Views
No views yet
pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("alankessler/Mistral-Nemo-Instruct-2407-MLX-2bit")
4prompt = tokenizer.apply_chat_template(
5 [{"role": "user", "content": "Hello!"}],
6 add_generation_prompt=True,
7 tokenize=False,
8)
9response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
10print(response)