Update README.md

README.md

@@ -24,7 +24,7 @@ SmolDocling is a multimodal Image-Text-to-Text model designed for efficient docu
 - 📝 **Caption Correspondence** – Links captions to relevant images and figures.  
 - 📜 **List Grouping** – Organizes and structures list elements correctly.  
 - 📄 **Full-Page Conversion** – Processes entire pages for comprehensive document transformation.  
-- 📂 **General Document Processing** – Optimized for non-scientific documents.  
+- 📂 **General Document Processing** – Trained for non-scientific documents and scientific.  
 - 🔄 **Seamless Docling Integration** – Import into **Docling** and export in multiple formats.
 - 📚 **Multi-Page & Full Document Conversion** – *Coming soon!* 🚧
 
@@ -33,7 +33,7 @@ SmolDocling is a multimodal Image-Text-to-Text model designed for efficient docu
 **Demo [optional]:** [More Information Needed]
 
 
-## Model Summary
+#### Model Summary
 
 - **Developed by:** Docling Team
 - **Model type:** Multi-modal model (image+text)
@@ -42,12 +42,11 @@ SmolDocling is a multimodal Image-Text-to-Text model designed for efficient docu
 - **Finetuned from model:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
 
 
-### How to get started
+## How to get started
 
 You can use transformers or docling to perform inference:
 
-# Transformers:
-
+#### Transformers:
 
 ```python
 import torch