@colafan
colafan 暂无简介
1st reasoning models, DeepSeek-R1-Zero and DeepSeek-R1
Breaking the Barrier of Closed-Source Models in Code Intelligence
DeepSeek-V3 是一个强大的 Mixture-of-Experts (MoE) 语言模型,它拥有671B个总参数,每个 token 有37B个激活参数