deepseek-ai / deepseek-ai/DeepSeek-OCR

Adding a special tag for LaTex formulas

Open
#219 10 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
23.9k
Forks
2.2k
PR merge metrics
No merged PRs in 30d

Description

I am prompting the model using: `\n<|grounding|>Convert the document to markdown.`
Anyway, the generated text is invalid because of the sequence `\(` not being a valid escape sequence.
The real reason is that there are no fences for the generated LaTex syntax.
Furthermore, markdown readers need the LaTeX syntax to be between `$$ ... $$` to correctly parsing the document.

The text causing the error is:
```
\(\mathrm{A} > 50\%\)
```

Would it be possible to add a special tag (i.e. <|math|> <|/math|>) to fence the LaTeX syntax?

Thanks

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.