deepseek-ai / deepseek-ai/DeepSeek-OCR-2

Any plans to open-source the training code

Open
#22 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3.4k
Forks
306
PR merge metrics
No merged PRs in 30d

Description

Hello,
I've recently been looking into applying the DeepSeek-OCR 2.0 approach to train a model based on a pre-trained embedding model. I noticed in the paper that the training process is divided into three stages.
Could you please let me know if there are any plans to open-source the code for this part of the training?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.