update

Author: anxiangsir

README.md

@@ -0,0 +1,14 @@
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="asset/llava_vit_white.png">
+    <source media="(prefers-color-scheme: light)" srcset="asset/llava_vit_white.png">
+    <img alt="LLaVA-OneVision 1.5" src="output/llava_onevision_white.png" width="600" style="max-width: 100%;">
+  </picture>
+</p>
+
+---
+
+
+# LLaVA-ViT: Native ViT For Multimodal Large Language Models
+
+