Update README.md

README.md

@@ -34,7 +34,7 @@ pipeline_tag: image-text-to-text
 
 **Model Summary**: 
 
-Granite Docling 258M builds upon the IDEFICS3 architecture, but introduces two key modifications: it replaces the vision encoder with siglip2-base-patch16-512 and substitutes the language model with a Granite 165M LLM.
+Granite Docling 258M builds upon the IDEFICS3 architecture, but introduces two key modifications: it replaces the vision encoder with siglip2-base-patch16-512 and substitutes the language model with a Granite 165M LLM. Try out our [Granite-Docling-258](https://huggingface.co/spaces/ibm-granite/granite-docling-258m-demo) demo today.
 
 - **Developed by**: IBM Research
 - **Model type**: Multi-modal model (image+text-to-text)