The evaluation dataset data/samples-1680.jsonl.gz is the test set used in the following paper:
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:…
The main features of unitaryai/detoxify are: Moderation APIs, Natural Language Processing, Guardrails and AI Safety.
Open-source alternatives to unitaryai/detoxify include: openai/moderation-api-release — The evaluation dataset data/samples-1680.jsonl.gz is the test set used in the following paper:. 7compass/sentimental — Simple sentiment analysis with Ruby. a2800276/porter — porter stemmer. abadojack/whatlanggo — Natural language detection library for Go. abitdodgy/gibran — Gibran is an Elixir natural language processor, and a port of WordsCounted. 2shou/textgrocery — A simple short-text classification tool based on LibLinear.