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

Update marker cost

Browse Source
This commit is contained in:
Vik Paruchuri 2025-06-06 13:47:29 -04:00
parent f21ff08c2f
commit 267f52bd79
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
olmocr/bench/runners/run_marker.py
View File

@ -18,7 +18,7 @@ def run_marker(pdf_path: str, page_num: int = 1) -> str:
if _marker_converter is None:
# Create a configuration dictionary with the necessary settings
config = {
"format_lines": True, # This enables conversion of inline math to LaTeX
"force_ocr": True, # This enables conversion of inline math to LaTeX
"use_llm": google_key_exists, # Activate LLM mode if google key is specified
"disable_tqdm": True, # Disable tqdm for cleaner output
"recognition_batch_size": 256,

4
scripts/pareto_plot.py
View File

@ -69,7 +69,7 @@ data = {
"Qwen 2 VL",
"Qwen 2.5 VL",
],
COST_COLUMN_NAME: [12480, 6240, 1000, 596, 499, 249, 235, 178, 178, 178], # Same cost as Ours # Same cost as Ours
COST_COLUMN_NAME: [12480, 6240, 1000, 596, 499, 249, 75, 178, 178, 178], # Same cost as Ours # Same cost as Ours
PERF_COLUMN_NAME: [
69.9, # GPT-4o (Anchored)
69.9, # Same performance for batch
@ -77,7 +77,7 @@ data = {
61.5, # MinerU
63.8, # Gemini Flash 2 (Anchored)
63.8, # Same performance for batch
74.3, # marker v1.7.4 hybrid
70.0, # marker v1.7.4 base
77.4, # Ours (performance is the same across hardware)
31.5, # Qwen2VL
65.5, # Qwen2.5VL