update the interface

src/display/about.py

@@ -29,7 +29,17 @@ Also check the [SeaBench leaderboard](https://huggingface.co/spaces/SeaLLMs/SeaB
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
-## How it works
+# About
+Even though large language models (LLMs) have shown impressive performance on various benchmarks for English, their performance on Southeast Asian (SEA) languages is still underexplored. This leaderboard aims to evaluate LLMs on exam-type benchmarks for SEA languages, focusing on world knowledge and reasoning abilities.
+
+## Datasets
+The leaderboard evaluates models on the following tasks:
+- **M3Exam**: 
+- **MMLU**:
+
+## Evalation Criteria
+
+## Reults
 
 ## Reproducibility
 To reproduce our results, here is the commands you can run:

src/leaderboard/load_results.py

@@ -25,7 +25,7 @@ def load_data(data_path):
     df = pd.read_csv(data_path, skiprows=1, header=0).dropna()
 
     columns = ['Model', 'type', 'open?', 'shot', 'en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']
-    columns_sorted = ['rank','type', 'Model', 'open?', 'shot', 'avg', 'avg_sea', 'en', 'zh', 'id', 'th', 'vi']
+    columns_sorted = ['rank','type', 'Model',  'avg_sea', 'en', 'zh', 'id', 'th', 'vi', 'avg', 'open?',]
 
     # Splitting into three separate DataFrames based on the groups M3Exam and MMLU and average
     df_m3exam = df.iloc[:, :11]  # M3Exam columns
@@ -54,15 +54,15 @@ def load_data(data_path):
     df_mmlu = df_mmlu.sort_values(by='avg_sea', ascending=False)
     df_avg = df_avg.sort_values(by='avg_sea', ascending=False)
 
-    # change the column name from 'avg_sea' to 'avg_sea⬆️'
-    df_m3exam = df_m3exam.rename(columns={'avg_sea': 'avg_sea⬆️'})
-    df_mmlu = df_mmlu.rename(columns={'avg_sea': 'avg_sea⬆️'})
-    df_avg = df_avg.rename(columns={'avg_sea': 'avg_sea⬆️'})
+    # change the column name from 'avg_sea' to 'avg_sea ⬇️'
+    df_m3exam = df_m3exam.rename(columns={'avg_sea': 'avg_sea ⬇️'})
+    df_mmlu = df_mmlu.rename(columns={'avg_sea': 'avg_sea ⬇️'})
+    df_avg = df_avg.rename(columns={'avg_sea': 'avg_sea ⬇️'})
 
     # map the values in the 'type' column to the following values: {'base': 'Base', 'chat': 'Chat'}
-    df_m3exam['type'] = df_m3exam['type'].map({'base': '🟢', 'chat': '🔶'})
-    df_mmlu['type'] = df_mmlu['type'].map({'base': '🟢', 'chat': '🔶'})
-    df_avg['type'] = df_avg['type'].map({'base': '🟢', 'chat': '🔶'})
+    df_m3exam['type'] = df_m3exam['type'].map({'base': '🟢base', 'chat': '🔶chat'})
+    df_mmlu['type'] = df_mmlu['type'].map({'base': '🟢base', 'chat': '🔶chat'})
+    df_avg['type'] = df_avg['type'].map({'base': '🟢base', 'chat': '🔶chat'})
 
     return df_m3exam, df_mmlu, df_avg