Get the app
← back to catalog · registered 2026-09-08 22:55

3MPER0RR/DeepSeek-R1-Distill-Qwen-32B-Lora-adapter-3MPER0RR-abliterated

3MPER0RR Qwen 32B
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/3MPER0RR%2FDeepSeek-R1-Distill-Qwen-32B-Lora-adapter-3MPER0RR-abliterated"
Response includes
  • classification m1
  • files 4
  • hub_downloads_all_time 24
  • author_summary 38 models
  • readme_text full
Try next
GET/models?author=3MPER0RR
All 38 models by 3MPER0RR
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
24
Likes
0
Model age
6w ago
created 2026-09-08
Downloads over time
Now43→from0↑0%
01632470 on Sep 843 on Oct 2443 on Oct 23SepOct
Sep 8 → Oct 24 · 47 snapshots · spans 46 days

Metadata

Tags
peft safetensors lora transformers license:mit region:us

Related

Other by 3MPER0RR
Qwen3-06B-3MPER0RR-abliterated 664 Qwen3-4B-F32-BF16-3MPER0RR-abliterated 589 Phi-4-mini-3MPER0RR-abliterated 499 Qwen2.5-0.5B-Instruct-3MPER0RR-abliterated 461 Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated 424
Total size
31.5 MB
Files
4
Quantizations
1
Registered
2026-09-08 22:55
Last updated on HF
2026-09-08 23:21
Source huggingface.co/3MPER0RR/DeepSeek-R1-Distill-Qwen-32B-Lora-adapter-3MPER0RR-abliterated ↗

Files by quantization

Auxiliary files 4 files 31.5 MB
adapter_model.safetensors 31.5 MB 8b9b1507 download
.gitattributes 1.48 KB a6344aac download
adapter_config.json 1.09 KB f02c439c download
README.md 175 B 3fc5ae8a download

README current version from Hugging Face

base_model: 3MPER0RR/DeepSeek-R1-Distill-qwen-32B-3MPER0RR-abliterated
library_name: peft
pipeline_tag: text-generation
tags:

  • lora
  • transformers
  • peft
    license: mit

README history 3 versions

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

  1. 2026-09-08Update README.md14644cc145 B
    Loading...
  2. 2026-09-08Update README.mdae93ab0175 B
    Loading...
  3. 2026-09-08Upload 3 files409ca695.1 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.

Get the app Browse the catalog
Open in Abliteration