google/gemma-2-2b-jpn-it

Google's Gemma-2-2B-JPN-IT is a 2.6 billion parameter instruction-tuned, decoder-only large language model from the Gemma 2 family, specifically fine-tuned for Japanese text. It supports a context length of 8192 tokens and is designed to perform at the same level for Japanese queries as English-only Gemma 2 models. This model excels in various Japanese text generation tasks, including question answering, summarization, and reasoning, and can also be used for translation.