# Japanese Large Language Model

A Japanese large language model based on the modernBERT-base architecture, supporting a maximum sequence length of 8192, trained on 3.4TB of Japanese corpus

A large-scale Japanese-English hybrid MoE language model developed by Japan's National Institute of Informatics, supporting an 8x13B parameter scale with instruction fine-tuning optimization

Japanese large language model released by CyberAgent, distilled and optimized based on Qwen-32B

A large language model developed by Japan's National Institute of Informatics, supporting Japanese and English, based on Transformer architecture with 13 billion parameters

A large Japanese/English bilingual language model trained by SB Intuitions, based on the Llama2 architecture

A large-scale language model developed by the Japanese collaborative project LLM-jp, supporting Japanese and English, primarily used for text generation tasks.

Stockmark-13b is a 13-billion-parameter large language model pre-trained from scratch on a corpus of approximately 220 billion Japanese tokens, developed by Stockmark Inc.

A large language model developed by the Japanese collaborative project LLM-jp, supporting Japanese and English text generation