← back to catalog · registered 2026-11-12 09:03

SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit

SolsticeAI 27B second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/SolsticeAI%2FArete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit"
Response includes
  • classification m3
  • files 12
  • author_summary 9 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
349
Likes
1
Model age
1w ago
created 2026-11-12

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now 349 → from 0 ↑ 0%
0128256384 0 on Nov 12 349 on Nov 22 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 nous-research arete supervised-fine-tuning value-alignment heretic uncensored decensored abliterated reproducible

Related

Total size
17.2 GB
Files
12
Quantizations
1
Registered
2026-11-12 09:03
Last updated on HF
2026-11-12 08:43

Files by quantization

Auxiliary files 12 files 17.2 GB
model-00001-of-00004.safetensors 4.99 GB 05780efe download
model-00003-of-00004.safetensors 4.99 GB 202e9cf3 download
model-00002-of-00004.safetensors 4.97 GB 125838cd download
model-00004-of-00004.safetensors 2.27 GB 830b9f4f download
tokenizer.json 19.1 MB a5cd9732 download
model.safetensors.index.json 185 KB 272fae1f download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 3.98 KB 65bdc77a download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.21 KB 393eb766 download
tokenizer_config.json 1.20 KB 159b5c47 download
generation_config.json 244 B 2f9feacb download

README current version from Hugging Face


pipeline_tag: text-generation
tags:

  • nous-research
  • arete
  • supervised-fine-tuning
  • value-alignment
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible
  • mlx
  • mlx-my-repo
    license: apache-2.0
    datasets:
  • NousResearch/arete-data-pairs
    base_model: SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic

SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit

The Model SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit was converted to MLX format from SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit")

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)

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-12 Upload folder using huggingface_hub adf98a3 1.2 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration