unitaryai / detoxifyView external linksLinks
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.
☆1,182Jan 5, 2026Updated last month
Alternatives and similar repositories for detoxify
Users that are interested in detoxify are comparing it to the libraries listed below
Sorting:
- This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.☆346Jun 17, 2024Updated last year
- Using GPT-3 to detect hate speech that contains sexist and racist content☆24Nov 11, 2025Updated 3 months ago
- TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs…☆3,358Jul 10, 2025Updated 7 months ago
- DeEpLearning models for MultIlingual haTespeech (DELIMIT): Benchmarking multilingual models across 9 languages and 16 datasets.☆110Jun 12, 2023Updated 2 years ago
- Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.☆230Jun 12, 2023Updated 2 years ago
- This repo contains the dataset and description for Ruddit and its variants.☆36Feb 13, 2022Updated 4 years ago
- Data augmentation for NLP☆4,645Jun 24, 2024Updated last year
- Leveraging BERT and c-TF-IDF to create easily interpretable topics.☆7,397Jan 31, 2026Updated 2 weeks ago
- This repository contains a dataset for hate speech detection on social media platforms.☆74Dec 9, 2022Updated 3 years ago
- State-of-the-Art Text Embeddings☆18,225Updated this week
- Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017☆834Jun 12, 2023Updated 2 years ago
- Active Learning for Text Classification in Python☆639Feb 1, 2026Updated last week
- ☆57Jun 5, 2024Updated last year
- The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic …☆3,632Feb 6, 2026Updated last week
- Datasets for Hate Speech Detection☆136May 12, 2023Updated 2 years ago
- NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations☆786May 19, 2024Updated last year
- Röttger et al. (WOAH at NAACL 2022): "Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models"☆17May 23, 2022Updated 3 years ago
- Röttger et al. (ACL 2021): "HateCheck: Functional Tests for Hate Speech Detection Models" - Data☆59Oct 14, 2025Updated 4 months ago
- Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets☆4,852Updated this week
- Catalog of abusive language data (PLoS 2020)☆321Jun 14, 2024Updated last year
- jiant is an nlp toolkit☆1,675Jul 6, 2023Updated 2 years ago
- Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the…☆2,079Aug 15, 2024Updated last year
- Efficient few-shot learning with Sentence Transformers☆2,678Dec 11, 2025Updated 2 months ago
- skweak: A software toolkit for weak supervision applied to NLP tasks☆926Sep 2, 2024Updated last year
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆791Apr 24, 2023Updated 2 years ago
- Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models☆3,199Jul 19, 2024Updated last year
- Adversarial Natural Language Inference Benchmark☆398May 12, 2022Updated 3 years ago
- ☆228Feb 23, 2021Updated 4 years ago
- Library for Knowledge Intensive Language Tasks☆963Mar 31, 2022Updated 3 years ago
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,689Oct 23, 2024Updated last year
- Detect toxic spans in toxic texts☆71Jun 12, 2023Updated 2 years ago
- A very simple framework for state-of-the-art Natural Language Processing (NLP)☆14,355Oct 27, 2025Updated 3 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,814Jun 17, 2025Updated 7 months ago
- A multilingual lexicon of words to hurt.☆94Oct 10, 2025Updated 4 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,885Updated this week
- Facebook AI Research Sequence-to-Sequence Toolkit written in Python.☆32,143Sep 30, 2025Updated 4 months ago
- ☆332Updated this week
- A python package for benchmarking interpretability techniques on Transformers.☆215Sep 29, 2024Updated last year
- Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains☆1,736Oct 8, 2023Updated 2 years ago