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 large language model with approximately 172 billion parameters. The pre-training corpus is also available.

• Pre-trained model: https://huggingface.co/llm-jp/llm-jp-3-172b-beta1
• Instruction model: https://huggingface.co/llm-jp/llm-jp-3-172b-beta1-instruct
• Pre-training corpus: https://gitlab.llm-jp.nii.ac.jp/datasets/llm-jp-corpus-v3

For more details and the latest development status, please visit the project page (in Japanese only).