Upload README.md

README.md

@@ -68,19 +68,19 @@ We provide dequantized model weights in bfloat16 to run DeepSeek-R1 on NVIDIA GP
 
 ```bash
 pip install modelscope
-modelscope download --model <Model Name> --local_dir <Cache Path>
+modelscope download --model deepseek-ai/DeepSeek-R1 --local_dir /nfs/DeepSeek-R1
 ```
 
 ### Download the FlagOS image
 
 ```bash
-docker pull <IMAGE>
+docker pull flagrelease-registry.cn-beijing.cr.aliyuncs.com/flagrelease/flagrelease:deepseek-flagos-nvidia
 ```
 
 ### Start the inference service
 
 ```bash
-docker run -itd --name flagrelease_nv  --privileged --gpus all --net=host --ipc=host --device=/dev/infiniband --shm-size 512g --ulimit memlock=-1 -v <CKPT_PATH>:<CKPT_PATH> flagrelease-registry.cn-beijing.cr.aliyuncs.com/flagrelease/flagrelease:deepseek-flagos-nvidia /bin/bash
+docker run -itd --name flagrelease_nv  --privileged --gpus all --net=host --ipc=host --device=/dev/infiniband --shm-size 512g --ulimit memlock=-1 -v /nfs:/nfs flagrelease-registry.cn-beijing.cr.aliyuncs.com/flagrelease/flagrelease:deepseek-flagos-nvidia /bin/bash
 
 docker exec -it flagrelease_nv /bin/bash
 
@@ -95,6 +95,7 @@ cd FlagGems
 pip install .
 cd ../
 ```
+
 ### Modify the configuration
 
 ```bash
@@ -140,7 +141,7 @@ cd FlagScale/examples/deepseek_r1/conf/serve
 - serve_id: vllm_model
   engine: vllm
   engine_args:
-    model: /models/deepseek_r1 # path of weight of deepseek r1
+    model: /nfs/deepseek_r1 # path of weight of deepseek r1
     tensor_parallel_size: 8
     pipeline_parallel_size: 4
     gpu_memory_utilization: 0.9
@@ -161,7 +162,7 @@ pip install .
 ### Serve
 
 ```
-flagscale serve <Model>
+flagscale serve deepseek_r1
 ```
 
 # 
@@ -180,8 +181,8 @@ We warmly welcome global developers to join us:
 Scan the QR code below to add our WeChat group
 send "FlagRelease"
 
-![WeChat](https://cdn-uploads.huggingface.co/production/uploads/673326280dbcb3477ecc2af6/aETN9Zswqts2P9YLrizrz.png)
+![WeChat](image/group.png)
 
 # License
 
-This project and related model weights are licensed under the MIT License.
+The weights of this model are based on deepseek-ai/DeepSeek-R1 and are open-sourced under the Apache 2.0 License: https://www.apache.org/licenses/LICENSE-2.0.txt.