unsloth/DeepSeek-OCR-2

Read our Guide How to: Run & Fine-tune DeepSeek-OCR 2.

✨ Read our DeepSeek-OCR 2 Guide here!

• Fine-tune DeepSeek-OCR 2 for free using our Google Colab notebook
• View the rest of our notebooks in our docs here.

---

---

🌟 Github | 📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link |

DeepSeek-OCR 2: Visual Causal Flow

Explore more human-like visual encoding.

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8：

torch==2.6.0
transformers==4.46.3
tokenizers==0.20.3
einops
addict 
easydict
pip install flash-attn==2.7.3 --no-build-isolation

from transformers import AutoModel, AutoTokenizer
import torch
import os
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
model_name = 'deepseek-ai/DeepSeek-OCR-2'

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(model_name, _attn_implementation='flash_attention_2', trust_remote_code=True, use_safetensors=True)
model = model.eval().cuda().to(torch.bfloat16)

# prompt = "<image>\nFree OCR. "
prompt = "<image>\n<|grounding|>Convert the document to markdown. "
image_file = 'your_image.jpg'
output_path = 'your/output/dir'


res = model.infer(tokenizer, prompt=prompt, image_file=image_file, output_path = output_path, base_size = 1024, image_size = 768, crop_mode=True, save_results = True)

vLLM

Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.

Support-Modes

• Dynamic resolution
  • Default: (0-6)×768×768 + 1×1024×1024 — (0-6)×144 + 256 visual tokens ✅

Prompts examples

# document: <image>\n<|grounding|>Convert the document to markdown.
# other image: <image>\n<|grounding|>OCR this image.
# without layouts: <image>\nFree OCR.
# figures in document: <image>\nParse the figure.
# general: <image>\nDescribe this image in detail.
# rec: <image>\nLocate <|ref|>xxxx<|/ref|> in the image.

Acknowledgement

We would like to thank DeepSeek-OCR, Vary, GOT-OCR2.0, MinerU, PaddleOCR for their valuable models and ideas.

We also appreciate the benchmark OmniDocBench.

Citation

coming soon~