LICENSE
README.md
pyproject.toml
olmocr/__init__.py
olmocr/check.py
olmocr/datatypes.py
olmocr/image_utils.py
olmocr/loadertest.py
olmocr/metrics.py
olmocr/pipeline.py
olmocr/py.typed
olmocr/repeatdetect.py
olmocr/s3_utils.py
olmocr/version.py
olmocr/work_queue.py
olmocr.egg-info/PKG-INFO
olmocr.egg-info/SOURCES.txt
olmocr.egg-info/dependency_links.txt
olmocr.egg-info/requires.txt
olmocr.egg-info/top_level.txt
olmocr/bench/__init__.py
olmocr/bench/benchmark.py
olmocr/bench/convert.py
olmocr/bench/prompts.py
olmocr/bench/report.py
olmocr/bench/review_app.py
olmocr/bench/review_app_latex.py
olmocr/bench/tests.py
olmocr/bench/utils.py
olmocr/bench/katex/__init__.py
olmocr/bench/katex/render.py
olmocr/bench/miners/check_headers_footers.py
olmocr/bench/miners/check_multicolumn.py
olmocr/bench/miners/check_old_scans_math.py
olmocr/bench/miners/cleanup_data.py
olmocr/bench/miners/cleanup_urls.py
olmocr/bench/miners/delete_rejected.py
olmocr/bench/miners/download_math.py
olmocr/bench/miners/mine_diffs.py
olmocr/bench/miners/mine_headers_footers.py
olmocr/bench/miners/mine_long_tiny_text.py
olmocr/bench/miners/mine_math.py
olmocr/bench/miners/mine_multi_column.py
olmocr/bench/miners/mine_old_scan_pdf.py
olmocr/bench/miners/mine_old_scans.py
olmocr/bench/miners/mine_old_scans_math.py
olmocr/bench/miners/mine_reading_order.py
olmocr/bench/miners/mine_tables_gemini.py
olmocr/bench/miners/mine_tables_gpt.py
olmocr/bench/miners/pick_mediod.py
olmocr/bench/runners/__init__.py
olmocr/bench/runners/run_chatgpt.py
olmocr/bench/runners/run_claude.py
olmocr/bench/runners/run_docling.py
olmocr/bench/runners/run_gemini.py
olmocr/bench/runners/run_gotocr.py
olmocr/bench/runners/run_marker.py
olmocr/bench/runners/run_mineru.py
olmocr/bench/runners/run_mistral.py
olmocr/bench/runners/run_olmocr_pipeline.py
olmocr/bench/runners/run_rolmocr.py
olmocr/bench/runners/run_server.py
olmocr/bench/runners/run_transformers.py
olmocr/bench/scripts/difference_viewer.py
olmocr/bench/scripts/run_difference.py
olmocr/bench/scripts/url_matcher.py
olmocr/bench/synth/__init__.py
olmocr/bench/synth/mine_html_templates.py
olmocr/bench/synth/test_mine.py
olmocr/data/__init__.py
olmocr/data/buildsilver.py
olmocr/data/buildsilverdatasummary.py
olmocr/data/buildtestset.py
olmocr/data/convertsilver_birr.py
olmocr/data/convertsilver_openai.py
olmocr/data/renderpdf.py
olmocr/data/runopenaibatch.py
olmocr/eval/__init__.py
olmocr/eval/buildelo.py
olmocr/eval/evalhtml.py
olmocr/eval/evalhtml_template.html
olmocr/eval/runeval.py
olmocr/eval/scoreelo.py
olmocr/eval/dolma_refine/aligners.py
olmocr/eval/dolma_refine/metrics.py
olmocr/eval/dolma_refine/registry.py
olmocr/eval/dolma_refine/segmenters.py
olmocr/filter/__init__.py
olmocr/filter/coherency.py
olmocr/filter/filter.py
olmocr/prompts/__init__.py
olmocr/prompts/anchor.py
olmocr/prompts/prompts.py
olmocr/train/__init__.py
olmocr/train/dataloader.py
olmocr/train/dataprep.py
olmocr/train/fixqwen25vlcheckpoint.py
olmocr/train/inference.py
olmocr/train/loaddataset.py
olmocr/train/train.py
olmocr/train/utils.py
olmocr/train/core/__init__.py
olmocr/train/core/adapters.py
olmocr/train/core/cli.py
olmocr/train/core/compression.py
olmocr/train/core/config.py
olmocr/train/core/errors.py
olmocr/train/core/loggers.py
olmocr/train/core/paths.py
olmocr/train/core/state.py
olmocr/train/hf/__init__.py
olmocr/train/hf/convertjsontoparquet.py
olmocr/train/hf/hfhub_upload.py
olmocr/train/hf/warc_parser.py
olmocr/train/molmo/__init__.py
olmocr/train/molmo/config_molmo.py
olmocr/train/molmo/image_processing_molmo.py
olmocr/train/molmo/modeling_molmo.py
olmocr/train/molmo/preprocessing_molmo.py
olmocr/viewer/__init__.py
olmocr/viewer/dolmaviewer.py
olmocr/viewer/dolmaviewer_template.html
tests/test_anchor.py
tests/test_dataloader.py
tests/test_dataprep.py
tests/test_filter.py
tests/test_integration.py
tests/test_molmo.py
tests/test_s3_work_queue.py
tests/test_sglang.py
tests/test_tests.py