Public KG record
DeepSeek-OCR
Recorded overview
Github Model Download Paper Link Arxiv Paper Link Explore the boundaries of visual-text compression.
Extract text from images, scans, or PDFs while preserving layout, tables, and document structure.
Recorded details
- Benchmarks: olmOCR-Bench：76.0
- Benchmarks: olmOCR-Bench得分76.0
- Capabilities: feature extraction / embeddings
- Capabilities: 作为jina-ocr-v1的后训练基础模型
- Integrations: transformers integration
- Integrations: safetensors integration
- Languages: multilingual
- License: mit
Evidence coverage
The KG currently records 13 known information dimensions and has 6 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- DeepSeek — develops
- jina-ocr-v1 — based on