Update README.md

README.md

@@ -282,6 +282,18 @@ bash scripts/zeroshot_eval.sh 0 \
     ViT-B-16 RoBERTa-wwm-ext-base-chinese \
     ./pretrained_weights/QA-CLIP-base.pt
 ```
+<br><br>
+
+# Huggingface Model and Online Demo
+We have open-sourced our model on the HuggingFace for easier access and utilization. Additionally, we have prepared a simple online demo for zero-shot classification, allowing everyone to experience it firsthand. We encourage you to give it a try!
+
+[:star:QA-CLIP-ViT-B-16:star:](https://huggingface.co/TencentARC/QA-CLIP-ViT-B-16)
+
+[:star:QA-CLIP-ViT-L-14:star:](https://huggingface.co/TencentARC/QA-CLIP-ViT-L-14)
+
+Here are some examples for demonstration:
+![sample](./examples/sample.png)
+
 <br><br>
 # Acknowledgments
 The project code is based on implementation of <b>[Chinese-CLIP](https://github.com/OFA-Sys/Chinese-CLIP)</b>, and we are very grateful for their outstanding open-source contributions.