Remove arXiv tag from metadata, add pipeline tag

This PR cleans up the model card metadata by:
- Removing the `arxiv:2609.33437` tag from the YAML (the arXiv ID should only appear in the Markdown content, per Hugging Face guidelines).
- Adding `pipeline_tag: image-classification` so the model is properly categorized and discoverable under image classification tasks.

The paper link and GitHub link in the content remain unchanged.

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 · FT · MNIST
 
 A FT 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.