Views
No views yet
pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/LongCat-Flash-Thinking-2601-4bit")
4
5prompt = "hello"
6
7if tokenizer.chat_template is not None:
8 messages = [{"role": "user", "content": prompt}]
9 prompt = tokenizer.apply_chat_template(
10 messages, add_generation_prompt=True, return_dict=False,
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)