Episode Details
Back to Episodes
【第114期】DeepSeek V3技术报告
Published 1 year, 5 months ago
Description
Seventy3: 用NotebookLM将论文生成播客，让大家跟着AI一起进步。
今天的主题是：
DeepSeek-V3 Technical Report
Summary
The document details DeepSeek-V3, a 671B-parameter Mixture-of-Experts large language model. It covers the model's architecture, including Multi-Head Latent Attention and an innovative auxiliary-loss-free load balancing strategy for DeepSeekMoE. The training process, encompassing pre-training on 14.8 trillion tok...去小宇宙查看完整单集简介
前往小宇宙评论区与主播互动
今天的主题是：
DeepSeek-V3 Technical Report
Summary
The document details DeepSeek-V3, a 671B-parameter Mixture-of-Experts large language model. It covers the model's architecture, including Multi-Head Latent Attention and an innovative auxiliary-loss-free load balancing strategy for DeepSeekMoE. The training process, encompassing pre-training on 14.8 trillion tok...去小宇宙查看完整单集简介
前往小宇宙评论区与主播互动