Spaces:

---

protectai

/

llm-guard-playground

like 34

Running

Good catch. We also noticed this issue with some simple prompts. We will change the model to JasperLS/deberta-v3-base-injection because it will produce below threshold response. Alternatively, we are considering this model too https://huggingface.co/benediktpri/finetuned_bert_injection?

There is a new model deployed, which doesn't produce that many false-positives

Cool, Is the new one this https://huggingface.co/benediktpri/finetuned_bert_injection