|
|
import gradio as gr
|
|
|
import pandas as pd
|
|
|
import numpy as np
|
|
|
import joblib
|
|
|
|
|
|
|
|
|
model = joblib.load("model/optimized_model.pkl")
|
|
|
|
|
|
|
|
|
def predict_quality(provider, open_source, context_window, speed, latency,
|
|
|
mmlu_score, arena_score, price, dataset_size, compute, energy):
|
|
|
|
|
|
input_data = {
|
|
|
"Provider": provider,
|
|
|
"Open-Source": int(open_source),
|
|
|
"Context Window": context_window,
|
|
|
"Speed (tokens/sec)": speed,
|
|
|
"Latency (sec)": latency,
|
|
|
"Benchmark (MMLU)": mmlu_score,
|
|
|
"Benchmark (Chatbot Arena)": arena_score,
|
|
|
"Price / Million Tokens": price,
|
|
|
"Training Dataset Size": dataset_size,
|
|
|
"Compute Power": compute,
|
|
|
"Energy Efficiency": energy
|
|
|
}
|
|
|
|
|
|
input_df = pd.DataFrame([input_data])
|
|
|
prediction = model.predict(input_df)[0]
|
|
|
|
|
|
if prediction > 2.8:
|
|
|
quality_class = "🌟 Excellent"
|
|
|
elif prediction > 2.5:
|
|
|
quality_class = "✨ Very Good"
|
|
|
elif prediction > 2.2:
|
|
|
quality_class = "👍 Good"
|
|
|
elif prediction > 1.8:
|
|
|
quality_class = "🔄 Average"
|
|
|
else:
|
|
|
quality_class = "⚠️ Below Average"
|
|
|
|
|
|
return round(prediction, 2), quality_class
|
|
|
|
|
|
|
|
|
provider_list = ['OpenAI', 'Anthropic', 'Meta', 'Google', 'Mistral', 'Cohere', 'Other']
|
|
|
|
|
|
iface = gr.Interface(
|
|
|
fn=predict_quality,
|
|
|
inputs=[
|
|
|
gr.Dropdown(provider_list, label="Provider"),
|
|
|
gr.Checkbox(label="Open Source?"),
|
|
|
gr.Slider(1000, 200000, value=50000, step=1000, label="Context Window"),
|
|
|
gr.Slider(10, 300, value=100, step=5, label="Speed (tokens/sec)"),
|
|
|
gr.Slider(0.1, 5.0, value=1.0, step=0.1, label="Latency (sec)"),
|
|
|
gr.Slider(40, 95, value=70, step=1, label="MMLU Score"),
|
|
|
gr.Slider(500, 1500, value=1000, step=1, label="Chatbot Arena Score"),
|
|
|
gr.Slider(0.1, 50.0, value=10.0, step=0.1, label="Price / Million Tokens (USD)"),
|
|
|
gr.Slider(100, 2000, value=1000, step=100, label="Training Dataset Size (GB)"),
|
|
|
gr.Slider(10, 100, value=50, step=5, label="Compute Power"),
|
|
|
gr.Slider(10, 100, value=50, step=5, label="Energy Efficiency"),
|
|
|
],
|
|
|
outputs=[
|
|
|
gr.Number(label="Predicted Quality Rating (0-10)"),
|
|
|
gr.Text(label="Rating Class")
|
|
|
],
|
|
|
title="🔍 LLM Quality Predictor",
|
|
|
description="Enter LLM specs to predict its expected quality rating using a trained ML model."
|
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
iface.launch()
|
|
|
|
