RakutenAI-7B：擴展大型語言模型以應用於日文

RakutenAI-7B: Extending Large Language Models for Japanese

March 21, 2024

作者: Rakuten Group, Aaron Levine, Connie Huang, Chenguang Wang, Eduardo Batista, Ewa Szymanska, Hongyi Ding, Hou Wei Chou, Jean-François Pessiot, Johanes Effendi, Justin Chiu, Kai Torben Ohlhus, Karan Chopra, Keiji Shinzato, Koji Murakami, Lee Xiong, Lei Chen, Maki Kubota, Maksim Tkachenko, Miroku Lee, Naoki Takahashi, Prathyusha Jwalapuram, Ryutaro Tatsushima, Saurabh Jain, Sunil Kumar Yadav, Ting Cai, Wei-Te Chen, Yandi Xia, Yuki Nakayama, Yutaka Higashiyama

cs.AI

摘要

我們介紹了 RakutenAI-7B，這是一套針對日本語的大型語言模型，其在日本語 LM Harness benchmarks 中表現優異，位居開放式 7B 模型之首。除了基礎模型外，我們還釋出了經過指示和聊天微調的模型，分別為 RakutenAI-7B-instruct 和 RakutenAI-7B-chat，並採用 Apache 2.0 授權。

English

We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models. Along with the foundation model, we release instruction- and chat-tuned models, RakutenAI-7B-instruct and RakutenAI-7B-chat respectively, under the Apache 2.0 license.