Add pipeline tag and remove arxiv identifier from metadata

This PR updates the YAML metadata of the model card:
- Adds the correct `pipeline_tag: image-classification` so the model is discoverable at https://huggingface.co/models?pipeline_tag=image-classification.
- Removes the `arxiv:2609.33437` tag from the metadata, as per the policy that arXiv IDs should only be referenced in the Markdown content (e.g., as a link), not in the YAML front matter.

The content already includes the paper and GitHub links, so no further changes are needed.

README.md

@@ -1,16 +1,17 @@
 ---
-license: mit
 base_model: openai/clip-vit-base-patch32
+license: mit
+pipeline_tag: image-classification
 tags:
 - smat
 - model-merging
 - vision
-- arxiv:2609.33437
 ---
+
 # CLIP ViT base-patch32 · SMAT · DTD
 
 A SMAT expert from Table 2 of **SMAT: Simple and Efficient Merge-Aware Training** (seed 42). SMAT trains experts with model merging in mind.
 
 [Paper](https://arxiv.org/abs/2609.33437) · [GitHub & usage](https://github.com/egangu/smat/blob/main/docs/HUGGINGFACE.md)
 
-`encoder.pt` is the original FP32 vision-encoder state dictionary; load it with the SMAT code and the matching OpenAI CLIP base model. Dataset terms apply separately.
+`encoder.pt` is the original FP32 vision-encoder state dictionary; load it with the SMAT code and the matching OpenAI CLIP base model. Dataset terms apply separately.