mlx-community/yayi2-30b-llama-hf-4bit-mlx

This model was converted to MLX format from cognitivecomputations/yayi2-30b-llama. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/yayi2-30b-llama-hf-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)