Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek OCR

github.com

Post reply on HN
Print view View original

31–40 of 252 posts

Re: DeepSeek OCR

#31

Post by looobay »

krackers wrote: post #24
looobay wrote: post #14

Earlier quoted context omitted.

Vision tokens are a good compression medium because with one vision token you have one vector of N elements, but with textual tokens you have M vectors of N elements, because one vision token represent multiple pixels (and possibly multiple words). This is why its a good compression medium for compute. It will never be as precise as textual tokens but it can be really good as they show in the paper.

>with one vision token you have one vector of N elements, but with textual tokens you have M vectors of N elements Each vision token represents a 16x16 patch, but to fully cover a word you might need multiple vision tokens. So assuming that the embedding size of the vision token and text token is the same `d` (which I think has to be the case for multimodal models), then wouldn't the fair comparison be `x * d` elemen…

You should read the 6th page of the paper (and page 5 for architecture breakdown), they show that they are compressing the vision tokens with convolution to keep a strong semantic understanding and keep a small amount of tokens.

But I think it's still experimentall.

Re: DeepSeek OCR

#32

Post by gudzpoz »

x______________ wrote: post #23

>先天下之忧而忧 How is this an example of a prompt? Google translated this to "Worry about the world first" while Bing says "Worry before the worries of the world." Can anyone shed some light on this saying or why it's in the article?

This clause is usually used together with the next sentence in the original poem:

> 先天下之忧而忧，后天下之乐而乐

> (put the world's worries before yours, and put your happiness after the world's) > edit: this translation is wrong, and raincole has a definitely better translation

Since the model is a language model, they probably use this to demonstrate the model's language capabilities – the model should be able to complete the whole sentence pair. The paper also mentions this:

> To ensure the model’s language capabilities, we introduced 10% of in-house text-only pretrain data.

So I believe it is just a text-only demonstration.

Re: DeepSeek OCR

#33

Post by ozim »

Etheryte wrote: post #22
ozim wrote: post #4

Earlier quoted context omitted.

Any vision model is better than commercial OCR software.

I'm not really sure if that's an accurate summary of the state of the art, [0] is a better overview. In short, SOTA multi-modal LLMs are the best option for handwriting, nearly anything is good at printed text, for printed media, specialty models from hyperscalers are slightly better than multi-modal LLMs. [0] https://research.aimultiple.com/ocr-accuracy/

I see it confirms what I wrote state of art is “not using tessaract anymore” and I think bunch of commercial solutions are stuck with tessaract.

Re: DeepSeek OCR

#34

Post by runeblaze »

krackers wrote: post #8

The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote >Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios,…

each text token is often subword unit, but in VLMs the visual tokens are in semantic space. Semantic space obviously compresses much more than subword slices.

disclaimer: not expert, on top of my head

Re: DeepSeek OCR

#35

Post by numpad0 »

krackers wrote: post #11
looobay wrote: post #10

Earlier quoted context omitted.

LLMs are compute heavy with quadratic scaling (in compute) per tokens. They are trying to compress text tokens into visual tokens with their VLM. Maybe they would render texts to an image before tokenizing to reduce the compute cost.

But naively wouldn't you expect the representation of a piece of text in terms of vision tokens to be roughly the same number of bits (or more) than the representation as textual token? You're changing representation sure, but that by itself doesn't give you any compute advantages unless there is some sparsity/compressability you can take advantage of in the domain you transform to right? So I guess my question is wh…

just a hunch but like, from something to do with Unicode?

Re: DeepSeek OCR

#37

Post by psb217 »

krackers wrote: post #11
looobay wrote: post #10

Earlier quoted context omitted.

LLMs are compute heavy with quadratic scaling (in compute) per tokens. They are trying to compress text tokens into visual tokens with their VLM. Maybe they would render texts to an image before tokenizing to reduce the compute cost.

But naively wouldn't you expect the representation of a piece of text in terms of vision tokens to be roughly the same number of bits (or more) than the representation as textual token? You're changing representation sure, but that by itself doesn't give you any compute advantages unless there is some sparsity/compressability you can take advantage of in the domain you transform to right? So I guess my question is wh…

The trick is that the vision tokens are continuous valued vectors, while the text tokens are elements from a small discrete set (which are converted into continuous valued vectors by a lookup table). So, vision tokens can convey significantly more bits per token than text tokens. This allows them to pack the content of multiple text tokens into a single vision token.

Re: DeepSeek OCR

#38

Post by jdthedisciple »

raincole wrote: post #29
x______________ wrote: post #23

>先天下之忧而忧 How is this an example of a prompt? Google translated this to "Worry about the world first" while Bing says "Worry before the worries of the world." Can anyone shed some light on this saying or why it's in the article?

It's a very famous (classical) Chinese phrase. Both translations don't catch the meaning well though. It means: "worry before the rest of the world (notice that they have something to) worry." The next part is 後天下之樂而樂("be happy only after the rest of the world is happy.") I don't know why it's a prompt example.

Sibling comment has the second part as

后天下之乐而乐

which one is correct?

Re: DeepSeek OCR

#39

Post by jdthedisciple »

gudzpoz wrote: post #32
x______________ wrote: post #23

>先天下之忧而忧 How is this an example of a prompt? Google translated this to "Worry about the world first" while Bing says "Worry before the worries of the world." Can anyone shed some light on this saying or why it's in the article?

This clause is usually used together with the next sentence in the original poem: > 先天下之忧而忧，后天下之乐而乐 > (put the world's worries before yours, and put your happiness after the world's) > edit: this translation is wrong, and raincole has a definitely better translation Since the model is a language model, they probably use this to demonstrate the model's language capabilities – the model should be able to complete the w…

Sibling comment has the second part as

後天下之樂而樂

Which one is correct?

Re: DeepSeek OCR

#40

Post by raincole »

jdthedisciple wrote: post #38
raincole wrote: post #29

Earlier quoted context omitted.

It's a very famous (classical) Chinese phrase. Both translations don't catch the meaning well though. It means: "worry before the rest of the world (notice that they have something to) worry." The next part is 後天下之樂而樂("be happy only after the rest of the world is happy.") I don't know why it's a prompt example.

Sibling comment has the second part as 后天下之乐而乐 which one is correct?

Traditional vs Simplified Chinese.

There are two (modern) "spellings" of written Chinese. Basically colour vs color.

Post reply on HN