Skip to content

Commit

Permalink
Bump version to v0.1.53 for release
Browse files Browse the repository at this point in the history
  • Loading branch information
jakep-allenai committed Feb 14, 2025
1 parent 58bdfa5 commit 08f7612
Show file tree
Hide file tree
Showing 3 changed files with 197 additions and 0 deletions.
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ pdelfin_testset/*
localworkspace/*
gpt4otestset/*
gpt4otestset_output/*
pdfs/*
/*.html
scoreelo.csv
debug.log
Expand Down
2 changes: 2 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,4 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## Unreleased

## [v0.1.53](https://github.com/allenai/olmocr/releases/tag/v0.1.53) - 2025-02-14

- Fixed git checks
194 changes: 194 additions & 0 deletions viewer.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,194 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>page_number</th>\n",
" <th>response</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>c6b0a0a792c8b9d789ca640885e5c27062b0dcca-10</th>\n",
" <td>http://www.research.ed.ac.uk/portal/files/4213...</td>\n",
" <td>10</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>c6b0a0a792c8b9d789ca640885e5c27062b0dcca-9</th>\n",
" <td>http://www.research.ed.ac.uk/portal/files/4213...</td>\n",
" <td>9</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>c6b0a0a792c8b9d789ca640885e5c27062b0dcca-3</th>\n",
" <td>http://www.research.ed.ac.uk/portal/files/4213...</td>\n",
" <td>3</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>a12049cb0a97a037ddcf1b59c75388ac6a961d0a-2</th>\n",
" <td>https://hal.archives-ouvertes.fr/hal-01518465/...</td>\n",
" <td>2</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>a12049cb0a97a037ddcf1b59c75388ac6a961d0a-8</th>\n",
" <td>https://hal.archives-ouvertes.fr/hal-01518465/...</td>\n",
" <td>8</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6ca9ff4bd92da89149bf2734f79e3d7f84079090-49</th>\n",
" <td>https://publications.parliament.uk/pa/ld201415...</td>\n",
" <td>49</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6ca9ff4bd92da89149bf2734f79e3d7f84079090-46</th>\n",
" <td>https://publications.parliament.uk/pa/ld201415...</td>\n",
" <td>46</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6ca9ff4bd92da89149bf2734f79e3d7f84079090-32</th>\n",
" <td>https://publications.parliament.uk/pa/ld201415...</td>\n",
" <td>32</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73c0ecd2b6e4e762244adf8b45b041c700b4f26d-3</th>\n",
" <td>http://ajpendo.physiology.org/content/ajpendo/...</td>\n",
" <td>3</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73c0ecd2b6e4e762244adf8b45b041c700b4f26d-1</th>\n",
" <td>http://ajpendo.physiology.org/content/ajpendo/...</td>\n",
" <td>1</td>\n",
" <td>{\"primary_language\":\"en\",\"is_rotation_valid\":t...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1166 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" url \\\n",
"id \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-10 http://www.research.ed.ac.uk/portal/files/4213... \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-9 http://www.research.ed.ac.uk/portal/files/4213... \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-3 http://www.research.ed.ac.uk/portal/files/4213... \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-2 https://hal.archives-ouvertes.fr/hal-01518465/... \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-8 https://hal.archives-ouvertes.fr/hal-01518465/... \n",
"... ... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-49 https://publications.parliament.uk/pa/ld201415... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-46 https://publications.parliament.uk/pa/ld201415... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-32 https://publications.parliament.uk/pa/ld201415... \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-3 http://ajpendo.physiology.org/content/ajpendo/... \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-1 http://ajpendo.physiology.org/content/ajpendo/... \n",
"\n",
" page_number \\\n",
"id \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-10 10 \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-9 9 \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-3 3 \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-2 2 \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-8 8 \n",
"... ... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-49 49 \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-46 46 \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-32 32 \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-3 3 \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-1 1 \n",
"\n",
" response \n",
"id \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-10 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-9 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"c6b0a0a792c8b9d789ca640885e5c27062b0dcca-3 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-2 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"a12049cb0a97a037ddcf1b59c75388ac6a961d0a-8 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"... ... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-49 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-46 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"6ca9ff4bd92da89149bf2734f79e3d7f84079090-32 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-3 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"73c0ecd2b6e4e762244adf8b45b041c700b4f26d-1 {\"primary_language\":\"en\",\"is_rotation_valid\":t... \n",
"\n",
"[1166 rows x 3 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas\n",
"\n",
"with open(\"eval-s2pdf.parquet\", \"rb\") as f:\n",
" df = pandas.read_parquet(f)\n",
"\n",
"df"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "pdf",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

0 comments on commit 08f7612

Please sign in to comment.