---
title: olmOCR-7B-0225-preview
canonical_url: "https://www.modelscope.cn/models/allenai/olmOCR-7B-0225-preview"
md_url: "https://www.modelscope.cn/models/allenai/olmOCR-7B-0225-preview.md"
repository: allenai/olmOCR-7B-0225-preview
last_updated: 2025-08-20
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_vl
architectures:
  - Qwen2VLForConditionalGeneration
base_model:
  - Qwen/Qwen2-VL-7B-Instruct
base_model_relation: finetune
parameters: 8.3B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 82762
stars: 70
---

# olmOCR-7B-0225-preview

> olmOCR-7B-0225-preview - allenai 在 ModelScope 开源的模型。olmOCR-7B-0225-preview

allenai/olmOCR-7B-0225-preview 是 ModelScope 魔搭社区上的 8.3B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen2-VL-7B-Instruct 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: allenai/olmOCR-7B-0225-preview
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 8.3B
- **Base model**: Qwen/Qwen2-VL-7B-Instruct
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 82762
- **Stars**: 70
- **Last updated**: 2025-08-20

Source: https://www.modelscope.cn/models/allenai/olmOCR-7B-0225-preview

---

<img alt="olmOCR Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmocr/olmocr.png" width="242px" style="margin-left:'auto' margin-right:'auto' display:'block'">

# olmOCR-7B-0225-preview

This is a preview release of the olmOCR model that's fine tuned from Qwen2-VL-7B-Instruct using the 
[olmOCR-mix-0225](https://huggingface.co/datasets/allenai/olmOCR-mix-0225) dataset.

Quick links:
- 📃 [Paper](https://olmocr.allenai.org/papers/olmocr.pdf)
- 🤗 [Dataset](https://huggingface.co/datasets/allenai/olmOCR-mix-0225)
- 🛠️ [Code](https://github.com/allenai/olmocr)
- 🎮 [Demo](https://olmocr.allenai.org/)

The best way to use this model is via the [olmOCR toolkit](https://github.com/allenai/olmocr).
The toolkit comes with an efficient inference setup via sglang that can handle millions of documents
at scale.

## Usage

This model expects as input a single document image, rendered such that the longest dimension is 1024 pixels.

The prompt must then contain the additional metadata from the document, and the easiest way to generate this
is to use the methods provided by the [olmOCR toolkit](https://github.com/allenai/olmocr).


## Manual Prompting

If you want to prompt this model manually instead of using the [olmOCR toolkit](https://github.com/allenai/olmocr), please see the code below.

In normal usage, the olmOCR toolkit builds the prompt by rendering the PDF page, and
extracting relevant text blocks and image metadata. To duplicate that you will need to

```bash
pip install olmocr
```

and then run the following sample code.


```python
import torch
import base64
import urllib.request

from io import BytesIO
from PIL import Image
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration

from olmocr.data.renderpdf import render_pdf_to_base64png
from olmocr.prompts import build_finetuning_prompt
from olmocr.prompts.anchor import get_anchor_text

# Initialize the model
model = Qwen2VLForConditionalGeneration.from_pretrained("allenai/olmOCR-7B-0225-preview", torch_dtype=torch.bfloat16).eval()
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

# Grab a sample PDF
urllib.request.urlretrieve("https://molmo.allenai.org/paper.pdf", "./paper.pdf")

# Render page 1 to an image
image_base64 = render_pdf_to_base64png("./paper.pdf", 1, target_longest_image_dim=1024)

# Build the prompt, using document metadata
anchor_text = get_anchor_text("./paper.pdf", 1, pdf_engine="pdfreport", target_length=4000)
prompt = build_finetuning_prompt(anchor_text)

# Build the full prompt
messages = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": prompt},
                    {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_base64}"}},
                ],
            }
        ]

# Apply the chat template and processor
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
main_image = Image.open(BytesIO(base64.b64decode(image_base64)))

inputs = processor(
    text=[text],
    images=[main_image],
    padding=True,
    return_tensors="pt",
)
inputs = {key: value.to(device) for (key, value) in inputs.items()}


# Generate the output
output = model.generate(
            **inputs,
            temperature=0.8,
            max_new_tokens=50,
            num_return_sequences=1,
            do_sample=True,
        )

# Decode the output
prompt_length = inputs["input_ids"].shape[1]
new_tokens = output[:, prompt_length:]
text_output = processor.tokenizer.batch_decode(
    new_tokens, skip_special_tokens=True
)

print(text_output)
# ['{"primary_language":"en","is_rotation_valid":true,"rotation_correction":0,"is_table":false,"is_diagram":false,"natural_text":"Molmo and PixMo:\\nOpen Weights and Open Data\\nfor State-of-the']
```

## License and use

olmOCR is licensed under the Apache 2.0 license.
olmOCR is intended for research and educational use.
For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).