Optical test bench
Send an image.
Read it back.
Drop a document photo or scan. The extracted fields come back structured on the right.
prompt contract: the model was trained on “Text Recognition:” —
any other instruction degrades it into empty output.
engine: vLLM bf16 · A10G · memory-snapshot cold starts
Readings
idleNo document loaded
Drop an image on the left to see what the model reads out of it.