Repository Issue Activity (beta)

#473 Photorealistic derivative dataset based on olmOCR-mix-1025

#472 Your project is on StackMap — a curated map of the AI stack

#470 Document if multiple instances can use the same workspace

#463 Fail to parse b4c3c4ac3d6f7b52a993cec7ca8b3ad43cecabad_page_3.pdf

#461 olmocr.bench scoring: `partial_ratio` falsely matches when candidate is near-empty (e.g. single `\\n`)

#460 Model allenai/olmOCR-2-7B-1025 on DeepInfra will be deprecated on 2026-05-07

#459 Writing markdown error : 'gbk' codec can't encode character '\u1eca' in position 3419

#458 Make the model run on lower GPU at the expense of time/speed

#455 configurable timeout for HTTP client in server method

#452 numpy is missing from [bench] dependencies

#451 [bug] badly formed help string

#447 option to generate simple json report for benchmark

#446 max_tokens argument for server method instead of fixed value

#445 unable to set endpoint argument in server method because of colon arg delimiter

#444 ‌repetitive‌ text, math, or other same content that need to be verified

#443 Demo extracts populated table, self-hosted run returns 'No document text` for same page

#424 Out of Memory Error on a 12GB GPU

#442 does the model support predicting the bounding box of text? Which prompt to use?

#433 [bug] Tends to get stuck at the last few pages

#440 1

#429 [bug] Too Many Open Files

#434 olmocr bench

#437 [Bug/Improvement] Image bounding box coordinate unreliable

#384 Adding page number in image tags

#428 Returns markdown content with header