Update README.md

README.md

@@ -222,7 +222,7 @@ Tell me the weather in Seoul<|im_end|>
 
 ```
 
-- Note that the prompt ends with `assistant/think\n`(think + `\n`).
+- Note that the prompt ends with `assistant/think\n`(think + `\n).
 - Generation continues until either the <|stop|> or <|endofturn|> token appears immediately after `<|im_end|>`.
 
 To have the assistant respond in non-reasoning mode (i.e., answer directly), you can input the following prompt.
@@ -555,10 +555,10 @@ The HyperCLOVA X SEED Think model is built on a custom LLM architecture based on
     git clone https://github.com/NAVER-Cloud-HyperCLOVA-X/hcx-vllm-plugin
     ```
 
-2. vLLM Plugin Build & Installation: While keeping the HyperCLOVAX_modeling path downloaded in step 1, refer to the commands below.
+2. vLLM Plugin Build & Installation: While keeping the NAVER-Cloud-HyperCLOVA-X/hcx-vllm-plugin path downloaded in step 1, refer to the commands below.
 
     ```bash
-    pip install vllm
+    pip install -e .
     ```
 
 After downloading the model checkpoint to a local path (`/path/to/hyperclova-x-seed-think-14b`), you can perform text inference by running the following commands on a GPU environment with A100 or higher.
@@ -601,4 +601,3 @@ The model is licensed under [HyperCLOVA X SEED Model License Agreement](./LICENS
 ## Questions
 
 For any other questions, please feel free to contact us at [dl_hcxtuneup@navercorp.com](mailto:dl_hcxtuneup@navercorp.com).
-