architectures · baidu

Unlimited-OCR

Compact vision-language architecture for document OCR: a vision encoder paired with a small sparse-expert language decoder (12 layers, 64 routed experts with 6 active per token). Task-specific rather than general-purpose, which is why the parameter count is small relative to its capability on document images. Declared as model_type `unlimited-ocr`.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Re-check this yourself → Source → Full record →

What is recorded

Publisher	baidu
Origin	China
Licence	Apache-2.0

Elsewhere in the registry

All architectures → Browse with filters → What will run on my hardware? →

Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.