Views
No views yet
pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit")
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)