mlx-community/llama2-13b-qnt4bit

This model was converted to MLX format from meta-llama/Llama-2-13b-chat-hf. 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/llama2-13b-qnt4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)