Upload README.md with huggingface_hub

README.md

@@ -47,7 +47,7 @@ tags:
 
 ## Model Description
 
-**Gestalt** is an interplay-centric large multimodal model built on a unified discrete diffusion framework. Through progressive training — multimodal pretraining, continual pretraining, and interplay-oriented supervised fine-tuning — Gestalt supports both **multimodal understanding** (e.g., visual question answering, image captioning) and **multimodal generation** (e.g., text-to-image generation, image editing) within a single model.
+**Gestalt** is an interplay-centric large multimodal model built on a unified discrete diffusion framework. Through multimodal pretraining, continual pretraining, and interplay-oriented supervised fine-tuning,Gestalt supports both understanding and generation.
 
 | Property | Value |
 |:--|:--|