Views
No views yet
pip install mlx-lm1from mlx_lm import load, generate
2model, tokenizer = load("Float16-cloud/llama3.1-typhoon2-8b-instruct-mlx-4bit")
3prompt="hello"
4if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
5 messages = [{"role": "user", "content": prompt}]
6 prompt = tokenizer.apply_chat_template(
7 messages, tokenize=False, add_generation_prompt=True
8 )
9response = generate(model, tokenizer, prompt=prompt, verbose=True)