from mlx_lm import load, generate

model, tokenizer = load("CallMcMargin/Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)