Update README.md

Corrected doc to use

```python
--rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072
```

README.md

@@ -290,7 +290,7 @@ YaRN is currently supported by several inference frameworks, e.g., `transformers
 
   For `vllm`, you can use
     ```shell
-    vllm serve ... --rope-scaling '{"type":"rope_type","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072  
+    vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072
     ```
 
   For `sglang`, you can use