yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-06-27 04:00:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hmm adjusting params

Browse Source
This commit is contained in:
Jake Poznanski 2025-06-21 04:04:12 +00:00
parent c85324b936
commit f003933f54
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

@ -336,7 +336,7 @@ async def apost_streaming_completion(url, json_data):
full_content += delta["content"]
repeat_detector.add_letters(delta["content"])
if any(ngram > 100 for ngram in repeat_detector.ngram_repeats()):
if any(ngram > 300 for ngram in repeat_detector.ngram_repeats()):
logger.warning(f"Error, detected ngram repeat in generation {repeat_detector.ngram_repeats()}, aborting")
finish_reason = "repeats"
break