File size: 1,753 Bytes
c08abba
 
d5b71b9
 
c08abba
 
 
 
 
 
 
 
 
d5b71b9
c08abba
d5b71b9
c08abba
d5b71b9
dfc075f
d5b71b9
 
 
 
 
3b7b492
d5b71b9
3b7b492
d5b71b9
 
3b7b492
 
d5b71b9
3b7b492
dfc075f
 
c08abba
 
afb233a
c08abba
 
 
af0f401
c08abba
 
 
af0f401
c08abba
 
 
254da86
 
 
 
 
 
 
 
 
 
 
 
c08abba
 
 
 
af0f401
 
c08abba
 
 
 
 
af0f401
 
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
from dataclasses import dataclass
from enum import Enum
import json


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


# Init: to update with your specific keys
def create_task_list():
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    with open("src/datasets.json") as f:
    
        data = json.load(f)
    
    groups = []
    names = []
    for d in data:
        groups.append(d['group'])
        names.append(d['name'])
    groups = list(set(groups))
    tasks = []
    grouped_tasks = []
    for name in names:
        tasks.append(Task(name, "metric_name", name))
    for group in groups:
        grouped_tasks.append(Task(group, "metric_name", group))
    
    return tasks, grouped_tasks
    


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title"> Azerbaijani LLM Leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Welcome to Kapital Bank's Azerbaijani LLM Leaderboard. We use benchmarks in finance, banking, and general knowledge for accurate evaluations.

πŸš€ Submit Your Model πŸš€

If you have a fine-tuned Azerbaijani LLM, submit it for evaluation!

"""

LLM_BENCHMARKS_TEXT = f"""
## How it works
## Reproducibility
HERE we have about part
"""

LLM_DATASET_TEXT = f"""
## How it works
## Reproducibility
HERE we have about part
"""


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

### 1) Make sure your model exists on hub.
### 2) Make sure your model is public.


## 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.
Please contact us if you are facing any trouble!
"""