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

Bump version to v0.1.68 for release

Browse Source
This commit is contained in:
Jake Poznanski 2025-05-19 16:57:20 +00:00
parent db9972c39a
commit d2755adf55
4 changed files with 19 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## Unreleased
## [v0.1.68](https://github.com/allenai/olmocr/releases/tag/v0.1.68) - 2025-05-19
## [v0.1.60](https://github.com/allenai/olmocr/releases/tag/v0.1.60) - 2025-03-17
## [v0.1.58](https://github.com/allenai/olmocr/releases/tag/v0.1.58) - 2025-02-15

1
olmOCR-bench Submodule

@ -0,0 +1 @@
Subproject commit 346419907b212a6c25906c0e17c15e186af9708c

4
scripts/build-docker.sh
View File

@ -8,5 +8,5 @@ echo "$VERSION"
docker build --platform linux/amd64 -f ./scripts/beaker/Dockerfile-inference -t olmocr-inference-$VERSION .
beaker image create --workspace ai2/oe-data-pdf --name olmocr-inference-$VERSION olmocr-inference-$VERSION
# docker build --platform linux/amd64 -f ./scripts/beaker/Dockerfile-tagging -t olmocr-tagging-$VERSION .
# beaker image create --workspace ai2/oe-data-pdf --name olmocr-tagging-$VERSION olmocr-tagging-$VERSION
docker build --platform linux/amd64 -f ./scripts/beaker/Dockerfile-tagging -t olmocr-tagging-$VERSION .
beaker image create --workspace ai2/oe-data-pdf --name olmocr-tagging-$VERSION olmocr-tagging-$VERSION

16
scripts/check_qual.sh
View File

@ -4,9 +4,21 @@ set -e
python scripts/pii_rule_comparison.py \
--docs-folder /home/ubuntu/s2pdf_dedupe_minhash_v1_with_no_pii/documents \
--ref-rule "ft_lang_id_en_doc_v2__ft_lang_id_en_doc_v2__en:avg>0.5" \
--hyp-rule "ft_lang_id_en_doc_v2__ft_lang_id_en_doc_v2__en:avg>0.4" \
--ref-rule "ft_lang_id_en_doc_v2__ft_lang_id_en_doc_v2__en:avg>0.5 and \
fineweb_edu_fasttext_gt2__fineweb_edu_fasttext_gt2__score:avg>0.001 and \
avg_fraction_numbers_in_line_v1__avg_fraction_numbers_in_line_v1__avg_fraction_numbers_in_line_ratio:avg<0.2 and \
pipe_delimited_lines_v1__pipe_delimited_lines_v1__pipe_delimited_lines_ratio:avg<0.3 \
" \
--hyp-rule "ft_lang_id_en_doc_v2__ft_lang_id_en_doc_v2__en:avg>0.5 and \
fineweb_edu_fasttext_gt2__fineweb_edu_fasttext_gt2__score:avg>0.001 and \
avg_fraction_numbers_in_line_v1__avg_fraction_numbers_in_line_v1__avg_fraction_numbers_in_line_ratio:avg<0.2 and \
pipe_delimited_lines_v1__pipe_delimited_lines_v1__pipe_delimited_lines_ratio:avg<0.4 \
" \
--output-dir results/pii_detection \
# Run1, langid, pipes and numbers
# Prompt, boilerplate, reference, prose, table classification -> train fasttext
# 50k docs to train fast text
tinyhost results/pii_detection/*