Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("itayl/Hebrew-Gemma-11B-V2-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Authors
Trained by Yam Peleg.
In collaboration with Jonathan Rouach and Arjeo, inc.
