File size: 3,187 Bytes
4a78d34 8ad1a09 1d1f5e9 4a78d34 ed6229f 4a78d34 8ad1a09 4a78d34 ed6229f 4a78d34 aa87c61 ed6229f 4410a31 4a78d34 bb10943 11c3aa7 4a78d34 9c55d6d 8ad1a09 1d1f5e9 ed6229f 4a78d34 |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
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 src.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 (
COLS,
ST_BENCHMARK_COLS,
AGENTIC_BENCHMARK_COLS,
EVAL_COLS,
EVAL_TYPES,
AutoEvalColumn,
ModelType,
fields,
WeightType,
Precision
)
from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
from src.populate import get_evaluation_queue_df, get_leaderboard_df, TASK_NAME_INVERSE_MAP
from src.submission.submit import add_new_eval
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()
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, token=TOKEN
)
except Exception:
restart_space()
ST_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, ST_BENCHMARK_COLS)
AGENTIC_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, AGENTIC_BENCHMARK_COLS)
(
finished_eval_queue_df,
running_eval_queue_df,
pending_eval_queue_df,
) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
def init_leaderboard(dataframe, benchmark_type):
if dataframe is None or dataframe.empty:
raise ValueError("Leaderboard DataFrame is empty or None.")
AutoEvalColumnSubset = [c for c in fields(AutoEvalColumn) if ((c.name=="Model") or (TASK_NAME_INVERSE_MAP.get(c.name, dict()).get("type", "")==benchmark_type))]
return gr.components.Dataframe(
value=dataframe,
datatype=[c.type for c in AutoEvalColumnSubset],
column_widths=["150px" if c.name != "Model" else "250px" for c in AutoEvalColumnSubset],
wrap=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("Base Benchmark", elem_id="llm-benchmark-tab-table", id=0):
leaderboard = init_leaderboard(ST_LEADERBOARD_DF, "base")
with gr.TabItem("Agentic Benchmark", elem_id="llm-benchmark-tab-table", id=1):
leaderboard = init_leaderboard(AGENTIC_LEADERBOARD_DF, "agentic")
with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=1800)
scheduler.start()
demo.queue(default_concurrency_limit=40).launch() |