Hy3 preview Released and Open-Sourced Following Hunyuan Reconstruction: Emphasizing Comprehensive Practicality with Significantly Enhanced Agent Capabilities
The Hunyuan Hy3 preview language model by Tencent has been released and open-sourced. This is a mixture-of-experts model that integrates fast and slow thinking, featuring a total of 295 billion parameters and 21 billion activated parameters, with support for a maximum context length of 256K. As the first model trained following the Hunyuan reconstruction, it is also the most intelligent model to date for Hunyuan, achieving substantial improvements in complex reasoning, instruction following, in-context learning, code handling, agent capabilities, and inference performance.
Source: Wallstreetcn The copyright of this article belongs to the original author/organization.
The views expressed herein are solely those of the author and do not reflect the stance of the platform. The content is intended for investment reference purposes only and shall not be considered as investment advice. Please contact us if you have any questions or suggestions regarding the content services provided by the platform.
Post your comment
No Comments