app.py

import streamlit as st
from llmware.prompts import Prompt

def register_gguf_model():

    prompter = Prompt()

    your_model_name = "my_model"
    hf_repo_name = "TheBloke/Llama-2-7B-Chat-GGUF"
    model_file = "llama-2-7b-chat.Q5_K_S.gguf"
    print("registering model")
    prompter.model_catalog.register_gguf_model(your_model_name,hf_repo_name, model_file, prompt_wrapper="open_chat")
    print("loading model")
    prompter.load_model(your_model_name)

    return prompter

def main():
    st.title("GGUF model loading test")
    
    with st.spinner("Loading model..."):
        prompter = register_gguf_model()
    if prompter:
        st.success("Model loaded!")
        
if __name__ == "__main__":
    main()