---
title: DeepSeek-OCR
canonical_url: "https://www.modelscope.ai/models/AMD/DeepSeek-OCR"
md_url: "https://www.modelscope.ai/models/AMD/DeepSeek-OCR.md"
repository: AMD/DeepSeek-OCR
last_updated: 2026-03-05
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseek_vl_v2
architectures:
  - DeepseekOCRForCausalLM
parameters: 3.3B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
language:
  - multilingual
downloads: 155
stars: 0
tags:
  - deepseek
  - vision-language
  - ocr
  - custom_code
---

# DeepSeek-OCR

> DeepSeek-OCR - An open-source model by AMD on ModelScope. Model Architecture: DeepSeek-OCR Input: Image/Text Output: Text Supported Hardware Microarchitecture: AMD MI300/MI350/MI355 ROCm: 7.1.0 PyTorch: 2.8.0 Transformers: 4.57.3 Operating System(s): Linux

AMD/DeepSeek-OCR is a 3.3B-parameter image-text-to-text model on ModelScope. licensed under mit.

- **Repository**: AMD/DeepSeek-OCR
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 3.3B
- **Tags**: deepseek, vision-language, ocr, custom_code
- **Downloads**: 155
- **Stars**: 0
- **Last updated**: 2026-03-05

Source: https://www.modelscope.ai/models/AMD/DeepSeek-OCR

---

# Model Overview

- **Model Architecture:** DeepSeek-OCR
  - **Input:** Image/Text
  - **Output:** Text
- **Supported Hardware Microarchitecture:** AMD MI300/MI350/MI355
- **ROCm**: 7.1.0
- **PyTorch**: 2.8.0
- **Transformers**: 4.57.3
- **Operating System(s):** Linux

# Model Details
The official version of [deepseek-ai/DeepSeek-OCR](https://huggingface.co/deepseek-ai/DeepSeek-OCR) restricts the transformers library to version 4.46.3 and has not been updated to support the latest release. In this community edition, the `modeling_deepseekocr.py` file has been updated for improved usability, and `modeling_deepseekv2.py` has been removed in favor of using the DeepSeekV2 model definitions provided by the transformers library, eliminating the need for downgrading transformers. 

This model can be quantized by using [AMD-Quark](https://quark.docs.amd.com/latest/index.html), and the resulting quantized model is available at [amd/DeepSeek-OCR-MXFP4](https://huggingface.co/amd/DeepSeek-OCR-MXFP4).


# Usage
```python
from transformers import AutoModel, AutoTokenizer
import torch
import os
os.environ["HIP_VISIBLE_DEVICES"] = '0'
model_name = 'amd/DeepSeek-OCR'

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'

# infer(self, tokenizer, prompt='', image_file='', output_path = ' ', base_size = 1024, image_size = 640, crop_mode = True, test_compress = False, save_results = False):

# Tiny: base_size = 512, image_size = 512, crop_mode = False
# Small: base_size = 640, image_size = 640, crop_mode = False
# Base: base_size = 1024, image_size = 1024, crop_mode = False
# Large: base_size = 1280, image_size = 1280, crop_mode = False

# Gundam: base_size = 1024, image_size = 640, crop_mode = True

res = model.infer(tokenizer, prompt=prompt, image_file=image_file, output_path = output_path, base_size = 1024, image_size = 640, crop_mode=True, save_results = True, test_compress = True)
```

# License
Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.