DeepSeek-OCR
DeepSeek-OCR is DeepSeek's 3B mixture-of-experts model for documents. LibreYOLO runs DeepSeek-OCR and DeepSeek-OCR-2 on the ocr task through a vendored PyTorch port: text lines with boxes, layout blocks, or the whole page as markdown.
- 작업
- ocr
- 크기
- 1, 2 at 1024 px
- 설치
pip install "libreyolo[vlm]"- 지원 티어
- 별도 티어, v1.8.0부터 지원. 자체 팩토리와 계약을 갖춘 별도의 제품 영역입니다.
- 라이선스
- 코드 MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2), 가중치 MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2). 상업적 사용
Install
DeepSeek-OCR belongs to LibreYOLO's VLM tier and needs the vlm extra.
pip install "libreyolo[vlm]"Predict
Weights download on first use from byte-identical LibreYOLO mirrors,
LibreYOLO/LibreDeepSeekOCR1 and LibreYOLO/LibreDeepSeekOCR2, pinned to a
revision. The architecture is a PyTorch port of the release's inference path;
no remote code runs.
from libreyolo import LibreVLM model = LibreVLM("deepseek-ocr") # weights download on first useresult = model.predict("page.png") # a scanned or rendered page for text, quad in zip(result.ocr.texts, result.ocr.polygons): print(text, quad.tolist()) # one region per text linefrom libreyolo import LibreVLM model = LibreVLM("deepseek-ocr", prompt="markdown")result = model.predict("page.png") print(result.ocr.markdown) # the whole page as markdownprint(result.ocr.labels) # layout category per blockfrom libreyolo import LibreVLM model = LibreVLM("deepseek-ocr-2") # resolution "gundam" or "base"result = model.predict("page.png")print(result.ocr.texts)The family loads through LibreVLM(), or the LibreDeepSeekOCR class. The
prompt setting (constructor or set_prompt()) picks what lands in
Results.ocr:
prompt | Results.ocr |
|---|---|
"ocr" (default) | one region per text line, labels all text, markdown empty |
"markdown" | one region per layout block, the layout category in labels, the page in markdown |
"free" | no regions, the page text in markdown |
| any other string | whatever grounding the model emits, plus markdown |
Boxes come on the model's 0 to 999 grid and are scaled to the original image
as axis-aligned 4-point quads, sorted top to bottom then left to right. A
generative model emits no score, so conf and det_conf are a constant 1.0.
model.chat("page.png", "Parse the figure.") returns raw generated text for
any prompt. Decoding is greedy, up to 8192 new tokens, with
no_repeat_ngram_size=20 as in the release.
Variants
| Name | Model | Resolutions | License |
|---|---|---|---|
deepseek-ocr | DeepSeek-OCR (size 1) | tiny (512), small (640), base (1024), large (1280), gundam (default) | MIT |
deepseek-ocr-2 | DeepSeek-OCR-2 (size 2) | base (1024), gundam (default) | Apache-2.0 |
gundam combines a 1024 px global view with local crops: 2 to 9 crops of
640 px on DeepSeek-OCR, up to 6 crops of 768 px on DeepSeek-OCR-2. DeepSeek-OCR-2
keeps the decoder and the SAM stage and replaces CLIP with a Qwen2 encoder;
prompts and outputs are the same.
CUDA runs the bf16 weights under torch.autocast, as the release does (fp16
on GPUs without bf16). CPU and MPS run float32 with eager attention, about
13 GB of memory; MPS has not been run on hardware. EXIF orientation is not
applied. On an RTX 3090 the port reproduces the release token for token on
17 cases for DeepSeek-OCR and 14 for DeepSeek-OCR-2. Benchmark numbers are in
the release papers and are not reproduced by LibreYOLO.
Validate
val() runs the shared OCR validator and reports detection hmean,
end-to-end F1 and 1-NED.
from libreyolo import LibreVLM model = LibreVLM("deepseek-ocr")metrics = model.val(data="ocr_dataset/") # det hmean, end-to-end F1, 1-NEDExport
Inference only: train() and export() raise.
Licensing
내려받는 특정 가중치의 Hugging Face 저장소에서 라이선스를 확인하십시오. LibreYOLO 조직의 모든 체크포인트에는 라이선스가 있으며 한 계열 안에서도 항상 같지는 않습니다. 해당 저장소가 신뢰할 수 있는 기준입니다. 아래 요약은 이 페이지를 마지막으로 검증했을 때 적용된 내용을 설명합니다.
관련 라이선스에 관한 설명이며 법률 자문이 아닙니다. 상업적으로 중요한 사안이라면 라이선스를 직접 읽고 별도의 법률 자문을 받으십시오.
- 원작
- DeepSeek-OCR, DeepSeek
- 업스트림 라이선스
- MIT (size 1); Apache-2.0 (size 2)
- LibreYOLO 코드
- MIT
- 가중치
- MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2), huggingface.co/LibreYOLO에 다시 게시됨
- 해석
- This family covers two releases with different permissive licences. Size "1" is DeepSeek-OCR (paper arXiv:2510.18234), released under MIT: commercial and closed-source use is allowed if you keep the copyright and license notice. Size "2" is DeepSeek-OCR 2 (paper arXiv:2601.20552, 'Visual Causal Flow'), released under Apache-2.0: commercial use is allowed if you keep the license text and notices, and it grants a patent license. LibreYOLO ports the inference path of the Hugging Face releases (deepseek-ai/DeepSeek-OCR at 9f30c71f441d010e5429c532364a86705536c53a and deepseek-ai/DeepSeek-OCR-2 at aaa02f3811945a91062062994c5c4a3f4c0af2b0) and runs none of their remote code; ported parts keep their lineage, Apache-2.0 for the DeepSeek-V2 decoder, the Transformers Llama and Qwen2 attention, the detectron2-derived SAM encoder and the FastChat template, MIT for the ConvNeXt LayerNorm (libreyolo/models/deepseekocr/NOTICE), while the adapter is MIT. Weights are byte-identical, ungated mirrors at LibreYOLO/LibreDeepSeekOCR1 and LibreYOLO/LibreDeepSeekOCR2 with no learned parameter changed.
DeepSeek-OCR is MIT and DeepSeek-OCR-2 is Apache-2.0, code and weights, both by DeepSeek. Both allow commercial use. The weights are byte-identical, ungated mirrors.
Citation
@article{wei2025deepseek,
title={DeepSeek-OCR: Contexts Optical Compression},
author={Wei, Haoran and Sun, Yaofeng and Li, Yukun},
journal={arXiv preprint arXiv:2510.18234},
year={2025}
}huggingface.co/deepseek-ai/DeepSeek-OCR#citation에 있는 저자의 인용 블록에서 복사했습니다.