update scripts

src/display/about.py

@@ -20,8 +20,8 @@ TITLE = """<h1 align="center" id="space-title">SeaExam Leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-🟢: pre-trained 
-🔶: fine-tuned
+🟢: base
+🔶: chat
 """
 
 # Which evaluations are you running? how can people reproduce what you have?

src/leaderboard/load_results.py

@@ -4,6 +4,8 @@ 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']
+
     
     # Splitting into three separate DataFrames based on the groups M3Exam and MMLU and average
     df_m3exam = df.iloc[:, :11]  # M3Exam columns
@@ -17,22 +19,23 @@ def load_data(data_path):
         df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']] *= 100
         df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']] = df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']].round(2)
         df_tmp['rank'] = df_tmp['avg'].rank(ascending=False).astype(int)
-        
-    # change the order of the columns to ['Model', 'type', 'open?', 'shot', 'avg', 'avg_sea', 'en', 'zh', 'id', 'th', 'vi'] 
-    # and sort the columns by 'avg' in descending order
-    columns_sorted = ['rank','type', 'Model', 'open?', 'shot', 'avg', 'avg_sea', 'en', 'zh', 'id', 'th', 'vi']
-    df_m3exam = df_m3exam[columns_sorted].sort_values(by='avg', ascending=False)
-    df_mmlu = df_mmlu[columns_sorted].sort_values(by='avg', ascending=False)
-    df_avg = df_avg[columns_sorted].sort_values(by='avg', ascending=False)
-
-    # change the column name from 'avg' to 'avg⬆️'
-    df_m3exam = df_m3exam.rename(columns={'avg': 'avg⬆️'})
-    df_mmlu = df_mmlu.rename(columns={'avg': 'avg⬆️'})
-    df_avg = df_avg.rename(columns={'avg': 'avg⬆️'})
-
-    # 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_tmp = df_tmp[columns_sorted].sort_values(by='avg_sea', ascending=False)
+        df_tmp = df_tmp.rename(columns={'avg_sea': 'avg_sea⬆️'})
+        df_tmp['type'] = df_tmp['type'].map({'base': '🟢', 'chat': '🔶'})
+
+    # df_m3exam = df_m3exam[columns_sorted].sort_values(by='avg_sea', ascending=False)
+    # df_mmlu = df_mmlu[columns_sorted].sort_values(by='avg', ascending=False)
+    # df_avg = df_avg[columns_sorted].sort_values(by='avg', ascending=False)
+
+    # # change the column name from 'avg' to 'avg⬆️'
+    # df_m3exam = df_m3exam.rename(columns={'avg': 'avg⬆️'})
+    # df_mmlu = df_mmlu.rename(columns={'avg': 'avg⬆️'})
+    # df_avg = df_avg.rename(columns={'avg': 'avg⬆️'})
+
+    # # 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': '🔶'})
+
     return df_m3exam, df_mmlu, df_avg