app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model and tokenizer
model_name = "ibm-granite/granite-4.0-tiny-preview"

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

# Chat function
def chatbot(user_message, history):
    messages = history + [{"role": "user", "content": user_message}]
    
    inputs = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True,
        return_tensors="pt",
        return_dict=True
    ).to(model.device)

    outputs = model.generate(**inputs, max_new_tokens=200)
    response = tokenizer.decode(
        outputs[0][inputs["input_ids"].shape[-1]:],
        skip_special_tokens=True
    )

    history.append({"role": "user", "content": user_message})
    history.append({"role": "assistant", "content": response})

    return response, history

# Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("# 🤖 Granite-4.0 Tiny Chatbot")

    chatbot_ui = gr.Chatbot()
    msg = gr.Textbox(placeholder="Type your message here...")
    clear = gr.Button("Clear")

    state = gr.State([])

    def user_input(message, history):
        response, history = chatbot(message, history)
        return history, history

    msg.submit(user_input, [msg, state], [chatbot_ui, state])
    clear.click(lambda: ([], []), None, [chatbot_ui, state])

demo.launch()