Update README.md

README.md

@@ -19,11 +19,11 @@ citation: |
 
 # DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
 
-**DinoBloom** is a ViT (Vision Transformer) built upon [DINOv2](https://arxiv.org/abs/2304.07193) (Meta AI) and is trained on **13 diverse publicly available datasets** of single cells from peripheral blood and bone marrow. The models in this repository can be used for feature extraction. The project was developed by Koch et al. and more information can be found on their [GitHub repository](https://github.com/MarrLab/DinoBloom) and in the [accompanying paper](https://arxiv.org/abs/2404.05022). This repository is fork of the original repo of the authors: [HuggingFace repository](https://huggingface.co/MarrLab/DinoBloom). 
+## Short description
 
----
+**DinoBloom** is a ViT (Vision Transformer) built upon [DINOv2](https://arxiv.org/abs/2304.07193) (Meta AI) and is trained on **13 diverse publicly available datasets** of single cells from peripheral blood and bone marrow. The models in this repository can be used for feature extraction. The project was developed by Koch et al. and more information can be found on their [GitHub repository](https://github.com/MarrLab/DinoBloom) and in the [accompanying paper](https://arxiv.org/abs/2404.05022). This repository is fork of the original repo of the authors: [HuggingFace repository](https://huggingface.co/MarrLab/DinoBloom). 
 
-## 🧠 Model Variants
+## Model Versions
 
 DinoBloom is available in **four sizes**:
 
@@ -34,16 +34,12 @@ DinoBloom is available in **four sizes**:
 | **DinoBloom-L** | 1024 | 304M | `pytorch_model_l.bin` |
 | **DinoBloom-G** | 1536 | 1136M | `pytorch_model_g.bin` |
 
----
-
 ## 🔧 Requirements
 
 ```bash
 pip install torch torchvision huggingface_hub
 ```
 
----
-
 ## 🚀 Usage
 
 ```python