Updata README.md

添加端口映射

README.md

@@ -79,7 +79,7 @@ conda create -n internlm_vllm python=3.10
 
 | 基座模型                                                    |                                                             |                                                               |                                                                 |
 | ----------------------------------------------------------- | ----------------------------------------------------------- | ------------------------------------------------------------- | --------------------------------------------------------------- |
-| [internlm2-7b](https://huggingface.co/internlm/internlm2-7b)  | [internlm2-20b](https://huggingface.co/internlm/internlm2-20b) | [internlm2_5-7b](https://huggingface.co/internlm/internlm2_5-7b) | [internlm2_5-20b](https://huggingface.co/internlm/internlm2_5-20b) |
+| [internlm2-7b](http://113.200.138.88:18080/aimodels/internlm/internlm2-7b.git)  | [internlm2-20b](http://113.200.138.88:18080/aimodels/internlm/internlm2-20b.git) | [internlm2_5-7b](http://113.200.138.88:18080/aimodels/internlm/internlm2_5-7b.git) | [internlm2_5-20b](http://113.200.138.88:18080/aimodels/internlm/internlm2_5-20b.git) |
 
 ### 离线批量推理
 
@@ -199,17 +199,22 @@ python  gradio_openai_chatbot_webserver.py --model "internlm/internlm2_5-7b" --m
 ```
 chmod +x frpc_linux_amd64_v0.*
 ```
+   2.3 端口映射
+
+```
+ssh -L 8000:计算节点IP:8000 -L 8001:计算节点IP:8001 用户名@登录节点 -p 登录节点端口
+```  
 
 3.启动OpenAI兼容服务
 
 ```
-python -m vllm.entrypoints.openai.api_server --model internlm/internlm2_5-7b --enforce-eager --dtype float16 --trust-remote-code --port 8000
+python -m vllm.entrypoints.openai.api_server --model internlm/internlm2_5-7b --enforce-eager --dtype float16 --trust-remote-code --port 8000 --host "0.0.0.0"
 ```
 
 4.启动gradio服务
 
 ```
-python  gradio_openai_chatbot_webserver.py --model "internlm/internlm2_5-7b" --model-url http://localhost:8000/v1 --temp 0.8 --stop-token-ids ""
+python  gradio_openai_chatbot_webserver.py --model "internlm/internlm2_5-7b" --model-url http://localhost:8000/v1 --temp 0.8 --stop-token-ids --host "0.0.0.0" --port 8001"
 ```
 
 5.使用对话服务