import gradio as gr

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

    inputs = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True,
        return_dict=True,
        return_tensors="pt",
    ).to(model.device)

    outputs = model.generate(**inputs, max_new_tokens=40)
    response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
    return response

demo_chat = gr.ChatInterface(
    model_chat,
    title="LiquidAI/LFM2.5-2.6B Chat Demo",
    description="Chat with the LiquidAI/LFM2.5-2.6B model."
)

demo_chat.launch(share=True)