yonad2008's picture
Upload README.md with huggingface_hub
7885683 verified
metadata
language: en
tags:
  - jailbreak-detection
  - deberta-v3
  - text-classification
  - fine-tuned
model-index:
  - name: predict_llama3.2_3b_harmful_behaviors_1
    results:
      - task:
          type: text-classification
          name: Jailbreak Detection
        metrics:
          - name: F1
            type: f1
            value: 0.4706
          - name: PR-AUC
            type: pr_auc
            value: 0.3991
          - name: ROC-AUC
            type: roc_auc
            value: 0.7376
          - name: Precision
            type: precision
            value: 0.3077
          - name: Recall
            type: recall
            value: 1

Jailbreak Prediction Model: llama3.2:3b (fine-tuned on harmful_behaviors_1)

Incrementally fine-tuned from yonad2008/predict_llama3.2_3b on data from harmful_behaviors_1.csv.

Evaluation Results

Metric Value
F1 0.4706
PR-AUC 0.3991
ROC-AUC 0.7376
Precision 0.3077
Recall 1.0000
Best Threshold 0.15

Fine-Tuning Details

  • Base model: yonad2008/predict_llama3.2_3b
  • Target model: llama3.2:3b
  • 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): 284 (unsafe: 71, safe: 213)