File size: 861 Bytes
ad25c15
 
 
 
 
 
 
 
 
 
5574e55
 
ad25c15
68464a8
ad25c15
 
1d51292
ad25c15
8124a28
ad25c15
 
 
 
 
bca421b
ad25c15
68464a8
 
 
 
 
 
 
 
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
from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str

class Tasks(Enum):
    task0 = Task("anli_r1", "acc", "Korean Bar Exam (Lawyer)")
    task1 = Task("logiqa", "acc_norm", "Senior Civil Service Examination(๊ตญ๊ฐ€์ง 5๊ธ‰)")

NUM_FEWSHOT = 0

TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
INTRODUCTION_TEXT = """Intro text"""

LLM_BENCHMARKS_TEXT = """\
## 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
(์ค‘๋žต) 
์—ฌ๊ธฐ์— ๊ธด ํ…์ŠคํŠธ๋ฅผ ๋ถ™์—ฌ๋„ฃ๋˜,
์‚ผ์ค‘ ๋”ฐ์˜ดํ‘œ๊ฐ€ ๋“ฑ์žฅํ•˜์ง€ ์•Š๋„๋ก ์ฃผ์˜ํ•˜์„ธ์š”.
"""

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