Add pipeline_tag and library_name to metadata

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

This pull request improves the model card by adding relevant metadata to the YAML header. Specifically:
- `pipeline_tag: text-generation`: Categorizes the model for the text generation task.
- `library_name: transformers`: Enables the "Use in Transformers" button on the Hub, as the model uses `auto_map` in its `config.json`.

These changes help users discover the model more easily and provide guidance on how to use it within the Hugging Face ecosystem.

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: JetLM/SDAR-8B-Chat
 language:
 - en
 - zh
@@ -7,8 +8,9 @@ tags:
 - math
 - reasoning
 - diffusion
-base_model: JetLM/SDAR-8B-Chat
 model_type: sdar
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 <h1 align="center">DiRL-8B-Instruct</h1>