Add pipeline tag, library name, and link to paper

This PR adds the `pipeline_tag` and `library_name` to the model card metadata. The `pipeline_tag` is set to `text-to-text` given the classification and retrieval tasks described in the paper, and the `library_name` is set to `transformers`. It also adds a link to the paper.

README.md

@@ -1,4 +1,9 @@
 ---
 license: mit
+library_name: transformers
+pipeline_tag: text-to-text
 ---
-Pretrained models used for evaluation under the CARE benchmarks, which were trained using the training splits in CARE. For Task 1, we include CLEAN and Pika. For Task 2, we include CREEP and CLIPZyme.
+
+Pretrained models used for evaluation under the CARE benchmarks, which were trained using the training splits in CARE. For Task 1, we include CLEAN and Pika. For Task 2, we include CREEP and CLIPZyme.
+
+This repository contains models described in [CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes](https://arxiv.org/abs/2406.15669).