src/about.py

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
TITLE = """<h1 align="center" id="space-title">🏅 Korean AI leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
[2024 국립국어원 인공 지능 언어 능력 평가]
- 인공 지능, 인간의 감정을 이해하고 이야기를 완성하다
- 과제 상세 링크: https://kli.korean.go.kr/benchmark/taskBoardsOrdtm/boardsOrdtm/noticeView.do?page=0&recordId=130&boardOrdtmId=&base.condition=boardOrdtm.title&base.keyword=&size=10

🚀 경진 대회 과제
- 2024년 7~8월 개최 예정인 "2024년 인공지능의 한국어 능력 평가" 경진대회 과제입니다.
- 일상 대화 요약: 다자간 대화에서 주제별 요약문을 생성
- 대화 맥락 추론: 발화의 맥락을 정확하게 추론한 문장을 선택

🚀 상시 평가 과제
- 연구·개발자들이 인공지능의 한국어 성능을 검증하고 평가할 수 있도록 상시 공개합니다.
- 연결 문장 추론: 두 문장 사이에 들어갈 가장 적합한 문장을 선택
- 부적절 발언 탐지: 다양한 문서에서 명시적·비명시적 부적절 발언 탐지
- 함의 분석 결과 설명문 생성: 두 문장 사이의 함의 관계 근거를 생성
- 국회 회의록 요약: 국회 회의록 내 주요 안건별 요약문을 작성
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works

## Reproducibility
To reproduce our results, here is the commands you can run:

"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗

### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
"""