An experiment in bringing reasoning capability to the Pantheon roleplay series in the shape of a Gemma 4 MoE, which is generally the only variant that doesn’t take half a lifetime to train. Though Qwen 3.6 27B is a really, really smart model its writing, like any Qwen model in existence, is distinctly lackluster. The same theory from my previous release applies: take the data that Pantheon is built on, pair it with full thinking traces, and let the model reason its way through character work — weighing tone, planning narrative beats, considering how a character would actually respond before committing to a line. Whether that meaningfully improves roleplay quality over a non-reasoning model is a question you’ll hopefully be able to help me answer. New in 1.1: I really tightened down on the reasoning traces this time around, with each going through multiple QA stages to ensure they’re as perfect as can be. I also drastically altered the recipe to allow only the highest quality to make it through, which meant dropping the WorldSim and Tiamat datasets, with my cobbled together WorldSim data and Tiamat’s highly specific style simply not meeting my personal standards. Base model is…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Следование инструкциям Диалог / чат
Задача: Генерация текста
Автор: Vortex5
Теги: gemma4, conversational, instruct, finetune, axolotl, roleplay, reasoning, creative-writing
Лайков: 4 | Загрузок: 65
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
