README.md

metadata

license: other
tags:
  - mlx
base_model: TheDrummer/Cydonia-24B-v2.1

gg000/Cydonia-24B-v2.1-8bit

The Model gg000/Cydonia-24B-v2.1-8bit was converted to MLX format from TheDrummer/Cydonia-24B-v2.1 using mlx-lm version 0.22.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("gg000/Cydonia-24B-v2.1-8bit")

prompt = "hello"

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

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