app.py

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

model_name = "Qwen/Qwen2.5-Coder-1.5B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

def respond(message, history):
    messages = []
    for user, bot in history:
        messages.append({"role": "user", "content": user})
        messages.append({"role": "assistant", "content": bot})
    messages.append({"role": "user", "content": message})

    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(**model_inputs, max_new_tokens=512)
    output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
    content = tokenizer.decode(output_ids, skip_special_tokens=True)

    return content

demo = gr.ChatInterface(respond)
demo.launch()