app.py

import gradio as gr
from llama_cpp import Llama
from huggingface_hub import hf_hub_download

hf_hub_download(repo_id="LLukas22/gpt4all-lora-quantized-ggjt", filename="ggjt-model.bin", local_dir=".")

llm = Llama(model_path="./ggjt-model.bin")

def chat(input):
    return llm(input)['text']

gr.Interface(fn=chat, inputs="text", outputs="text", description="Assistant-style large language model with ~800k GPT-3.5-Turbo Generations", examples=[['What is a three word topic describing the following keywords: baseball, football, soccer'],['List 10 dogs.'],['Reverse a string in python.']]).launch()