Minami-su/qwen_7b_chat_roleplay_4bit - Каталог нейросетей
Генерация текста

Minami-su/qwen_7b_chat_roleplay_4bit

Добавлено:

基于self-instruct生成的多轮对话roleplay数据在qwen 7b chat上训练的模型,约1k条不同的人格数据和对话和约3k alpaca指令 1.roleplay数据基于模型自身生成,所以roleplay存在模型本身价值观融入情况,导致roleplay不够真实,不够准确。 我是小雨的开发者,小雨是一个情感ai,人格ai,如果对小雨感兴趣的话欢迎支持一下,她目前在bilibili直播,目前我仍在不断的改进 未来,“小雨”的目标是成为一个 具有真正人类情感的多模态通用人工智能。 url:https://live.bilibili.com/27357528?broadcasttype=0&isroomfeed=1&spmidfrom=333.999.liveuserscard.0.click&livefrom=86001 This model is trained on qwen 7b chat using self-instructed, multi-turn dialogue roleplay data, consisting o The roleplay data is generated based on the model itself, resulting in potential incorporation of the model’s own values into roleplay scenarios. This may lead to roleplay that lacks authenticity and accuracy. For usage instructions, please refer to https://github.com/PanQiWei/AutoGPTQ I am the developer of Xiaoyu, an AI specializing in emotion and personality. If you’re interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements. In the future, ‘小雨’ aims to become a multimodal general artificial intelligence with genuine…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: Minami-su
Теги: qwen, roleplay, self_instruct, custom_code
Лайков: 2  |  Загрузок: 14

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.