Update pipeline tag and add descriptive tags

This PR updates the model card for `MingTok-Vision` by:
- Changing the `pipeline_tag` from `image-to-image` to `image-feature-extraction` to better reflect its primary function as a visual tokenizer.
- Adding new descriptive tags like `visual-tokenizer`, `feature-extraction`, `image-reconstruction`, and `autoregressive` to enhance discoverability and clarity.

All existing links and the sample usage remain unchanged as they are already correctly provided.

README.md

@@ -1,12 +1,18 @@
 ---
-license: apache-2.0
 language:
 - en
 - zh
-pipeline_tag: image-to-image
 library_name: transformers
+license: apache-2.0
+pipeline_tag: image-feature-extraction
+tags:
+- visual-tokenizer
+- feature-extraction
+- image-reconstruction
+- autoregressive
 ---
-##  MingTok: A Unified Tokenizer for Visual Understanding and Generation without Vector Quantization
+
+## MingTok: A Unified Tokenizer for Visual Understanding and Generation without Vector Quantization
 
 <p align="center">📑 <a href="https://arxiv.org/pdf/2510.06590">Technical Report</a> ｜ 📖 <a href="https://inclusionai.github.io/blog/mingtok/">Project Page</a> ｜ 🤗 <a href="https://huggingface.co/inclusionAI/MingTok-Vision">Hugging Face</a> ｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/MingTok-Vision">ModelScope</a> ｜ 💾 <a href="https://github.com/inclusionAI/Ming-UniVision">GitHub</a></p>