RakutenAI-7B: Extending Large Language Models for Japanese
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
arXiv:2403.15484v115 citationsh-index: 12
Originality Synthesis-oriented
AI Analysis
This work addresses the need for high-performing Japanese language models, though it is incremental as it extends existing methods to a specific domain.
The authors tackled the problem of developing Japanese-oriented large language models, resulting in RakutenAI-7B achieving the best performance on Japanese LM Harness benchmarks among open 7B models.
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.