Correct pipeline tag and add library name

This PR corrects the `pipeline_tag` to `feature-extraction` which is more appropriate for a reranking model. It also adds the `library_name` as `transformers` given the provided usage examples.

README.md

@@ -1,15 +1,16 @@
 ---
-license: mit
-datasets:
-- jhu-clsp/rank1-training-data
 base_model:
 - Qwen/Qwen2.5-14B
-pipeline_tag: text-generation
+datasets:
+- jhu-clsp/rank1-training-data
+language:
+- en
+license: mit
+pipeline_tag: feature-extraction
 tags:
 - reranker
 - retrieval
-language:
-- en
+library_name: transformers
 ---
 
 # rank1-14b: Test-Time Compute for Reranking in Information Retrieval
@@ -177,4 +178,4 @@ If you use rank1 in your research, please cite our work:
 
 ## License
 
-[MIT License](https://github.com/orionw/rank1/blob/main/LICENSE) 
+[MIT License](https://github.com/orionw/rank1/blob/main/LICENSE)