Updated 6 months ago

detoxify • Rank 21.0 • Science 44%

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.

Updated 6 months ago

napolab • Rank 7.0 • Science 36%

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.

Updated 6 months ago

virc • Science 44%

Vulnerable Identities Recognition Corpus (VIRC) for analyzing hate speech in Italian and Spanish news headlines. Provides fine-grained annotations for vulnerable identities, dangerous speech, and derogatory expressions.