app.py

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

model_id = "Qwen/Qwen2.5-Coder-7B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def code_agent(prompt):
    output = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2)
    return output[0]["generated_text"]

demo = gr.Interface(fn=code_agent, inputs="text", outputs="text")
demo.launch()