Add pipeline tag

This PR ensures the model can be found at https://huggingface.co/models?pipeline_tag=image-to-text&sort=trending.

README.md

@@ -1,13 +1,15 @@
 ---
+base_model:
+- apple/DFN5B-CLIP-ViT-H-14
+datasets:
+- mlfoundations/datacomp_1b
+license: mit
 tags:
 - pytorch_model_hub_mixin
 - model_hub_mixin
-license: mit
-datasets:
-- mlfoundations/datacomp_1b
-base_model:
-- apple/DFN5B-CLIP-ViT-H-14
+pipeline_tag: image-to-text
 ---
+
 ## Official implementation of fine-tuned ViT-H/14 ProLIP on DataComp 1B
 
 - This weight is a fine-tuned version of ViT-H/14 by Probabilistic Language-Image Pre-Training (ProLIP)