XuanYuan-70B is a 70 billion parameter large language model developed by Duxiaoman-DI, based on the Llama2-70B architecture. It features significant Chinese language enhancement and is specifically optimized for financial domain applications, maintaining strong general capabilities. Notably, it extends the context length to 8192 tokens during pre-training, making it one of the first 70B models with such an extended context window. The model is designed to serve financial industry use cases while preserving robust general-purpose language understanding.
No reviews yet. Be the first to review!
Hugging Face