occupation
Data Scientists
description
DeepSeek-V4 思维框架蒸馏,关于模型架构、训练成本、MoE、MLA、MTP、GRPO 等技术问题
Source text: Mixed languages
updated
Menu
SkillsMP has collected 1 skills from wukongnotnull/pangu-deepseek-v4. Open a skill to review its source and details.
Showing 1 of 1 collected skills.
DeepSeek-V4 思维框架蒸馏,关于模型架构、训练成本、MoE、MLA、MTP、GRPO 等技术问题
Source text: Mixed languages