Add pipeline tag, GitHub link, and update project page URL

This PR improves the model card by:

- Adding the `pipeline_tag: image-feature-extraction` to the metadata, which helps users discover the model on the Hugging Face Hub under relevant tasks and enables the automated "Use in Transformers" widget.
- Adding an explicit GitHub badge for easier access to the code repository: https://github.com/SihanXU/nepa.
- Updating the project page URL in the existing badge to `https://sihanxu.me/nepa` to reflect the provided official project page.

README.md

@@ -1,13 +1,16 @@
 ---
-library_name: transformers
-license: apache-2.0
 datasets:
 - ILSVRC/imagenet-1k
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-feature-extraction
 ---
+
 # NEPA: Next-Embedding Prediction Makes Strong Vision Learners
 
 [![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=b31b1b)](https://arxiv.org/abs/2512.16922)
-[![Project Page](https://img.shields.io/badge/Project-Website-5B7493?logo=googlechrome&logoColor=5B7493)](https://sihanxu.github.io/nepa)
+[![Project Page](https://img.shields.io/badge/Project-Website-5B7493?logo=googlechrome&logoColor=5B7493)](https://sihanxu.me/nepa)
+[![GitHub](https://img.shields.io/badge/GitHub-Code-181717?logo=github)](https://github.com/SihanXU/nepa)
 [![Hugging Model Card](https://img.shields.io/badge/huggingface-model:NEPA-lightblue)](https://huggingface.co/collections/SixAILab/nepa)
 
 This is a PyTorch/GPU re-implementation of Next-Embedding Prediction Makes Strong Vision Learners.