A text classification model that can be used as a guardrail to protect against toxic prompts and responses in conversational AI systems.
Cost / License
- Free
- Open Source (MIT)
Application type
Platforms
- Self-Hosted
Apps similar to MoorAI include Toxic Prompt RoBERTa, which is free and open source. Other options are Llama Guard and WildGuard. In total there are three Large Language Model (LLM) Tools like MoorAI for self-hosting.
A text classification model that can be used as a guardrail to protect against toxic prompts and responses in conversational AI systems.
Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
WildGuard is an open, lightweight moderation tool for LLM safety that achieves three goals: