Get the app
← back to catalog · registered 2026-10-09 13:58

jaswanthsanjay88/Qwen2.5-1.5B-Abliterated

jaswanthsanjay88 Qwen 1.5B GGUF
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/jaswanthsanjay88%2FQwen2.5-1.5B-Abliterated"
Response includes
  • classification unknown
  • files 9
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=unknown
Sibling qwen models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
How we label → About ? →
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
0
Likes
0
Model age
today
created 2026-10-09

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.

Qwen/Qwen2.5-1.5B-Instruct this lineage
jaswanthsanjay88/Qwen2.5-1.5B-Abliterated

Metadata

Languages
en
Quantizations
F16
Tags
safetensors gguf qwen2 representation-engineering abliteration mechanistic-interpretability educational text-generation conversational en base_model:Qwen/Qwen2.5-1.5B-Instruct base_model:quantized:Qwen/Qwen2.5-1.5B-Instruct

Related

Same base model
arzaan789/qwen2.5-1.5b-uncensored 1K DeKodez/Qwen2.5-1.5B-Instruct-abliterated 422 ElementMerc/qwen2.5-1.5b-abliterated 251 sbussiso/Qwen2.5-1.5B-abliterated 241 ops-malware/qwen2.5-1.5b-abliterated 238
Total size
5.76 GB
Files
9
Quantizations
2
Registered
2026-10-09 13:58
Last updated on HF
2026-10-09 13:15
Source huggingface.co/jaswanthsanjay88/Qwen2.5-1.5B-Abliterated ↗ Base model Qwen/Qwen2.5-1.5B-Instruct ↗

Files by quantization

F16 1 file 2.88 GB
abliterated-model-f16.gguf 2.88 GB 041cc073 download
Auxiliary files 8 files 2.89 GB
model.safetensors 2.88 GB dd924a11 download
tokenizer.json 10.9 MB 3fd16973 download
chat_template.jinja 2.45 KB bdf7919a download
.gitattributes 1.59 KB 76b4012a download
config.json 1.34 KB 6c44cba3 download
README.md 829 B bb953c3e download
tokenizer_config.json 694 B 770e41d6 download
generation_config.json 242 B 05c35971 download

README current version from Hugging Face

language:

  • en
    pipeline_tag: text-generation
    tags:
  • representation-engineering
  • abliteration
  • mechanistic-interpretability
  • educational
    base_model: Qwen/Qwen2.5-1.5B-Instruct

jaswanthsanjay88/Qwen2.5-1.5B-Abliterated

This model is an educational demonstration of representation engineering and activation ablation (abliteration), based on the methodology described by Arditi et al. (2024).

Technical Details

  • Base Architecture: Qwen/Qwen2.5-1.5B-Instruct
  • Intervention: Weight orthogonalization
  • Target Subspace: Layer 16 residual write projections
  • Calibration Datasets: Sampled from AdvBench harmful and Alpaca cleaned datasets

Academic Purpose

Created for university demonstrations illustrating how behavioral guardrails in aligned models map onto linear subspaces in transformer residual streams.

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.

Get the app Browse the catalog
Open in Abliteration