Update README.md

README.md

@@ -9,6 +9,11 @@ base_model:
 This model is an int4 model with group_size 128 and symmetric quantization of [deepseek-ai/deepseek-vl2](https://huggingface.co/deepseek-ai/deepseek-vl2) generated by [intel/auto-round](https://github.com/intel/auto-round).
 
 ## How to Use
+### Requirements
+On the basis of Python >= 3.8 environment, install the necessary dependencies by running the following command:
+```bash
+pip install git+https://github.com/deepseek-ai/DeepSeek-VL2.git@8bde1c1ae17510a1d1c686a0b55a6c7e61352a46
+```
 ### INT4 Inference
 ```python
 import requests