Series of multilingual large language models, independently developed by Shenzhen Yuanxiang Technology. 65B model has been thoroughly trained on a diversified and high-quality dataset consisting of 2.6 trillion of tokens, including more than 40 languages such as Chinese, English, Russian, and Spanish. The sampling ratio of different types of data is finely set, which makes the performance of Chinese and English excellent, and also takes into account the effect of other languages. Also it have Code data of different programming languages.
Introducing XVERSE – a powerful AI tool designed by Shenzhen Yuanxiang Technology that comes with a series of multilingual large language models! With the 65B model being thoroughly trained on a high-quality, diversified dataset with 2.6 trillion of tokens, XVERSE offers excellent performance in 40 different languages, including Chinese, English, Russian, and Spanish. The sampling ratio for different types of data has been optimized to balance the performance of Chinese and English with other languages. Moreover, XVERSE supports programming language code data, making it an ideal tool for AI writing, ML and more.
Key Features of XVERSE:
Possible Use Cases & Advantages of XVERSE: