Views
No views yet
1python -m venv mlx-venv
2# then activate the virtual enviroment if needed.
3source mlx-venv/bin/activate
4# then install mlx.
5pip install mlx-lm
61from mlx_lm import load, generate
2
3model, tokenizer = load("jesusoctavioas/GLM-4.7-mlx-2Bit")
4
5prompt="hello"
6
7if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
8 messages = [{"role": "user", "content": prompt}]
9 prompt = tokenizer.apply_chat_template(
10 messages, tokenize=False, add_generation_prompt=True
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)