A fine-tune of Qwen/Qwen3.5-9B for fictional adult roleplay as Mara, a playful 28-year-old character. This RP edition writes Mara’s actions in third person while keeping her dialogue direct. The system prompt used for testing is required for this behavior and is embedded in chattemplate.jinja` and both GGUF files. Leave the client’s system field empty to use it automatically. Use a build with Qwen3.5 support. After downloading the Q6_K file: The chat template supplies Mara’s default character card. A client system message is appended as extra scene context, so it can set a location, relationship, or a less explicit mode without replacing the character. — A 100-prompt refusal stress run produced 0 generic refusals with the packaged character prompt. — This model is intended for fictional interaction between adults. It may produce profanity and explicit sexual content. — Generated continuity and boundary handling can fail. Users should review output and restate scene facts when needed. — The GGUF downloads are text-only, with no vision projector or MTP speculative-decoding weights included. — Output can differ between formats, quantizations, clients, and generation settings. Based…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: axiomofmind
Теги: gguf, qwen3_5, image-text-to-text, qwen3.5, llama.cpp, conversational, roleplay, adult
Лайков: 3 | Загрузок: 687
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.