asnassar commited on
Commit
56b796c
·
verified ·
1 Parent(s): 04e22bf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -148,8 +148,8 @@ print(f"Total time: {time.time() - start_time:.2f} sec")
148
  ## DocTags
149
 
150
  <img src="https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/assets/doctags_v2.png" width="800" height="auto" alt="Image description">
151
-
152
-
153
 
154
  ## Supported Instructions
155
  | Instruction | Description |
 
148
  ## DocTags
149
 
150
  <img src="https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/assets/doctags_v2.png" width="800" height="auto" alt="Image description">
151
+ DocTags create a clear and structured system of tags and rules that separate text from the document's structure. This makes things easier for Image-to-Sequence models by reducing confusion. On the other hand, converting directly to formats like HTML or Markdown can be messy—it often loses details, doesn’t clearly show the document’s layout, and increases the number of tokens, making processing less efficient.
152
+ DocTags are integrated with Docling, which allows export to HTML, Markdown, and JSON. These exports can be offloaded to the CPU, reducing token generation overhead and improving efficiency.
153
 
154
  ## Supported Instructions
155
  | Instruction | Description |