DAMO-NLP-SG
/

VL3-SigLIP-NaViT

Image Feature Extraction

videollama3_vision_encoder

feature-extraction

multi-modal-large-language-model

Model card Files Files and versions Community

Cyril666 commited on Jan 24

Commit

ed2c154

·

verified ·

1 Parent(s): 50d747a

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -33,11 +33,11 @@ Before training, the model parameters and architecture are initialized from [Sig
 ## 🚀 Model Porfermance
-| Model                           | GQA        | AI2D       | ChartQA     | DocVQA<sub>val</sub>     | MME        |
 |---------------------------------|------------|------------|-------------|--------------------------|------------|
 | clip-vit-large-patch14-336      |   61.50    |   56.28    |   18.32     |   24.86                  | **1668.41**|
 | dfn5B-clip-vit-h-14-378         |   62.70    |   56.87    |   16.40     |   23.09                  |   1665.35  |
-| siglip-so400m-patch14-384       | **62.92**  | **57.12**  | **22.44**   | **31.32**                |   1667.92  |
 * A more detailed analysis can be found in our [paper](https://arxiv.org/abs/2501.13106).

 ## 🚀 Model Porfermance
+| Base Model                           | GQA        | AI2D       | ChartQA     | DocVQA<sub>val</sub>     | MME        |
 |---------------------------------|------------|------------|-------------|--------------------------|------------|
 | clip-vit-large-patch14-336      |   61.50    |   56.28    |   18.32     |   24.86                  | **1668.41**|
 | dfn5B-clip-vit-h-14-378         |   62.70    |   56.87    |   16.40     |   23.09                  |   1665.35  |
+| siglip-so400m-patch14-384 **This Implementation**       | **62.92**  | **57.12**  | **22.44**   | **31.32**                |   1667.92  |
 * A more detailed analysis can be found in our [paper](https://arxiv.org/abs/2501.13106).