Instructions to use NAMAA-Space/Ara-Prompt-Guard_V0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NAMAA-Space/Ara-Prompt-Guard_V0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="NAMAA-Space/Ara-Prompt-Guard_V0")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("NAMAA-Space/Ara-Prompt-Guard_V0") model = AutoModelForSequenceClassification.from_pretrained("NAMAA-Space/Ara-Prompt-Guard_V0") - Inference
- Notebooks
- Google Colab
- Kaggle
PromptGuard version used
#1
by juanbaquero-airia - opened
Hi Omar, I would like to confirm if the model was fine-tuned on PromptGuard (PG) v1 or v2?
As PG v2 performs binary classification rather than three labeled classification: benign/injection/jailbreak labeling like PG v1.