Update README.md

README.md

@@ -1,16 +1,24 @@
----
-library_name: r2r
-pipeline_tag: text-classification
-tags:
-- router
-- efficiency
-- language-model
----
+---
+library_name: r2r
+pipeline_tag: text-classification
+tags:
+- router
+- efficiency
+- language-model
+datasets:
+- nics-efc/R2R_Router_Training
+- nics-efc/R2R_query
+language:
+- en
+---
 
 # R2R Router Models
 
 This repository provides a collection of **R2R** routers (Mixture of Small and Large Language Models) and its training config built for different model pairs.
 
+They are the routers from paper [R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing](https://huggingface.co/papers/2505.21600)
+
+
 ## Model Description
 
 R2R routers are lightweight classifiers that decide, at the token level, whether to generate with a small language model (SLM) or delegate to a large language model (LLM). The goal is to retain LLM-level quality while improving end-to-end efficiency.
@@ -22,4 +30,4 @@ We currently support routers for the **Qwen3** series and the **DeepSeek-R1-Qwen
 For setup instructions, checkpoints, and examples, please visit our GitHub repository:
 
 - GitHub: [https://github.com/thu-nics/R2R](https://github.com/thu-nics/R2R)  
-- Project page: [https://fuvty.github.io/R2R_Project_Page/](https://fuvty.github.io/R2R_Project_Page/)
+- Project page: [https://fuvty.github.io/R2R_Project_Page/](https://fuvty.github.io/R2R_Project_Page/)