update readme

Former-commit-id: 9b8e7ccdab167f53fb897e1940562682324e8ff0

README.md

@@ -245,8 +245,6 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 
 </details>
 
-Please refer to [data/README.md](data/README.md) for details.
-
 Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands.
 
 ```bash
@@ -366,8 +364,18 @@ docker compose -f ./docker-compose.yml up -d
 
 See [examples](examples) for usage.
 
-> [!TIP]
-> Use `python src/train_bash.py -h` to display arguments description.
+Use `python src/train_bash.py -h` to display arguments description.
+
+### Deploy with OpenAI-style API and vLLM
+
+```bash
+CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
+    --model_name_or_path path_to_model \
+    --adapter_name_or_path path_to_lora_adapter \
+    --template default \
+    --finetuning_type lora \
+    --infer_backend vllm
+```
 
 ### Use ModelScope Hub
 
@@ -381,6 +389,8 @@ Train the model by specifying a model ID of the ModelScope Hub as the `--model_n
 
 ## Projects using LLaMA Factory
 
+If you have a project that should be incorporated, please contact via email or create a pull request.
+
 <details><summary>Click to show</summary>
 
 1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223)
@@ -414,9 +424,6 @@ Train the model by specifying a model ID of the ModelScope Hub as the `--model_n
 
 </details>
 
-> [!TIP]
-> If you have a project that should be incorporated, please contact via email or create a pull request.
-
 ## License
 
 This repository is licensed under the [Apache-2.0 License](LICENSE).