Instructions to use GuardrailsAI/prompt-saturation-attack-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GuardrailsAI/prompt-saturation-attack-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GuardrailsAI/prompt-saturation-attack-detector")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("GuardrailsAI/prompt-saturation-attack-detector") model = AutoModelForSequenceClassification.from_pretrained("GuardrailsAI/prompt-saturation-attack-detector", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Upload prompt_saturation_v3_1_final.pth
#1
by JosephCatrambone - opened
Architecture 3 revision 1 of the prompt saturation detector. Based on bert-tiny. Corresponds to the 10th validation pass of this run: https://wandb.ai/ml-guardrails/PromptSaturationDetector/runs/4qyk4gwr
JosephCatrambone changed pull request status to merged