NII develops new domestic LL trained on a high-quality corpus of 12 trillion tokens 2026.05.21 研究成果 英語：NII develops new domestic LL trained on a high-quality corpus of 12 trillion tokens | News | Science Japan 中国語：科学研究 – NII开源发布新一代国产LLM：基于约12万亿词元优质语料训练 – 客观日本
