HanXiao1999
/

DocMark-Pretrain-2B

Image-Text-to-Text

feature-extraction

Model card Files Files and versions

nielsr HF Staff commited on Jun 18

Commit

f0be3a6

·

verified ·

1 Parent(s): 6c34a9b

Add metadata and link to paper

This PR ensures your model shows up at https://huggingface.co/papers/2505.05446.

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -1,6 +1,10 @@
 ---
 datasets:
 - HanXiao1999/DocMark-Pile
 base_model:
 - OpenGVLab/InternVL2-2B
----

 ---
 datasets:
 - HanXiao1999/DocMark-Pile
+library_name: transformers
+pipeline_tag: image-text-to-text
 base_model:
 - OpenGVLab/InternVL2-2B
+---
+This repository contains the model presented in [DocMark: Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding](https://huggingface.co/papers/2505.05446).