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>

docling/cli/main.py

@@ -210,7 +210,7 @@ def convert(
     table_mode: Annotated[
         TableFormerMode,
         typer.Option(..., help="The mode to use in the table structure model."),
-    ] = TableFormerMode.FAST,
+    ] = TableFormerMode.ACCURATE,
     enrich_code: Annotated[
         bool,
         typer.Option(..., help="Enable the code enrichment model in the pipeline."),

docling/datamodel/pipeline_options.py

@@ -99,7 +99,7 @@ class TableStructureOptions(BaseModel):
         #        are merged across table columns.
         # False: Let table structure model define the text cells, ignore PDF cells.
     )
-    mode: TableFormerMode = TableFormerMode.FAST
+    mode: TableFormerMode = TableFormerMode.ACCURATE
 
 
 class OcrOptions(BaseModel):

docling/models/table_structure_model.py

@@ -95,7 +95,7 @@ class TableStructureModel(BasePageModel):
             repo_id="ds4sd/docling-models",
             force_download=force,
             local_dir=local_dir,
-            revision="v2.1.0",
+            revision="v2.2.0",
         )
 
         return Path(download_path)