Massive refactor from pdelfin to olmocr

.github/CONTRIBUTING.md

@@ -6,10 +6,10 @@ Thanks for considering contributing! Please read this document to learn the vari
 
 ### Did you find a bug?
 
-First, do [a quick search](https://github.com/allenai/pdelfin/issues) to see whether your issue has already been reported.
+First, do [a quick search](https://github.com/allenai/olmocrissues) to see whether your issue has already been reported.
 If your issue has already been reported, please comment on the existing issue.
 
-Otherwise, open [a new GitHub issue](https://github.com/allenai/pdelfin/issues).  Be sure to include a clear title
+Otherwise, open [a new GitHub issue](https://github.com/allenai/olmocrissues).  Be sure to include a clear title
 and description.  The description should include as much relevant information as possible.  The description should
 explain how to reproduce the erroneous behavior as well as the behavior you expect to see.  Ideally you would include a
 code sample or an executable test case demonstrating the expected behavior.
@@ -21,7 +21,7 @@ We use GitHub issues to track feature requests. Before you create a feature requ
 * Make sure you have a clear idea of the enhancement you would like. If you have a vague idea, consider discussing
 it first on a GitHub issue.
 * Check the documentation to make sure your feature does not already exist.
-* Do [a quick search](https://github.com/allenai/pdelfin/issues) to see whether your feature has already been suggested.
+* Do [a quick search](https://github.com/allenai/olmocrissues) to see whether your feature has already been suggested.
 
 When creating your request, please:
 
@@ -41,31 +41,31 @@ When you're ready to contribute code to address an open issue, please follow the
 
     Then clone your fork locally with
 
-        git clone https://github.com/USERNAME/pdelfin.git
+        git clone https://github.com/USERNAME/olmocrgit
 
     or 
 
-        git clone git@github.com:USERNAME/pdelfin.git
+        git clone git@github.com:USERNAME/olmocrgit
 
-    At this point the local clone of your fork only knows that it came from *your* repo, github.com/USERNAME/pdelfin.git, but doesn't know anything the *main* repo, [https://github.com/allenai/pdelfin.git](https://github.com/allenai/pdelfin). You can see this by running
+    At this point the local clone of your fork only knows that it came from *your* repo, github.com/USERNAME/olmocrgit, but doesn't know anything the *main* repo, [https://github.com/allenai/oolmocrit](https://github.com/allenai/ololmocrYou can see this by running
 
         git remote -v
 
     which will output something like this:
 
-        origin https://github.com/USERNAME/pdelfin.git (fetch)
+        origin https://github.com/USERNAME/olmocrgit (fetch)
-        origin https://github.com/USERNAME/pdelfin.git (push)
+        origin https://github.com/USERNAME/olmocrgit (push)
 
-    This means that your local clone can only track changes from your fork, but not from the main repo, and so you won't be able to keep your fork up-to-date with the main repo over time. Therefore you'll need to add another "remote" to your clone that points to [https://github.com/allenai/pdelfin.git](https://github.com/allenai/pdelfin). To do this, run the following:
+    This means that your local clone can only track changes from your fork, but not from the main repo, and so you won't be able to keep your fork up-to-date with the main repo over time. Therefore you'll need to add another "remote" to your clone that points to [https://github.com/allenai/olmocrgit](https://github.com/allenai/oolmocr To do this, run the following:
 
-        git remote add upstream https://github.com/allenai/pdelfin.git
+        git remote add upstream https://github.com/allenai/olmocrgit
 
     Now if you do `git remote -v` again, you'll see
 
-        origin https://github.com/USERNAME/pdelfin.git (fetch)
+        origin https://github.com/USERNAME/olmocrgit (fetch)
-        origin https://github.com/USERNAME/pdelfin.git (push)
+        origin https://github.com/USERNAME/olmocrgit (push)
-        upstream https://github.com/allenai/pdelfin.git (fetch)
+        upstream https://github.com/allenai/olmocrgit (fetch)
-        upstream https://github.com/allenai/pdelfin.git (push)
+        upstream https://github.com/allenai/olmocrgit (push)
 
     Finally, you'll need to create a Python 3 virtual environment suitable for working on this project. There a number of tools out there that making working with virtual environments easier.
     The most direct way is with the [`venv` module](https://docs.python.org/3.7/library/venv.html) in the standard library, but if you're new to Python or you don't already have a recent Python 3 version installed on your machine,
@@ -77,8 +77,8 @@ When you're ready to contribute code to address an open issue, please follow the
 
     Then you can create and activate a new Python environment by running:
 
-        conda create -n pdelfin python=3.9
+        conda create -n olmocrpython=3.9
-        conda activate pdelfin
+        conda activate olmocr
 
     Once your virtual environment is activated, you can install your local clone in "editable mode" with
 
@@ -93,7 +93,7 @@ When you're ready to contribute code to address an open issue, please follow the
 
     <details><summary>Expand details 👇</summary><br/>
 
-    Once you've added an "upstream" remote pointing to [https://github.com/allenai/python-package-temlate.git](https://github.com/allenai/pdelfin), keeping your fork up-to-date is easy:
+    Once you've added an "upstream" remote pointing to [https://github.com/allenai/python-package-temlate.git](https://github.com/allenai/olmocr, keeping your fork up-to-date is easy:
 
         git checkout main  # if not already on main
         git pull --rebase upstream main
@@ -119,7 +119,7 @@ When you're ready to contribute code to address an open issue, please follow the
 
     <details><summary>Expand details 👇</summary><br/>
 
-    Our continuous integration (CI) testing runs [a number of checks](https://github.com/allenai/pdelfin/actions) for each pull request on [GitHub Actions](https://github.com/features/actions). You can run most of these tests locally, which is something you should do *before* opening a PR to help speed up the review process and make it easier for us.
+    Our continuous integration (CI) testing runs [a number of checks](https://github.com/allenai/olmocractions) for each pull request on [GitHub Actions](https://github.com/features/actions). You can run most of these tests locally, which is something you should do *before* opening a PR to help speed up the review process and make it easier for us.
 
     First, you should run [`isort`](https://github.com/PyCQA/isort) and [`black`](https://github.com/psf/black) to make sure you code is formatted consistently.
     Many IDEs support code formatters as plugins, so you may be able to setup isort and black to run automatically everytime you save.
@@ -137,9 +137,9 @@ When you're ready to contribute code to address an open issue, please follow the
 
         mypy .
 
-    We also strive to maintain high test coverage, so most contributions should include additions to [the unit tests](https://github.com/allenai/pdelfin/tree/main/tests). These tests are run with [`pytest`](https://docs.pytest.org/en/latest/), which you can use to locally run any test modules that you've added or changed.
+    We also strive to maintain high test coverage, so most contributions should include additions to [the unit tests](https://github.com/allenai/olmocrtree/main/tests). These tests are run with [`pytest`](https://docs.pytest.org/en/latest/), which you can use to locally run any test modules that you've added or changed.
 
-    For example, if you've fixed a bug in `pdelfin/a/b.py`, you can run the tests specific to that module with
+    For example, if you've fixed a bug in `olmocra/b.py`, you can run the tests specific to that module with
 
         pytest -v tests/a/b_test.py
 
@@ -152,9 +152,9 @@ When you're ready to contribute code to address an open issue, please follow the
 
     If the build fails, it's most likely due to small formatting issues. If the error message isn't clear, feel free to comment on this in your pull request.
 
-    And finally, please update the [CHANGELOG](https://github.com/allenai/pdelfin/blob/main/CHANGELOG.md) with notes on your contribution in the "Unreleased" section at the top.
+    And finally, please update the [CHANGELOG](https://github.com/allenai/olmocrblob/main/CHANGELOG.md) with notes on your contribution in the "Unreleased" section at the top.
 
-    After all of the above checks have passed, you can now open [a new GitHub pull request](https://github.com/allenai/pdelfin/pulls).
+    After all of the above checks have passed, you can now open [a new GitHub pull request](https://github.com/allenai/olmocrpulls).
     Make sure you have a clear description of the problem and the solution, and include a link to relevant issues.
 
     We look forward to reviewing your PR!

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -6,7 +6,7 @@ body:
 - type: markdown
   attributes:
     value: >
-      #### Before submitting a bug, please make sure the issue hasn't been already addressed by searching through [the existing and past issues](https://github.com/allenai/pdelfin/issues?q=is%3Aissue+sort%3Acreated-desc+).
+      #### Before submitting a bug, please make sure the issue hasn't been already addressed by searching through [the existing and past issues](https://github.com/allenai/olmocr/issues?q=is%3Aissue+sort%3Acreated-desc+).
 - type: textarea
   attributes:
     label: 🐛 Describe the bug
@@ -17,7 +17,7 @@ body:
 
       ```python
       # All necessary imports at the beginning
-      import pdelfin
+      import olmocr
 
       # A succinct reproducing example trimmed down to the essential parts:
       assert False is True, "Oh no!"

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,5 +1,5 @@
 name: 📚 Documentation
-description: Report an issue related to https://pdelfin.readthedocs.io/latest
+description: Report an issue related to https://olmocr.readthedocs.io/latest
 labels: 'documentation'
 
 body:
@@ -7,7 +7,7 @@ body:
   attributes:
     label: 📚 The doc issue
     description: >
-      A clear and concise description of what content in https://pdelfin.readthedocs.io/latest is an issue.
+      A clear and concise description of what content in https://olmocr.readthedocs.io/latest is an issue.
   validations:
     required: true
 - type: textarea

.github/pull_request_template.md

@@ -10,9 +10,9 @@ Changes proposed in this pull request:
 ## Before submitting
 
 <!-- Please complete this checklist BEFORE submitting your PR to speed along the review process. -->
-- [ ] I've read and followed all steps in the [Making a pull request](https://github.com/allenai/pdelfin/blob/main/.github/CONTRIBUTING.md#making-a-pull-request)
+- [ ] I've read and followed all steps in the [Making a pull request](https://github.com/allenai/olmocr/blob/main/.github/CONTRIBUTING.md#making-a-pull-request)
     section of the `CONTRIBUTING` docs.
 - [ ] I've updated or added any relevant docstrings following the syntax described in the
-    [Writing docstrings](https://github.com/allenai/pdelfin/blob/main/.github/CONTRIBUTING.md#writing-docstrings) section of the `CONTRIBUTING` docs.
+    [Writing docstrings](https://github.com/allenai/olmocr/blob/main/.github/CONTRIBUTING.md#writing-docstrings) section of the `CONTRIBUTING` docs.
 - [ ] If this PR fixes a bug, I've added a test that will fail without my fix.
 - [ ] If this PR adds a new feature, I've added tests that sufficiently cover my new functionality.

.github/workflows/main.yml

@@ -97,7 +97,7 @@ jobs:
         if: always()
         run: |
           . .venv/bin/activate
-          pip uninstall -y pdelfin
+          pip uninstall -y olmocr
 
   release:
     name: Release

.github/workflows/pr_checks.yml

@@ -9,7 +9,7 @@ on:
     branches:
       - main
     paths:
-      - 'pdelfin/**'
+      - 'olmocr/**'
 
 jobs:
   changelog:

README.md

@@ -7,12 +7,12 @@ Toolkit for training language models to work with PDF documents in the wild.
 
 
 What is included:
- - A prompting strategy to get really good natural text parsing using ChatGPT 4o - [buildsilver.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/data/buildsilver.py)
+ - A prompting strategy to get really good natural text parsing using ChatGPT 4o - [buildsilver.py](https://github.com/allenai/olmocr/blob/main/olmocr/data/buildsilver.py)
- - An eval toolkit for comparing different pipeline versions - [runeval.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/eval/runeval.py)
+ - An eval toolkit for comparing different pipeline versions - [runeval.py](https://github.com/allenai/olmocr/blob/main/olmocr/eval/runeval.py)
- - Basic filtering by language and SEO spam removal - [filter.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/filter/filter.py)
+ - Basic filtering by language and SEO spam removal - [filter.py](https://github.com/allenai/olmocr/blob/main/olmocr/filter/filter.py)
- - Finetuning code for Qwen2-VL (and soon other VLMs) - [train.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/train/train.py)
+ - Finetuning code for Qwen2-VL (and soon other VLMs) - [train.py](https://github.com/allenai/olmocr/blob/main/olmocr/train/train.py)
- - Processing millions of PDFs through a finetuned model using Sglang - [beakerpipeline.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/beakerpipeline.py)
+ - Processing millions of PDFs through a finetuned model using Sglang - [beakerpipeline.py](https://github.com/allenai/olmocr/blob/main/olmocr/beakerpipeline.py)
- - Viewing Dolma Docs created from PDFs - [dolmaviewer.py](https://github.com/allenai/pdelfin/blob/main/pdelfin/viewer/dolmaviewer.py)
+ - Viewing Dolma Docs created from PDFs - [dolmaviewer.py](https://github.com/allenai/olmocr/blob/main/olmocr/viewer/dolmaviewer.py)
 
 ### Installation
 
@@ -22,10 +22,10 @@ You will need to install poppler-utils and then also some fonts on your computer
 sudo apt-get install poppler-utils ttf-mscorefonts-installer msttcorefonts fonts-crosextra-caladea fonts-crosextra-carlito gsfonts lcdf-typetools
 ```
 
-Then, clone and install the pdelfin package
+Then, clone and install the olmocr package
 ```bash
-git clone https://github.com/allenai/pdelfin.git
+git clone https://github.com/allenai/olmocr.git
-cd pdelfin
+cd olmocr
 pip install -e .
 ```
 
@@ -43,7 +43,7 @@ It also runs at 2,800+ tokens per second per H100 GPU.
 
 For example:
 ```bash
-python -m pdelfin.beakerpipeline s3://ai2-oe-data/[your username]/pdfworkspaces/[workspacename] --pdfs s3://ai2-oe-data/jakep/gnarly_pdfs/*.pdf --beaker
+python -m olmocr.beakerpipeline s3://ai2-oe-data/[your username]/pdfworkspaces/[workspacename] --pdfs s3://ai2-oe-data/jakep/gnarly_pdfs/*.pdf --beaker
 ```
 
 This will convert all the pdfs at `s3://ai2-oe-data/jakep/gnarly_pdfs/*.pdf` and output dolma formatted documents at `s3://ai2-oe-data/[your username]/pdfworkspaces/[workspacename]/results`
@@ -53,7 +53,7 @@ With default settings, it should work fine on any available GPUs.
 
 
 ```bash
-python -m pdelfin.beakerpipeline --help
+python -m olmocr.beakerpipeline --help
 usage: beakerpipeline.py [-h] [--pdfs PDFS] [--workspace_profile WORKSPACE_PROFILE] [--pdf_profile PDF_PROFILE] [--pages_per_group PAGES_PER_GROUP]
                          [--max_page_retries MAX_PAGE_RETRIES] [--max_page_error_rate MAX_PAGE_ERROR_RATE] [--workers WORKERS] [--stats]
                          [--model MODEL] [--model_max_context MODEL_MAX_CONTEXT] [--model_chat_template MODEL_CHAT_TEMPLATE]

RELEASE_PROCESS.md

@@ -2,7 +2,7 @@
 
 ## Steps
 
-1. Update the version in `pdelfin/version.py`.
+1. Update the version in `olmocr/version.py`.
 
 3. Run the release script:
 

docs/source/conf.py

@@ -18,11 +18,11 @@ from datetime import datetime
 
 sys.path.insert(0, os.path.abspath("../../"))
 
-from pdelfin import VERSION, VERSION_SHORT  # noqa: E402
+from olmocr import VERSION, VERSION_SHORT  # noqa: E402
 
 # -- Project information -----------------------------------------------------
 
-project = "pdelfin"
+project = "olmocr"
 copyright = f"{datetime.today().year}, Allen Institute for Artificial Intelligence"
 author = "Allen Institute for Artificial Intelligence"
 version = VERSION_SHORT
@@ -82,7 +82,7 @@ typehints_defaults = "comma"
 #
 html_theme = "furo"
 
-html_title = f"pdelfin v{VERSION}"
+html_title = f"olmocr v{VERSION}"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
@@ -97,7 +97,7 @@ html_theme_options = {
     "footer_icons": [
         {
             "name": "GitHub",
-            "url": "https://github.com/allenai/pdelfin",
+            "url": "https://github.com/allenai/olmocr",
             "html": """
                 <svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 16 16">
                     <path fill-rule="evenodd" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z"></path>

docs/source/index.md

@@ -1,4 +1,4 @@
-# **pdelfin**
+# **olmocr**
 
 ```{toctree}
 :maxdepth: 2
@@ -15,8 +15,8 @@ overview
 
 CHANGELOG
 CONTRIBUTING
-License <https://raw.githubusercontent.com/allenai/pdelfin/main/LICENSE>
+License <https://raw.githubusercontent.com/allenai/olmocr/main/LICENSE>
-GitHub Repository <https://github.com/allenai/pdelfin>
+GitHub Repository <https://github.com/allenai/olmocr>
 ```
 
 ## Indices and tables

docs/source/installation.md

@@ -1,23 +1,23 @@
 Installation
 ============
 
-**pdelfin** supports Python >= 3.8.
+**olmocr** supports Python >= 3.8.
 
 ## Installing with `pip`
 
-**pdelfin** is available [on PyPI](https://pypi.org/project/pdelfin/). Just run
+**olmocr** is available [on PyPI](https://pypi.org/project/olmocr/). Just run
 
 ```bash
-pip install pdelfin
+pip install olmocr
 ```
 
 ## Installing from source
 
-To install **pdelfin** from source, first clone [the repository](https://github.com/allenai/pdelfin):
+To install **olmocr** from source, first clone [the repository](https://github.com/allenai/olmocr):
 
 ```bash
-git clone https://github.com/allenai/pdelfin.git
+git clone https://github.com/allenai/olmocr.git
-cd pdelfin
+cd olmocr
 ```
 
 Then run

olmocr/beakerpipeline.py

@@ -31,15 +31,15 @@ from typing import Optional, Tuple, List, Dict, Set
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from concurrent.futures.process import BrokenProcessPool
 
-from pdelfin.s3_queue import S3WorkQueue, WorkItem
+from olmocr.s3_queue import S3WorkQueue, WorkItem
-from pdelfin.s3_utils import expand_s3_glob, get_s3_bytes, get_s3_bytes_with_backoff, parse_s3_path, download_zstd_csv, upload_zstd_csv, download_directory
+from olmocr.s3_utils import expand_s3_glob, get_s3_bytes, get_s3_bytes_with_backoff, parse_s3_path, download_zstd_csv, upload_zstd_csv, download_directory
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.filter.filter import PdfFilter, Language
+from olmocr.filter.filter import PdfFilter, Language
-from pdelfin.prompts import build_finetuning_prompt, PageResponse
+from olmocr.prompts import build_finetuning_prompt, PageResponse
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.check import check_poppler_version
+from olmocr.check import check_poppler_version
-from pdelfin.metrics import MetricsKeeper, WorkerTracker
+from olmocr.metrics import MetricsKeeper, WorkerTracker
-from pdelfin.version import VERSION
+from olmocr.version import VERSION
 
 # Initialize logger
 logger = logging.getLogger(__name__)
@@ -380,7 +380,7 @@ def build_dolma_document(pdf_s3_path, page_results):
     # Build the Dolma document
     metadata = {
         "Source-File": pdf_s3_path,
-        "pdelfin-version": VERSION,
+        "olmocr-version": VERSION,
         "pdf-total-pages": len(page_results),
         "total-input-tokens": sum(page.input_tokens for page in page_results),
         "total-output-tokens": sum(page.output_tokens for page in page_results),
@@ -392,7 +392,7 @@ def build_dolma_document(pdf_s3_path, page_results):
     dolma_doc = {
         "id": id_,
         "text": document_text,
-        "source": "pdelfin",
+        "source": "olmocr",
         "added": datetime.datetime.now().strftime("%Y-%m-%d"),
         "created": datetime.datetime.now().strftime("%Y-%m-%d"),
         "metadata": metadata,
@@ -463,7 +463,7 @@ async def worker(args, work_queue: S3WorkQueue, semaphore, worker_id):
 
 
 async def sglang_server_task(args, semaphore):
-    model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'pdelfin', 'model')
+    model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'olmocr', 'model')
     download_directory(args.model, model_cache_dir)
 
     # Check the rope config and make sure it's got the proper key
@@ -642,7 +642,7 @@ def submit_beaker_job(args):
     owner = account.name
     beaker_image = f"jakep/pdelfin-inference-{VERSION}"
 
-    task_name = f"pdelfin-{os.path.basename(args.workspace.rstrip('/'))}"
+    task_name = f"olmocr-{os.path.basename(args.workspace.rstrip('/'))}"
 
     # Take out --beaker flag so the workers will just run things
     args_list = [arg for arg in sys.argv[1:] if arg != "--beaker"]
@@ -695,7 +695,7 @@ def submit_beaker_job(args):
                     preemptible=True,
                 ),
                 image=ImageSource(beaker=beaker_image),
-                command=["python", "-m", "pdelfin.beakerpipeline"] + args_list,
+                command=["python", "-m", "olmocr.beakerpipeline"] + args_list,
                 env_vars=[
                     EnvVar(name="BEAKER_JOB_NAME", value=task_name),
                     EnvVar(name="OWNER", value=owner),
@@ -857,7 +857,7 @@ async def main():
 
     # Beaker/job running stuff
     parser.add_argument('--beaker', action='store_true', help='Submit this job to beaker instead of running locally')
-    parser.add_argument('--beaker_workspace', help='Beaker workspace to submit to', default='ai2/pdelfin')
+    parser.add_argument('--beaker_workspace', help='Beaker workspace to submit to', default='ai2/olmocr')
     parser.add_argument('--beaker_cluster', help='Beaker clusters you want to run on', default=["ai2/jupiter-cirrascale-2", "ai2/ceres-cirrascale", "ai2/neptune-cirrascale", "ai2/saturn-cirrascale", "ai2/augusta-google-1"])
     parser.add_argument('--beaker_gpus', type=int, default=1, help="Number of gpu replicas to run")
     parser.add_argument('--beaker_priority', type=str, default="normal", help="Beaker priority level for the job")

olmocr/birrpipeline.py

@@ -25,11 +25,11 @@ from urllib.parse import urlparse
 import concurrent.futures
 from concurrent.futures import ProcessPoolExecutor, as_completed
 
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.prompts import build_finetuning_prompt, PageResponse
+from olmocr.prompts import build_finetuning_prompt, PageResponse
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.s3_utils import parse_custom_id, expand_s3_glob, get_s3_bytes, parse_s3_path
+from olmocr.s3_utils import parse_custom_id, expand_s3_glob, get_s3_bytes, parse_s3_path
-from pdelfin.check import check_poppler_version
+from olmocr.check import check_poppler_version
 
 # Initialize logger
 logger = logging.getLogger(__name__)
@@ -79,7 +79,7 @@ class DatabaseManager:
 
     def __init__(self, s3_workspace: str, skip_init: bool=False):
         cache_key = hashlib.sha256(s3_workspace.strip().lower().encode('utf-8')).hexdigest()
-        home_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'pdelfin', cache_key)
+        home_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'olmocr', cache_key)
         os.makedirs(home_cache_dir, exist_ok=True)
         self.db_path = os.path.join(home_cache_dir, 'index.db')
         
@@ -618,7 +618,7 @@ def build_dolma_doc(s3_workspace: str, pdf: DatabaseManager.PDFRecord) -> Option
     dolma_doc = {
         "id": id_,
         "text": document_text,
-        "source": "pdelfin",
+        "source": "olmocr",
         "added": datetime.datetime.now().strftime("%Y-%m-%d"),
         "created": datetime.datetime.now().strftime("%Y-%m-%d"),
         "metadata": metadata,

olmocr/check.py

@@ -14,7 +14,7 @@ def check_poppler_version():
             sys.exit(1)
     except FileNotFoundError:
         logger.error("pdftoppm is not installed.")
-        logger.error("Check the README in the https://github.com/allenai/pdelfin/blob/main/README.md for installation instructions")
+        logger.error("Check the README in the https://github.com/allenai/olmocr/blob/main/README.md for installation instructions")
         sys.exit(1)
 
 if __name__ == "__main__":

olmocr/data/buildsilver.py

@@ -12,10 +12,10 @@ from typing import Generator
 from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor, as_completed
 from urllib.parse import urlparse
 
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.prompts import build_openai_silver_data_prompt, openai_response_format_schema
+from olmocr.prompts import build_openai_silver_data_prompt, openai_response_format_schema
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.filter import PdfFilter
+from olmocr.filter import PdfFilter
 
 TARGET_IMAGE_DIM = 2048
 

olmocr/data/buildtestset.py

@@ -10,8 +10,8 @@ from concurrent.futures import ProcessPoolExecutor, as_completed
 from urllib.parse import urlparse
 from typing import List
 
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.filter import PdfFilter
+from olmocr.filter import PdfFilter
 
 pdf_filter = PdfFilter()
 

olmocr/data/convertsilver_birr.py

@@ -10,9 +10,9 @@ import os
 
 import smart_open
 import boto3
-from pdelfin.prompts import build_finetuning_prompt
+from olmocr.prompts import build_finetuning_prompt
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
 
 # Import Plotly for plotting
 import plotly.express as px

olmocr/data/convertsilver_openai.py

@@ -9,7 +9,7 @@ import logging
 
 import smart_open
 from cached_path import cached_path
-from pdelfin.prompts import build_finetuning_prompt
+from olmocr.prompts import build_finetuning_prompt
 
 
 def setup_logging():
@@ -73,12 +73,12 @@ def process_file(input_file: str, output_file: str, rewrite_prompt_str: bool):
                         # Save the pdf to a temporary cache folder
                         local_pdf_path = cached_path(s3_path, quiet=True)
 
-                        from pdelfin.prompts.anchor import get_anchor_text
+                        from olmocr.prompts.anchor import get_anchor_text
-                        from pdelfin.data.buildsilver import build_page_query
+                        from olmocr.data.buildsilver import build_page_query
                         obj = build_page_query(local_pdf_path, s3_path, page)
                         # raw_page_text = get_anchor_text(local_pdf_path, page, pdf_engine="pdfreport")
 
-                        # from pdelfin.prompts import build_openai_silver_data_prompt
+                        # from olmocr.prompts import build_openai_silver_data_prompt
                         # obj["body"]["messages"][0]["content"][0]["text"] = build_openai_silver_data_prompt(raw_page_text)
 
                 if obj is not None:

olmocr/eval/buildelo.py

@@ -8,12 +8,12 @@ import functools
 
 from tqdm import tqdm
 from itertools import combinations
-from pdelfin.s3_utils import parse_s3_path, expand_s3_glob, get_s3_bytes
+from olmocr.s3_utils import parse_s3_path, expand_s3_glob, get_s3_bytes
 from dolma_refine.evaluate.metrics import DocumentEditSimilarity
 from dolma_refine.evaluate.segmenters import SpacySegmenter
 from dolma_refine.evaluate.aligners import HirschbergAligner
 
-from pdelfin.eval.evalhtml import create_review_html
+from olmocr.eval.evalhtml import create_review_html
 
 @dataclasses.dataclass
 class Comparison:

olmocr/eval/evalhtml.py

@@ -7,7 +7,7 @@ from jinja2 import Template
 from urllib.parse import urlparse
 from difflib import SequenceMatcher
 from tqdm import tqdm
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
 
 session = boto3.Session(profile_name='s2')
 s3_client = session.client('s3')

olmocr/filter/filter.py

@@ -125,7 +125,7 @@ class PdfFilter:
 if __name__ == "__main__":
     import tempfile
     import boto3
-    from pdelfin.s3_utils import parse_s3_path
+    from olmocr.s3_utils import parse_s3_path
     from concurrent.futures import ProcessPoolExecutor, wait, FIRST_COMPLETED
     from tqdm import tqdm
 

olmocr/prompts/anchor.py

@@ -19,11 +19,11 @@ from functools import lru_cache
 import pypdfium2 as pdfium
 import pymupdf
 
-from pdelfin.filter.coherency import get_document_coherency
+from olmocr.filter.coherency import get_document_coherency
 
 from pypdf import PdfReader
 from pypdf.generic import RectangleObject
-from pdelfin.prompts._adv_anchor import mult
+from olmocr.prompts._adv_anchor import mult
 
 
 def get_anchor_text(local_pdf_path: str, page: int, pdf_engine: Literal["pdftotext", "pdfium", "pymupdf", "pypdf", "topcoherency", "pdfreport"], target_length: int=4000) -> str:

olmocr/s3_queue.py

@@ -9,7 +9,7 @@ from dataclasses import dataclass
 import asyncio
 from functools import partial
 
-from pdelfin.s3_utils import (
+from olmocr.s3_utils import (
     expand_s3_glob,
     download_zstd_csv,
     upload_zstd_csv,

olmocr/train/buildparquetdataset.py

@@ -5,7 +5,7 @@ import os
 import boto3
 from datasets import Dataset
 from botocore.exceptions import NoCredentialsError, PartialCredentialsError
-from pdelfin.train.dataloader import build_batch_query_response_vision_dataset
+from olmocr.train.dataloader import build_batch_query_response_vision_dataset
 
 
 def save_dataset_in_parquet(dataset: Dataset, output_dir: str, rows_per_file: int = 10000, s3_endpoint_url: str = None):

olmocr/train/dataloader.py

@@ -16,9 +16,9 @@ import boto3
 from datasets import Dataset, Features, Value, load_dataset, concatenate_datasets, DatasetDict
 from .core.config import DataConfig, SourceConfig
 
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.s3_utils import parse_custom_id, get_s3_bytes, parse_s3_path
+from olmocr.s3_utils import parse_custom_id, get_s3_bytes, parse_s3_path
-from pdelfin.data.renderpdf import get_pdf_media_box_width_height
+from olmocr.data.renderpdf import get_pdf_media_box_width_height
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -143,7 +143,7 @@ def cache_s3_files(dataset: Dataset, pdf_cache_location: str, num_proc: int = 32
 
 def build_finetuning_dataset(response_glob_path: str, pdf_cache_location: Optional[str]=None, num_proc: int=32) -> Dataset:
     if pdf_cache_location is None:
-        pdf_cache_location = os.path.join(os.path.expanduser('~'), '.cache', 'pdelfin_pdfs')
+        pdf_cache_location = os.path.join(os.path.expanduser('~'), '.cache', 'olmocr_pdfs')
 
     logger.info("Loading fine tuning dataset from OpenAI style batch responses")
     response_data = load_jsonl_into_ds(response_glob_path)

olmocr/train/dataprep.py

@@ -6,9 +6,9 @@ import base64
 import random
 import torch  # Make sure to import torch as it's used in the DataCollator
 
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.prompts import build_finetuning_prompt
+from olmocr.prompts import build_finetuning_prompt
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
 
 
 def prepare_data_for_qwen2_training(example, processor, target_longest_image_dim: Union[int, list[int]], target_anchor_text_len: Union[int, list[int]]):

olmocr/train/fixqwen2vlcheckpoint.py

@@ -9,7 +9,7 @@ import concurrent.futures
 from smart_open import smart_open
 
 from transformers import Qwen2VLForConditionalGeneration
-from pdelfin.s3_utils import parse_s3_path
+from olmocr.s3_utils import parse_s3_path
 
 s3_client = boto3.client('s3')
 

olmocr/train/inference.py

@@ -29,11 +29,11 @@ from transformers import (
 )
 
 
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
-from pdelfin.prompts.prompts import build_finetuning_prompt
+from olmocr.prompts.prompts import build_finetuning_prompt
 
-from pdelfin.train.dataprep import prepare_data_for_qwen2_inference
+from olmocr.train.dataprep import prepare_data_for_qwen2_inference
 
 def build_page_query(local_pdf_path: str, page: int) -> dict:
     image_base64 = render_pdf_to_base64png(local_pdf_path, page, 1024)

olmocr/train/loaddataset.py

@@ -3,8 +3,8 @@ from transformers import (
     DataCollatorForSeq2Seq
 )
 
-from pdelfin.train.core.cli import make_cli
+from olmocr.train.core.cli import make_cli
-from pdelfin.train.core.config import TrainConfig
+from olmocr.train.core.config import TrainConfig
 from tqdm import tqdm
 from .utils import (
     make_dataset, TruncatingCollator

olmocr/train/train.py

@@ -36,11 +36,11 @@ from torch.utils.data import DataLoader
 
 import wandb
 
-from pdelfin.train.core.cli import make_cli, save_config, to_native_types
+from olmocr.train.core.cli import make_cli, save_config, to_native_types
-from pdelfin.train.core.config import TrainConfig
+from olmocr.train.core.config import TrainConfig
-from pdelfin.train.core.loggers import get_logger
+from olmocr.train.core.loggers import get_logger
-from pdelfin.train.core.paths import copy_dir, join_path
+from olmocr.train.core.paths import copy_dir, join_path
-from pdelfin.train.core.state import BeakerState
+from olmocr.train.core.state import BeakerState
 
 from .utils import (
     RunName,

olmocr/train/utils.py

@@ -28,8 +28,8 @@ from .core.state import BeakerState
 
 T = TypeVar("T")
 
-from pdelfin.train.dataloader import build_finetuning_dataset, list_dataset_files
+from olmocr.train.dataloader import build_finetuning_dataset, list_dataset_files
-from pdelfin.train.dataprep import batch_prepare_data_for_qwen2_training, batch_prepare_data_for_molmo_training
+from olmocr.train.dataprep import batch_prepare_data_for_qwen2_training, batch_prepare_data_for_molmo_training
 
 
 def accelerator_to_dtype(accelerator: Accelerator) -> torch.dtype:

olmocr/viewer/dolmaviewer.py

@@ -11,8 +11,8 @@ from tqdm import tqdm
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import markdown2
 
-from pdelfin.s3_utils import get_s3_bytes
+from olmocr.s3_utils import get_s3_bytes
-from pdelfin.data.renderpdf import render_pdf_to_base64webp
+from olmocr.data.renderpdf import render_pdf_to_base64webp
 
 def read_jsonl(path):
     with smart_open.smart_open(path, 'r', encoding='utf-8') as f:

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 # See https://setuptools.pypa.io/en/latest/userguide/quickstart.html for more project configuration options.
-name = "pdelfin"
+name = "olmocr"
 dynamic = ["version"]
 readme = "README.md"
 classifiers = [
@@ -42,10 +42,10 @@ dependencies = [
 license = {file = "LICENSE"}
 
 [project.urls]
-Homepage = "https://github.com/allenai/pdelfin"
+Homepage = "https://github.com/allenai/olmocr"
-Repository = "https://github.com/allenai/pdelfin"
+Repository = "https://github.com/allenai/olmocr"
-Changelog = "https://github.com/allenai/pdelfin/blob/main/CHANGELOG.md"
+Changelog = "https://github.com/allenai/olmocr/blob/main/CHANGELOG.md"
-# Documentation = "https://pdelfin.readthedocs.io/"
+# Documentation = "https://olmocr.readthedocs.io/"
 
 [project.optional-dependencies]
 dev = [
@@ -103,10 +103,10 @@ exclude = [
 include-package-data = true
 
 [tool.setuptools.package-data]
-pdelfin = ["py.typed"]
+olmocr = ["py.typed"]
 
 [tool.setuptools.dynamic]
-version = {attr = "pdelfin.version.VERSION"}
+version = {attr = "olmocr.version.VERSION"}
 
 [tool.black]
 line-length = 120

scripts/beaker/Dockerfile-inference

@@ -36,17 +36,17 @@ RUN /root/.local/bin/uv pip install --system flashinfer -i https://flashinfer.ai
 ENV PYTHONUNBUFFERED=1
 WORKDIR /root
 COPY pyproject.toml pyproject.toml
-COPY pdelfin/version.py pdelfin/version.py
+COPY olmocr/version.py olmocr/version.py
 
 RUN /root/.local/bin/uv pip install --system --no-cache -e .[inference]
 
-COPY pdelfin pdelfin
+COPY olmocr olmocr
 
 # TODO You can remove this once pypdf > 5.10 comes out
 RUN /root/.local/bin/uv pip install --system --no-cache git+https://github.com/py-pdf/pypdf.git@c6e43374ab002d76811ec85333fdc2c82c268251
 
 WORKDIR /root
-COPY pdelfin pdelfin
+COPY olmocr olmocr
 
 RUN python3 -m sglang.launch_server --help
-RUN python3 -m pdelfin.beakerpipeline --help
+RUN python3 -m olmocr.beakerpipeline --help

scripts/build-docker.sh

@@ -2,8 +2,8 @@
 
 set -e
 
-VERSION=$(python -c 'import pdelfin.version; print(pdelfin.version.VERSION)')
+VERSION=$(python -c 'import olmocr.version; print(olmocr.version.VERSION)')
 echo "$VERSION"
 
-docker build --platform linux/amd64 -f ./scripts/beaker/Dockerfile-inference  -t pdelfin-inference-$VERSION .
+docker build --platform linux/amd64 -f ./scripts/beaker/Dockerfile-inference  -t olmocr-inference-$VERSION .
-beaker image create --workspace ai2/oe-data-pdf --name pdelfin-inference-$VERSION pdelfin-inference-$VERSION
+beaker image create --workspace ai2/oe-data-pdf --name olmocr-inference-$VERSION olmocr-inference-$VERSION

scripts/molmo-7b-lora-gantry.sh

@@ -10,7 +10,7 @@ then
 fi
 
 
-EXTRA_ARGS="-c pdelfin/train/config/molmo-o-lora-8192.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/molmo-pdf/v1/models/\${BEAKER_USER_ID}\""
+EXTRA_ARGS="-c olmocr/train/config/molmo-o-lora-8192.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/molmo-pdf/v1/models/\${BEAKER_USER_ID}\""
 
 run_name=$(basename "$0" .sh)
 
@@ -45,4 +45,4 @@ gantry run \
     --env-secret WANDB_API_KEY=JAKE_WANDB_API_KEY \
     --shared-memory 10GiB \
     --yes \
-    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m pdelfin.train.loaddataset ${EXTRA_ARGS} && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m pdelfin.train.train ${EXTRA_ARGS}"
+    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m olmocr.train.loaddataset ${EXTRA_ARGS} && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m olmocr.train.train ${EXTRA_ARGS}"

scripts/prepare_changelog.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 from pathlib import Path
 
-from pdelfin.version import VERSION
+from olmocr.version import VERSION
 
 
 def main():
@@ -27,7 +27,7 @@ def main():
     lines.insert(insert_index, "\n")
     lines.insert(
         insert_index + 1,
-        f"## [v{VERSION}](https://github.com/allenai/pdelfin/releases/tag/v{VERSION}) - "
+        f"## [v{VERSION}](https://github.com/allenai/olmocr/releases/tag/v{VERSION}) - "
         f"{datetime.now().strftime('%Y-%m-%d')}\n",
     )
 

scripts/qwen2vl-2b-gantry.sh

@@ -10,7 +10,7 @@ then
 fi
 
 
-EXTRA_ARGS="-c pdelfin/train/config/qwen2vl-2b.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
+EXTRA_ARGS="-c olmocr/train/config/qwen2vl-2b.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
 
 run_name=$(basename "$0" .sh)
 
@@ -43,4 +43,4 @@ gantry run \
     --env-secret WANDB_API_KEY=JAKE_WANDB_API_KEY \
     --shared-memory 10GiB \
     --yes \
-    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m pdelfin.train.train ${EXTRA_ARGS}"
+    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m olmocr.train.train ${EXTRA_ARGS}"

scripts/qwen2vl-7b-gantry.sh

@@ -10,7 +10,7 @@ then
 fi
 
 
-EXTRA_ARGS="-c pdelfin/train/config/qwen2vl-7b.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
+EXTRA_ARGS="-c olmocr/train/config/qwen2vl-7b.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
 
 run_name=$(basename "$0" .sh)
 
@@ -44,4 +44,4 @@ gantry run \
     --env-secret WANDB_API_KEY=JAKE_WANDB_API_KEY \
     --shared-memory 10GiB \
     --yes \
-    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m pdelfin.train.loaddataset ${EXTRA_ARGS} && accelerate launch --use_fsdp --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --fsdp_offload_params false --fsdp_sharding_strategy FULL_SHARD --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP --mixed_precision bf16 -m pdelfin.train.train ${EXTRA_ARGS}"
+    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m olmocr.train.loaddataset ${EXTRA_ARGS} && accelerate launch --use_fsdp --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --fsdp_offload_params false --fsdp_sharding_strategy FULL_SHARD --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP --mixed_precision bf16 -m olmocr.train.train ${EXTRA_ARGS}"

scripts/qwen2vl-7b-lora-gantry.sh

@@ -10,7 +10,7 @@ then
 fi
 
 
-EXTRA_ARGS="-c pdelfin/train/config/qwen2vl-7b-lora.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
+EXTRA_ARGS="-c olmocr/train/config/qwen2vl-7b-lora.yaml --num_proc 64 --save.path \"s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/\${BEAKER_USER_ID}\""
 
 run_name=$(basename "$0" .sh)
 
@@ -46,4 +46,4 @@ gantry run \
     --env-secret WANDB_API_KEY=JAKE_WANDB_API_KEY \
     --shared-memory 10GiB \
     --yes \
-    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m pdelfin.train.loaddataset ${EXTRA_ARGS} && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m pdelfin.train.train ${EXTRA_ARGS}"
+    -- /bin/bash -c "source scripts/beaker/${CLUSTER}-ib.sh && python -m olmocr.train.loaddataset ${EXTRA_ARGS} && accelerate launch --multi_gpu --num_processes \${BEAKER_ASSIGNED_GPU_COUNT} --mixed_precision bf16 -m olmocr.train.train ${EXTRA_ARGS}"

scripts/release.sh

@@ -2,7 +2,7 @@
 
 set -e
 
-TAG=$(python -c 'from pdelfin.version import VERSION; print("v" + VERSION)')
+TAG=$(python -c 'from olmocr.version import VERSION; print("v" + VERSION)')
 
 read -p "Creating new release for $TAG. Do you want to continue? [Y/n] " prompt
 

tests/test_anchor.py

@@ -6,8 +6,8 @@ import glob
 
 from pypdf import PdfReader
 
-from pdelfin.prompts.anchor import _pdf_report, _linearize_pdf_report, get_anchor_text
+from olmocr.prompts.anchor import _pdf_report, _linearize_pdf_report, get_anchor_text
-from pdelfin.data.renderpdf import get_pdf_media_box_width_height
+from olmocr.data.renderpdf import get_pdf_media_box_width_height
 
 class AnchorTest(unittest.TestCase):
     def testExtractText(self):
@@ -168,11 +168,11 @@ class BuildSilverTest(unittest.TestCase):
     def testSmallPage(self):
         local_pdf_path = os.path.join(os.path.dirname(__file__), "gnarly_pdfs", "small_page_size.pdf")
 
-        from pdelfin.data.buildsilver import build_page_query
+        from olmocr.data.buildsilver import build_page_query
 
         result = build_page_query(local_pdf_path, "s3://test.pdf", 1)
 
-        from pdelfin.data.renderpdf import get_png_dimensions_from_base64
+        from olmocr.data.renderpdf import get_png_dimensions_from_base64
 
         base64data = result["body"]["messages"][0]["content"][1]["image_url"]["url"]
 

tests/test_birr_outputs.py

@@ -4,15 +4,15 @@ from io import BytesIO
 from PIL import Image
 from transformers import AutoProcessor
 
-from pdelfin.data.renderpdf import render_pdf_to_base64png
+from olmocr.data.renderpdf import render_pdf_to_base64png
-from pdelfin.train.dataprep import (
+from olmocr.train.dataprep import (
     prepare_data_for_qwen2_training, build_finetuning_prompt
 )
 import numpy as np
 from tqdm import tqdm
 from torch.utils.data import DataLoader
-from pdelfin.train.utils import make_dataset
+from olmocr.train.utils import make_dataset
-from pdelfin.train.core.config import TrainConfig, DataConfig, SourceConfig
+from olmocr.train.core.config import TrainConfig, DataConfig, SourceConfig
 
 import math
 
@@ -138,7 +138,7 @@ class TestBirrTokenization(unittest.TestCase):
         from birr.core.config import FormatConfig, LLMModelConfig
         from birr.batch_inference.data_models import RawInputItem
 
-        from pdelfin.birrpipeline import build_page_query
+        from olmocr.birrpipeline import build_page_query
 
         original_query = build_page_query(os.path.join(
             os.path.dirname(__file__),

tests/test_birrpipeline.py

@@ -7,11 +7,11 @@ import base64
 from PIL import Image
 
 # Adjust the import path to match where your code resides
-from pdelfin.birrpipeline import build_dolma_doc, DatabaseManager, build_finetuning_prompt, build_page_query
+from olmocr.birrpipeline import build_dolma_doc, DatabaseManager, build_finetuning_prompt, build_page_query
 
 class TestBuildDolmaDoc(unittest.TestCase):
-    @patch('pdelfin.birrpipeline.DatabaseManager')
+    @patch('olmocr.birrpipeline.DatabaseManager')
-    @patch('pdelfin.birrpipeline.get_s3_bytes')
+    @patch('olmocr.birrpipeline.get_s3_bytes')
     def test_build_dolma_doc_with_multiple_page_entries(self, mock_get_s3_bytes, mock_DatabaseManager):
         # Mock DatabaseManager instance
         mock_db_instance = MagicMock()

tests/test_cappedpool.py

@@ -4,7 +4,7 @@ import concurrent.futures
 from concurrent.futures import TimeoutError
 
 # Assuming the CappedProcessPoolExecutor code is in a module named 'capped_executor'
-from pdelfin.cappedpool import CappedProcessPoolExecutor
+from olmocr.cappedpool import CappedProcessPoolExecutor
 
 # Define functions at the top level to ensure they are picklable by multiprocessing
 

tests/test_coherency.py

@@ -5,9 +5,9 @@ import time
 import unittest
 
 
-from pdelfin.filter.coherency import get_document_coherency
+from olmocr.filter.coherency import get_document_coherency
 
-from pdelfin.prompts.anchor import get_anchor_text
+from olmocr.prompts.anchor import get_anchor_text
 
 class TestCoherencyScores(unittest.TestCase):
     def testBadOcr1(self):

tests/test_dataloader.py

@@ -5,14 +5,14 @@ from functools import partial
 
 from transformers import AutoProcessor
 
-from pdelfin.train.dataloader import (
+from olmocr.train.dataloader import (
     build_finetuning_dataset,
     extract_openai_batch_response,
     load_jsonl_into_ds,
     list_dataset_files
 )
 
-from pdelfin.train.dataprep import batch_prepare_data_for_qwen2_training
+from olmocr.train.dataprep import batch_prepare_data_for_qwen2_training
 
 
 class TestBatchQueryResponseDataset(unittest.TestCase):

tests/test_dataprep.py

@@ -10,19 +10,19 @@ from PIL import Image
 from transformers import AutoProcessor
 from unittest.mock import patch
 
-from pdelfin.train.dataloader import (
+from olmocr.train.dataloader import (
     build_finetuning_dataset,
 )
 
-from pdelfin.train.dataprep import (
+from olmocr.train.dataprep import (
     prepare_data_for_qwen2_training, build_finetuning_prompt,
     prepare_data_for_molmo_training, batch_prepare_data_for_molmo_training
 )
 import numpy as np
 from tqdm import tqdm
 from torch.utils.data import DataLoader
-from pdelfin.train.utils import make_dataset
+from olmocr.train.utils import make_dataset
-from pdelfin.train.core.config import TrainConfig, DataConfig, SourceConfig
+from olmocr.train.core.config import TrainConfig, DataConfig, SourceConfig
 
 class TestDataprep(unittest.TestCase):
     def testFullDataloader(self):
@@ -215,8 +215,8 @@ class TestMolmoDataPrep(unittest.TestCase):
         random.seed(42)
 
         # Mock the functions that require actual PDF files
-        with patch('pdelfin.prompts.anchor.get_anchor_text') as mock_get_anchor_text, \
+        with patch('olmocr.prompts.anchor.get_anchor_text') as mock_get_anchor_text, \
-            patch('pdelfin.data.renderpdf.render_pdf_to_base64png') as mock_render_pdf_to_base64png:
+            patch('olmocr.data.renderpdf.render_pdf_to_base64png') as mock_render_pdf_to_base64png:
 
             # Set return values for the mocked functions
             mock_get_anchor_text.return_value = "This is the anchor text."
@@ -323,8 +323,8 @@ class TestMolmoDataPrep(unittest.TestCase):
         target_anchor_text_len = [0, 6000]
 
         # Mock the necessary functions
-        with patch('pdelfin.prompts.anchor.get_anchor_text') as mock_get_anchor_text, \
+        with patch('olmocr.prompts.anchor.get_anchor_text') as mock_get_anchor_text, \
-            patch('pdelfin.data.renderpdf.render_pdf_to_base64png') as mock_render_pdf_to_base64png:
+            patch('olmocr.data.renderpdf.render_pdf_to_base64png') as mock_render_pdf_to_base64png:
 
             mock_get_anchor_text.return_value = "This is the anchor text."
             img = Image.new('RGB', (100, 100), color='red')

tests/test_filter.py

@@ -3,7 +3,7 @@ import unittest
 
 from pypdf import PdfReader
 
-from pdelfin.filter import PdfFilter
+from olmocr.filter import PdfFilter
 
 
 class PdfFilterTest(unittest.TestCase):

tests/test_s3_work_queue.py

@@ -7,7 +7,7 @@ import hashlib
 from typing import List, Dict
 
 # Import the classes we're testing
-from pdelfin.s3_queue import S3WorkQueue, WorkItem
+from olmocr.s3_queue import S3WorkQueue, WorkItem
 
 class TestS3WorkQueue(unittest.TestCase):
     def setUp(self):
@@ -70,8 +70,8 @@ class TestS3WorkQueue(unittest.TestCase):
     async def test_populate_queue_new_items(self):
         """Test populating queue with new items"""
         # Mock empty existing index
-        with patch('pdelfin.s3_queue.download_zstd_csv', return_value=[]):
+        with patch('olmocr.s3_queue.download_zstd_csv', return_value=[]):
-            with patch('pdelfin.s3_queue.upload_zstd_csv') as mock_upload:
+            with patch('olmocr.s3_queue.upload_zstd_csv') as mock_upload:
                 await self.work_queue.populate_queue(self.sample_paths, items_per_group=2)
                 
                 # Verify upload was called with correct data
@@ -97,8 +97,8 @@ class TestS3WorkQueue(unittest.TestCase):
         existing_hash = S3WorkQueue._compute_workgroup_hash(existing_paths)
         existing_line = f"{existing_hash},{existing_paths[0]}"
         
-        with patch('pdelfin.s3_queue.download_zstd_csv', return_value=[existing_line]):
+        with patch('olmocr.s3_queue.download_zstd_csv', return_value=[existing_line]):
-            with patch('pdelfin.s3_queue.upload_zstd_csv') as mock_upload:
+            with patch('olmocr.s3_queue.upload_zstd_csv') as mock_upload:
                 await self.work_queue.populate_queue(existing_paths + new_paths, items_per_group=1)
                 
                 # Verify upload called with both existing and new items
@@ -116,8 +116,8 @@ class TestS3WorkQueue(unittest.TestCase):
         
         completed_items = [f"s3://test-bucket/workspace/results/output_{work_hash}.jsonl"]
         
-        with patch('pdelfin.s3_queue.download_zstd_csv', return_value=[work_line]):
+        with patch('olmocr.s3_queue.download_zstd_csv', return_value=[work_line]):
-            with patch('pdelfin.s3_queue.expand_s3_glob', return_value=completed_items):
+            with patch('olmocr.s3_queue.expand_s3_glob', return_value=completed_items):
                 await self.work_queue.initialize_queue()
                 
                 # Queue should be empty since all work is completed

tests/test_sglang.py

@@ -17,8 +17,8 @@ from io import BytesIO
 from PIL import Image
 from transformers import AutoProcessor, AutoTokenizer, Qwen2VLForConditionalGeneration
 from pathlib import Path
-from pdelfin.beakerpipeline import sglang_server_task, sglang_server_ready, build_page_query, SGLANG_SERVER_PORT, render_pdf_to_base64png, get_anchor_text, download_directory
+from olmocr.beakerpipeline import sglang_server_task, sglang_server_ready, build_page_query, SGLANG_SERVER_PORT, render_pdf_to_base64png, get_anchor_text, download_directory
-from pdelfin.prompts import PageResponse
+from olmocr.prompts import PageResponse
 from httpx import AsyncClient
 import torch.nn.functional as F
 MODEL_FINETUNED_PATH = "s3://ai2-oe-data/jakep/experiments/qwen2vl-pdf/v1/models/jakep/Qwen_Qwen2-VL-7B-Instruct-e4ecf8-01JAH8GMWHTJ376S2N7ETXRXH4/checkpoint-9500/bf16/"
@@ -103,7 +103,7 @@ class TestSglangServer(unittest.IsolatedAsyncioTestCase):
 class TestHuggingFaceModel(unittest.IsolatedAsyncioTestCase):
     async def asyncSetUp(self):
         # Set up the Hugging Face model and tokenizer
-        model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'pdelfin', 'model')
+        model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'olmocr', 'model')
         download_directory([MODEL_FINETUNED_PATH], model_cache_dir)
 
         # Check the rope config and make sure it's got the proper key
@@ -249,7 +249,7 @@ class TestHuggingFaceModel(unittest.IsolatedAsyncioTestCase):
 class RawSGLangTest(unittest.IsolatedAsyncioTestCase):
     def setUp(self):
         # Set up the Hugging Face model and tokenizer
-        model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'pdelfin', 'model')
+        model_cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'olmocr', 'model')
         download_directory([MODEL_FINETUNED_PATH], model_cache_dir)
 
         # Check the rope config and make sure it's got the proper key