Update README.md (#98)

deepglint · Feb 7, 2025 · da70e85 · da70e85
1 parent d92b56a
commit da70e85
Showing 1 changed file with 9 additions and 9 deletions.
diff --git a/README.md b/README.md
@@ -11,19 +11,19 @@ This repository focuses on building foundational visual models for large languag
 
 We used the official LLaVA-NeXT and conducted training and validation with the official data.
 
-| Vision Tower                                                                                 | ChartQA | DocVQA | InfoVQA | OCRBench | MMMU  |
-| :------------------------------------------------------------------------------------------- | :------ | :----- | :------ | :------- | :---- |
-| CLIP (ViT-L-14-336px)                                                                        | 66.52   | 75.21  | 38.88   | 525.00   | 44.20 |
-| MLCD (ViT-L-14-336px)   | 67.84   | 76.46  | 43.48   | 531.00   | 44.30 |
-| MLCD (ViT-bigG-14-336px) | 71.92   | 79.63  | 44.38   | 577.00   | 46.78 |
+| Vision Tower             | RoPE2D | ChartQA | DocVQA | InfoVQA | OCRBench | MMMU  |
+| :----------------------- | :----: | :------ | :----- | :------ | :------- | :---- |
+| CLIP (ViT-L-14-336px)    |   ×    | 66.52   | 75.21  | 38.88   | 525.00   | 44.20 |
+| MLCD (ViT-L-14-336px)    |   ×    | 67.84   | 76.46  | 43.48   | 531.00   | 44.30 |
+| MLCD (ViT-bigG-14-336px) |   √    | 71.92   | 79.63  | 44.38   | 577.00   | 46.78 |
 
 The results of the ImageNet linear probe are as follows:
 
-| Model Name             | ImageNet Linear Probe | Hugging Face                                                                               | 
+| Model Name             | ImageNet Linear Probe | Hugging Face                                                                               |
 | :--------------------- | :-------------------: | :----------------------------------------------------------------------------------------- |
-| MLCD-ViT-bigG-14-224px |         87.1          | [HF:MLCD-ViT-bigG-14-224px](https://huggingface.co/DeepGlint-AI/mlcd-vit-bigG-patch14-224) |      
-| MLCD-ViT-L-14-336px    |         86.3          | [HF:MLCD-ViT-L-14-336px](https://huggingface.co/DeepGlint-AI/mlcd-vit-large-patch14-336)   |      
-| MLCD-ViT-B-32-224px    |         79.1          | [HF:MLCD-ViT-B-32-224px](https://huggingface.co/DeepGlint-AI/mlcd-vit-base-patch32-224)    |      
+| MLCD-ViT-bigG-14-224px |         87.1          | [HF:MLCD-ViT-bigG-14-224px](https://huggingface.co/DeepGlint-AI/mlcd-vit-bigG-patch14-224) |
+| MLCD-ViT-L-14-336px    |         86.3          | [HF:MLCD-ViT-L-14-336px](https://huggingface.co/DeepGlint-AI/mlcd-vit-large-patch14-336)   |
+| MLCD-ViT-B-32-224px    |         79.1          | [HF:MLCD-ViT-B-32-224px](https://huggingface.co/DeepGlint-AI/mlcd-vit-base-patch32-224)    | 
 
 
 ## Latest News