diff --git a/README-en.md b/README-en.md
index d02e6eb..23cd075 100644
--- a/README-en.md
+++ b/README-en.md
@@ -194,7 +194,11 @@ We have supported inference with [llama.cpp](https://github.com/ggerganov/llama.
 More parameters adjustment [see this](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
 
 **ollama**
-Solving [this issue](https://github.com/ollama/ollama/issues/2383)
+1. [install ollama](https://github.com/ollama/ollama)
+2. In command line:
+```
+ollama run modelbest/minicpm-2b-dpo 
+```
 
 **fastllm**
 1. install [fastllm](https://github.com/ztxz16/fastllm)
diff --git a/README.md b/README.md
index 017f2e9..b3a368e 100644
--- a/README.md
+++ b/README.md
@@ -201,7 +201,11 @@ MiniCPM支持[llama.cpp](https://github.com/ggerganov/llama.cpp/) 、[ollama](ht
 更多参数调整[详见](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
 
 **ollama**
-正在解决[这个问题](https://github.com/ollama/ollama/issues/2383)
+1. [安装ollama](https://github.com/ollama/ollama)
+2. 在命令行运行:
+```
+ollama run modelbest/minicpm-2b-dpo
+```
 
 **fastllm**
 1. [编译安装fastllm](https://github.com/ztxz16/fastllm)