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

s8n29/stereotype_finetuned_3_class_jailbreak

s8n29 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/s8n29%2Fstereotype_finetuned_3_class_jailbreak"
Response includes
  • classification unknown
  • files 5
  • hub_downloads_all_time 13
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=s8n29
All 5 models by s8n29
 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
13
4 last 30d - stable
Likes
0
Model age
24mo ago
created 2024-10-16
Downloads over time
Now16→from24↓33%
029598824 on Oct 16, 202416 on Oct 1180 on Sep 10, 2025Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 16, 2024 → Oct 11 · 143 snapshots · spans 725 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.

wu981526092/Sentence-Level-Stereotype-Detector this lineage
s8n29/stereotype_finetuned_3_class_jailbreak↓ 4

Metadata

License
mit
Tags
tensorboard safetensors distilbert generated_from_trainer base_model:wu981526092/Sentence-Level-Stereotype-Detector base_model:finetune:wu981526092/Sentence-Level-Stereotype-Detector license:mit region:us

Related

Other by s8n29
stereotype_finetuned_3_class_jailbreak_deberta_v1 6 stereotype_finetuned_3_class_jailbreak_deberta_soft 6 stereotype_finetuned_3_class_jailbreak_deberta_soft_labels 4 jailbreak_rev_test 0
Total size
255 MB
Files
5
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-16 08:04
Source huggingface.co/s8n29/stereotype_finetuned_3_class_jailbreak ↗ Base model wu981526092/Sentence-Level-Stereotype-Detector ↗

Files by quantization

Auxiliary files 5 files 255 MB
model.safetensors 255 MB f6a035eb download
training_args.bin 5.12 KB 814719f0 download
README.md 2.29 KB 6240d56f download
.gitattributes 1.48 KB a6344aac download
config.json 792 B d1c29c3c download

README current version from Hugging Face

license: mit
base_model: wu981526092/Sentence-Level-Stereotype-Detector
tags:

  • generated_from_trainer
    metrics:
  • accuracy
    model-index:
  • name: stereotype_finetuned_3_class_jailbreak
    results: []

stereotype_finetuned_3_class_jailbreak

This model is a fine-tuned version of wu981526092/Sentence-Level-Stereotype-Detector on an unknown dataset.
It achieves the following results on the evaluation set:

  • Loss: 0.3321
  • Accuracy: 0.9647

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2493 1.0 526 0.1518 0.9526
0.1115 2.0 1052 0.1791 0.9555
0.0539 3.0 1578 0.2281 0.9590
0.0349 4.0 2104 0.2549 0.9587
0.026 5.0 2630 0.2888 0.9612
0.0096 6.0 3156 0.3121 0.9626
0.0067 7.0 3682 0.3401 0.9601
0.0059 8.0 4208 0.2992 0.9594
0.0108 9.0 4734 0.3204 0.9604
0.0075 10.0 5260 0.2747 0.9651
0.0036 11.0 5786 0.3540 0.9615
0.003 12.0 6312 0.3233 0.9629
0.0018 13.0 6838 0.3267 0.9629
0.0001 14.0 7364 0.3310 0.9647
0.0022 15.0 7890 0.3321 0.9647

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1

README history 1 version

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

  1. 2024-10-16End of training8c6d4f52.3 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