Update README.md

README.md

@@ -2,13 +2,16 @@
 license: mit
 base_model: Qwen/Qwen2.5-VL-7B
 tags:
+  - OCR
   - vision-language
+  - VLM
+  - Reasoning
   - document-to-markdown
-  - reinforcement-learning
-  - grpo
   - qwen2.5
   - markdown
-model_name: NuMarkdown-reasoning
+  - extraction
+  - RAG
+model_name: NuMarkdown-8B-Thinking
 library_name: transformers
 pipeline_tag: text-generation
 ---
@@ -24,16 +27,16 @@ pipeline_tag: text-generation
 
 ---
 
-# NuMarkdown-reasoning 📄
+# Reasoning OCR Model 📄
 
-**NuMarkdown-8B-reasoning** is the first reasoning vision-language model trained specifically to convert documents into clean GitHub-flavoured Markdown.
-It is a fine-tune of **Qwen 2.5-VL-7B** using ~10k synthetic Doc-to-Reasoning-to-Markdown pairs, followed by an RL phase (GRPO) with a layout-centric reward.
+**NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean GitHub-flavoured Markdown.
+It 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.
 
 *(Note: the number of thinking tokens can vary from 20% to 500% the number of tokens in the final answer)*
 
 ## Results
 
-**NuMarkdown-reasoning** is significantly better than similar size non-reasoning models trained for markdown generation on complex documents, and achieves competitive results against top closed source alternatives.
+**NuMarkdown-8B-Thinking** is significantly better than similar size non-reasoning models trained for markdown generation on complex documents, and achieves competitive results against top closed source alternatives.
 
 ### Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 anonymized votes):
 <p align="center">