Nvidia has announced the launch of four new NVIDIA NIM microservices to support GenAI application development in Japan and Taiwan. These microservices are designed to work with popular community models tailored for regional needs and are available through NVIDIA AI Enterprise.
The new NIM microservices include Llama-3-Swallow-70 billion (trained on Japanese data), Llama-3-Taiwan-70 billion (trained on Mandarin data), and two RakutenAI 7 billion models for Chat and Instruct (trained on English and Japanese datasets). These models are optimized for inference with the NVIDIA TensorRT-LLM open-source library, offering improved performance in regional language understanding, legal tasks, question-answering, and language translation.
NVIDIA claims these microservices will allow businesses, government agencies, and universities to host native LLMs in their environments, enabling developers to build copilots, chatbots, and AI assistants.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.