app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import gradio as gr
import os

# Initialize the Qwen model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-1_8B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-1_8B-Chat", device_map="auto", trust_remote_code=True).eval()

class ChatBot:
    def __init__(self):
        self.history = None

    def predict(self, user_input, system_prompt=""):
        response, self.history = model.chat(tokenizer, user_input, history=self.history, system=system_prompt)
        return response

bot = ChatBot()

title = "👋🏻Welcome to🌟Tonic's🦆Qwen📲On-Device🗣️Chat!"
description = """
You can use this Space to test out the current model [Qwen/Qwen-1_8B-Chat](https://huggingface.co/Qwen/Qwen-1_8B-Chat) You can also use 🧑🏻‍🚀Qwen/Qwen-1_8B-Chat🚀 by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic1/wen-1_8B-Chat?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> 
Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community on 👻Discord: [Discord](https://discord.gg/nXx5wbX9) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [PolyGPT](https://github.com/tonic-ai/polygpt-alpha)
"""
examples = [["Hello, how are you today?"]]

iface = gr.Interface(
    fn=bot.predict,
    title=title,
    description=description,
    examples=examples,
    inputs=["text", "text"],  # User input and system prompt
    outputs="text",
    theme="default"
)

iface.launch()