dtcxzyw's picture
Update
fc8fa64 unverified
raw
history blame
3.04 kB
import gradio as gr
from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
import pandas as pd
from apscheduler.schedulers.background import BackgroundScheduler
from huggingface_hub import snapshot_download
from datasets import load_dataset
from src.about import (
CITATION_BUTTON_LABEL,
CITATION_BUTTON_TEXT,
EVALUATION_QUEUE_TEXT,
INTRODUCTION_TEXT,
TITLE,
)
from src.display.css_html_js import custom_css
from src.display.utils import (
COLS,
AutoEvalColumn,
fields,
)
from src.envs import API, EVAL_REQUESTS_PATH, QUEUE_REPO, REPO_ID, TOKEN
from src.populate import get_leaderboard_df
def restart_space():
API.restart_space(repo_id=REPO_ID)
### Space initialisation
try:
print(EVAL_REQUESTS_PATH)
snapshot_download(
repo_id=QUEUE_REPO,
local_dir=EVAL_REQUESTS_PATH,
repo_type="dataset",
tqdm_class=None,
etag_timeout=30,
token=TOKEN,
)
except Exception:
restart_space()
total_issues = load_dataset("dtcxzyw/llvm-apr-benchmark").num_rows["test"]
LEADERBOARD_DF = get_leaderboard_df(EVAL_REQUESTS_PATH, COLS)
def init_leaderboard(dataframe):
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 fields(AutoEvalColumn)],
select_columns=SelectColumns(
default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
label="Select Columns to Display:",
),
search_columns=[AutoEvalColumn.method_name.name],
hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
filter_columns=[
ColumnFilter(AutoEvalColumn.with_hint.name, type="checkboxgroup", label="Hint"),
],
bool_checkboxgroup_label="Hide models",
interactive=False,
)
demo = gr.Blocks(css=custom_css)
with demo:
gr.HTML(TITLE)
gr.Markdown(INTRODUCTION_TEXT + f"\nTotal issues: {total_issues}\n", elem_classes="markdown-text")
with gr.Tabs(elem_classes="tab-buttons") as tabs:
with gr.TabItem("πŸ… Leaderboard", elem_id="llm-benchmark-tab-table", id=0):
leaderboard = init_leaderboard(LEADERBOARD_DF)
with gr.TabItem("πŸš€ Submission", elem_id="llm-benchmark-tab-table", id=1):
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
with gr.Row():
with gr.Accordion("πŸ“™ Citation", open=False):
citation_button = gr.Textbox(
value=CITATION_BUTTON_TEXT,
label=CITATION_BUTTON_LABEL,
lines=6,
elem_id="citation-button",
show_copy_button=True,
)
scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=1800)
scheduler.start()
demo.queue(default_concurrency_limit=40).launch()