←back to thread

DeepSeek OCR

(github.com)
990 points pierre | 1 comments | 20 Oct 25 06:26 UTC | HN request time: 0.2s | source
Show context
tinyhouse ◴[20 Oct 25 11:57 UTC] No.45642902[source]▶
OCR is not a great name for these models. While they can do traditional OCR such as digitize and scanned PDF for example, they do so much more.
replies(1): >>45645568 #
intalentive ◴[20 Oct 25 16:12 UTC] No.45645568[source]▶
>they do so much more I'm not familiar. What else are they good for?
replies(1): >>45646245 #
1. tinyhouse ◴[20 Oct 25 17:00 UTC] No.45646245[source]▶
They can take something like an image of a graph and provide a description of it. From my understanding, these are multimodal models with reasoning capabilities.