Downloads · 30 days
28
16% of all-time downloads
DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit
usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit
DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit is a machine learning model from usermma. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
The Model usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit was converted to MLX format from usermma/DeepHat-V1-7B-Heretic-Abliterated using mlx-lm version 0.31.2.
All-time downloads
172
Public
Parameters
7.6B
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
Parameter types
How the weights are stored.
U327.6B · 100%
Base models
Model card
From the Hugging Face model README
usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit
The Model usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit was converted to MLX format from usermma/DeepHat-V1-7B-Heretic-Abliterated using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-2Bit")
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)
- Library
- mlx
- Type
- qwen2
- Languages
- en
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026