vikhyatk
/

moondream2

Image-Text-to-Text

text-generation

Inference Endpoints

Model card Files Files and versions Community

vikhyatk commited on Jul 23

Commit

a84c5e1

•

1 Parent(s): de9591f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ moondream2 is a small vision language model designed to run efficiently on edge
 **Benchmarks**
-| Release | VQAv2 | GQA | TextVQA | TallyQA<br>(simple / full) | POPE<br>(random / popular / adversarial)
 | --- | --- | --- | --- | --- | --- |
 | **2024-05-20** (latest) | 79.4 | 63.1 | 57.2 | 82.1 / 76.6 | 91.5 / 89.6 / 86.2 |
 | 2024-05-08 | 79.0 | 62.7 | 53.1 | 81.6 / 76.1 | 90.6 / 88.3 / 85.0 |

 **Benchmarks**
+| Release | VQAv2 | GQA | TextVQA | TallyQA<br>(simple/full) | POPE<br>(rand/pop/adv)
 | --- | --- | --- | --- | --- | --- |
 | **2024-05-20** (latest) | 79.4 | 63.1 | 57.2 | 82.1 / 76.6 | 91.5 / 89.6 / 86.2 |
 | 2024-05-08 | 79.0 | 62.7 | 53.1 | 81.6 / 76.1 | 90.6 / 88.3 / 85.0 |