Update README.md

README.md

@@ -77,3 +77,7 @@ Inspired by Deepseek-R1, we further optimized the training procedures of NotaGen
 - We introduced a post-training stage between pre-training and fine-tuning, refining the model with a classical-style subset of the pre-training dataset.
 - We removed the key augmentation in the Fine-tune stage, making the instrument range of the generated compositions more reasonable.
 - After RL, we utilized the resulting checkpoint to gather a new set of post-training data. Starting from the pre-trained checkpoint, we conducted another round of post-training, fine-tuning, and reinforcement learning.
+
+
+For implementation of pre-training, fine-tuning and reinforcement learning on NotaGen, please view our [github page](https://github.com/ElectricAlexis/NotaGen).
+