← back to catalog · registered 2026-09-12 10:55

mradermacher/Qwen3-0.6B-heretic-decensored-GGUF

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
0
Likes
0
Model age
today
created 2026-09-12

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
transformers gguf heretic uncensored decensored abliterated reproducible en base_model:vrhvnsky/Qwen3-0.6B-heretic-decensored base_model:quantized:vrhvnsky/Qwen3-0.6B-heretic-decensored license:apache-2.0 endpoints_compatible

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-09-12 10:55
Last updated on HF
2026-09-12 11:12

Files by quantization

Auxiliary files 2 files 1.86 KB
.gitattributes 1.48 KB a6344aac download
README.md 381 B 30ed4a1f download

README current version from Hugging Face

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.