Skip to content

GitLab

"third_party/vscode:/vscode.git/clone" did not exist on "838e1e0a5388995f60ce57d49ff97c4a479ba4bf"
Commit 16b2fe7b authored by ACzhangchao's avatar ACzhangchao
Browse files

Update README

parent 94624442
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
README.md
View file @ 16b2fe7b
...@@ -8,7 +8,7 @@ https://www.modelscope.cn/models/JiuTian-AI/JIUTIAN-139MoE-chat/file/view/master ...@@ -8,7 +8,7 @@ https://www.modelscope.cn/models/JiuTian-AI/JIUTIAN-139MoE-chat/file/view/master
JIUTIAN-139MoE是一个拥有130亿参数的大型语言模型，使用解码器型的MoE架构，包含一对大专家和六个小专家。模型支持在不同GPU和NPU集群上训练，并能无损切换。在FFN层采用MoE设计，有特殊的激活和路由机制。 JIUTIAN-139MoE是一个拥有130亿参数的大型语言模型，使用解码器型的MoE架构，包含一对大专家和六个小专家。模型支持在不同GPU和NPU集群上训练，并能无损切换。在FFN层采用MoE设计，有特殊的激活和路由机制。
![1727158586419](C:\Users\zhang\AppData\Roaming\Typora\typora-user-images\1727158586419.png) ![jiutian.png](https://developer.hpccube.com/codes/modelzoo/jiutian-139moe-chat/-/raw/main/jiutian.png?inline=false)
## 算法原理 ## 算法原理
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment