Update README.md

README.md

@@ -31,6 +31,10 @@ If you use `ollama`, `llama-cpp`, `vllm` or any other inference iengine, you nee
 '\nRespond in the following format:\n<reasoning>\n...\n</reasoning>\n<answer>\n...\n</answer>\n'
 ```
 
+## Want to train your own?
+
+Read my article [here](https://medium.com/@hooman_66365/build-your-own-medical-mini-deepseek-r1-with-reinforcement-learning-508509cd7d83) or follow the [notebook](https://github.com/hooman650/MedQwenReasoner).
+
 ## Key Features
 
 - Medical domain expertise combined with mathematical reasoning capabilities