PetrolDolphin is the Dolphin-2.0-Mistral-7B model with the PetrolLoRA applied. The dataset consists of 2800 samples, with the composition as follows: AICG Logs (~34%) PygmalionAI/PIPPA (~33%) Squish42/bluemoon-fandom-1-1-rp-cleaned (~29%) OpenLeecher/Teatime (~4%) These samples were then back-filled using gpt-4/gpt-3.5-turbo-16k or otherwise converted to fit the prompt format. Install the bleeding-edge version of transformers from source: Or, alternatively, change modeltype in config.json from mistral to llama`.  As an addendum, you can include one of the following as the Last Output Sequence: The third one seems to work the best. I would recommend experimenting with creating your own to best suit your needs.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Norquinal
Теги: mistral, not-for-all-audiences, nsfw, conversational, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 6
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.