app.py

import gradio as gr
import subprocess

LLAMA_BIN = "./llama.cpp/build/bin/main"
MODEL = "./model.gguf"

def generate(prompt):
    result = subprocess.run(
        [
            LLAMA_BIN,
            "-m", MODEL,
            "-p", prompt,
            "-n", "200",
            "-t", "4"
        ],
        capture_output=True,
        text=True
    )
    return result.stdout

gr.Interface(fn=generate, inputs="text", outputs="text").launch(
    server_name="0.0.0.0",
    server_port=7860
)