app.py

import gradio as gr
from llama_cpp import Llama

llm = Llama(
    model_path="AstroSage-8B-Q8_0.gguf",
    n_ctx=2048,
    n_threads=4,
    seed=42,
    f16_kv=True,
    logits_all=False,
    use_mmap=True,
    use_gpu=True
)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})
    messages.append({"role": "user", "content": message})
    
    response = llm.generate_chat(
        messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p
    )
    
    return response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="Assume the role of AstroSage, a helpful chatbot designed to answer user queries about astronomy, astrophysics, and cosmology.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
    ]
)


if __name__ == "__main__":
    demo.launch()