gistfile1.txt

from mlx_lm import load, generate

model, tokenizer = load('Qwen/Qwen2-7B-Instruct-MLX', tokenizer_config={"eos_token": "<|im_end|>"})

prompt = "Why people call putin khuilo."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

result = generate(model, tokenizer, prompt=text, verbose=True, max_tokens=512)

gistfile2.txt

pip install mlx-lm