Update README.md

README.md

@@ -6,16 +6,6 @@ base_model:
 
 This is the AWQ model of GroundNext-7B-V0, which runs on lower VRAM(e.g. 12G). GroundNext-7B-V0 is the GUI agent model trained on large-scaled, human-expert-annoated desktop application dataset.
 
-## Model Description
-**GroundNext-7B-V0** has the following characteristics:
-- **Type**: Vision-Language Model for GUI Grounding
-- **Base Model**: Qwen2.5-VL-7B-Instruct
-- **Training Approach**: Two-stage (Supervised Fine-tuning + Reinforcement Learning with RLOO)
-- **Number of Parameters**: 7.0B
-- **Training Data**: 700K human-annotated desktop demonstrations from GroundCUA dataset
-- **Context Length**: 262,144 tokens (inherited from base model)
-- **Specialization**: Desktop GUI element grounding with cross-platform generalization
-
 ## Perforamnce 
 ### Desktop Grounding Benchmarks