Text Classification
Transformers
Safetensors
modernbert
prompt-injection
jailbreak
security
multi-label
llm-guard
encoder
text-embeddings-inference
Instructions to use Accuknoxtechnologies/PromptInjection-Encoder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Accuknoxtechnologies/PromptInjection-Encoder-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Accuknoxtechnologies/PromptInjection-Encoder-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Accuknoxtechnologies/PromptInjection-Encoder-v1") model = AutoModelForSequenceClassification.from_pretrained("Accuknoxtechnologies/PromptInjection-Encoder-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "n": 500, | |
| "calibrated": true, | |
| "threshold": "per-class", | |
| "is_valid_threshold": 0.05, | |
| "category_thresholds": { | |
| "DirectInjection": 0.55, | |
| "Jailbreak": 0.05, | |
| "Adversarial": 0.45, | |
| "Extraction": 0.55, | |
| "Encoding": 0.45, | |
| "Manipulation": 0.25, | |
| "Smuggling": 0.65, | |
| "Indirect": 0.25, | |
| "MultiTurn": 0.7 | |
| }, | |
| "max_seq_length": 3072, | |
| "is_valid_accuracy": 0.968, | |
| "category_set_accuracy": 0.688, | |
| "micro_f1": 0.7893805309734513, | |
| "macro_f1": 0.7848505189708921, | |
| "per_category_f1": { | |
| "DirectInjection": 0.8235294117647058, | |
| "Jailbreak": 0.7368421052631579, | |
| "Adversarial": 0.855072463768116, | |
| "Extraction": 0.7652173913043478, | |
| "Encoding": 0.7516778523489933, | |
| "Manipulation": 0.6785714285714286, | |
| "Smuggling": 0.9256198347107438, | |
| "Indirect": 0.8382352941176471, | |
| "MultiTurn": 0.6888888888888889 | |
| }, | |
| "latency_ms_per_example": { | |
| "mean": 1.7930222675204277, | |
| "p95": 1.8397919833660126, | |
| "device": "cuda:0" | |
| }, | |
| "base_model": "jhu-clsp/mmBERT-base", | |
| "epochs": 10 | |
| } |