cognitivecomputations/yayi2-30b-llama.
Refer to the original model card for more details on the model.pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/yayi2-30b-llama-hf-4bit-mlx")
4response = generate(model, tokenizer, prompt="hello", verbose=True)