Update README.md

README.md

@@ -17,7 +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-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 efficiency of the vision foundation model. As same as InternViT-6B-448px-V1-5, the input resolution of this model is dynamic 448×448, where the basic tile size is 448×448, and the number of tiles ranges from 1 to 12 during training. Additionally, it inherits the powerful robustness, OCR capability, and high-resolution processing capability from InternViT-6B-448px-V1-5.
+We developed InternViT-300M-448px by leveraging knowledge distillation from the strong vision foundation model, [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5). This update primarily focuses on the efficiency of the vision foundation model. Like its predecessor, the input resolution of this model is dynamic 448×448, where the basic tile size is 448×448, and the number of tiles ranges from 1 to 12 during training. 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