Update README.md

README.md

@@ -20,7 +20,6 @@ tags:
 
 **Nemotron-Terminal** is a family of models specialized for autonomous terminal interaction, fine-tuned from the Qwen3 base (8B, 14B, and 32B). Developed by NVIDIA, these models utilize [Terminal-Corpus](https://huggingface.co/datasets/nvidia/Terminal-Corpus), a large-scale open-source dataset for terminal tasks, to achieve performance that rivals frontier models many times their size.
 
-[Image of Terminal-Task-Gen pipeline architecture]
 
 ## Model Variants
 We release the following variants of the Nemotron-Terminal family:
@@ -41,6 +40,7 @@ The Nemotron-Terminal family demonstrates profound leaps in capability compared
 
 ## Usage
 The models are trained using the **Terminus 2** scaffolding and output a structured JSON format.
+For evaluation on terminal bench 2.0, we encourage using Terminus 2 scaffolding to maintain consistency with training.
 
 ### Expected Output Format
 ```json