app.py

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

model_name = "Qwen/Qwen2.5-0.5B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def chat(message, history):
    messages = [{"role": "user", "content": message}]
    inputs = tokenizer.apply_chat_template(
        messages, return_tensors="pt"
    )

    outputs = model.generate(
        inputs,
        max_new_tokens=100,
        do_sample=True,
        temperature=0.7
    )

    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return reply

demo = gr.ChatInterface(fn=chat)

demo.launch()