Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "b8fe2b4837c4ccf9f71c65d86ff336a98f45d1c3"
Commit dd913eff authored by xiabo's avatar xiabo
Browse files

Update README.md

parent a16a71d3
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
README.md
View file @ dd913eff
...@@ -16,7 +16,7 @@ Baichuan系列模型是由百川智能开发的开源大规模预训练模型， ...@@ -16,7 +16,7 @@ Baichuan系列模型是由百川智能开发的开源大规模预训练模型，
![img](./docs/baichuan.jpg) ![img](./docs/baichuan.jpg)
## 算法原理 ## 算法原理
Baichuan整体模型基于标准的Transformer结构，采用了和LLaMA一样的模型设计。其中，Baichuan-7B在结构上采用Rotary Embedding位置编码方案、SwiGLU激活函数、基于RMSNorm的Pre-Normalization。Baichuan-13B使用了ALiBi线性偏置技术，相对于Rotary Embedding计算量更小，对推理性能有显著提升。 Baichuan整体模型基于标准的Transformer结构，采用了和LLaMA一样的模型设计。其中，Baichuan-7B在结构上采用Rotary Embedding位置编码方案、SwiGLU激活函数、基于RMSNorm的Pre-Normalization。
![img](./docs/baichuan.png) ![img](./docs/baichuan.png)
......
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