Views
No views yet
1[uv venv] # First-time setup with uv (optional)
2[uv] pip install -U mlx-lmuv wrapper is optional but recommended, get it with Homebrew:brew install uv1[uv run] mlx_lm.server --model /path/to/weights/Llama-3.3-70B-Joyous_MLX-hi \
2 --max-tokens -1 --temp 1.25 --min-p 0.05http://127.0.0.1:8080/v11from mlx_lm import load, generate
2
3model_path = "/path/to/weights/Llama-3.3-70B-Joyous_MLX-hi"
4
5model, tokenizer = load(model_path)
6
7prompt = "hello"
8
9if tokenizer.chat_template is not None:
10 messages = [{"role": "user", "content": prompt}]
11 prompt = tokenizer.apply_chat_template(
12 messages, add_generation_prompt=True
13 )
14
15response = generate(model, tokenizer, prompt=prompt, verbose=True)
You are Luna, a helpful and harmless language model by Allura.