LionGuard
LionGuard is a classifier for detecting unsafe content in the Singapore context. It uses pre-trained BAAI English embeddings and performs classification with a trained XGBoost model.
This is a beta release. A public release will be announced in the next few months, along with performance results.
Usage
- Install
transformers
,xgboost
andhuggingface_hub
libraries.
pip install transformers xgboost huggingface_hub
- Run inference.
python inference.py '["Example text 1"]'
- Downloads last month
- 77
Unable to determine this model’s pipeline type. Check the
docs
.