Norquinal/llama-2-7b-claude-chat-rp - Каталог нейросетей
Генерация текста

Norquinal/llama-2-7b-claude-chat-rp

Добавлено:

This is a LLaMA-2-7b-hf model fine-tuned using QLoRA (4-bit precision) on my claudepippabluemoon2k dataset, which is a randomized subset of ~1000 samples from my claudemultiroundchat30k dataset combined with an additional ~600 randomized samplings from the PIPPA and Bluemoon RP datasets. The intent was to improve the finetune’s ability to RP and write creative fiction. To that end, it seems to have worked, if only marginally. Do not take this model very seriously, it is probably not very good. I haven’t a clue of what I’m doing. I just thought it was a fun thing to make. >USER: Write a story about a boy who wakes up in the middle of a magical forest. >ASSISTANT: Once upon a time there was a young boy named Jack. One night he had a dream that he was walking through a beautiful enchanted forest filled with talking animals and strange creatures. When he opened his eyes it turned out to be real! He found himself standing in the center of this mysterious place surrounded by tall trees and lush greenery. > >The first thing Jack did was ask for directions from one of the many colorful birds flying overhead. They told him that if he followed the path straight ahead he would eventually…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: Norquinal
Теги: llama, text-generation-inference, endpoints_compatible
Лайков: 2  |  Загрузок: 84

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.