app.py

import gradio as gr
import json
import pandas as pd
from urllib.request import urlopen
from urllib.error import URLError
import re
from datetime import datetime

CITATION_BUTTON_TEXT = r"""@misc{2023opencompass,
    title={OpenCompass: A Universal Evaluation Platform for Foundation Models},
    author={OpenCompass Contributors},
    howpublished = {\url{https://github.com/open-compass/opencompass}},
    year={2023}
}"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"


head_style = """
<style>
@media (min-width: 1536px)
{
    .gradio-container {
        min-width: var(--size-full) !important;
    }
}
</style>
"""


DATA_URL_BASE = "http://opencompass.oss-cn-shanghai.aliyuncs.com/dev-assets/hf-research/"

def findfile():
    model_meta_info = 'model-meta-info'
    results_sum = 'hf-academic'

    url = f"{DATA_URL_BASE}{model_meta_info}.json"
    response = urlopen(url)
    model_info = json.loads(response.read().decode('utf-8'))

    url = f"{DATA_URL_BASE}{results_sum}.json"
    response = urlopen(url)
    results = json.loads(response.read().decode('utf-8'))

    return model_info, results


MAIN_LEADERBOARD_DESCRIPTION = """## Main Evaluation Results
The CompassAcademic currently focuses on the comprehensive reasoning abilities of LLMs.
- The datasets selected so far include General Knowledge Reasoning (MMLU-Pro/GPQA-Diamond), Logical Reasoning (BBH), Mathematical Reasoning (MATH-500, AIME), Code Completion (LiveCodeBench, HumanEval), and Instruction Following (IFEval).
- Currently, the evaluation primarily targets chat models, with updates featuring the latest community models at irregular intervals. 
- Prompts and reproduction scripts can be found in [**OpenCompass**: A Toolkit for Evaluation of LLMs](https://github.com/open-compass/opencompass)🏆.
"""




def create_interface():
    model_info, results = findfile()

    with gr.Blocks(title="Math Leaderboard", head=head_style) as demo:
        with gr.Tabs(elem_classes='tab-buttons') as tabs:
            with gr.TabItem('Results', elem_id='main', id=0):
                # math_main_tab(results)
                pass
            with gr.TabItem('Predictions', elem_id='notmain', id=0):
                # dataset_tab(results, structs[i], dataset)
                pass

    return demo

# model_info, results = findfile()
# breakpoint()

if __name__ == '__main__':
    demo = create_interface()
    demo.queue()
    demo.launch(server_name='0.0.0.0')