr.Row():
                     gr.Markdown("""
-                    **ind_emotion Leaderboard** 🔮
-                    
+                    **Ind_emotion Leaderboard** 🔮
                     - **Metric:** Accuracy.
                     - **Languages:** Indonesian
                     """)
@@ -2878,7 +2854,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **SST2 Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -2909,7 +2884,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **DREAM Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -2935,7 +2909,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **SAMSum Leaderboard** 🔮
-                    
                     - **Metric:** ROUGE.
                     - **Languages:** English
                     """)
@@ -2962,7 +2935,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **DialogSum Leaderboard** 🔮
-                    
                     - **Metric:** ROUGE.
                     - **Languages:** English
                     """)
@@ -2993,7 +2965,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **OCNLI Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -3020,7 +2991,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **C3 Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** Chinese
                     """)
@@ -3049,7 +3019,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **COLA Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -3076,7 +3045,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **QQP Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -3103,7 +3071,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **MNLI Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -3130,7 +3097,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **QNLI Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -3158,7 +3124,6 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **WNLI Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
@@ -3186,13 +3151,10 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **RTE Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
 
-
-
             # dataset
             with gr.TabItem("MRPC"):
                 with gr.TabItem("Zero Shot"):
@@ -3214,12 +3176,10 @@ with block:
                 with gr.Row():
                     gr.Markdown("""
                     **MRPC Leaderboard** 🔮
-                    
                     - **Metric:** Accuracy.
                     - **Languages:** English
                     """)
 
-
     gr.Markdown(r"""
     ### If our datasets and leaderboard are useful, please consider cite:
     ```bibtex