Update README.md

README.md

@@ -8,6 +8,8 @@ datasets:
 Dpo trained from cognitivecomputations/dolphin-2.6-mistral-7b， used Intel/orca_dpo_pairs for the dataset. 
 Trained for 1200 steps.  Trained with 1024 context window.
 
+Training code: https://github.com/hengjiUSTC/learn-llm/blob/main/dpo_demo.ipynb
+
 # Model Details
 * **Trained by**: trained by HenryJJ.
 * **Model type:**  **dolphin-2.6-mistral-7b-dpo-orca** is an auto-regressive language model based on the Llama 2 transformer architecture.