Lints

olmocr/bench/katex/render.py

@@ -22,7 +22,6 @@ import threading
 import unittest
 import weakref
 from concurrent.futures import ThreadPoolExecutor
-from contextlib import contextmanager
 from dataclasses import dataclass
 from typing import List, Optional
 

olmocr/bench/miners/mine_blank_pages_gpt.py

@@ -16,7 +16,6 @@ import argparse
 import json
 import os
 import random
-import shutil
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import Optional
 

olmocr/bench/runners/run_paddlepaddle.py

@@ -1,6 +1,5 @@
 from threading import Lock
 
-import torch
 from paddleocr import PPStructureV3
 
 # Run's paddle paddle as in the docs here: https://huggingface.co/PaddlePaddle/PP-OCRv5_server_det

olmocr/bench/synth/mine_html_templates.py

@@ -20,7 +20,7 @@ from playwright.async_api import async_playwright
 from syntok.segmenter import process
 from tqdm import tqdm
 
-from olmocr.bench.tests import TableTest, TestType, load_single_test, parse_html_tables
+from olmocr.bench.tests import TableTest, TestType, parse_html_tables
 from olmocr.data.renderpdf import (
     get_png_dimensions_from_base64,
     render_pdf_to_base64png,

olmocr/bench/synth/rotate_html_templates.py

@@ -13,17 +13,12 @@ The script:
 """
 
 import argparse
-import json
 import os
 import random
-import re
 import shutil
-import subprocess
-from pathlib import Path
-from typing import Dict, List, Optional, Tuple
+from typing import List, Optional
 
 import pypdf
-from pypdf import PageObject, Transformation
 from tqdm import tqdm
 
 

olmocr/data/clean_olmocrmix.py

@@ -11,7 +11,7 @@ import sys
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Tuple
 
 from openai import OpenAI
 from pydantic import BaseModel, Field

olmocr/data/prepare_loc_transcripts.py

@@ -9,12 +9,11 @@
 import argparse
 import csv
 import hashlib
-import os
 import threading
 import time
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
-from typing import Dict, List, Optional, Set, Tuple
+from typing import Dict, Optional, Set, Tuple
 
 import img2pdf
 import requests

olmocr/data/repackage_olmocrmix.py

@@ -16,10 +16,9 @@ import json
 import tarfile
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Dict, Iterator, List, Optional, Tuple
+from typing import Dict, Iterator, List, Optional
 
 import pandas as pd
-import yaml
 from tqdm import tqdm
 
 from olmocr.prompts import PageResponse

olmocr/train/dataloader.py

@@ -32,14 +32,12 @@ from pypdf import PdfReader
 from torch.utils.data import Dataset
 from tqdm import tqdm
 
-from olmocr.bench.katex.render import render_equation
 from olmocr.data.renderpdf import render_pdf_to_base64png
 from olmocr.prompts.anchor import get_anchor_text
 from olmocr.prompts.prompts import (
     PageResponse,
     build_finetuning_prompt,
     build_no_anchoring_v4_yaml_prompt,
-    build_no_anchoring_yaml_prompt,
 )
 
 # Type alias for samples

olmocr/train/grpo_train.py

@@ -3,27 +3,23 @@ GRPO (Generative Reward-based Policy Optimization) training script for OlmOCR.
 """
 
 import argparse
-import asyncio
 import base64
 import glob
 import json
 import logging
 import os
-import random
 import sys
 from concurrent.futures import ThreadPoolExecutor
-from functools import lru_cache, partial
+from functools import lru_cache
 from io import BytesIO
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple
+from typing import Any, Dict, List, Optional, Tuple
 
-import numpy as np
 import torch
 import torch.distributed as dist
 import wandb
 from PIL import Image
 from rapidfuzz import fuzz
-from torch.utils.data import DataLoader, Dataset
+from torch.utils.data import Dataset
 from transformers import (
     AutoProcessor,
     Qwen2_5_VLForConditionalGeneration,

scripts/check_contamination.py

@@ -25,7 +25,6 @@
 
 import argparse
 import json
-import os
 import re
 import sqlite3
 from pathlib import Path