Name: NuMarkdown 8B Thinking
Author: numind

Overview

NuMarkdown 8B Thinking is a specialized vision-language model optimized for high-fidelity image-to-markdown conversion. Unlike general-purpose OCR, this model focuses on structural integrity, accurately translating complex visual layouts—such as nested tables, mathematical formulas, and hierarchical headers—into clean, semantic Markdown. For developers, this means significantly less post-processing when digitizing documentation or converting legacy PDFs into LLM-ready datasets. It bridges the gap between raw visual data and structured text, offering a streamlined pipeline for RAG systems that rely on precise document parsing. Its 8B parameter scale provides a balanced trade-off between inference latency and reasoning capabilities, making it suitable for integration into automated data ingestion workflows.

Highlights

High-precision conversion of visual layouts to semantic Markdown
Optimized for complex tables and mathematical notation
Ideal for RAG pipeline data preprocessing
Efficient 8B parameter scale for lower latency
Permissive MIT license for flexible commercial integration

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("numind/NuMarkdown-8B-Thinking")
tokenizer = AutoTokenizer.from_pretrained("numind/NuMarkdown-8B-Thinking")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download numind/NuMarkdown-8B-Thinking

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download numind/NuMarkdown-8B-Thinking config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('numind/NuMarkdown-8B-Thinking')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/numind/NuMarkdown-8B-Thinking

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/numind/NuMarkdown-8B-Thinking

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('numind/NuMarkdown-8B-Thinking')
tokenizer = AutoTokenizer.from_pretrained('numind/NuMarkdown-8B-Thinking')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model numind/NuMarkdown-8B-Thinking

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model numind/NuMarkdown-8B-Thinking README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('numind/NuMarkdown-8B-Thinking')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/numind/NuMarkdown-8B-Thinking.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/numind/NuMarkdown-8B-Thinking.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'numind/NuMarkdown-8B-Thinking')

Full Documentation

来源: HuggingFace

---
license: mit
base_model: Qwen/Qwen2.5-VL-7B-Instruct
new_version: numind/NuExtract3
tags:

OCR

vision-language

VLM

Reasoning

document-to-markdown

qwen2.5

markdown

extraction

RAG

model_name: NuMarkdown-8B-Thinking
library_name: transformers
pipeline_tag: image-to-text
---

<a href="https://nuextract.ai/">
<img src="numind.svg" width="400" height="400"/>
</a>


🖥️ <a href="https://nuextract.ai/">API / Platform</a>&nbsp&nbsp | &nbsp&nbsp🗣️ <a href="https://discord.gg/3tsEtJNCDe">Discord</a>&nbsp&nbsp | &nbsp&nbsp🔗 <a href="https://github.com/numindai/NuMarkdown">GitHub</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking">Demo</a>

---

Reasoning comes to OCR 🧠✨📄🤘

NuMarkdown-8B-Thinking is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file.
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 on synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward.

Try it out in the 🤗 space!

Results

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):

| Rank | Model | μ | σ | μ − 3σ | | ---- | --------------------------------------- | ----- | ---- | ------ | | 🥇 1 | gemini-flash-reasoning | 26.75 | 0.80 | 24.35 | | 🥈 2 | NuMarkdown-reasoning | 26.10 | 0.79 | 23.72 | | 🥉 3 | NuMarkdown-reasoning-w/o\_grpo | 25.32 | 0.80 | 22.93 | | 4 | OCRFlux-3B | 24.63 | 0.80 | 22.22 | | 5 | gpt-4o | 24.48 | 0.80 | 22.08 | | 6 | gemini-flash-w/o\_reasoning | 24.11 | 0.79 | 21.74 | | 7 | RolmoOCR | 23.53 | 0.82 | 21.07 |

*We plan to realease a markdown arena, similar to llmArena, for complex document-to-markdown tasks to provide a tool to evaluate different solutions.*

Win/Draw/Lose-rate against others models (image-only):

Training

1. SFT: Single epoch supervised fine-tuning on synthetic reasoning traces generated from public PDFs.
2. RL (GRPO): RL phase using a layout-centric reward with difficult image examples.

Example:

``<think> 1. Analyze the overall structure: The document consists of two main sections, each containing a header, a set of bullet points, a title, a table, and a footer. The layout is consistent within each section but different between the two.

2. Handle the first section header and bullet points: - The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading. - The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading. - Below the header, there are four bullet points. These are standard list items. I will use Markdown's unordered list syntax (- `).

3. Process the first section's main content - Table 1:
- Identify table structure: This is a complex table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- Determine columns: There are 5 columns.
- Handle merged cells:
- "Llengua Catalana" spans two rows.
- "Llengua Castellana" spans three rows.
- "Anglès" spans two rows.
- Populate table data: Transcribe all text, including multi-line content within cells (e.g., "Babulinka Books\nEditorialCol·lecció: Pettes\nJoies per a Grans Lectors.\n2013").
- Markdown table creation: Use standard Markdown table syntax, ensuring correct alignment and handling of multi-line content within cells.

4. Handle the first section's footer:
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 1 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.

5. Handle the second section header and bullet points:
- The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading.
- The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading.
- Below the header, there are no bullet points, but there is a table.

6. Process the second section's main content - Table 2:
- Identify table structure: This is a simpler table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- Determine columns: There are 5 columns.
- Populate table data: Transcribe all text, including multi-line content within cells (e.g., "Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books\nES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE").
- Markdown table creation: Use standard Markdown table syntax.

7. Handle the second section's footer:
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 2 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.

8. Final review: Check for any missed text, incorrect formatting, or issues with table alignment. Ensure all original content is present and accurately represented in GitHub-Flavored Markdown. The image placeholders are not needed as there are no images in the document.
</think>
<answer>

Generalitat de Catalunya

Departament d'Educació

Institut Gal·lecs

Curs 2021-22

Els llibres de color blau indiquen que es manté respecte al curs anterior.

Els llibres de color groc indiquen que es tracta d'un canvi per a aquest curs.

Els llibres de color vermell indiquen que no s'han de comprar perquè van a càrrec del centre.

Matèries sense llibre: Dossiers, llicències i el Kit de tecnologia s'hauran de pagar i de recollir a través de l'AMPA a partir de setembre.

1 ESO

| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| Llengua Catalana | Punt Volat | | Castellnou (Didacta +) | 9788417803124 |
| | Duna, Diari d'un estiu. | Muriel Villanueva | Babulinka Books EditorialCol·lecció: Pettes Joies per a Grans Lectors. 2013 | 9788494159077 |
| | El nen que xatejava amb Jack Sparrow. | Francesc Puigpelat | Bromera Col·lecció: L'Elefant. 2015 | 9788490264072 |
| Llengua Castellana | Proyecto Asterisco | | Castellnou (Didacta +) | 9788417803186 |
| | Manzanas rojas | Luis Matilla | Ed. Anaya | 978846673989 |
| | Fàbulas de Esopo | Jerry Pinkney | Vicens Vives | 978843671648 |
| Anglès | Think Ahead ESO 1. Student's book. Think Ahead ESO 1. Workbook (cat).