app.py

import gradio as gr
import os
from gpt4all import GPT4All
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
model = GPT4All(model_name='strela-q4_k_m.gguf', model_path=os.getcwd())

def stop_on_token_callback(token_id, token_string):
    print(token_string, end='')
    if '#' in token_string:
        return False
    else:
        return True
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    chat = f"""### System:
{system_message}
"""
    for group in history:
        chat += f"""### Human:
{group[0]}
### Assistant:
{group[1]}"""
    chat += f"""### Human:
    {message}
    ### Assistant:
"""
    tokens = ""
    for token in model.generate(chat, temp=temperature, callback=stop_on_token_callback, streaming=True):
        tokens += token
        yield tokens
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", 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()