Views
No views yet
prince-canuma/WizardLM-2-8x22B using mlx-lm version 0.9.0.pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/WizardLM-2-8x22B-4bit")
4response = generate(model, tokenizer, prompt="hello", verbose=True)