Update README.md

README.md

@@ -38,7 +38,8 @@ model-index:
 
 # ATLAS-8B-Thinking
 
-![ATLAS Banner](https://huggingface.co/Arc-Intelligence/ATLAS-8B-Thinking/resolve/main/ATLAS.jpg)
+![ATLAS Banner](https://huggingface.co/Arc-Intelligence/ATLAS-8B-Thinking/resolve/main/ATLAS.png)
+
 
 **ATLAS-8B-Thinking** is a specialized teacher model developed by Arc Intelligence, designed to solve the core reliability problem in reinforcement learning for LLMs. Standard RL fine-tuning is often brittle, leading to performance degradation where new skills are learned at the expense of old ones.
 
@@ -48,6 +49,9 @@ This model is a core component of the open-source [ATLAS Framework](https://gith
 
 ## Model Performance
 
+![Performance Chart](https://huggingface.co/Arc-Intelligence/ATLAS-8B-Thinking/resolve/main/performance-chart.png)
+
+
 The ATLAS framework, using this teacher model, produces the following improvements in a student model (Qwen3-4B) compared to the student baseline. The results highlight a rare combination of increased performance, higher efficiency, and fundamental reliability.
 
 | Metric                 | Improvement | Notes                                                      |