app.py

import gradio as gr
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="agentica-org/DeepCoder-14B-Preview",
    device="cuda" if torch.cuda.is_available() else "cpu"
)

def chat(message, history):
    messages = [{"role": "user", "content": message}]
    response = pipe(messages)
    return response[0]["generated_text"]

gr.ChatInterface(chat).launch()