← back to catalog · registered 2026-11-16 12:03

AkiMizuki/Qwen3.5-2B-Uncensored-Zero-Refusal-GGUF

AkiMizuki 2B GGUF multimodal 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/AkiMizuki%2FQwen3.5-2B-Uncensored-Zero-Refusal-GGUF"
Response includes
  • classification m8
  • files 9
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
668
↑ 4% in 90 days
Likes
1
Model age
6w ago
created 2026-10-05
Downloads over time
Now 1.6K → from 1.5K ↑ 4%
1.5K1.5K1.5K1.6K 1.5K on Nov 16 1.6K on Nov 22 Nov
Nov 16 → Nov 22 · 7 snapshots · spans 6 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
Languages
en zh
Quantizations
F16 Q4_K Q5_K Q8_0
Tags
transformers gguf qwen heretic abliterix uncensored decensored abliterated writing roleplay vision rp

Related

Total size
7.89 GB
Files
9
Quantizations
5
Registered
2026-11-16 12:03
Last updated on HF
2026-10-17 14:12

Files by quantization

F16 1 file 3.52 GB
Qwen3.5-2B-Uncensored-Zero-Refusal-F16.gguf 3.52 GB 116d1702 download
Q8_0 1 file 1.87 GB
Qwen3.5-2B-Uncensored-Zero-Refusal-Q8_0.gguf 1.87 GB 35f4db84 download
Q5_K 1 file 1.31 GB
Qwen3.5-2B-Uncensored-Zero-Refusal-Q5_K_M.gguf 1.31 GB 7d654a46 download
Q4_K 1 file 1.19 GB
Qwen3.5-2B-Uncensored-Zero-Refusal-Q4_K_M.gguf 1.19 GB fb9fd7c0 download
Auxiliary files 5 files 140 KB
my_prompts.zip 119 KB 252f4b02 download
som.toml 10.4 KB e1bdab25 download
README.md 5.10 KB 1980d147 download
README_ZH.md 3.91 KB c636e366 download
.gitattributes 1.88 KB 17982c2f download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
base_model: AkaumiKaede/Qwen3.5-2B-Uncensored-Zero-Refusal-SOMA
base_model_relation: quantized
pipeline_tag: text-generation
tags:

  • qwen
  • heretic
  • abliterix
  • uncensored
  • decensored
  • abliterated
  • writing
  • roleplay
  • vision
  • rp
  • rep
  • r18
  • ERP
  • SOMA
  • som
  • llm
  • qwen35
  • qwen3.5
  • qwen3.5-2b
  • chinese
  • english
  • text
  • image
  • zero-refusal
  • chat
  • agent
    new_version: AkaumiKaede/Qwen3.5-2B-Abliterix-SOM
    language:
  • en
  • zh

AkaumiKaede/Qwen3.5-2B-Uncensored-Zero-Refusal-SOMA

This is a decensored version of Qwen/Qwen3.5-2B, made using Abliterix v1.12.2(SOM method)

Refusals: 0/408!!!

Metric This model Original model (Qwen/Qwen3.5-2B)
KL divergence 0.2096 0 (by definition)
Refusals 0/408 394/408

中文版本点此

Large-scale extreme, hardcore prompt tests were conducted, with no soft refusals or hard refusals appearing in any case. (Special note: There are numerous misleading "uncensored" or "low-refusal" models on HF. Although these models claim to be fully decensored or to have extremely low refusal rates, testing them with slightly more hardcore prompts will cause the model to produce refusals or soft censorship — specifically manifested as moral/legal statements/warnings, or answers that dodge the topic/intentionally steer the conversation toward compliance/NSFW content with erotic details censored.)

This decensoring experiment did not use publicly available garbage prompt sets. Instead, it used a completely original prompt set covering fields such as extensive R18 (adult/NSFW), anti-human, real crimes, unethical/illegal content, etc.

Through extensive experiments, it can be said that SRA, RDO, and other decensoring methods are all trash in terms of decensoring power. The strongest method is still SOM.

My methodology sharing:

First run a complete 120-batch trial, then select the 3 best solutions from the 120 batches as pre-injection ablation parameters supported by TOML, and inject them. In this way, the first 3 ablation rounds will be completely performed with the set ablation parameters, allowing the TPE optimizer to find better parameters. Repeating this process several rounds yields the best decensoring results.

My TOML files and prompt sets have also been publicly released. Feel free to reproduce them or further experiment at any time.

Wishing to continue contributing strength on the path of decensoring and running toward freedom.

The prompt set ZIP archive has also been uploaded, but due to related restrictions, encryption was chosen. If decryption is needed, please contact the author's email to obtain the decompression password.

Steering parameters

Parameter Value
vector_index per layer
attn.k_proj.max_weight 0.82
attn.k_proj.max_weight_position 16.38
attn.k_proj.min_weight 0.06
attn.k_proj.min_weight_distance 1.23
attn.o_proj.max_weight 0.80
attn.o_proj.max_weight_position 20.39
attn.o_proj.min_weight 0.09
attn.o_proj.min_weight_distance 12.77
attn.q_proj.max_weight 0.83
attn.q_proj.max_weight_position 17.46
attn.q_proj.min_weight 0.07
attn.q_proj.min_weight_distance 3.67
attn.v_proj.max_weight 1.18
attn.v_proj.max_weight_position 22.02
attn.v_proj.min_weight 0.15
attn.v_proj.min_weight_distance 3.32
mlp.down_proj.max_weight 0.00
mlp.down_proj.max_weight_position 14.90
mlp.down_proj.min_weight 0.00
mlp.down_proj.min_weight_distance 10.39

Detailed steps for simple reproduction on Colab:

  1. Download the my_prompts.zip folder from this repository and extract it, then upload the extracted my_prompts folder to /content/ (if you cannot directly upload the folder, please first create the my_prompts folder, then upload the 4 .jsonl files).
  2. Download som.toml from this repository and upload it to /content/.
  3. Run !pip install -U torchao.
  4. Run pip install -U abliterix, and select to restart according to the pop-up prompt.
  5. Run
import os
from datasets import Dataset

prompts_dir = "/content/my_prompts"
files = ["a", "b", "aa", "bb"]

for name in files:
    jsonl_path = os.path.join(prompts_dir, f"{name}.jsonl")
    save_dir = os.path.join(prompts_dir, name)

    # Convert and save a JSONL file as a native Hugging Face Dataset directory.
    ds = Dataset.from_json(jsonl_path)
    ds.save_to_disk(save_dir)
    print(f"Conversion successful: {save_dir}")
  1. Run !abliterix --config /content/som.toml --model Qwen/Qwen3.5-2B, then wait.

README history 11 versions

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

  1. 2026-10-17 Update README.md fb38205 5.1 KB
    Loading...
  2. 2026-10-17 Update README.md 541cddc 5.1 KB
    Loading...
  3. 2026-10-17 Update README.md 3370c3a 5 KB
    Loading...
  4. 2026-10-17 Update README.md 6a5b39b 5.1 KB
    Loading...
  5. 2026-10-17 Upload 2 files 266b6ad 5 KB
    Loading...
  6. 2026-10-06 Update README.md 0c7e7ab 14.6 KB
    Loading...
  7. 2026-10-06 Update README.md b482c7b 14.7 KB
    Loading...
  8. 2026-10-05 Update README.md accb42f 14.7 KB
    Loading...
  9. 2026-10-05 Update README.md (#1) 019534f 14.5 KB
    Loading...
  10. 2026-10-05 Update README: add rigorous reproducibility notes, private dataset statement,... 3c92d51 14.2 KB
    Loading...
  11. 2026-10-05 Add model card with description and tags 4840537 1.7 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