Modelpublic

ailexleon/Orion-26B-A4B-v1-mlx-8Bit

sourceHugging Faceapache-2.0updated 28d agoView on Hugging Face

0likes311downloads

Model Card

ailexleon/Orion-26B-A4B-v1-mlx-8Bit

Converted to MLX format from TheDrummer/Orion-26B-A4B-v1 using mlx-lm version 0.31.3.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("ailexleon/Orion-26B-A4B-v1-mlx-8Bit")

prompt = "hello"

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

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