Improve model card: add metadata and sample usage

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR improves the model card for MedITok by:
- Adding the `text-to-image` pipeline tag to improve discoverability.
- Adding `library_name: transformers` metadata, as the repository contains configuration files and architectures compatible with the Hugging Face Transformers library.
- Including a sample usage section for image feature extraction, sourced directly from the official GitHub repository.
- Linking the model to its corresponding paper on the Hub.

Please review and merge if this looks good to you!

README.md

@@ -1,5 +1,7 @@
 ---
 license: cc-by-4.0
+library_name: transformers
+pipeline_tag: text-to-image
 ---
 
 <div align="center">
@@ -14,13 +16,46 @@ license: cc-by-4.0
 </p>
 
 ## 🚀 Introduction
-MedITok is the first unified visual tokenizer for medical images. Trained on 30M medical images and 2M image-caption pairs via a two-stage representation learning framework, MedITok:
+MedITok is the first unified visual tokenizer for medical images, introduced in [Unified Medical Image Tokenizer for Autoregressive Synthesis and Understanding](https://huggingface.co/papers/2505.19225). Trained on 33M medical images and 2M image-caption pairs via a two-stage representation learning framework, MedITok:
 - effectively encodes visual details and clinical semantics into a unified token space
 - achieves state-of-the-art performance across diverse medical imaging modalities and tasks.
 - can be incorporated into prevelant generative models (e.g., autoregressive architectures) for downstream medical image synthesis and interpretation.
 
 This work is supported by Shanghai Innovation Institute (SII).
 
+## 🎯 Sample Usage
+
+### Image feature extraction
+The following snippet demonstrates how to use the model for extracting features (requires the model implementation from the [official repository](https://github.com/masaaki-75/meditok)):
+
+```python
+import torch
+import numpy as np
+from PIL import Image
+
+def read_image(img, img_size=256):
+    if isinstance(img, str):
+        img = Image.open(img)
+        
+    if isinstance(img, Image.Image):
+        img = img.convert('RGB')
+        if img.size[0] != img_size:
+            img = img.resize((img_size, img_size), Image.LANCZOS)
+    return img
+
+def image_to_tensor(x):
+    # [H, W, C] -> [B, C, H, W]
+    x = torch.FloatTensor(np.array(x)).permute(2, 0, 1)
+    x = (x / 255.) * 2. - 1.
+    return x.unsqueeze(0)
+
+# Assuming 'net' is the loaded MedITok model
+img_path = 'assets/vis_imgs/sample1.png'
+img = read_image(img_path)
+x = image_to_tensor(img)
+with torch.no_grad():
+    f = net.forward_features(x)
+```
 
 ## ✏️ Citation
 
@@ -31,5 +66,4 @@ This work is supported by Shanghai Innovation Institute (SII).
   journal={arXiv preprint arXiv:2505.19225},
   year={2025}
 }
-
 ```