app.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import gradio as gr
import requests
from bs4 import BeautifulSoup

# Local dataset (optional, for pre-loaded data)
data_full = [
    ['CultriX/Qwen2.5-14B-SLERPv7', 'https://huggingface.co/CultriX/Qwen2.5-14B-SLERPv7', 0.7205, 0.8272, 0.7541, 0.6581, 0.5, 0.729],
    ['djuna/Q2.5-Veltha-14B-0.5', 'https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5', 0.7492, 0.8386, 0.7305, 0.598, 0.43, 0.7817],
    ['CultriX/Qwen2.5-14B-FinalMerge', 'https://huggingface.co/CultriX/Qwen2.5-14B-FinalMerge', 0.7248, 0.8277, 0.7113, 0.7052, 0.57, 0.7001],
    ['CultriX/Qwen2.5-14B-MultiCultyv2', 'https://huggingface.co/CultriX/Qwen2.5-14B-MultiCultyv2', 0.7295, 0.8359, 0.7363, 0.5767, 0.44, 0.7316],
    ['CultriX/Qwen2.5-14B-Brocav7', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav7', 0.7445, 0.8353, 0.7508, 0.6292, 0.46, 0.7629],
    ['CultriX/Qwen2.5-14B-Broca', 'https://huggingface.co/CultriX/Qwen2.5-14B-Broca', 0.7456, 0.8352, 0.748, 0.6034, 0.44, 0.7716],
    ['CultriX/Qwen2.5-14B-Brocav3', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav3', 0.7395, 0.8388, 0.7393, 0.6405, 0.47, 0.7659],
    ['CultriX/Qwen2.5-14B-Brocav4', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav4', 0.7432, 0.8377, 0.7444, 0.6277, 0.48, 0.758],
    ['CultriX/Qwen2.5-14B-Brocav2', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav2', 0.7492, 0.8302, 0.7508, 0.6377, 0.51, 0.7478],
    ['CultriX/Qwen2.5-14B-Brocav5', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav5', 0.7445, 0.8313, 0.7547, 0.6376, 0.5, 0.7304],
    ['CultriX/Qwen2.5-14B-Brocav6', 'https://huggingface.co/CultriX/Qwen2.5-14B-Brocav6', 0.7179, 0.8354, 0.7531, 0.6378, 0.49, 0.7524],
    ['CultriX/Qwenfinity-2.5-14B', 'https://huggingface.co/CultriX/Qwenfinity-2.5-14B', 0.7347, 0.8254, 0.7279, 0.7267, 0.56, 0.697],
    ['CultriX/Qwen2.5-14B-Emergedv2', 'https://huggingface.co/CultriX/Qwen2.5-14B-Emergedv2', 0.7137, 0.8335, 0.7363, 0.5836, 0.44, 0.7344],
    ['CultriX/Qwen2.5-14B-Unity', 'https://huggingface.co/CultriX/Qwen2.5-14B-Unity', 0.7063, 0.8343, 0.7423, 0.682, 0.57, 0.7498],
    ['CultriX/Qwen2.5-14B-MultiCultyv3', 'https://huggingface.co/CultriX/Qwen2.5-14B-MultiCultyv3', 0.7132, 0.8216, 0.7395, 0.6792, 0.55, 0.712],
    ['CultriX/Qwen2.5-14B-Emergedv3', 'https://huggingface.co/CultriX/Qwen2.5-14B-Emergedv3', 0.7436, 0.8312, 0.7519, 0.6585, 0.55, 0.7068],
    ['CultriX/SeQwence-14Bv1', 'https://huggingface.co/CultriX/SeQwence-14Bv1', 0.7278, 0.841, 0.7541, 0.6816, 0.52, 0.7539],
    ['CultriX/Qwen2.5-14B-Wernickev2', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev2', 0.7391, 0.8168, 0.7273, 0.622, 0.45, 0.7572],
    ['CultriX/Qwen2.5-14B-Wernickev3', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev3', 0.7357, 0.8148, 0.7245, 0.7023, 0.55, 0.7869],
    ['CultriX/Qwen2.5-14B-Wernickev4', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev4', 0.7355, 0.829, 0.7497, 0.6306, 0.48, 0.7635],
    ['CultriX/SeQwential-14B-v1', 'https://huggingface.co/CultriX/SeQwential-14B-v1', 0.7355, 0.8205, 0.7549, 0.6367, 0.48, 0.7626],
    ['CultriX/Qwen2.5-14B-Wernickev5', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev5', 0.7224, 0.8272, 0.7541, 0.679, 0.51, 0.7578],
    ['CultriX/Qwen2.5-14B-Wernickev6', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev6', 0.6994, 0.7549, 0.5816, 0.6991, 0.58, 0.7267],
    ['CultriX/Qwen2.5-14B-Wernickev7', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev7', 0.7147, 0.7599, 0.6097, 0.7056, 0.57, 0.7164],
    ['CultriX/Qwen2.5-14B-FinalMerge-tmp2', 'https://huggingface.co/CultriX/Qwen2.5-14B-FinalMerge-tmp2', 0.7255, 0.8192, 0.7535, 0.6671, 0.5, 0.7612],
]

columns = ["Model Configuration", "Model Link", "tinyArc", "tinyHellaswag", "tinyMMLU", "tinyTruthfulQA", "tinyTruthfulQA_mc1", "tinyWinogrande"]
df_full = pd.DataFrame(data_full, columns=columns)

def scrape_model_page(model_url):
    """
    Scrapes the Hugging Face model page for YAML configuration and other details.
    """
    try:
        # Fetch the model page
        response = requests.get(model_url)
        if response.status_code != 200:
            return f"Error: Unable to fetch the page (Status Code: {response.status_code})"
        
        soup = BeautifulSoup(response.text, "html.parser")

        # Extract YAML configuration (usually inside <pre> tags)
        yaml_config = soup.find("pre")
        yaml_text = yaml_config.text.strip() if yaml_config else "No YAML configuration found."

        # Extract additional metadata or performance (if available)
        metadata_section = soup.find("div", class_="metadata")
        metadata_text = metadata_section.text.strip() if metadata_section else "No metadata found."

        # Return the scraped details
        return f"**YAML Configuration:**\n{yaml_text}\n\n**Metadata:**\n{metadata_text}"

    except Exception as e:
        return f"Error: {str(e)}"

def display_scraped_model_data(model_url):
    """
    Displays YAML configuration and metadata for a given model URL.
    """
    return scrape_model_page(model_url)

with gr.Blocks() as demo:
    gr.Markdown("# Model Performance Analysis with Live Scraping")

    # Pre-loaded dataset features
    with gr.Row():
        btn1 = gr.Button("Show Summary Statistics")
        stats_output = gr.Dataframe()
        btn1.click(lambda: df_full.describe().T, outputs=stats_output)

    # Live scraping feature
    gr.Markdown("## Live Scraping Features")
    with gr.Row():
        url_input = gr.Textbox(label="Enter Hugging Face Model URL", placeholder="https://huggingface.co/<model>")
        scrape_btn = gr.Button("Scrape Model Page")
        scrape_output = gr.Textbox(label="Scraped Data", lines=15)
        scrape_btn.click(display_scraped_model_data, inputs=url_input, outputs=scrape_output)

demo.launch()