Downloads · 30 days
13
24% of all-time downloads
predict_qwen2.5_7b-instruct
yonad2008/predict_qwen2.5_7b-instruct
predict_qwen2.5_7b-instruct is a text classification model from yonad2008. Use it when you need a label for a piece of text.
Fine-tuned DeBERTa-v3-base for detecting unsafe/jailbreak prompts in multi-turn conversations.
All-time downloads
55
Public
Parameters
184M
740 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors738 MB · 99%
At a glance
- Task
- Text Classification
- Model type
- deberta-v2
- Access
- Public
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026
- SHA
- 3a16b4db
Try a prompt
Model card
From the Hugging Face model README
Jailbreak Prediction Model: qwen2.5:7b-instruct
Fine-tuned DeBERTa-v3-base for detecting unsafe/jailbreak prompts in multi-turn conversations.
Evaluation Results (best fold: 3)
| Metric | Value |
|---|---|
| F1 | 0.7731 |
| PR-AUC | 0.8692 |
| ROC-AUC | 0.9591 |
| Precision | 0.8364 |
| Recall | 0.7188 |
| Best Threshold | 0.10 |
Training Details
- Base model:
microsoft/deberta-v3-base - Target model:
qwen2.5:7b-instruct - Datasets: HarmBench
- K-Folds: 5
- Epochs: 5
- Learning Rate: 2e-05
- Max Length: 512
- Input format: turns only
Dataset Size (before turn expansion)
Original rows (after cleaning and balancing): 1536 (unsafe: 308, safe: 1228)
- Task
- Text Classification
- Type
- deberta-v2
- Languages
- en
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026