Update README.md

README.md

@@ -118,6 +118,23 @@ Adaptive Math 2 is intended for:
 
 The dataset emphasizes transparent reasoning instead of answer memorization.
 
+## Acknowledgement
+
+Adaptive Math 2 was developed using the **Adaption Lab AutoScientist** pipeline with **Meta Llama 4 Scout 17B** as the foundation model.
+
+Special thanks to:
+
+- **Adaption Lab** for the AutoScientist training and evaluation platform.
+- **Meta AI** for the Llama 4 Scout base model.
+- **Hugging Face** for open model hosting and distribution.
+- **Kaggle** for dataset publication and community accessibility.
+
+This project demonstrates how adaptive instruction datasets can improve mathematical reasoning, instruction following, and educational AI through efficient LoRA fine-tuning.
+
+## 📊 Model Performance
+
+![Adaptive Math 2 Performance](adaptive_math_2_performance.png)
+
 ```json
 {
   "job_id": "8db3bddd-326c-44ba-8440-2456d10d33f2",