quick links: Hugging Face model: huggingface.co/numind/NuMar...

- GitHub repository: github.com/numindai/NuM...

- Discord server: discord.gg/3tsEtJNCDe

We find that NuMarkdown is outperforming generalist non-reasoning models like GPT-4o, specialized OCR models like OCRFlux, and is competitive against large reasoning closed-source models like Gemini 2.5!

Congrats to Alexandre Constantin for this tour de force

This model 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.

It generates thought tokens to figure out the layout of the document before generating the Markdown. 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 task difficulty