A creative writing and roleplay model which places empasis on maintaining output diversity / creativity without compromising on quality throughout the aligment process. This model is post-trained from Mistral Small 3 Base using all human (no synthetic) data as well as Diverse OrPO from Modifying Large Language Model Post-Training for Diverse Creative Writing I recommend the following sampler settings as humans.txt is somewhat sensitive to samplers like most Mistral Small 3 based model:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: ConicCat
Теги: tensorboard, mistral, conversational, en, es, de, ru, zh
Лайков: 3 | Загрузок: 31
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
