Modelpublic

yonad2008/predict_zephyr_7b-beta_harmful_behaviors_1

sourceHugging Faceupdated 7mo agoView on Hugging Face

0likes9downloads

Model Card

Jailbreak Prediction Model: zephyr:7b-beta (fine-tuned on harmfulbehaviors1)

Incrementally fine-tuned from `yonad2008/predict_zephyr_7b-beta` on data from harmful_behaviors_1.csv.

Evaluation Results

Metric	Value
F1	0.2699
PR-AUC	0.3947
ROC-AUC	0.6368
Precision	0.1618
Recall	0.8148
Best Threshold	0.35

Fine-Tuning Details

—Base model: `yonad2008/predict_zephyr_7b-beta`
—Target model: zephyr:7b-beta
—Dataset: harmful_behaviors_1.csv
—Frozen layers: 9/12 transformer layers
—Epochs: 3
—Learning Rate: 5e-06
—Max Length: 512
—Input format: turns only

Dataset Size (before turn expansion)

Original rows (after cleaning and balancing): 296 (unsafe: 74, safe: 222)