LLM-jp-4 Technical Report
The research group LLM-jp has released the LLM-jp-4 family, consisting of an 8B dense model and a 32B-A3B mixture-of-experts model. These Japanese language models are designed to prioritize transparency, reproducibility, and practical utility for users.
Covered by 1 source
- AarXiv CS.AI↗LLM-jp, :, Chaoran Liu, Daisuke Kawahara, Hideyuki Tachibana, Hirokazu Kiyomaru, Jun Suzuki, Koshi Eguchi, Kouta Nakayama, Qianying Liu, Rio Yokota, Ryo Takahashi, Sadao Kurohashi, Sosuke Hosokawa, Taishi Nakamura, Takashi Kodama, Yun-Ang Wu, Yusuke Miyao, Yusuke Oda4d ago