This is a Llama 2-based model consisting of a merge between: — Sao10K/Euryale-1.3-L2-70B — allenai/tulu-2-dpo-70b — GOAT-AI/GOAT-70B-Storytelling — Doctor-Shotgun/limarpv3-llama2-70b-qlora This model combines the excellent Euryale v1.3 base with the DPO training of the Tulu v2 model and creative prose training of the GOAT Storytelling model. The LimaRP v3 qlora was then added for further roleplaying capability and the ability to tune the length of the outputs. The goal was to create a capable 70B model for collaborative storytelling and roleplay. The intended prompt format is the Alpaca instruction format of LimaRP v3: Due to the inclusion of LimaRP v3, it is possible to append a length modifier to the response instruction sequence, like this: This has an immediately noticeable effect on bot responses. The available lengths are: micro, tiny, short, medium, long, massive, huge, enormous, humongous, unlimited. The recommended starting length is medium. Keep in mind that the AI may ramble or impersonate the user with very long messages. The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: LoneStriker
Теги: llama, llama 2, en, text-generation-inference
Лайков: 3 | Загрузок: 9
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
