Ver como markdown

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.

Tarefas
ocr
Tamanhos
1, 2 at 1024 px
Instalação
pip install "libreyolo[vlm]"
Nível de suporte
Nível irmão, desde a v1.8.0. Uma superfície de produto separada, com sua própria fábrica e seu próprio contrato.
Origem
DeepSeek-OCR por DeepSeek, MIT (size 1); Apache-2.0 (size 2). Artigo, código-fonte
Licenças
Código MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2), pesos MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2). Uso comercial

Install

DeepSeek-OCR belongs to LibreYOLO's VLM tier and needs the vlm extra.

bash
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.

Python
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 line
Markdown
from 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 block
DeepSeek-OCR-2
from 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:

promptResults.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 stringwhatever 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

NameModelResolutionsLicense
deepseek-ocrDeepSeek-OCR (size 1)tiny (512), small (640), base (1024), large (1280), gundam (default)MIT
deepseek-ocr-2DeepSeek-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.

Python
from libreyolo import LibreVLM model = LibreVLM("deepseek-ocr")metrics = model.val(data="ocr_dataset/")   # det hmean, end-to-end F1, 1-NED

Export

Inference only: train() and export() raise.

Licensing

Confira a licença no repositório do Hugging Face correspondente aos pesos que você baixar. Cada checkpoint na organização LibreYOLO tem uma licença, e ela nem sempre é a mesma em toda a família. Esse repositório é a fonte oficial. O resumo abaixo descreve o que se aplicava na última verificação desta página.

Esta é uma descrição das licenças envolvidas, não uma orientação jurídica. Se a resposta tiver importância comercial, leia as licenças e procure sua própria assessoria.

Trabalho original
DeepSeek-OCR, DeepSeek
Licença original
MIT (size 1); Apache-2.0 (size 2)
Código do LibreYOLO
MIT
Pesos
MIT (DeepSeek-OCR); Apache-2.0 (DeepSeek-OCR 2), republicado em huggingface.co/LibreYOLO
Interpretação
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}
}

Copiado do bloco de citação dos autores em huggingface.co/deepseek-ai/DeepSeek-OCR#citation.

Verificado com o LibreYOLO v1.8.0. As tabelas de suporte, os checkpoints e os números de benchmark desta página são gerados a partir da biblioteca lançada e dos pesos publicados, não escritos à mão.