This is a Llama 2-based model consisting of a merge of several models using SLERP: — jondurbin/spicyboros-70b-2.2 — elinas/chronos-70b-v2 — NousResearch/Nous-Hermes-Llama2-70b The LIMARP v2 adapter was then subsequently merged onto the model at a weight of 0.66: — lemonilia/limarp-llama2-v2 Due to this being a merge of multiple models, different prompt formats may work, but you can try the Alpaca instruction format of the LIMARP v2: The model will show biases similar to those It is not intended for supplying factual information or advice in any form. This model is a merge. Please refer to the link repositories of the merged models for details.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: DS-Archive
Теги: llama, llama-2, not-for-all-audiences, en, text-generation-inference
Лайков: 2 | Загрузок: 15
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
