DeepSeek-OCR model published on Hugging Face
DeepSeek published DeepSeek-OCR, a vision-language model specialised for optical character recognition, on Hugging Face under the MIT license. The repository includes evaluation results and is deployable on SageMaker.
PUBLISHED2025-10-17
OBSERVED2026-08-11
AGE10mo
SOURCES1
- Repository created 2025-10-17, last modified 2025-11-04
- Pipeline: image-text-to-text, library: transformers
- Tags: deepseek_vl_v2, safetensors, vision-language, ocr, custom_code, multilingual, eval-results, endpoints_compatible
- License: MIT
- Reference: arxiv:2510.18234
- Deployment: SageMaker-compatible
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.