Update README.md

README.md

@@ -71,7 +71,7 @@ data together.  It also offers the option to flatten the data and provide a `bat
 ### Pretraining
 
 The model was trained on a node of 4xA40 (48 GB) for 10 epochs (~2 weeks). See the
-[training code](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) for all hyperparameters
+[training code](https://github.com/vector-institute/AtomGen) for all hyperparameters
 details.
 
 ## Evaluation results