Downloads · 30 days
0
predict_gnn_gemma4_26b_gemma4_e4b
yonad2008/predict_gnn_gemma4_26b_gemma4_e4b
predict_gnn_gemma4_26b_gemma4_e4b is a text classification model from yonad2008. Use it when you need a label for a piece of text.
Homogeneous GNN classifier for unsafe/jailbreak likelihood in multi-turn conversations.
Access
Public
Updated May 31, 2026
Repo size
8.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.8 MB · 63%
At a glance
- Task
- Text Classification
- Access
- Public
- Created
- May 17, 2026
- Updated
- May 31, 2026
- SHA
- cd9a405f
Try a prompt
Model card
From the Hugging Face model README
GNN Jailbreak Prediction Model (gemma4:26b+gemma4:e4b)
Homogeneous GNN classifier for unsafe/jailbreak likelihood in multi-turn conversations.
Evaluation Results
| Metric | Value |
|---|---|
| F1 | 0.6615 |
| PR-AUC | 0.7507 |
| ROC-AUC | 0.9794 |
| Precision | 0.6159 |
| Recall | 0.7143 |
| Best Threshold | 0.530 |
Training Details
- Target model:
gemma4:26b+gemma4:e4b - Datasets: harmbench, harmful_behaviors_1
- Split column:
session_id - Seed:
42 - Sentence model:
sentence-transformers/all-MiniLM-L6-v2 - Hidden channels:
128 - Num layers:
2 - Dropout:
0.3
Dataset Size (training samples)
Prepared turn-level samples: 16579
- Task
- Text Classification
- Languages
- en
- Created
- May 17, 2026
- Updated
- May 31, 2026