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.

Downloads last month: 37

Safetensors

Model size

2B params

Tensor type

F16

U32

MLX

Hardware compatibility

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support