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", n_threads=2)

def chat(input):
    resp = llm(input)
    return resp['choices'][0]['text']


g = gr.Interface(fn=chat, inputs="text", outputs="text", title="GPT4ALL", description="gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue")
g.queue(concurrency_count=1)
g.launch()