Downloads · 30 days
145
6% of all-time downloads
nightmedia/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx
Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx is a text generation model from nightmedia. Use it when you need the model to write or continue text. It is set up for mlx.
This model Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx was converted to MLX format from DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B
Downloads · 30 days
145
6% of all-time downloads
All-time downloads
2.5K
Public
Parameters
18.4B
20.7 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors20.7 GB · 100%
How the weights are stored.
U3218.4B · 100%
From the Hugging Face model README
This model Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx was converted to MLX format from DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B using mlx-lm version 0.26.0.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx")
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)