Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ pipeline_tag: image-feature-extraction
|
|
19 |
|
20 |
[\[π€ HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[π Quick Start\]](#model-usage) [\[π Community-hosted API\]](https://rapidapi.com/adushar1320/api/internvl-chat) [\[π δΈζ解读\]](https://zhuanlan.zhihu.com/p/675877376)
|
21 |
|
22 |
-
We develop InternViT-6B-448px-V1-5 based on the pre-training of the strong foundation of [InternViT-6B-448px-V1
|
23 |
Additionally, we enhance the data scale, quality, and diversity of the pre-training dataset, resulting in the powerful robustness, OCR capability, and high-resolution processing capability of our
|
24 |
1.5 version model.
|
25 |
|
|
|
19 |
|
20 |
[\[π€ HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[π Quick Start\]](#model-usage) [\[π Community-hosted API\]](https://rapidapi.com/adushar1320/api/internvl-chat) [\[π δΈζ解读\]](https://zhuanlan.zhihu.com/p/675877376)
|
21 |
|
22 |
+
We develop InternViT-6B-448px-V1-5 based on the pre-training of the strong foundation of [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2). In this update, the resolution of training images is expanded from 448×448 to dynamic 448×448, where the basic tile size is 448×448 and the number of tiles ranges from 1 to 12.
|
23 |
Additionally, we enhance the data scale, quality, and diversity of the pre-training dataset, resulting in the powerful robustness, OCR capability, and high-resolution processing capability of our
|
24 |
1.5 version model.
|
25 |
|