HF中国镜像站's logo

ds4sd
/
SmolDocling-256M-preview

Image-Text-to-Text
Transformers
ONNX
Safetensors
English
idefics3
conversational
Inference Endpoints
Model card Files Community
25
asnassar commited on
Commit
cd2c4cb
·
verified ·
1 Parent(s): b1e7508

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -8,9 +8,13 @@ base_model:
8
  pipeline_tag: image-text-to-text
9
  ---
10
 
11
- ### SmolDocling-256M-preview
12
-
13
- SmolDocling is a multimodal Image-Text-to-Text model designed for efficient document conversion. It retains Docling's most popular features while ensuring full compatibility with Docling through seamless support for **DoclingDocuments**.
 
 
 
 
14
 
15
  ### 🚀 Features:
16
  - 🏷️ **DocTags for Efficient Tokenization** – Introduces DocTags an efficient and minimal representation for documents that is fully compatible with **DoclingDocuments**.
 
8
  pipeline_tag: image-text-to-text
9
  ---
10
 
11
+ <div style="display: flex; align-items: center;">
12
+ <img src="https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/assets/SmolDocling_doctags1.png" alt="SmolDocling" style="width: 200px; height: auto; margin-right: 20px;">
13
+ <div>
14
+ <h3>SmolDocling-256M-preview</h3>
15
+ <p>SmolDocling is a multimodal Image-Text-to-Text model designed for efficient document conversion. It retains Docling's most popular features while ensuring full compatibility with Docling through seamless support for <strong>DoclingDocuments</strong>.</p>
16
+ </div>
17
+ </div>
18
 
19
  ### 🚀 Features:
20
  - 🏷️ **DocTags for Efficient Tokenization** – Introduces DocTags an efficient and minimal representation for documents that is fully compatible with **DoclingDocuments**.