Llama-3-8B-Distil-MetaHate is a distilled model of the Llama 3 architecture designed specifically for hate speech explanation and classification. This model leverages Chain-of-Thought methodologies to improve interpretability and operational efficiency in hate speech detection tasks. — Developed by: IRLab — Model type: text-generation — Language(s) (NLP): English — License: Llama3 — Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct — Repository: https://github.com/palomapiot/distil-metahate — Paper (Accepted at ECIR 2025): https://link.springer.com/chapter/10.1007/978-3-031-88711-6_24 This model is intended for research and practical applications in detecting and explaining hate speech. It aims to enhance the understanding of the model’s predictions, providing users with insights into why a particular text is classified as hate speech. While the model is designed to improve interpretability, it may still produce biased outputs, reflecting the biases present in the training data. Users should exercise caution and perform their due diligence when deploying the model. Details here: https://link.springer.com/chapter/10.1007/978-3-031-88711-6_24 Carbon emissions can be…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: irlab-udc
Теги: peft, hate-speech, distillation, explainable AI, Llama3, conversational, en
Лайков: 4 | Загрузок: 12
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
