Update README.md

README.md

@@ -21,7 +21,7 @@ For more details, please refer to [our blog post](https://note.com/elyza/n/n360b
 
 We have prepared two quantized model options, GGUF and AWQ. This is the [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) model.
 
-Here is a table showing the performance degradation due to quantization.
+The following table shows the performance degradation due to quantization:
 
 | Model | ELYZA-tasks-100 GPT4 score |
 | :-------------------------------- | ---: |
@@ -31,7 +31,7 @@ Here is a table showing the performance degradation due to quantization.
 
 ## Use with vLLM
 
-Install vLLM.
+Install vLLM:
 
 ```bash
 pip install vllm
@@ -74,8 +74,7 @@ for output in outputs:
 
 ### vLLM OpenAI Compatible Server
 
-Start the API server.
-
+Start the API server:
 ```bash
 python -m vllm.entrypoints.openai.api_server \
 --model elyza/Llama-3-ELYZA-JP-8B-AWQ \
@@ -85,8 +84,7 @@ python -m vllm.entrypoints.openai.api_server \
 ```
 
 
-Call the API using curl.
-
+Call the API using curl:
 ```bash
 curl http://localhost:8000/v1/chat/completions \
 -H "Content-Type: application/json" \
@@ -102,8 +100,7 @@ curl http://localhost:8000/v1/chat/completions \
 }'
 ```
 
-Call the API using Python.
-
+Call the API using Python:
 ```python
 import openai