Docling/docling
Christoph Auer eb97357b05
feat: Use new TableFormer model weights and default to accurate model version (#1100)
* feat: New tableformer model weights [WIP]

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

* Updated TF version

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated tests, after merging with Main, Switched to Accurate TF model by default

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
2025-03-11 10:53:49 +01:00
..
backend fix: enable locks for threadsafe pdfium (#1052) 2025-03-02 20:06:44 +01:00
chunking feat: expose new hybrid chunker, update docs (#384) 2024-12-09 08:28:29 +01:00
cli feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
datamodel feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
models feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
pipeline feat: [Experimental] Introduce VLM pipeline using HF AutoModelForVision2Seq, featuring SmolDocling model (#1054) 2025-02-26 14:43:26 +01:00
utils fix: Proper handling of orphan IDs in layout postprocessing (#1118) 2025-03-05 14:30:59 +01:00
__init__.py Initial commit 2024-07-15 09:42:42 +02:00
document_converter.py feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
exceptions.py feat: Introduce the enable_remote_services option to allow remote connections while processing (#941) 2025-02-12 15:18:01 +01:00
py.typed fix: Add py.typed marker file (#531) 2024-12-06 13:42:14 +01:00