---
license: mit
library_name: transformers
tags:
- dots_ocr
- image-to-text
- ocr
- document-parse
- layout
- table
- formula
- quantized
- 4-bit
base_model: rednote-hilab/dots.ocr
---

# dots.ocr-4bit: A 4-bit Quantized Version

This repository contains a 4-bit quantized version of the powerful `dots.ocr` model by the **Rednote HiLab**. The quantization was performed using `bitsandbytes` (NF4 precision), providing significant memory and speed improvements with minimal performance loss, making this state-of-the-art model accessible on consumer-grade GPUs.

This work is entirely a derivative of the original model. All credit for the model architecture, training, and groundbreaking research goes to the original authors. A huge thank you to them for open-sourcing their work.

*   **Original Model:** [rednote-hilab/dots.ocr](https://huggingface.co/rednote-hilab/dots.ocr)
*   **Original GitHub:** [https://github.com/rednote-hilab/dots.ocr](https://github.com/rednote-hilab/dots.ocr)
*   **Live Demo (Original):** [https://dotsocr.xiaohongshu.com](https://dotsocr.xiaohongshu.com)

## Model Description (from original authors)
> **dots.ocr** is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance.

## How to Use This 4-bit Version

First, ensure you have the necessary dependencies installed. Because this model uses custom code, you **must** clone the original repository and install it.

```bash
# It's recommended to clone the original repo to get all utility scripts
git clone https://github.com/rednote-hilab/dots.ocr.git
cd dots.ocr

# Install the custom code and dependencies
pip install -e .
pip install torch transformers accelerate bitsandbytes peft sentencepiece
```

You can then use the 4-bit model with the following Python script. Note the inclusion of generation parameters (repetition_penalty, do_sample, etc.), which are recommended to prevent potential looping with the quantized model.

```python
import torch
from transformers import AutoModelForCausalLM, AutoProcessor
from PIL import Image
import os
import traceback

# This assumes the utility script is available in your environment
from qwen_vl_utils import process_vision_info

MODEL_ID = "helizac/dots.ocr-4bit"

print("Loading 4-bit quantized model from the Hub...")
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    device_map="auto",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16, 
)
processor = AutoProcessor.from_pretrained(
    MODEL_ID,
    trust_remote_code=True
)
print("✅ Model and processor loaded successfully!")

# --- Inference ---
image_path = "demo/demo_image1.jpg" # Make sure you have this image
image = Image.open(image_path)
prompt_text = "Parse all layout info, both detection and recognition"

messages = [
    {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": prompt_text}]}
]

# Prepare inputs using the official workflow
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, _ = process_vision_info(messages)
inputs = processor(
    text=[text], images=image_inputs, padding=True, return_tensors="pt"
).to(model.device)

# Generate with parameters to prevent looping with the 4-bit model
generated_ids = model.generate(
    **inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.9, repetition_penalty=1.15
)

# Trim and decode output
generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

print("\n--- Inference Result ---")
print(output_text)
```

## License

This model is released under the MIT License, same as the original model.