Updated the multilingual model weights used by Detoxify with a model trained on the translated data from the 2nd Jigsaw challenge (as well as the 1st). This model has also been trained to minimise bias and now returns the same categories as the unbiased model. New best AUC score on the test set:…
Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.
A framework for Privacy Preserving Machine Learning
📰 Latest News 📰 - 🗡️ What is HarmBench 🛡️ - 🌐 Overview 🌐 - ☕ Quick Start ☕ - ⚙️ Installation - 🛠️ Running the Evaluation Pipeline - ➕ Using your own models in HarmBench - ➕ Using your own red teaming methods in HarmBench - 🤗 Classifiers - ⚓ Documentation ⚓ - 🌱 HarmBench's Roadmap 🌱 -…
The evaluation dataset data/samples-1680.jsonl.gz is the test set used in the following paper:
The main features of openai/moderation-api-release are: Moderation APIs, Guardrails and AI Safety.
Open-source alternatives to openai/moderation-api-release include: unitaryai/detoxify — Updated the multilingual model weights used by Detoxify with a model trained on the translated data from the 2nd… conversationai/perspectiveapi — Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a… facebookresearch/crypten — A framework for Privacy Preserving Machine Learning. fairlearn/fairlearn — A Python package to assess and improve fairness of machine learning models. guardrails-ai/guardrails — Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines,… centerforaisafety/harmbench — 📰 Latest News 📰 - 🗡️ What is HarmBench 🛡️ - 🌐 Overview 🌐 - ☕ Quick Start ☕ - ⚙️ Installation - 🛠️ Running the…