Update README.md

README.md

@@ -1,9 +1,21 @@
+---
+datasets:
+- THU-KEG/ReaRAG-20k
+language:
+- en
+base_model:
+- THUDM/glm-4-9b
+pipeline_tag: question-answering
+tags:
+- rag
+- reasoning
+---
 # ReaRAG-9B
 <p align="center">
    🤗 <a href="https://huggingface.co/datasets/THU-KEG/ReaRAG-20k" target="_blank">Dataset</a> • 💻 <a href="https://github.com/THU-KEG/ReaRAG" target="_blank">GitHub</a> • 📃 <a href="https://arxiv.org/abs/2503.21729" target="_blank">Paper</a>
 </p>
 
-ReaRAG-9B is trained based on glm-4-9b, with enhanced capability to generate knowledge-guided reasoning chains for iterative RAG. The model supports a context window of up to 8k tokens.
+ReaRAG-9B is trained based on [glm-4-9b](https://huggingface.co/THUDM/glm-4-9b), with enhanced capability to generate knowledge-guided reasoning chains for iterative RAG. The model supports a context window of up to 8k tokens.
 
 Please refer to the [Inference](https://github.com/THU-KEG/ReaRAG?tab=readme-ov-file#%EF%B8%8F-inference) section in the GitHub repository for usage detail.