Modelpublic

beezu/Behemoth-ReduX-123B-v1-MLX-3Bit

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes8downloads

Model Card

beezu/Behemoth-ReduX-123B-v1-MLX-3Bit

This model beezu/Behemoth-ReduX-123B-v1-MLX-3Bit was converted to MLX format from TheDrummer/Behemoth-ReduX-123B-v1 using mlx-lm version 0.27.1.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("beezu/Behemoth-ReduX-123B-v1-MLX-3Bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)