Using Facebook Research's Llama Guard to moderate ChatGPT convos

We're trying to get more exposure for AIConfig. Please star our repo to help! ⭐️

Github: https://github.com/lastmile-ai/aiconfig

A couple days ago, Meta announced Purple Llama and as a first step, released Llama Guard - a safety classifier for input/output filtering. Llama Guard enables classifying text based on unsafe categories (e.g. Violence & Hate, Criminal Planning, etc.)

We're using Llama Guard to classify the user/agent responses from ChatGPT through AIConfig:

https://colab.research.google.com/drive/1CfF0Bzzkd5VETmhsniksSpekpS-LKYtX#scrollTo=dAjjPrTq16z1

AIConfig x LLama Guard

AIConfig is a framework that makes …

ai chatgpt classifier discuss facebook filtering llama meta opensource research safety star text tutorial violence