Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,7 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
|
|
| 27 |
- Architecture: InternViT-6B + MLP + LLaMA2-13B
|
| 28 |
- Params (M): 19B
|
| 29 |
- Image size: 448 x 448
|
|
|
|
| 30 |
|
| 31 |
- **Training Strategy:**
|
| 32 |
- Pretraining Stage
|
|
|
|
| 27 |
- Architecture: InternViT-6B + MLP + LLaMA2-13B
|
| 28 |
- Params (M): 19B
|
| 29 |
- Image size: 448 x 448
|
| 30 |
+
- Number of visual tokens: 256
|
| 31 |
|
| 32 |
- **Training Strategy:**
|
| 33 |
- Pretraining Stage
|