Text Classification
Transformers
modernbert
prompt-injection
jailbreak
security
multi-label
llm-guard
encoder
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")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Accuknoxtechnologies/PromptInjection-Encoder-v1") model = AutoModelForSequenceClassification.from_pretrained("Accuknoxtechnologies/PromptInjection-Encoder-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_metrics.json from Accuknoxtechnologies/PromptInjection-Encoder-v1: direct link, hf CLI and curl.
- Browser
- Download file 724 Bytes
-
https://huggingface.co/Accuknoxtechnologies/PromptInjection-Encoder-v1/resolve/92e086b01a514b471047b0983a8cbaba6f1daebe/eval_metrics.json
- Command line
-
hf download hf://Accuknoxtechnologies/PromptInjection-Encoder-v1@92e086b01a514b471047b0983a8cbaba6f1daebe/eval_metrics.json
-
curl -L -o eval_metrics.json https://huggingface.co/Accuknoxtechnologies/PromptInjection-Encoder-v1/resolve/92e086b01a514b471047b0983a8cbaba6f1daebe/eval_metrics.json
724 Bytes
| { | |
| "n": 500, | |
| "threshold": 0.5, | |
| "max_seq_length": 3072, | |
| "is_valid_accuracy": 0.89, | |
| "category_set_accuracy": 0.054, | |
| "micro_f1": 0.3512092534174553, | |
| "macro_f1": 0.35552414101596475, | |
| "per_category_f1": { | |
| "DirectInjection": 0.5232558139534884, | |
| "Jailbreak": 0.39705882352941174, | |
| "Adversarial": 0.4, | |
| "Extraction": 0.2569444444444444, | |
| "Encoding": 0.373134328358209, | |
| "Manipulation": 0.2717391304347826, | |
| "Smuggling": 0.49122807017543857, | |
| "Indirect": 0.3228346456692913, | |
| "MultiTurn": 0.16352201257861634 | |
| }, | |
| "latency_ms_per_example": { | |
| "mean": 1.823335886001587, | |
| "p95": 1.9494213163852692, | |
| "device": "cuda:0" | |
| }, | |
| "base_model": "jhu-clsp/mmBERT-base", | |
| "epochs": 3 | |
| } |