Update README.md
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
|
|
| 26 |
- **Model Stats:**
|
| 27 |
- Params (M): 5540 (the last 3 blocks are discarded)
|
| 28 |
- Image size: 448 x 448
|
| 29 |
-
- **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
|
| 30 |
- **Note:** InternViT-6B originally had 48 blocks, and we found that using the output after the fourth-to-last block worked best for VLLM. For ease of use and to save GPU memory, we simply discarded the last 3 blocks. Now the model has only 45 blocks and the number of parameters has been reduced from 5.9B to 5.5B. **Please set mm_vision_select_layer=-1 when using this model.**
|
| 31 |
## Model Usage (Image Embeddings)
|
| 32 |
|
|
|
|
| 26 |
- **Model Stats:**
|
| 27 |
- Params (M): 5540 (the last 3 blocks are discarded)
|
| 28 |
- Image size: 448 x 448
|
| 29 |
+
- **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi, OCR data
|
| 30 |
- **Note:** InternViT-6B originally had 48 blocks, and we found that using the output after the fourth-to-last block worked best for VLLM. For ease of use and to save GPU memory, we simply discarded the last 3 blocks. Now the model has only 45 blocks and the number of parameters has been reduced from 5.9B to 5.5B. **Please set mm_vision_select_layer=-1 when using this model.**
|
| 31 |
## Model Usage (Image Embeddings)
|
| 32 |
|