Qwen
/

Qwen2-VL-72B-Instruct

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

bluelike commited on Sep 18

Commit

90dedb5

•

1 Parent(s): b33bc7d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -59,7 +59,7 @@ We have three models with 2, 8 and 72 billion parameters. This repo contains the
 | InfoVQA<sub>test</sub>  | 82.0 | - | - | **84.5**
 | ChartQA<sub>test</sub>  | 88.4 | **90.8** | 85.7 | 88.3
 | TextVQA<sub>val</sub>  | 84.4 | - | - | **85.5**
-| OCRBench | 852 | 788 | 736 | **881**
 | MTVQA | 17.3 | 25.7 | 27.8 | **30.9**
 | VCR<sub>en easy</sub>  | 84.67 | 63.85 | 91.55 | **91.93**
 | VCR<sub>zh easy</sub>  | 22.09 | 1.0| 14.87 | **65.37**

 | InfoVQA<sub>test</sub>  | 82.0 | - | - | **84.5**
 | ChartQA<sub>test</sub>  | 88.4 | **90.8** | 85.7 | 88.3
 | TextVQA<sub>val</sub>  | 84.4 | - | - | **85.5**
+| OCRBench | 852 | 788 | 736 | **877**
 | MTVQA | 17.3 | 25.7 | 27.8 | **30.9**
 | VCR<sub>en easy</sub>  | 84.67 | 63.85 | 91.55 | **91.93**
 | VCR<sub>zh easy</sub>  | 22.09 | 1.0| 14.87 | **65.37**