Hugging Face's logo

RhapsodyAI
/
MiniCPM-V-Embedding-preview

Feature Extraction
Transformers
PyTorch
English
minicpmv
information retrieval
embedding model
visual information retrieval
custom_code
Model card Files Community
2
MiniCPM-V-Embedding-preview / README.md
bokesyo's picture
bokesyo
Create README.md
80c6598 verified
preview code
|
raw
history blame
746 Bytes
metadata
language:
  - en

MiniCPM-Visual-Embedding: An OCR-free Visual Document Embedding Model Based on MiniCPM-V-2.0

With MiniCPM-Visual-Embedding, it is possible to directly build knowledge base with raw PDF/Book/Document without any OCR technique nor OCR pipeline. The model only takes images as document-side inputs and produce vectors representing document pages.

Github Repo

Memex Archtechture

News

  • 2024-06-27: We released our first visual embedding model on huggingface.

  • 2024-05-08: We released our training code (full-parameter tuning with GradCache and DeepSpeed, supports large batch size across multiple GPUs with zero-stage1) and eval code.