Update README.md

README.md

@@ -65,14 +65,17 @@ vllm serve Qwen/Qwen3.6-35B-A3B \
     --gpu-memory-utilization 0.925 
 
 ## client访问
-curl -X POST "http://localhost:8001/v1/chat/completions"   -H "Content-Type: application/json"   -d '{
-    "model": "Qwen/Qwen3.6-35B-A3B",
+ curl -X POST "http://localhost:8001/v1/chat/completions"   -H "Content-Type: application/json"   -d '{
+    "model": "/public/home/raojy/project/model_code/qwen36",
     "messages": [
       {"role": "system", "content": "你是一个有用的助手。"},
       {"role": "user", "content": "你好，请做一下简单的自我介绍。"}
     ],
+    "max_tokens": 512,
+    "temperature": 0.7,
     "stream": false
   }'
+
 ```
 
 ## 效果展示
@@ -87,7 +90,7 @@ DCU与GPU精度一致，推理框架：vllm。
 |  模型名称  | 权重大小 | DCU型号  | 最低卡数需求 |         下载地址          |
 |:------:|:----:|:----------:|:------:|:---------------------:|
 | Qwen3.6-35B-A3B | 35 | BW1000 |   4   | [Hugging Face](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) |
-| Qwen3.6-35B-A3B-FP8 | 35B | BW1000 |   2   | [Hugging Face](https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8) |
+
 
 
 ## 源码仓库及问题反馈