unitary / text-classification Open weights updated 3 years ago

unbiased-toxic-roberta

Name: unbiased-toxic-roberta
Author: unitary

⚠️ Disclaimer: 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

Params

—

Context

512

Downloads 30d

871 K

Likes

Commercial use: allowed apache-2.0 Not gated View on Hugging Face ↗

Download history

daily snapshots · 30 days

1.0 M240 K

Sep 25Oct 5Oct 15Oct 24

Specifications

Architecture: RobertaForSequenceClassification
Context length: 512
Vocabulary: 50,265
Layers / heads: 12 / 12
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: undisclosed
Added to our catalog: 2026-09-25

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative unbiased-toxic-roberta-onnx protectai 213 K

Compare with any text-classification model

Popular comparisons

bge-reranker-v2-m3 14.7 M roberta-base-go_emotions 4.6 M finbert 3.9 M bge-reranker-base 3.0 M distilbert-base-uncased-finetuned-sst-2-english 2.6 M Prompt-Guard-86M 2.4 M