Erebus-RP-12B-Instruct-2608-v1: Complex Finetune of Gemma 3 12b it Aimed at Enhancing Roleplay and Creative Writing. — «Specialized dataset was used to aggressively make the model roleplay close to how bigger models do, resulting in longer messages and better track of the story.» Model was trained on carefully selected number of high quality chat logs, filtered only for long term conversations with proper assistant turns. Entire process was carefully controlled by me to ensure that model can change its writing style without overcooking, this version is a result of repeated attempts until I finally found the right setup. * Reduced refusals due to dataset containing a number of explicit logs. BF16: Overkill Q80: Highest quality, still overkill Q6K: Extremely high quality, near lossless Q5KM: Very high quality, fast, recommended. Q4KM: High quality, very fast, saves a lot of space, recommended. Q3KM: Lower quality, fastest. This model turned out pretty well, Nyx is more intelligent and better and instruction following, Erebus is more creative. I didn’t select gemma 4 12b as the base because it was a hell to work with, and was in my observations way more heavily RLed than the…
Модальности:
Генерация текста
Области применения:
Следование инструкциям Диалог / чат
Задача: Генерация текста
Автор: Indexnusrefather
Теги: gemma3_text, RP, Roleplay, Creative, Writer, gemma3, finetune, ERP
Лайков: 3 | Загрузок: 68
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
