LLM-jp-3 172B beta1 Released
The Research and Development Center for Large Language Models at the National Institute of Informatics has released the preview version of “LLM-jp-3 172B,” a...
LLM-jp
In this consortium, researchers in natural language processing and computer systems gather regularly to share information on the research and development of large language models.
We are working specifically for the following purposes:
- Develop open source, state-of-the-art Japanese large language models and advance related research and development
- Facilitate the exchange of knowledge on model training and recent research developments among researchers in natural language processing and related fields
- Promote cross-organizational collaboration among researchers based on the premise of sharing data, computational resources, etc.
- Release products such as models, tools, technical materials, etc.
News
Launch of the Website for the Research and Development Center for Large Language Models
The website for the Research and Development Center for Large Language Models at the National Institute of Informatics has been launched.
AnswerCarefully Version 2.0 Now Available
NII-LLMC is releasing AnswerCarefully Version 2.0, an instruction dataset for safety alignment of Japanese LLMs.
Announcement for Weights & Biases User Summit “Fully Connected Tokyo”
Weights & Biases, sponsored by LLM-jp as a community sponsor, will host the user summit “Fully Connected Tokyo.”
Announcement for the LLM Symposium 2024
The LLM Symposium 2024 is set to take place.
Contact
LLM-jp Office: llm-jp(at)nii.ac.jp
NII PR Team: media(at)nii.ac.jp (For media inquiries)