v0.17.0

datalab-to/suryav0.17.0Sep 23, 2025by tarun-menta

AI Summary

Major release introducing a new layout model with a completely rearchitected system trained from scratch, delivering significant improvements across many document domains.

Key Highlights

  • New layout model release
  • New unified tokenizer
  • Significant improvements across many domains
  • New architecture trained from scratch

New Features

  • New layout model with improved architecture
  • New unified tokenizer

Full Release Notes

## Releasing new layout model
- Moving to a new architecture for layout, trained from scratch. Significant improvements across many domains

## What's Changed
* feat: new unified tokenizer by @VikParuchuri in https://github.com/datalab-to/surya/pull/442
* Layout Model Release by @tarun-menta in https://github.com/datalab-to/surya/pull/461
* Dev by @tarun-menta in https://github.com/datalab-to/surya/pull/463


**Full Changelog**: https://github.com/datalab-to/surya/compare/v0.16.7...v0.17.0