Hugging Face's logo

DAMO-NLP-SG
/
VL3-SigLIP-NaViT

Image Feature Extraction
Transformers
Safetensors
English
videollama3_vision_encoder
feature-extraction
visual-encoder
multi-modal-large-language-model
custom_code
Model card Files Community
6
Cyril666 commited on
Commit
bd1afa4
·
verified ·
1 Parent(s): 6217c34

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -37,7 +37,7 @@ Before training, the model parameters and architecture are initialized from [Sig
37
  |---------------------------------|------------|------------|-------------|--------------------------|------------|
38
  | clip-vit-large-patch14-336 | 61.50 | 56.28 | 18.32 | 24.86 | **1668.41**|
39
  | dfn5B-clip-vit-h-14-378 | 62.70 | 56.87 | 16.40 | 23.09 | 1665.35 |
40
- | siglip-so400m-patch14-384 **(This Implementation)** | **62.92** | **57.12** | **22.44** | **31.32** | 1667.92 |
41
 
42
  * A more detailed analysis can be found in our [paper](https://arxiv.org/abs/2501.13106).
43
 
 
37
  |---------------------------------|------------|------------|-------------|--------------------------|------------|
38
  | clip-vit-large-patch14-336 | 61.50 | 56.28 | 18.32 | 24.86 | **1668.41**|
39
  | dfn5B-clip-vit-h-14-378 | 62.70 | 56.87 | 16.40 | 23.09 | 1665.35 |
40
+ | siglip-so400m-patch14-384 **(Our Implementation)** | **62.92** | **57.12** | **22.44** | **31.32** | 1667.92 |
41
 
42
  * A more detailed analysis can be found in our [paper](https://arxiv.org/abs/2501.13106).
43