athirdpath/Orca-2-13b-Alpaca-Uncensored - Каталог нейросетей
Генерация текста

athirdpath/Orca-2-13b-Alpaca-Uncensored

Добавлено:

This model is a fine-tuned version of microsoft/Orca-2-13b on a subset of the Vezora/MiniOrcaUncencored_Alpaca dataset, adjusted to demonstrate the relationship between instruction and input, with some particularly spicy prompts added to reduce the risk of rejections. Only the qproj and kproj modules were targeted and a low rank (8) was used, in hopes of containing the adjustments to the prompt format and alignment. This is promising on paper, with the training’s per-step loss averaging Reasoning stayed solid (for a 13b model) and I consider this a success. Performance is slighty worse than OG Orca-2 in Ooba’s chat mode, comparable in Alpaca chat-instruct mode to the OG in ChatLM chat-instruct mode. May still reject some shocking prompts, but can easily be overcome with author’s note or character card.

Модальности:
Генерация текста


Задача: Генерация текста
Автор: athirdpath
Теги: llama, model-index, text-generation-inference, endpoints_compatible
Лайков: 2  |  Загрузок: 58

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.