CPU-only page classifier for text extracted from PDFs (no OCR), designed for, "label": one of invoice|lab|radiology|dischargesummary}, split train/val/test. Point steps 2-4 at it with --data-dir; re-calibrate thresholds on your val split before deploying.
Model Card
CPU-only page classifier for text extracted from PDFs (no OCR), designed for, "label": one of invoice|lab|radiology|dischargesummary}, split train/val/test. Point steps 2-4 at it with --data-dir; re-calibrate thresholds on your val split before deploying. Note traintransformer.py targets transformers==4.57. — 5.x removed several TrainingArguments kwargs this script uses. - Live-metrics trackio dashboard could not be hosted on this account (Gradio Spaces require PRO), so run metrics live in the job logs.
Excerpt from the card by Azhar.
Identity and Version
- Repository
- amohammed3339/doc-cascade-fastpath
- Publisher
- Azhar
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 2bd40ea68ac453127b7ba8ccfb1808b7ed5578e3
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
12 files, 1.4 MB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| artifacts/cascade_config.json | Configuration | 211 B | — |
| scripts/calibrate_cascade.py | Configuration | 4.2 KB | — |
| scripts/classify_pages.py | Configuration | 5.2 KB | — |
| scripts/generate_synth_pages.py | Configuration | 13.5 KB | — |
| scripts/train_fastpath.py | Configuration | 3.5 KB | — |
| scripts/train_transformer.py | Configuration | 5.1 KB | — |
| README.md | Documentation | 4.2 KB | — |
| artifacts/fastpath.pkl | Other | 1.3 MB | 87b3a44acc78 |
| artifacts/fastpath_test_probs.npy | Other | 32.1 KB | 374f7f0018d5 |
| artifacts/fastpath_val_probs.npy | Other | 32.1 KB | c47e9650a131 |
| requirements.txt | Other | 302 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Released by Azhar through its official repository on Hugging Face.