Downloads · 30 days
383
37% of all-time downloads
osxest/Huihui-CyberStrike-OffSec-35B-abliterated-mlx-6Bit
Huihui-CyberStrike-OffSec-35B-abliterated-mlx-6Bit is a text generation model from osxest. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model osxest/Huihui-CyberStrike-OffSec-35B-abliterated-mlx-6Bit was converted to MLX format from huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated using mlx-lm version 0.31.2.
Downloads · 30 days
383
37% of all-time downloads
All-time downloads
1K
Public
Parameters
34.7B
28.2 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors28.2 GB · 100%
How the weights are stored.
U3234.7B · 100%
From the Hugging Face model README
The Model osxest/Huihui-CyberStrike-OffSec-35B-abliterated-mlx-6Bit was converted to MLX format from huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("osxest/Huihui-CyberStrike-OffSec-35B-abliterated-mlx-6Bit")
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)