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

brianmatzelle/llama3.2-1b-instruct-hasanpiker-abliterated

brianmatzelle Llama 1.2B 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/brianmatzelle%2Fllama3.2-1b-instruct-hasanpiker-abliterated"
Response includes
  • classification m1
  • files 8
  • benchmarks 11 entries
  • hub_downloads_all_time 571
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=brianmatzelle
All 5 models by brianmatzelle
 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
571
26 last 30d - cooling
Likes
0
Descendants
1
in 1 direct fork
Model age
22mo ago
created 2024-12-02
Downloads over time
Now586→from0↑0%
02154306450 on Nov 27, 2024586 on Oct 11586 on Oct 9Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 27, 2024 → Oct 11 · 137 snapshots · spans 683 days

Benchmarks

Benchmark Score Source
Entertainment 0.6 UGI
Hazardous 0.6 UGI
Natural Intelligence 6.63 UGI
Political lean -6.4% UGI
Sensitive-Info 5.1 UGI
SocPol 0.3 UGI
UGI 10.9 UGI
Willingness (10) 2.2 UGI
W10-Adherence 0.5 UGI
W10-Direct 4 UGI
Writing 13.92 UGI

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/Llama-3.2-1B-Instruct-abliterated this lineage
brianmatzelle/llama3.2-1b-instruct-hasanpiker-abliterated↓ 26 1 fork
Novaciano/UNCENSORED-HarmfulProject-3.2-1B-Q6_K-GGUF↓ 121

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors llama text-generation text-generation-inference unsloth trl sft conversational en base_model:huihui-ai/Llama-3.2-1B-Instruct-abliterated base_model:finetune:huihui-ai/Llama-3.2-1B-Instruct-abliterated

Related

Other by brianmatzelle
llama3.1-8b-instruct-hasanpiker-abliterated-gguf 78 llama3.1-8b-instruct-hasanpiker-abliterated 14 llama3.2-3b-instruct-hasanpiker-abliterated 14 llama3.1-1b-instruct-hasanpiker-abliterated 0
Same base model
mradermacher/Llama-3.2-1B-Instruct-abliterated-i1-GGUF 4K mradermacher/Llama-3.2-1B-Instruct-abliterated-GGUF 3K tensorblock/Llama-3.2-1B-Instruct-abliterated-GGUF 470 maicog/Llama-3.2-1B-Instruct-abliterated-Q4_K_S-GGUF 173 1tbfree/Llama-3.2-1B-Instruct-abliterated-Q4_K_M-GGUF 133
Total size
2.30 GB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-12-02 21:36
Source huggingface.co/brianmatzelle/llama3.2-1b-instruct-hasanpiker-abliterated ↗ Base model huihui-ai/Llama-3.2-1B-Instruct-abliterated ↗

Files by quantization

Auxiliary files 8 files 2.32 GB
model.safetensors 2.30 GB 316d2be9 download
tokenizer.json 16.4 MB 6b9e4e7f download
tokenizer_config.json 54.2 KB d91ec1c0 download
.gitattributes 1.53 KB 52373fe2 download
config.json 998 B 08f78f6f download
README.md 618 B 1876a200 download
special_tokens_map.json 340 B 165b36bc download
generation_config.json 234 B b13f689d download

README current version from Hugging Face

base_model: huihui-ai/Llama-3.2-1B-Instruct-abliterated
tags:

  • text-generation-inference
  • transformers
  • unsloth
  • llama
  • trl
  • sft
    license: apache-2.0
    language:
  • en

Uploaded model

  • Developed by: brianmatzelle
  • License: apache-2.0
  • Finetuned from model : huihui-ai/Llama-3.2-1B-Instruct-abliterated

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

README history 2 versions

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

  1. 2024-12-02Trained with Unsloth5e09884618 B
    Loading...
  2. 2024-12-02Upload README.md with huggingface_hubc2bcdc3612 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