Check in updated files

app.py

@@ -82,7 +82,7 @@ def init_leaderboard(dataframe):
                 label="Select the number of parameters (B)",
             ),
             ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=False
+                AutoEvalColumn.still_on_hub.name, type="boolean", label="External Providers", default=False
             ),
         ],
         bool_checkboxgroup_label="Hide models",

src/about.py

@@ -6,20 +6,21 @@ class Task:
     benchmark: str
     metric: str
     col_name: str
+    reference_url: str
 
 
 # Select your tasks here
 # ---------------------------------------------------
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("aiera_speaker_assign", "accuracy,none", "SPEAKER_ID")
-    task1 = Task("aiera_transcript_sentiment", "accuracy,none","SENT")
-    task2 = Task("bbh_zeroshot_causal_judgement", "exact_match,flexible-extract","BBH0")
-    task3 = Task("flare_ectsum", "recall,none","ECTSUM")
-    task4 = Task("flare_edtsum", "rougeLsum,none","EDTSUM")
-    task5 = Task("flare_finqa", "exact_match_manual,none","FINQA")
-    task6 = Task("flare_fiqasa", "accuracy,none","FIQASA")
-    task7 = Task("flare_ner", "accuracy,none","NER")
+    task0 = Task("aiera_speaker_assign", "accuracy,none", "Speaker ID")
+    task1 = Task("aiera_transcript_sentiment", "accuracy,none","Speaker Sentiment")
+    task2 = Task("bbh_zeroshot_causal_judgement", "exact_match,flexible-extract","BBH-causal-judgement")
+    task3 = Task("flare_ectsum", "recall,none", "flare-ect-sum")
+    task4 = Task("flare_edtsum", "rougeLsum,none","flare-edt-sum")
+    task5 = Task("flare_finqa", "exact_match_manual,none","finqa")
+    task6 = Task("flare_fiqasa", "accuracy,none","fiqasa")
+    task7 = Task("flare_ner", "accuracy,none","flare-ner")
 
 
 NUM_FEWSHOT = 0 # Change with your few shot