fix readme.md

README.md

@@ -25,7 +25,8 @@ tags:
 
 Paper: [Your ViT is Secretly an Image Segmentation Model (arXiv:2503.19108)](https://arxiv.org/abs/2503.19108) · [HF Papers](https://huggingface.co/papers/2503.19108)
 
-EoMT (Encoder-only Mask Transformer) keeps segmentation inside a plain ViT: learned query tokens are concatenated with patch tokens and run through the same ViT blocks. No pixel decoder, no deformable attention decoder.\n
+EoMT (Encoder-only Mask Transformer) keeps segmentation inside a plain ViT: learned query tokens are concatenated with patch tokens and run through the same ViT blocks. No pixel decoder, no deformable attention decoder.
+
 For more details on the model, please go to the upstream [model card](https://huggingface.co/tue-mps/coco_instance_eomt_large_640).
 
 Pure-**Keras 3** conversion of [`tue-mps/coco_instance_eomt_large_640`](https://huggingface.co/tue-mps/coco_instance_eomt_large_640) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
@@ -39,10 +40,10 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
 from PIL import Image
-from {meta['import_path']} import {meta['load_cls']}, {meta['proc_cls']}
+from kerasformers.models.eomt import EoMTUniversalSegment, EoMTImageProcessor
 
-model = {meta["load_cls"]}.from_weights("kerasformers/{variant}")
-processor = {meta['proc_cls']}()
+model = EoMTUniversalSegment.from_weights("kerasformers/eomt_large_coco_instance_640")
+processor = EoMTImageProcessor()
 
 image = Image.open("your_image.jpg").convert("RGB")
 output = model(processor(image)["pixel_values"], training=False)