add tw tasks

src/about.py

@@ -12,8 +12,9 @@ class Task:
 # ---------------------------------------------------
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("anli_r1", "acc", "ANLI")
-    task1 = Task("logiqa", "acc_norm", "LogiQA")
+    task2 = Task("tmlu", "acc", "TMLU")
+    task3 = Task("twllm_eval", "acc", "TW Truthful QA")
+    task4 = Task("tw_legal", "acc", "TW Legal Eval")
 
 NUM_FEWSHOT = 0 # Change with your few shot
 # ---------------------------------------------------
@@ -35,6 +36,7 @@ LLM_BENCHMARKS_TEXT = f"""
 ## Reproducibility
 To reproduce our results, here is the commands you can run:
 
+please checkout this command https://github.com/adamlin120/lm-evaluation-harness/blob/main/run_all.sh
 """
 
 EVALUATION_QUEUE_TEXT = """
@@ -69,7 +71,7 @@ If everything is done, check you can launch the EleutherAIHarness on your model
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 CITATION_BUTTON_TEXT = r"""
-@misc{open-ko-llm-leaderboard,
+@misc{open-tw-llm-leaderboard,
   author = {Yen{-}Ting Lin, Yun{-}Nung Chen},
   title = {Open TW-LLM Leaderboard},
   year = {2024},