Llama 3.2
Collection
Meta goes small with Llama3.2, both in 1B and 3B.
•
9 items
•
Updated
•
6
The Model mlx-community/Llama-3.2-3B-Instruct-8bit was converted to MLX format from meta-llama/Llama-3.2-3B-Instruct using mlx-lm version 0.17.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Llama-3.2-3B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)