Update README.md

README.md

@@ -64,7 +64,7 @@ pip install numpy==1.26.1
 ```bash
 ## serve启动
 
-vllm serve /public/home/raojy/project/model_code/Qwen3-Omni-30B-A3B-Instruct \
+vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct \
     --trust-remote-code \
     --tensor-parallel-size 4 \
     --dtype bfloat16 
@@ -74,7 +74,7 @@ curl http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer EMPTY" \
   -d '{
-    "model": "/public/home/raojy/project/model_code/Qwen3-Omni-30B-A3B-Instruct",
+    "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
     "messages": [
       {
         "role": "user",
@@ -110,8 +110,7 @@ DCU与GPU精度一致，推理框架：vllm。
 ## 预训练权重
 |  模型名称  | 权重大小 | DCU型号  | 最低卡数需求 |         下载地址          |
 |:------:|:----:|:----------:|:------:|:---------------------:|
-| 
-Qwen3-Omni-30B-A3B-Instruct | 30B | BW1000 |   2   | [Hugging Face](https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct) |
+| Qwen3-Omni-30B-A3B-Instruct | 30B | BW1000 |   2   | [Hugging Face](https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct) |
 
 
 ## 源码仓库及问题反馈