---
title: PDF-Extract-Kit-1.0
canonical_url: "https://www.modelscope.ai/models/OpenDataLab/PDF-Extract-Kit-1.0"
md_url: "https://www.modelscope.ai/models/OpenDataLab/PDF-Extract-Kit-1.0.md"
repository: OpenDataLab/PDF-Extract-Kit-1.0
last_updated: 2026-06-17
pipeline_tag: ocr-detection
tasks:
  - ocr-detection
parameters: 1.6B
tensor_type:
  - I64
  - F32
  - BF16
library_name:
  - safetensors
  - onnx
  - pytorch
frameworks:
  - Pytorch
downloads: 1540
stars: 0
---

# PDF-Extract-Kit-1.0

> PDF-Extract-Kit-1.0 - An open-source model by OpenDataLab on ModelScope. PDF-Extract-Kit-1.0 Model Repository

- **Repository**: OpenDataLab/PDF-Extract-Kit-1.0
- **Tasks**: ocr-detection
- **Parameters**: 1.6B
- **Downloads**: 1540
- **Stars**: 0
- **Last updated**: 2026-06-17

Source: https://www.modelscope.ai/models/OpenDataLab/PDF-Extract-Kit-1.0

---

## PDF-Extract-Kit-1.0 Model Repository

This is the model repository corresponding to version 1.0 of PDF-Extract-Kit. For usage, please refer to:

- [PDF-Extract-Kit-1.0](https://github.com/opendatalab/PDF-Extract-Kit)
- [MinerU](https://github.com/opendatalab/MinerU)


### SDK Download

```bash
# First, install the ModelScope library using pip:
pip install modelscope
```

```python
# Use the following Python code to download the model using the ModelScope SDK:
from modelscope import snapshot_download
model_dir = snapshot_download('opendatalab/PDF-Extract-Kit-1.0')
```

### Git Download
Alternatively, you can use Git to clone the model repository from ModelScope:

```bash
git clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit-1.0.git
```

---
license: apache-2.0
---