sigjhl/Llama-3.1-Minitron-4B-Width-Base_mlx_q8

The Model sigjhl/Llama-3.1-Minitron-4B-Width-Base_mlx_q8 was converted to MLX format from nvidia/Llama-3.1-Minitron-4B-Width-Base using mlx-lm version 0.17.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("sigjhl/Llama-3.1-Minitron-4B-Width-Base_mlx_q8")
response = generate(model, tokenizer, prompt="hello", verbose=True)