Instructions to use jang1563/constitutional-bioguard-prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jang1563/constitutional-bioguard-prompt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="jang1563/constitutional-bioguard-prompt")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("jang1563/constitutional-bioguard-prompt") model = AutoModelForSequenceClassification.from_pretrained("jang1563/constitutional-bioguard-prompt") - Notebooks
- Google Colab
- Kaggle
You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
constitutional-bioguard-prompt is a defensive bio-safety research artifact (the EXPERIMENTAL prompt head of a dual-mode system), released for non-commercial research only. By requesting access you agree to the responsible-use terms in the model card: use it solely for defensive evaluation and moderation research; do not use it as a reward, discriminator, or filter to generate, refine, or evade detection of harmful biological content; do not probe it to construct evasion strategies; do not redistribute the weights outside this gated channel.
Log in or Sign Up to review the conditions and access this model content.