ksampath02
Joined 2 years ago
Karma
78
Submissions
6
Member since
Jul 25
https://www.karansampath.com/
View on Hacker NewsRecent submissions
Comment · 1 year ago
One interesting part of this model's pretraining process is how they used Qwen2.5VL and Qwen 2.5 to parse public unstructured data and expand the corpus from 18T to 36T. The ability to consistently do this will push legacy companies to train their own models and enhance their edge.
Comment · 1 year ago
You could try Aryn DocParse, which segments your documents first before running OCR: https://www.aryn.ai/ (full disclosure: I work there).
Comment · 2 years ago
May he rest in peace, his name will be remembered and impact felt for long.