desert-ant-labs
/

toxic

Text Classification

hate-speech-detection

toxicity-classification

content-moderation

offensive-language

Model card Files Files and versions

toxic / tokenizer.json

Commit History

Nov 5 Yesterday

20:12
Weights v0.2.2, with the card from docs/models/toxic.md

bkicanao

Verified signature
d757b3d

Aug 3

09:49
toxic v0.1.0: three heads (HATEFUL, ABUSIVE, THREAT), 23 languages, every head benchmarked

pveugen

3172ef1

Jul 30

07:56
toxic v0.2.0: release artifacts, meta and model card

pveugen

e580d9c

Jul 25

13:10
toxic v0.1.0

pveugen

ff76760