README.md

metadata

license: mit
base_model: Qwen/Qwen2.5-VL-7B
tags:
  - vision-language
  - document-to-markdown
  - reinforcement-learning
  - grpo
  - qwen2.5
  - markdown
model_name: NuMarkdown-reasoning
library_name: transformers
pipeline_tag: text-generation

🖥️ API / Platform   |   🗣️ Discord

---

NuMarkdown-reasoning 📄

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.

(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.

Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 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 (10K input/output pairs).
2. RL (GRPO): RL phase using a layout-centric reward (5K 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<br>EditorialCol·lecció: Pettes<br>Joies per a Grans Lectors.<br>2013 | 9788494159077 |
| | El nen que xatejava amb Jack Sparrow. | Francesc Puigpelat | Bromera<br>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.<br>Think Ahead ESO 1. Workbook (cat). | | Burlington Books<br>Burlington Books | 9788925300662<br>9789925300686 |

Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 1 de 2

### Generalitat de Catalunya
### Departament d'Educació
### Institut Gal·lecs

### Curs 2021-22

| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| FRANCÈS | Nouvelle Génération A1-A2 | | Santillana | 9788490494745 |
| CIÈNCIES EXPERIMENTALS | Science Bits<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | 9788412213485 (llicència digital) |
| MATEMÀTIQUES | Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | |
| TECNOLOGIA | Tecnologia 1 ESO | TEIDE | | 9788430783175 |
| VISUAL I PLÀSTICA | SENSE LLIBRE-KIT DE MATERIAL | | | |
| CIÈNCIES SOCIALS | SENSE LLIBRE-dossier | | | |

Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 2 de 2
</answer>

Quick start:

vLLM:

vllm serve numind/NuMarkdown-8B-reasoning --trust_remote_code --limit-mm-per-prompt image=1

import json
from openai import OpenAI
import base64

openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

def encode_image(image_path):
    """
    Encode the image file to base64 string
    """
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

base64_image = encode_image("invoice.png")

chat_response = client.chat.completions.create(
    model="numind/NuMarkdown-8B-reasoning",
    temperature=0.8,
    messages=[
        {
            "role": "user", 
            "content": [
                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}},
            ],
        },
    ]
)

reasoning = chat_response.choices[0].message.content.split("<thining>")[1].split("</thining>")[0]
answer  = chat_response.choices[0].message.content.split("<answer>")[1].split("</answer>")[0]

🤗 Transformers:

from __future__ import annotations

import torch
from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration

model_id = "numind/NuMarkdown-8B-reasoning"       

processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,       
)

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
    trust_remote_code=True,
)

img = Image.open("invoice.png").convert("RGB")
messages = [{
    "role": "user",
    "content": [
        {"type": "image"},
    ],
}]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
enc = processor(text=prompt, images=[img], return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(**enc, max_new_tokens=5000)

print(processor.decode(out[0].split("<answer>")[1].split("</answer>")[0], skip_special_tokens=True))