Spaces:
Sleeping
Sleeping
File size: 994 Bytes
efeee6d 314f91a 95f85ed efeee6d 314f91a b899767 efeee6d 943f952 783e5a7 1ffc326 b899767 efeee6d 783e5a7 58733e4 efeee6d 8c49cb6 783e5a7 0227006 efeee6d 0227006 d313dbd 8c49cb6 58733e4 2a73469 783e5a7 217b585 9833cdb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
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("0-shot", "acc", "0-shot")
task1 = Task("1-shot", "acc", "1-shot")
task5 = Task("5-shot", "acc", "5-shot")
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------
# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">PsychoLex leaderboard</h1>"""
# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Accuracy of LLMs on the PsychoLexEval dataset in Persian.
"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
"""
EVALUATION_QUEUE_TEXT = """
"""
CITATION_BUTTON_LABEL = ""
CITATION_BUTTON_TEXT = r"""
"""
|