Search Packages

detoxify

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

lexicont

Policy-driven agent for real-time text moderation

toxicity

Репозиторий python-пакета "toxicity". Выявление токсичного контента в русскоязычных текстах c помощью глубокого обучения.

honest

A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.

napolab

The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest advancements in Portuguese language models and their performance across carefully curated Portuguese language tasks.