From ffee4c9740c51be523d26a7cc0a58a89d8d2a9f1 Mon Sep 17 00:00:00 2001 From: Jake Poznanski Date: Wed, 14 May 2025 19:51:00 +0000 Subject: [PATCH] Big bug fix, moving the prompt to match how training was done, 2.3 point boost on olmocr-bench --- olmocr/pipeline.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/olmocr/pipeline.py b/olmocr/pipeline.py index e14e6bb..d9acc7f 100644 --- a/olmocr/pipeline.py +++ b/olmocr/pipeline.py @@ -138,8 +138,8 @@ async def build_page_query(local_pdf_path: str, page: int, target_longest_image_ { "role": "user", "content": [ - {"type": "text", "text": build_finetuning_prompt(anchor_text)}, {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_base64}"}}, + {"type": "text", "text": build_finetuning_prompt(anchor_text)}, ], } ],