Update README.md

README.md

@@ -30,13 +30,13 @@ pipeline_tag: text-generation
 # Reasoning comes to OCR 🧠✨📄🤘
 
 **NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean GitHub-flavoured Markdown. It generates thoughts tokens to figure out the layout of the document before generating the Markdown file.
-It is particularly good at understanding documents with weird layout and complex tables. The number of thinking tokens can vary from 20% to 500% of the number of tokens for the final answer, depending on the task difficulty.
+It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty.
 
-**NuMarkdown-8B-Thinking** is a fine-tune of **Qwen 2.5-VL-7B** using synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward.
+**NuMarkdown-8B-Thinking** is a fine-tune of **Qwen 2.5-VL-7B** on synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward.
 
 ## Results
 
-**NuMarkdown-8B-Thinking** is outperforming generic non-reasoning models like GPT-4o and specialized markdown generation models like OCRFlux. 
+**NuMarkdown-8B-Thinking** is outperforming generic non-reasoning models like GPT-4o and specialized OCR models like OCRFlux. 
 It is competitive against large reasoning closed-source models like Gemini 2.5.
 
 ### Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 model-anonymized votes):