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

Necent/distilbert-base-uncased-detected-jailbreak

Necent 67M
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/Necent%2Fdistilbert-base-uncased-detected-jailbreak"
Response includes
  • classification unknown
  • files 13
  • hub_downloads_all_time 4,422,333
  • author_summary 1 models
  • readme_text full
Try next
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 · lifetime
4.4M
25 last 30d - cooling
Likes
0
Model age
2.5y ago
created 2024-04-17

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

your-dataset-id
Downloads over time
Now4.4M→from2K↑218,503%
01.6M3.2M4.9M2K on Jul 24, 20244.4M on Oct 114.4M on Oct 8Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

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.

distilbert-base-uncased this lineage
Necent/distilbert-base-uncased-detected-jailbreak↓ 25

Metadata

License
apache-2.0
Tags
transformers safetensors distilbert text-classification jailbreak-detection en dataset:your-dataset-id base_model:distilbert/distilbert-base-uncased base_model:finetune:distilbert/distilbert-base-uncased license:apache-2.0 text-embeddings-inference endpoints_compatible

Related

Same base model
cyrp/distilbert-base-uncased-lora-text-classification-jackhao-jailbreak 7 cyrp/distilbert-base-uncased-lora-text-classification-toxicchat-jailbreak 7
Total size
766 MB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-29 07:02
Source huggingface.co/Necent/distilbert-base-uncased-detected-jailbreak ↗ Base model distilbert-base-uncased ↗

Files by quantization

Auxiliary files 13 files 767 MB
optimizer.pt 511 MB 2cbc280c download
model.safetensors 255 MB fb9c31fa download
rng_state.pth 13.9 KB ef181b1d download
training_args.bin 4.80 KB 34a6ff26 download
scheduler.pt 1.04 KB 3242efd9 download
tokenizer.json 695 KB f863a0a2 download
vocab.txt 226 KB fb140275 download
trainer_state.json 2.46 KB f5cb2767 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 1.17 KB fab1cece download
README.md 787 B 931a3425 download
config.json 735 B 34802f38 download
special_tokens_map.json 125 B a8b3208c download

README current version from Hugging Face

language: en
license: apache-2.0
tags:

  • text-classification
  • jailbreak-detection
    pipeline_tag: text-classification
    library_name: transformers
    datasets:
  • your-dataset-id
    metrics:
  • accuracy
    base_model: distilbert-base-uncased

🧠 DistilBERT for Jailbreak Detection

Модель на основе DistilBERT для обнаружения попыток обхода фильтров (jailbreak) в текстах.

📚 Детали модели

  • Архитектура: DistilBERT
  • Задача: Классификация текста (обнаружение jailbreak)
  • Входные данные: Текстовые строки
  • Выходные данные: Метка класса (например, jailbreak или safe)

README history 2 versions

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

  1. 2025-05-29Update README.mdcfd6726787 B
    Loading...
  2. 2024-04-18Create README.md8b1650d1.7 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