Update README.md

vllm model card update

README.md

@@ -120,12 +120,12 @@ print("generate_text:", generate_text)
 
 ```bash
 # 80G * 16 GPU
-vllm serve baidu/ERNIE-4.5-300B-A47B-PT --trust-remote-code
+vllm serve baidu/ERNIE-4.5-300B-A47B-PT --tensor-parallel-size 16
 ```
 
 ```bash
-# FP8 online quantification 80G * 16 GPU
-vllm serve baidu/ERNIE-4.5-300B-A47B-PT --trust-remote-code --quantization fp8
+# FP8 online quantification 80G * 8 GPU
+vllm serve baidu/ERNIE-4.5-300B-A47B-PT --tensor-parallel-size 8 --quantization fp8
 ```
 
 ## Best Practices