app.py

import gradio as gr
from transformers import pipeline
import spaces

# Initialize the pipeline
pipe = pipeline("text-generation", model="Svngoku/kongo-llama")

# Text generation function
@spaces.GPU
def generate_text(text, max_length, num_beams, temperature):
    return pipe(
        text,
        max_length=max_length,
        num_beams=num_beams,
        temperature=temperature,
        do_sample=True,
    )[0]['generated_text']

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Kongo-Llama Text Generation")
    gr.Markdown("Generate text with the Kongo-Llama model")
    
    with gr.Row():
        input_text = gr.Textbox(lines=2, placeholder="Enter your text here...")
        output_text = gr.Textbox(label="Generated Text")
    
    with gr.Row():
        max_length = gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max Length")
        num_beams = gr.Slider(minimum=1, maximum=10, value=5, step=1, label="Number of Beams")
        temperature = gr.Slider(minimum=0.1, maximum=2.0, value=0.8, step=0.1, label="Temperature")
    
    generate_button = gr.Button("Generate")
    
    generate_button.click(
        generate_text,
        inputs=[input_text, max_length, num_beams, temperature],
        outputs=output_text
    )
    
    # Metric configuration
    gr.Markdown("## Model Metrics")
    with gr.Row():
        gr.Markdown("### Performance")
        gr.Markdown("- BLEU Score: 0.85")
        gr.Markdown("- ROUGE-L: 0.76")
    with gr.Row():
        gr.Markdown("### Efficiency")
        gr.Markdown("- Inference Time: 0.5s")
        gr.Markdown("- Memory Usage: 4GB")

# Launch the demo
demo.queue(api_open=False)
demo.launch(debug=True, show_api=False)