# pip install -U transformers accelerate
# 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")Quick Links
Model Card for Model ID
A small model to detect saturation jailbreak attacks. Not intended for standalone use against other kinds of jailbreaks.
Model Details
Model Description
- Developed by: Guardrails AI, Joseph Catrambone
- Funded by [optional]: Guardrails AI
- Model type: Transformer, BERT
- Language(s) (NLP): English
- License: Restrictive
- Finetuned from model [optional]: bert-tiny
Model Sources [optional]
Uses
Designed as a small prefilter for a subset of saturation attacks.
Out-of-Scope Use
Not designed to catch other types of jailbreaks. Saturation protection is one part of a more complite suite of defenses against improper use of ML systems.
- Downloads last month
- 203,550
Model tree for GuardrailsAI/prompt-saturation-attack-detector
Base model
google-bert/bert-base-uncased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GuardrailsAI/prompt-saturation-attack-detector")