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

alperiox/SmolLM2-1.7B-Instruct-arithmetic-abliterated

alperiox Llama 1.7B
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/alperiox%2FSmolLM2-1.7B-Instruct-arithmetic-abliterated"
Response includes
  • classification m1
  • files 9
  • hub_downloads_all_time 67
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=alperiox
All 3 models by alperiox
 GET/models?family=llama&method=m1
Sibling llama 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
67
10 last 30d - stable
Likes
0
Model age
5mo ago
created 2026-04-23
Downloads over time
Now73→from34↑115%
3247627734 on Apr 2273 on Oct 1173 on Oct 7AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 days

Metadata

Tags
safetensors llama region:us

Related

Other by alperiox
Qwen2.5-1.5B-Instruct-arithmetic-abliterated 7 Qwen2.5-0.5B-Instruct-arithmetic-abliterated 7
Total size
3.19 GB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-23 13:29
Source huggingface.co/alperiox/SmolLM2-1.7B-Instruct-arithmetic-abliterated ↗

Files by quantization

Auxiliary files 9 files 3.19 GB
model.safetensors 3.19 GB 8b9bbfb3 download
tokenizer.json 3.36 MB c963c97e download
.gitattributes 1.48 KB a6344aac download
config.json 952 B 682c100e download
README.md 929 B d942dd89 download
tokenizer_config.json 405 B 95afe10b download
chat_template.jinja 368 B a3c992f0 download
abliteration_metadata.json 329 B 21e0c6da download
generation_config.json 131 B d63f450d download

README current version from Hugging Face

SmolLM2-1.7B-Instruct - Arithmetic Abliteration

Base model: HuggingFaceTB/SmolLM2-1.7B-Instruct

Modified layer: 14/24 (58.3% depth)
Method: Difference-in-means + Weight Orthogonalization
Reference: Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (2024)

What is this?

This is a permanently abliterated version. The arithmetic direction was projected
out of the model weights using:

W_new = W - r * (r^T * W)

No hooks needed. Works with any inference pipeline or quantization.

Behavior

  • Arithmetic accuracy: ~0% (suppressed)
  • General language: preserved

Note

~50pp arith suppression, 100% neutral coherence. Layer 14/24 (58% depth). Auto-selected layer 1 caused collapse; layer 14 is the surgical sweet spot.

Original experiment

https://github.com/alperiox/abliteration-example-mlintern

README history 1 version

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

  1. 2026-04-23Add arithmetic abliterated checkpoint (layer 14/24)d4c5c6a929 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.

Get the app Browse the catalog
Open in Abliteration