Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
We adopted the official [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT) and the official training dataset [LLaVA-NeXT-Data](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Data) for evaluating the foundational visual models.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
| Vision Tower | RoPE2D | ChartQA | DocVQA | InfoVQA | OCRBench | MMMU |
|
| 9 |
+
| :--------------------------- | :----: | :-------- | :-------- | :-------- | :--------- | :-------- |
|
| 10 |
+
| CLIP (ViT-L-14-336px) | × | 66.52 | 75.21 | 38.88 | 525.00 | 44.20 |
|
| 11 |
+
| SigLIP (ViT-SO400M-384px) | × | 69.28 | 76.71 | 41.38 | 554.00 | 46.78 |
|
| 12 |
+
| DFN5B (ViT-H-14-378px) | × | 64.36 | 70.87 | 38.59 | 473.00 | **48.00** |
|
| 13 |
+
| **MLCD (ViT-L-14-336px)** | × | 67.84 | 76.46 | 43.48 | 531.00 | 44.30 |
|
| 14 |
+
| **MLCD (ViT-bigG-14-336px)** | √ | **71.07** | **79.63** | **44.38** | **572.00** | 46.78 |
|