Update README.md

README.md

@@ -13,22 +13,22 @@ license: apache-2.0
 ## Benchmark Result
 |Metrics|MiniMax-M2.7-Nvidia-Origin|MiniMax-M2.7-Nvidia-FlagOS|
 |-------|---------------|---------------|
-| | | |
-|  |   | |
+|GPQA_Diamond |0.7071 |0.6313|
+|Aime24  | 0.9  | 0.9|
 
 # User Guide
 Environment Setup
 
 | Item             | Version              |
 |------------------|----------------------|
-| Docker Version   |  |
-| Operating System |  |
+| Docker Version   | 24.0.0 |
+| Operating System | Ubuntu 22.04.4 |
 
 ## Operation Steps
 
 ### Download FlagOS Image
 ```bash
-
+docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-minimax:202604120915
 ```
 
 ### Download Open-source Model Weights
@@ -39,16 +39,38 @@ modelscope download --model FlagRelease/MiniMax-M2.7-nvidia-FlagOS --local_dir /
 
 ### Start the Container
 ```bash
-
+#Container Startup
+docker run --init --detach --net=host --user 0 --ipc=host \
+           -v /data:/data --security-opt=seccomp=unconfined \
+           --privileged --ulimit=stack=67108864 --ulimit=memlock=-1 \
+           --shm-size=512G --gpus all  \
+           --name flagos harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-minimax:202604120915 sleep infinity
+docker exec -it flagos bash
 ```
 ### Start the Server
 ```bash
-
+vllm serve /data/MiniMax-M2.7 \
+--served-model-name minimax_m2.7 \
+--tensor-parallel-size 8 
+--gpu-memory-utilization 0.6 \
+--tool-call-parser minimax_m2 \
+--reasoning-parser minimax_m2_append_think \
+--host 0.0.0.0 \
+--port 8000 \
+--load-format fastsafetensors \
+--enable-auto-tool-choice \
+--trust-remote-code
 ```
 
 ## Service Invocation
 ### Invocation Script
 ```bash
+curl http://localhost:8000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "minimax_m2.7",
+    "messages": [{"role": "user", "content": "你好"}]
+  }'
 
 ```