Improve model card: Add metadata (pipeline, library, license, tags) and paper link

This PR updates the model card for `sii-research/InnoSpark-72B-0710`.

It adds the following metadata:
- `pipeline_tag: text-generation` to correctly classify the model's primary function and improve its discoverability on the Hugging Face Hub.
- `library_name: transformers` to ensure compatibility with the Hugging Face `transformers` library is correctly recognized, enabling the "Use in Transformers" widget.
- `license: other` as the specific license is stated to be on "relevant model pages" rather than directly in this model card.
- Relevant `tags` such as `qwen`, `educational-llm`, `llm`, and `innospark` for better categorization.

It also adds a prominent link to the paper "[ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios](https://huggingface.co/papers/2507.22947)" at the top of the README.

README.md

@@ -1,7 +1,20 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+license: other
+tags:
+  - qwen
+  - educational-llm
+  - llm
+  - innospark
+---
+
 <div align="center">
 
 # 🌟 InnoSpark 🌟
 
+This model is related to the paper [ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios](https://huggingface.co/papers/2507.22947).
+
 [![Official Website](https://img.shields.io/badge/🌐-Official%20Website-blue?style=for-the-badge)](https://innospark.aiecnu.cn/innospark/)
 [![Hugging Face](https://img.shields.io/badge/🤗-Hugging%20Face-yellow?style=for-the-badge)](https://huggingface.co/sii-research)
 [![GitHub](https://img.shields.io/badge/💻-GitHub-black?style=for-the-badge)](https://github.com/Inno-Spark/elmes)
@@ -113,7 +126,8 @@ def Innospark_stream(inputs,history):
 
     for chunk in response.iter_lines(chunk_size=1,
                                      decode_unicode=False,
-                                     delimiter=b"\n"):
+                                     delimiter=b"
+"):
         if chunk:
             string_data = chunk.decode("utf-8")
             try:
@@ -247,4 +261,4 @@ Please refer to the relevant model pages for specific license information.
 
 <sub>🚀 Empowering Education with AI</sub>
 
-</div> 
+</div>