yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-13 17:22:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

ALlowing more tokens

Browse Source
This commit is contained in:
Jake Poznanski 2025-05-29 19:59:58 +00:00
parent 022be37723
commit 2cb14cceae
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
olmocr/pipeline.py
View File

@ -106,7 +106,7 @@ class PageResult:
async def build_page_query(local_pdf_path: str, page: int, target_longest_image_dim: int, target_anchor_text_len: int, image_rotation: int = 0) -> dict: async def build_page_query(local_pdf_path: str, page: int, target_longest_image_dim: int, target_anchor_text_len: int, image_rotation: int = 0) -> dict:
MAX_TOKENS = 3000 MAX_TOKENS = 4000
assert image_rotation in [0, 90, 180, 270], "Invalid image rotation provided in build_page_query" assert image_rotation in [0, 90, 180, 270], "Invalid image rotation provided in build_page_query"
# Allow the page rendering to process in the background while we get the anchor text (which blocks the main thread) # Allow the page rendering to process in the background while we get the anchor text (which blocks the main thread)