Update README.md

README.md

@@ -15,6 +15,7 @@ base_model:
 
 [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20HF-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/Step-3.5-Flash)
 [![ModelScope](https://img.shields.io/badge/ModelScope-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/step3p5_preview/tree/main)
+[![Webpage](https://img.shields.io/badge/Webpage-Blog-blue)](https://static.stepfun.com/blog/step-3.5-flash/)
 [![Paper](https://img.shields.io/badge/Paper-Arxiv-red)](https://huggingface.co/stepfun-ai/Step-3.5-Flash)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green)]()
 
@@ -22,7 +23,7 @@ base_model:
 
 ## 1. Introduction 
 
-**Step 3.5 Flash** is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
+**Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 
 ## 2. Key Capabilities