app.py

import gradio as gr
from gradio_leaderboard import Leaderboard
import pandas as pd
from huggingface_hub import snapshot_download

from src.about import (
    INTRODUCTION_TEXT,
    LLM_BENCHMARKS_TEXT,
    TITLE,
)
from src.display.css_html_js import custom_css
from src.display.utils import (
    BENCHMARK_COLS,
    COLS,
    AutoEvalColumn,
)
from src.envs import API, EVAL_RESULTS_PATH, RESULTS_REPO, TOKEN
from src.populate import get_leaderboard_df
from src.evaluation.dynamic_eval import run_dynamic_perplexity_eval

def init_leaderboard(dataframe):
    if dataframe is None or dataframe.empty:
        raise ValueError("Leaderboard DataFrame is empty or None.")
    
    return Leaderboard(
        dataframe,
        headers=COLS,
        column_config={
            AutoEvalColumn.model.name: "markdown",
        },
    )

def run_perplexity_test(model_name, revision, precision):
    """Run perplexity evaluation on demand."""
    if not model_name:
        return "Please enter a model name."
    
    success, result = run_dynamic_perplexity_eval(model_name, revision, precision)
    
    if success:
        return f"✅ Perplexity evaluation completed!\nPerplexity: {result:.4f}\n\nResults have been saved and will appear in the leaderboard shortly."
    else:
        return f"❌ Evaluation failed: {result}"

# Initialize results directory
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 as e:
    print(f"Error initializing results: {e}")

# Get initial leaderboard data
LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, COLS, BENCHMARK_COLS)

# Create the Gradio interface
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("🏅 Leaderboard", elem_id="leaderboard-tab", id=0):
            leaderboard = init_leaderboard(LEADERBOARD_DF)

        with gr.TabItem("📝 About", elem_id="about-tab", id=1):
            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")

        with gr.TabItem("🧪 Test Model", elem_id="test-model-tab", id=2):
            with gr.Row():
                with gr.Column():
                    model_name = gr.Textbox(label="Model name", placeholder="org/model-name")
                    revision = gr.Textbox(label="Revision", placeholder="main", value="main")
                    precision = gr.Dropdown(
                        choices=["float16", "bfloat16"],
                        label="Precision",
                        value="float16"
                    )
                
                with gr.Column():
                    test_button = gr.Button("🚀 Run Perplexity Test", variant="primary")
                    result = gr.Markdown()
            
            test_button.click(
                run_perplexity_test,
                [model_name, revision, precision],
                result
            )

demo.queue(default_concurrency_limit=5).launch()