Improve model card: Add metadata and GitHub link

#2
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +10 -2
README.md CHANGED
@@ -1,7 +1,16 @@
 
 
 
 
 
 
 
1
  # CLIP Model for Chart Understanding
2
 
3
  This repository contains the CLIP model implementation from our paper "[On the Perception Bottleneck of VLMs for Chart Understanding](https://arxiv.org/abs/2503.18435)".
4
 
 
 
5
  ## Overview
6
 
7
  This CLIP model is specifically trained to address the perception bottleneck in Vision Language Models (VLMs) when processing and understanding charts and visualizations. Our work explores and aims to improve how CLIP effect its LVLMs.
@@ -29,5 +38,4 @@ If you find this model useful in your research, please consider citing our paper
29
  primaryClass={cs.CV},
30
  url={https://arxiv.org/abs/2503.18435},
31
  }
32
- ```
33
-
 
1
+ ---
2
+ pipeline_tag: image-feature-extraction
3
+ library_name: transformers
4
+ datasets:
5
+ - Junteng/Vision4Chart
6
+ ---
7
+
8
  # CLIP Model for Chart Understanding
9
 
10
  This repository contains the CLIP model implementation from our paper "[On the Perception Bottleneck of VLMs for Chart Understanding](https://arxiv.org/abs/2503.18435)".
11
 
12
+ **Code**: https://github.com/hkust-nlp/Vision4Chart
13
+
14
  ## Overview
15
 
16
  This CLIP model is specifically trained to address the perception bottleneck in Vision Language Models (VLMs) when processing and understanding charts and visualizations. Our work explores and aims to improve how CLIP effect its LVLMs.
 
38
  primaryClass={cs.CV},
39
  url={https://arxiv.org/abs/2503.18435},
40
  }
41
+ ```