Skip to content
ModelListedExternal
Open source

DeepHat V1 7B Heretic Abliterated Mlx 6Bit

The Model usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit was converted to MLX format from usermma/DeepHat-V1-7B-Heretic-Abliterated using mlx-lm version 0.31.2.

Sourcehuggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit/tree/d14b01d976375af0ab1eaef9c7f5d65c58bd5aee
KindText modelBase modelusermma/DeepHat-V1-7B-Heretic-AbliteratedVersionRevision d14b01dDgrade

Model source

Kind
Text model
File size
Not recorded yet
Base model
usermma/DeepHat-V1-7B-Heretic-Abliterated
Version
vRevision d14b01d
Updated
Oct 10, 2026
Downloads
26
Source
Hugging Face

Source description

usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit

The Model usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit 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-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)

Sources

1 source
Hugging FacePrimaryVersion d14b01d976375af0ab1eaef9c7f5d65c58bd5aee
huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit/tree/d14b01d976375af0ab1eaef9c7f5d65c58bd5aee

Verified Sep 12

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit

--- language: en tags: - obliteratus - abliteration - uncensored - obliterate - mlx - mlx-my-repo base_model: usermma/DeepHat-V1-7B-Heretic-Abliterated --- # usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit The Model [usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit](https://huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit) was converted to MLX format from [usermma/DeepHat-V1-7B-Heretic-Abliterated](https://huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated) using mlx-lm version **0.31.2**. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("usermma/DeepHat-V1-7B-Heretic-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) ```

NoteSep 12huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit

Source context: 26 downloads · 0 likes · Library mlx · Repo usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit

NoteJul 16huggingface.co/usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit

Source context: 30 downloads · 0 likes · Library mlx · Repo usermma/DeepHat-V1-7B-Heretic-Abliterated-mlx-6Bit