Correct pipeline tag to text-generation

This PR corrects the `pipeline_tag` to `text-generation`, reflecting the model's function as a text generation model. The previous tag was not appropriate for the model.

README.md

@@ -1,15 +1,17 @@
 ---
+base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 license: apache-2.0
-base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
 - generated_from_trainer
 model-index:
 - name: WritingBench-Writing-Model-7b
   results: []
+pipeline_tag: text-generation
 ---
 
+```markdown
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
@@ -57,4 +59,5 @@ The following hyperparameters were used during training:
       year={2025},
       url={https://arxiv.org/abs/2503.05244}, 
 }
+```
 ```