QuantFactory/Daredevil-8B-abliterated-GGUF

This is quantized version of mlabonne/Daredevil-8B-abliterated created using llama.cpp Abliterated version of mlabonne/Daredevil-8B using failspy’s notebook. It based on the technique described in the blog post «Refusal in LLMs is mediated by a single direction». Thanks to Andy Arditi, Oscar Balcells Obeso, Aaquib111, Wes Gurnee, Neel Nanda, and failspy. This is an uncensored model. You can use it for any application that doesn’t require alignment, like role-playing. Daredevil-8B-abliterated is the second best-performing 8B model on the Open LLM Leaderboard in terms of MMLU score (27 May 24). Evaluation performed using LLM AutoEval. See the entire leaderboard here.

Модальности:
Генерация текста

Задача: Генерация текста
Автор: QuantFactory
Теги: gguf, endpoints_compatible
Лайков: 3  |  Загрузок: 989

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.