Skip to content

Deepseek-OCR or PaddleOCR-VL fine-tune ? #7

Description

@Glider95

Hello Numind team,

First of all, I would like to highlight that the work done with NuExtract really make sense from my point of view.
Being able to have a consistent schema for each document extraction is really important when processing millions of documents, particularly for industry use-cases.

With the recent release of Deepseek-OCR https://huggingface.co/deepseek-ai/DeepSeek-OCR and their new encoder compression, can we expected a similar fine-tune from you?
As well https://huggingface.co/PaddlePaddle/PaddleOCR-VL is an interesting one to consider.

Cheers

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions