Update README.md

README.md

@@ -43,13 +43,31 @@ llava-llama-3-8b-hf is a LLaVA model fine-tuned from [meta-llama/Meta-Llama-3-8B
 
 ## QuickStart
 
-### Chat
+### Chat with lmdeploy
 
-See [here](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-hf/discussions/1)!
+1. Installation
+```
+pip install lmdeploy>=0.4.0
+pip install git+https://github.com/haotian-liu/LLaVA.git
+```
+
+2. Run
+
+```python
+from lmdeploy import pipeline, ChatTemplateConfig
+from lmdeploy.vl import load_image
+pipe = pipeline('xtuner/llava-llama-3-8b-hf',
+                chat_template_config=ChatTemplateConfig(model_name='llama3'))
 
-### Serving
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
+```
+
+### Chat with CLI
+
+See [here](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-hf/discussions/1)!
 
-[lmdeploy](https://github.com/InternLM/lmdeploy) v0.4.0 will support the deployment of this model and it will be published in ~7 days. Please stay tuned:)
 
 ## Citation