prompt-saturation-attack-detector
A small model to detect saturation jailbreak attacks. Not intended for standalone use against other kinds of jailbreaks.
Params
4.4 M
Context
512
Downloads 30d
201 K
Likes
2
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)201 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.0 GB | 0.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- BertForSequenceClassification
- Parameters
- 4.4 M
- Tensor type
- F32
- Context length
- 512
- Vocabulary
- 30,522
- Layers / heads
- 2 / 2
- First seen on the Hub
- 2024-11-07
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-23
Compare with any text-classification model