The model is based on SuperNova-Medius (as the current best 14B model) with a 128k context with an emphasis on creativity, including NSFW and multi-turn conversations. According to my tests, this finetune is much more stable with different samplers than the original model. Censorship and refusals have been reduced. The model started to follow the system prompt better, and the responses in ChatML format with bad samplers stopped reaching 800+ tokens for no reason. I have increased the amount of dataset and added instructions mixed with NSFW RP, which in theory will improve the quality of the model.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Ttimofeyka
Теги: qwen2, unsloth, trl, sft, conversational, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 22
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
