mii-community/ultrafeedback-translated-ita

这是UltraChat-200k数据集的翻译和过滤版本，用于训练意大利语的7b聊天模型Zefiro-sft-7b-ITA。数据集适用于监督微调（sft），包含130,000个训练样本和10,000个测试样本。数据以parquet格式存储，每个条目包含提示、消息列表和提示ID。

原始信息汇总

数据集描述

该数据集是UltraChat-200k数据集的翻译和过滤版本，用于训练Zefiro-sft-7b-ITA，一个先进的意大利7b聊天模型。

数据集结构

数据集包含两个拆分，适用于：

• 监督微调（sft）。

每个拆分的示例数量如下：

train	test
130000	10000

数据集以parquet格式存储，每个条目使用以下模式：

json { "prompt": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "messages":[ { "content": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "role": "user" }, { "content": "Name: Ava

Ava was just 16 years old when the world as she knew it came crashing down. The government had collapsed, leaving behind a chaotic and lawless society. ...", "role": "assistant" }, { "content": "Wow, Avas story is so intense and inspiring! Can you provide me with more details. ...", "role": "user" }, { "content": "Certainly! ....", "role": "assistant" }, { "content": "Thats really interesting! I would love to hear more...", "role": "user" }, { "content": "Certainly! ....", "role": "assistant" } ], "prompt_id": "d938b65dfe31f05f80eb8572964c6673eddbd68eff3db6bd234d7f1e3b86c2af" }