nk2t/Llama-3-8B-Instruct-japanese-nk2t-v0.2

The nk2t/Llama-3-8B-Instruct-japanese-nk2t-v0.2 model is an 8 billion parameter instruction-tuned causal language model, fine-tuned by nk2t from Meta's Llama-3-8B-Instruct. It is specifically optimized for responding to Japanese questions in Japanese, despite its base model being primarily intended for English. This model demonstrates an average ELYZA-tasks-100 score of 3.12, indicating its proficiency in Japanese language tasks.