Add pipeline tag and library name metadata

Hi! I'm Niels from the Hugging Face team.

This PR improves the model card for RIME-7B by:
1. Adding the `pipeline_tag: feature-extraction` metadata so that the model is properly categorized and discoverable.
2. Adding `library_name: transformers` metadata since this model uses `Qwen2VLForConditionalGeneration` from the `transformers` library.
3. Adding a link to the paper page on Hugging Face to make it easy for users to find the original research.

Let me know if you have any questions!

README.md

@@ -1,10 +1,12 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: feature-extraction
 ---
 
 # RIME-7B
 
-**RIME** (**R**ewrite-dr**I**ven **M**ultimodal **E**mbedding) model based on Qwen2-VL-7B-Instruct.
+**RIME** (**R**ewrite-dr**I**ven **M**ultimodal **E**mbedding) is a generative multimodal embedding model based on Qwen2-VL-7B-Instruct, presented in the paper [Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings](https://huggingface.co/papers/2604.22280).
 
 ## Model Description
 
@@ -23,4 +25,4 @@ See the [RIME repository](https://github.com/PeppaWu/RIME) for inference and eva
   journal={arXiv preprint arXiv:2604.22280},
   year={2026}
 }
-```
+```