Update README.md

deepglint · Feb 7, 2025 · a834d19 · a834d19
1 parent 71e64fc
commit a834d19
Showing 1 changed file with 8 additions and 11 deletions.
diff --git a/README.md b/README.md
@@ -17,6 +17,14 @@ We used the official LLaVA-NeXT and conducted training and validation with the o
 | MLCD (ViT_L_14_336px) [HF](https://huggingface.co/DeepGlint-AI/mlcd-vit-large-patch14-336)   | 67.84   | 76.46  | 43.48   | 531.00   | 44.30 |
 | MLCD (ViT_bigG_14_336px) [HF](https://huggingface.co/DeepGlint-AI/mlcd-vit-bigG-patch14-336) | 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                                                                               | Google Drive |
+| :--------------------- | :-------------------: | :----------------------------------------------------------------------------------------- | :----------: |
+| 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
 🎅 [2024/12] We have launched the [MLCD-Seg-7B](https://github.com/deepglint/unicom/tree/main/downstream), achieving scores of 85.3/81.5 on RefCOCO[testA/B], 82.9/75.6 on RefCOCO+[testA/B], and 80.5 on RefCOCOg[test].  
@@ -123,17 +131,6 @@ MLCD improves upon traditional approaches by clustering the the LAION dataset, w
 </div>
 
 
-### Model Zoo
-
-| Model Name             | ImageNet Linear Probe | Hugging Face                                                                               | Google Drive |
-| :--------------------- | :-------------------: | :----------------------------------------------------------------------------------------- | :----------: |
-| 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)    |      -       |
-
-
-
-
 ###  MLLMs Evaluation Results
 
 <p align="center" width="100%">