OpenGVLab
/

InternVL-14B-Flickr30K-FT-364px

Feature Extraction

Image-to-Text Retrieval

Text-To-Image Retrieval

Model card Files Files and versions Metrics Training metrics Community

czczup commited on Mar 1

Commit

6e93733

•

1 Parent(s): def293b

Update README.md

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -26,6 +26,10 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
   - Image size: 364 x 364
 - **Finetune Dataset:** Flickr30K
 ## Performance
 See this [document](https://github.com/OpenGVLab/InternVL/tree/main/internvl_g#flickr30k) for more details about the evaluation.

   - Image size: 364 x 364
 - **Finetune Dataset:** Flickr30K
+## Setting
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/yuGYJIUQmgc6o87JulBMK.png)
 ## Performance
 See this [document](https://github.com/OpenGVLab/InternVL/tree/main/internvl_g#flickr30k) for more details about the evaluation.