Google Gemma2
Collection
20 items
•
Updated
•
11
The Model mlx-community/gemma-2-2b-8bit was converted to MLX format from google/gemma-2-2b using mlx-lm version 0.16.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/gemma-2-2b-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)