import gradio as gr
from llama_cpp import Llama

# Load model (gunakan versi GGUF yang ringan)
model_path = "TheBloke/MythoMax-L2-13B-GGUF/mythomax.gguf"
llm = Llama(model_path=model_path, n_ctx=2048)

def chat(input_text):
    output = llm(input_text, max_tokens=100)
    return output["choices"][0]["text"]

iface = gr.Interface(
    fn=chat,
    inputs="text",
    outputs="text",
    title="Dika AI - MythoMax Lite",
    description="Chatbot AI berbasis MythoMax 13B GGUF, optimized for Hugging Face CPU!"
)

iface.launch()