---
base_model: google/gemma-2b
---
This lora is trained on openai content moderation data as well as Nvidias [Aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-1.0) dataset.

**Prompt Template:** 

```
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
```