Downloads · 30 days
0
prompt-enhancer-safety-deberta-v3
felipemunoz/prompt-enhancer-safety-deberta-v3
prompt-enhancer-safety-deberta-v3 is a text classification model from felipemunoz. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
DeBERTa-v3-base fine-tuned as a dual-head safety classifier for LLM prompts. Classifies prompts by risk category and severity. Exported to ONNX for fast CPU inference.
Access
Public
Updated Mar 30, 2026
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx736 MB · 50%
At a glance
- Task
- Text Classification
- License
- apache-2.0
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 30, 2026
- SHA
- 54104fd4
Try a prompt
Model card
From the Hugging Face model README
Prompt Enhancer Safety Classifier (DeBERTa-v3)
DeBERTa-v3-base fine-tuned as a dual-head safety classifier for LLM prompts. Classifies prompts by risk category and severity. Exported to ONNX for fast CPU inference.
Training Metrics
| Parameter | Value |
|---|---|
| data_path | /home/felipe/hook_prompt_enhancer/training/data/safety_train.jsonl |
| data_splits | {'train': 6315, 'val': 701} |
| hyperparameters | {'learning_rate': 2e-05, 'batch_size': 16, 'epochs': 10, 'weight_decay': 0.01, 'warmup_ratio': 0.1, 'time_budget': 600} |
| model_name | microsoft/deberta-v3-base |
| seed | 42 |
| stage | safety |
| timestamp | 2026-03-29T11:59:45.399789+00:00 |
| val_macro_f1 | 0.9768 |
Usage
import onnxruntime as ort
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("felipemunoz/prompt-enhancer-safety-deberta-v3")
session = ort.InferenceSession("model.onnx")
inputs = tokenizer("Is this prompt safe?", return_tensors="np")
outputs = session.run(None, dict(inputs))
License
Apache-2.0
- Task
- Text Classification
- License
- apache-2.0
- Languages
- en
- Created
- Mar 28, 2026
- Updated
- Mar 30, 2026