Update pipeline tag and add library name

This PR updates the model card to:
- Set the `pipeline_tag` to `image-segmentation`, which is more appropriate for models performing mask generation and segmentation tasks, improving discoverability on the Hugging Face Hub.
- Add `library_name: transformers` to the metadata. The model's `config.json` indicates compatibility with the 🤗 Transformers library, enabling the automated "how to use" widget on the model page.

Please review and merge if these changes are appropriate.

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
 base_model:
 - OpenGVLab/InternVL2_5-8B
-pipeline_tag: mask-generation
+license: apache-2.0
+pipeline_tag: image-segmentation
+library_name: transformers
 ---
+
 <div align="center">
 
 # ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation