Update model metadata to set pipeline tag to the new `text-ranking`

Hello!

## Pull Request overview
* Update metadata to set pipeline tag to the new `text-ranking`

## Changes
This is an automated pull request to update the metadata of the model card. We recently introduced the [`text-ranking`](https://huggingface.co/models?pipeline_tag=text-ranking) pipeline tag for models that are used for ranking tasks, and we have a suspicion that this model is one of them.

Feel free to respond if you have questions or concerns.

- Tom Aarsen

README.md

@@ -102,15 +102,30 @@ datasets:
 - lightblue/reranker_continuous_filt_max7_train
 base_model:
 - Qwen/Qwen2.5-0.5B-Instruct
-pipeline_tag: text-generation
+pipeline_tag: text-ranking
 tags:
 - reranker
 widget:
-- text: "<<<Query>>>\nHow many languages has LB-Reranker been trained on?\n\n\n<<<Context>>>\nLB-Reranker has been trained on more than 95 languages."
+- text: '<<<Query>>>
+
+    How many languages has LB-Reranker been trained on?
+
+
+
+    <<<Context>>>
+
+    LB-Reranker has been trained on more than 95 languages.'
   example_title: Positive example (7/7)
-- text: "<<<Query>>>\nHow many languages has LB-Reranker been trained on?\n\n\n<<<Context>>>\nAA-Reranker is applicable to a broad range of use cases."
-  example_title: Negative example (2/7)
+- text: '<<<Query>>>
 
+    How many languages has LB-Reranker been trained on?
+
+
+
+    <<<Context>>>
+
+    AA-Reranker is applicable to a broad range of use cases.'
+  example_title: Negative example (2/7)
 ---
 
 # LB Reranker v1.0