Downloads · 30 days
75
7% of all-time downloads
CuckmeisterFuller/Cydonia-v1.2-Magnum-v4-22B-Q2-mlx
Cydonia-v1.2-Magnum-v4-22B-Q2-mlx is a text generation model from CuckmeisterFuller. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
The Model CuckmeisterFuller/Cydonia-v1.2-Magnum-v4-22B-Q2-mlx was converted to MLX format from knifeayumu/Cydonia-v1.2-Magnum-v4-22B using mlx-lm version 0.20.5.
Downloads · 30 days
75
7% of all-time downloads
All-time downloads
1K
Public
Parameters
22.2B
7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7 GB · 100%
How the weights are stored.
U3222.2B · 100%
From the Hugging Face model README
The Model CuckmeisterFuller/Cydonia-v1.2-Magnum-v4-22B-Q2-mlx was converted to MLX format from knifeayumu/Cydonia-v1.2-Magnum-v4-22B using mlx-lm version 0.20.5.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("CuckmeisterFuller/Cydonia-v1.2-Magnum-v4-22B-Q2-mlx")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)