Update README.md

README.md

@@ -17,9 +17,7 @@ pipeline_tag: image-feature-extraction
 
 \[[InternVL 1.5 Technical Report](https://arxiv.org/abs/2404.16821)\]  \[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\] \[[中文解读](https://zhuanlan.zhihu.com/p/675877376)]
 
-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.
-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
-1.5 version model. 
+We develop InternViT-300M-448px based on the distillation of the strong foundation of [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5). This update primarily focuses on the parameter count. 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. Additionally, it inherits the powerful robustness, OCR capability, and high-resolution processing capability from InternViT-6B-448px-V1-5.
 
 ## Model Details
 - **Model Type:** vision foundation model, feature backbone