NuMarkdown-8B-Thinking GGUF Models
Model Generation Details
This model was generated using llama.cpp at commit cd6983d5.
Quantization Beyond the IMatrix
I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp
While this does increase model file size, it significantly improves precision for a given quantization level.
I'd love your feedback—have you tried this? How does it perform for you?
Click here to get info on choosing the right GGUF model format
🖥️ API / Platform | 🗣️ Discord | 🔗 GitHub | 🤗 Demo
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
-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
- SFT: Single epoch supervised fine-tuning on synthetic reasoning traces generated from public PDFs.
- 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<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-Thinking --trust_remote_code --limit-mm-per-prompt image=1
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("image.png")
data_url = f"data:image/jpeg;base64,{base64_image}"
chat_response = client.chat.completions.create(
model="numind/NuMarkdown-8B-Thinking",
temperature=0.7,
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {"url": data_url},
"min_pixels": 100 * 28 * 28,
"max_pixels": 5000 * 28 * 28,
},
],
},
]
)
result = chat_response.choices[0].message.content
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
🤗 Transformers:
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,
min_pixels=100*28*28, max_pixels=5000*28*28
)
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("image.png").convert("RGB")
messages = [{
"role": "user",
"content": [
{"type": "image"},
],
}]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_input = processor(text=prompt, images=[img], return_tensors="pt").to(model.device)
with torch.no_grad():
model_output = model.generate(**model_input, temperature = 0.7, max_new_tokens=5000)
result = processor.decode(model_output[0])
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
🚀 If you find these models useful
Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:
The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder
💬 How to test:
Choose an AI assistant type:
TurboLLM(GPT-4.1-mini)HugLLM(Hugginface Open-source models)TestLLM(Experimental CPU-only)
What I’m Testing
I’m pushing the limits of small open-source models for AI network monitoring, specifically:
- Function calling against live network services
- How small can a model go while still handling:
- Automated Nmap security scans
- Quantum-readiness checks
- Network Monitoring tasks
🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):
- ✅ Zero-configuration setup
- ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
- 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!
Other Assistants
🟢 TurboLLM – Uses gpt-4.1-mini :
- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
- Create custom cmd processors to run .net code on Quantum Network Monitor Agents
- Real-time network diagnostics and monitoring
- Security Audits
- Penetration testing (Nmap/Metasploit)
🔵 HugLLM – Latest Open-source models:
- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
💡 Example commands you could test:
"Give me info on my websites SSL certificate""Check if my server is using quantum safe encyption for communication""Run a comprehensive security audit on my server"- '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!
Final Word
I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.
If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
I'm also open to job opportunities or sponsorship.
Thank you! 😊
- Downloads last month
- 15,071