feat: new torch-based docling models (#120)

---------

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>

docling/document_converter.py

@@ -67,7 +67,10 @@ class DocumentConverter:
         from huggingface_hub import snapshot_download
 
         download_path = snapshot_download(
-            repo_id="ds4sd/docling-models", force_download=force, local_dir=local_dir
+            repo_id="ds4sd/docling-models",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v2.0.0",
         )
 
         return Path(download_path)

docling/models/layout_model.py

@@ -33,6 +33,7 @@ class LayoutModel:
         "Page-footer",
         "Code",
         "List-item",
+        # "Title"
         # "Formula",
     ]
     PAGE_HEADER_LABELS = ["Page-header", "Page-footer"]
@@ -69,9 +70,7 @@ class LayoutModel:
             "Key-Value Region": 0.45,
         }
 
-        CLASS_REMAPPINGS = {
-            "Document Index": "Table",
-        }
+        CLASS_REMAPPINGS = {"Document Index": "Table", "Title": "Section-header"}
 
         _log.debug("================= Start postprocess function ====================")
         start_time = time.time()
@@ -277,6 +276,7 @@ class LayoutModel:
                     bbox=BoundingBox.model_validate(pred_item),
                     cells=[],
                 )
+
                 clusters.append(cluster)
 
             # Map cells to clusters

docling/pipeline/standard_model_pipeline.py

@@ -8,7 +8,7 @@ from docling.pipeline.base_model_pipeline import BaseModelPipeline
 
 
 class StandardModelPipeline(BaseModelPipeline):
-    _layout_model_path = "model_artifacts/layout/beehive_v0.0.5"
+    _layout_model_path = "model_artifacts/layout/beehive_v0.0.5_pt"
     _table_model_path = "model_artifacts/tableformer"
 
     def __init__(self, artifacts_path: Path, pipeline_options: PipelineOptions):