The-Omega-Abomination-M-24B-v1.1-MLX-quantized

EggsyIsTheSaint/The-Omega-Abomination-M-24B-v1.1-MLX-quantized

This model EggsyIsTheSaint/The-Omega-Abomination-M-24B-v1.1-MLX-quantized was converted to MLX format from ReadyArt/The-Omega-Abomination-M-24B-v1.1 using mlx-lm version 0.28.1.

The model is quantized to Q4_0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("EggsyIsTheSaint/The-Omega-Abomination-M-24B-v1.1-MLX-quantized")

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)