File size: 1,672 Bytes
c8be55c
 
f8efcf6
c8be55c
f8efcf6
c8be55c
40afe38
8285d94
 
c8be55c
 
 
 
 
f8efcf6
4661ccf
40afe38
f8efcf6
c8be55c
 
40afe38
c8be55c
 
40afe38
c8be55c
40afe38
 
c8be55c
 
4661ccf
40afe38
5a34fee
c8be55c
 
 
 
 
 
 
 
 
 
 
 
40afe38
c8be55c
 
 
40afe38
c8be55c
f8efcf6
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
import gradio as gr
from apscheduler.schedulers.background import BackgroundScheduler
from gradio_leaderboard import ColumnFilter, Leaderboard, SelectColumns

from src.about import INTRODUCTION_TEXT, TITLE
from src.display.css_html_js import custom_css
from src.envs import API, REPO_ID
from src.leaderboard.populate import load_results
from src.leaderboard.utils import COLUMNS


def restart_space():
    API.restart_space(repo_id=REPO_ID)


def init_leaderboard():
    dataframe = load_results()

    if dataframe is None or dataframe.empty:
        raise ValueError("Leaderboard DataFrame is empty or None.")

    return Leaderboard(
        value=dataframe,
        datatype=[c.type for c in COLUMNS],
        select_columns=SelectColumns(
            default_selection=[c.name for c in COLUMNS if c.displayed_by_default],
            cant_deselect=[c.name for c in COLUMNS if c.never_hidden],
            label="Select Columns to Display:",
        ),
        search_columns=[c.name for c in COLUMNS if c.searchable],
        hide_columns=[c.name for c in COLUMNS if c.hidden],
        filter_columns=[],
        bool_checkboxgroup_label="Hide models",
        interactive=False,
    )


demo = gr.Blocks(css=custom_css)
with demo:
    gr.HTML(TITLE)
    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")

    with gr.Tabs(elem_classes="tab-buttons") as tabs:
        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
            leaderboard = init_leaderboard()


scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=3600)
scheduler.start()
demo.queue(default_concurrency_limit=40).launch()