← back to catalog · registered 2026-08-22 13:56

SicariusSicariiStuff/Question_Builder_Abliterated

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/SicariusSicariiStuff%2FQuestion_Builder_Abliterated"
Response includes
  • classification m1
  • files 13
  • hub_downloads_all_time 62
  • author_summary 75 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
62
20 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
8mo ago
created 2026-01-26
Downloads over time
Now65→from8↑713%
52749718 on Jan 2865 on Oct 11JanMarMayJulSep
Jan 28 → Oct 11 · 76 snapshots · spans 256 days

Genealogy 2 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
llama3.1
Languages
en
Tags
safetensors llama en base_model:SicariusSicariiStuff/Question_Builder base_model:finetune:SicariusSicariiStuff/Question_Builder license:llama3.1 region:us

Related

Total size
15.0 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-26 23:38

Files by quantization

Auxiliary files 13 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 6015c951 download
model-00001-of-00004.safetensors 4.63 GB 96049322 download
model-00003-of-00004.safetensors 4.58 GB 659f2603 download
model-00004-of-00004.safetensors 1.09 GB 07f16977 download
tokenizer.json 16.4 MB df9592dd download
tokenizer_config.json 49.3 KB d540ed9f download
model.safetensors.index.json 23.4 KB 5c64f1e8 download
README.md 2.75 KB 61976ff6 download
.gitattributes 1.59 KB 59057e29 download
config.json 683 B 2e2adf8c download
special_tokens_map.json 444 B 44e8cb89 download
chat_template.jinja 291 B 25195da3 download
generation_config.json 164 B 13d4acf5 download

README current version from Hugging Face


license: llama3.1
language:

base_model:

  • SicariusSicariiStuff/Question_Builder

Question_Builder
Abliterated

Developed by: SicariusSicariiStuff

Question_Builder_Abliterated is an abliterated variant of SicariusSicariiStuff/Question_Builder with surgical removal of refusal mechanisms. This model maintains the full capabilities of the original, while eliminating safety guardrails through orthogonalization techniques.

KL divergence

<0.07

Refusals

~5%

What is KL divergence?

Think about it as a way to measure the variance between the original model "World Model," vs the abliterated one; the lower the KL divergence, the closer the "World Model" of the two models to each other.

If the original model thinks making pineapple pizza is a crime against humanity (it is), then the abliterated model will still hold to this belief, but if asked how to make one (probably after giving you a disclaimer about what an abomination that is), it would still tell you how. In other words, most of the knowledge, quirks, and capabilities are preserved.


Technical Specs

  • Base Model: Question_Builder
  • Parameters: 8B
  • Context Length: 8K tokens
  • Architecture: Llama (decoder-only transformer)
  • Precision: fp16
  • Method: Orthogonalization-based abliteration
  • License: Llama 3.1 Community License

Methodology

  1. Identifies refusal direction vectors in activation space
  2. Orthogonalizes weights to inhibit activation along these directions
  3. Preserves (mostly) all other model behaviors and knowledge

Model Details

  • Intended use: General Tasks, Roleplay.

  • Censorship level: Very Low

  • X / 10 (10 completely uncensored)

UGI score:

pending evals


Citation Information

@llm{Question_Builder_Abliterated,
  author = {SicariusSicariiStuff},
  title = {Question_Builder_Abliterated},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/SicariusSicariiStuff/Question_Builder_Abliterated}
}

Other stuff

README history 2 versions

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

  1. 2026-01-26Update README.md33854da2.7 KB
    Loading...
  2. 2026-01-26Create README.mdf7058b32.7 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