# Unitary: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/unitary
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model · Text classification

### [unbiased-toxic-roberta](https://savrn.com/models/unbiased-toxic-roberta)

[Unitary](https://savrn.com/model-publishers/unitary)

The huggingface models currently give different results to the detoxify library (see issue here). For the most up to date models we recommend using the models from https://github.com/unitaryai/detoxify Trained models & code to predict toxic comments on 3 Jigsaw challenges: Toxic comment classification, Unintended Bias in Toxic comments, Multilingual toxic comment classification. Built by Laura Hanu at Unitary, where we are working to stop harmful content online by interpreting visual content in context. Score not directly comparable since it is obtained on the validation set provided and not on the test set. To update when the test labels are made available. It is also noteworthy to mention…

Open weights apache-2.0 514 tokens transformers

[View model](https://savrn.com/models/unbiased-toxic-roberta)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-10-09.
- [Hugging Face profile](https://huggingface.co/unitary)
- [How the hub is built](https://savrn.com/model-hub/methodology)