Downloads · 30 days
147
10% of all-time downloads
osxest/Huihui-Ornith-1.5-9B-abliterated-mlx-4Bit
Huihui-Ornith-1.5-9B-abliterated-mlx-4Bit 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 mit.
The Model osxest/Huihui-Ornith-1.5-9B-abliterated-mlx-4Bit was converted to MLX format from huihui-ai/Huihui-Ornith-1.5-9B-abliterated using mlx-lm version 0.31.2.
Downloads · 30 days
147
10% of all-time downloads
All-time downloads
1.5K
Public
Parameters
9B
5.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors5 GB · 100%
How the weights are stored.
U329B · 100%
From the Hugging Face model README
The Model osxest/Huihui-Ornith-1.5-9B-abliterated-mlx-4Bit was converted to MLX format from huihui-ai/Huihui-Ornith-1.5-9B-abliterated using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("osxest/Huihui-Ornith-1.5-9B-abliterated-mlx-4Bit")
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)