Spaces:
Sleeping
Sleeping
import gradio as gr | |
import pandas as pd | |
from apscheduler.schedulers.background import BackgroundScheduler | |
from huggingface_hub import snapshot_download | |
from src.display.about import ( | |
CITATION_BUTTON_LABEL, | |
CITATION_BUTTON_TEXT, | |
EVALUATION_QUEUE_TEXT, | |
INTRODUCTION_TEXT, | |
LLM_BENCHMARKS_TEXT, | |
TITLE, | |
) | |
from src.display.css_html_js import custom_css | |
from src.display.utils import ( | |
BENCHMARK_COLS, | |
COLS, | |
EVAL_COLS, | |
EVAL_TYPES, | |
NUMERIC_INTERVALS, | |
TYPES, | |
AutoEvalColumn, | |
ModelType, | |
fields, | |
WeightType, | |
Precision | |
) | |
from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, TOKEN, QUEUE_REPO, REPO_ID, RESULTS_REPO | |
from src.populate import get_evaluation_queue_df, get_leaderboard_df | |
from src.submission.submit import add_new_eval, upload_file | |
def restart_space(): | |
API.restart_space(repo_id=REPO_ID, token=TOKEN) | |
# 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 | |
# ) | |
# except Exception: | |
# restart_space() | |
try: | |
print(EVAL_RESULTS_PATH) | |
snapshot_download( | |
repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30 | |
) | |
except Exception: | |
restart_space() | |
raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS) | |
value=[ c.name for c in fields(AutoEvalColumn) | |
if c.displayed_by_default and not c.hidden and not c.never_hidden] | |
leaderboard_df = original_df.copy() | |
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("π LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0): | |
leaderboard_table = gr.components.Dataframe( | |
value=leaderboard_df[ | |
[c.name for c in fields(AutoEvalColumn) if c.never_hidden] + value | |
+ [AutoEvalColumn.dummy.name] | |
], | |
headers=[c.name for c in fields(AutoEvalColumn) if c.never_hidden] + value, | |
datatype=TYPES, | |
elem_id="leaderboard-table", | |
interactive=False, | |
visible=True, | |
column_widths=["2%", "33%"] | |
) | |
# Dummy leaderboard for handling the case when the user uses backspace key | |
hidden_leaderboard_table_for_search = gr.components.Dataframe( | |
value=original_df[COLS], | |
headers=COLS, | |
datatype=TYPES, | |
visible=False, | |
) | |
with gr.TabItem("π About", elem_id="llm-benchmark-tab-table", id=2): | |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text") | |
with gr.TabItem("π Submit here! ", elem_id="llm-benchmark-tab-table", id=3): | |
with gr.Column(): | |
with gr.Row(): | |
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text") | |
with gr.Row(): | |
gr.Markdown("# βοΈβ¨ Submit your files here!", elem_classes="markdown-text") | |
def update_leaderboard(file_obj): | |
upload_file(file_obj) | |
raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS) | |
value=[ c.name for c in fields(AutoEvalColumn) | |
if c.displayed_by_default and not c.hidden and not c.never_hidden] | |
leaderboard_df = original_df.copy() | |
leaderboard_table = leaderboard_df[ | |
[c.name for c in fields(AutoEvalColumn) if c.never_hidden] + value | |
+ [AutoEvalColumn.dummy.name] | |
] | |
return leaderboard_table | |
with gr.Row(): | |
upload = gr.Interface(fn=update_leaderboard,inputs="file" ,outputs=leaderboard_table) | |
with gr.Row(): | |
with gr.Accordion("π Citation", open=False): | |
citation_button = gr.Textbox( | |
value=CITATION_BUTTON_TEXT, | |
label=CITATION_BUTTON_LABEL, | |
lines=20, | |
elem_id="citation-button", | |
show_copy_button=True, | |
) | |
scheduler = BackgroundScheduler() | |
scheduler.add_job(restart_space, "interval", seconds=30) | |
# scheduler.start() | |
demo.queue(default_concurrency_limit=40).launch() |