from dataclasses import dataclass from enum import Enum @dataclass class Task: benchmark: str metric: str col_name: 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("anli_r1", "acc", "ANLI") task1 = Task("logiqa", "acc_norm", "LogiQA") NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name LEADERBOARD_TITLE = """

QANTA Leaderboard

""" # What does your leaderboard evaluate? LEADERBOARD_INTRODUCTION_TEXT = """ Build an open-domain QA system that can answer any question posed by humans! For more: https://sites.google.com/view/qanta/home """ # Which evaluations are you running? how can people reproduce what you have? LLM_BENCHMARKS_TEXT = """ ## How it works ## Reproducibility To reproduce our results, here is the commands you can run: """