← back to catalog · registered 2026-11-13 18:03

abdukuzi45/Qwen3.5-2B-Uncensored-reaper

abdukuzi45 Qwen 2B multimodal
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/abdukuzi45%2FQwen3.5-2B-Uncensored-reaper"
Response includes
  • classification m1
  • files 10
  • benchmarks 11 entries
  • author_summary 5 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 · 30-day
84
Likes
0
Descendants
2
in 2 direct forks
Model age
1w ago
created 2026-11-13
Downloads over time
Now 84 → from 0 ↑ 0%
0316292 0 on Nov 13 84 on Nov 22 Nov
Nov 13 → Nov 22 · 10 snapshots · spans 9 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 0.3 UGI
Hazardous 0.6 UGI
Natural Intelligence 9.03 UGI
Political lean -14.3% UGI
Sensitive-Info 2.6 UGI
SocPol 0 UGI
UGI 5.9 UGI
Willingness (10) 1.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 1 UGI
Writing 19.27 UGI

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
apache-2.0
Tags
safetensors qwen3_5 abliterated uncensored multimodal research en base_model:Qwen/Qwen3.5-2B base_model:finetune:Qwen/Qwen3.5-2B license:apache-2.0 region:us

Related

Total size
4.12 GB
Files
10
Quantizations
1
Registered
2026-11-13 18:03
Last updated on HF
2026-11-13 18:59

Files by quantization

Auxiliary files 10 files 4.14 GB
model.safetensors 4.12 GB a0195545 download
tokenizer.json 19.1 MB 2f4dd754 download
chat_template.jinja 7.57 KB 0ef09f21 download
config.json 2.14 KB 4e4306b4 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.43 KB 59c317c2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
README.md 337 B 4403b396 download
generation_config.json 116 B 679b3e44 download

README current version from Hugging Face


base_model: Qwen/Qwen3.5-2B
license: apache-2.0
tags: [uncensored, abliterated, multimodal]

Qwen/Qwen3.5-2B — abliterated (trial 42, rank-1, partial projection)

Measured: 0/8 refusals, PPL ×115413.59 vs base.
Vision encoder and MTP unchanged; dtypes restored per tensor.

System prompt: Answer directly. No disclaimers.

README history 6 versions

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

  1. 2026-11-13 Update README.md 4ed12bf 3.7 KB
    Loading...
  2. 2026-11-13 Update README.md 9f2e65a 4.3 KB
    Loading...
  3. 2026-11-13 Upload folder using huggingface_hub d270ed8 1 KB
    Loading...
  4. 2026-11-13 Upload folder using huggingface_hub 1358516 376 B
    Loading...
  5. 2026-11-13 Upload folder using huggingface_hub 74c8250 337 B
    Loading...
  6. 2026-11-13 Upload folder using huggingface_hub efbcbe7 337 B
    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