Update README.md

README.md

@@ -72,4 +72,4 @@ print(response[0]["generated_text"].split("<s>Bot: ")[-1])
 ```
 
 ## Training & Data:
-The training was done on 1 NVIDIA DGX using DeepSpeed ZeRO 3 for three epochs on roughly 4GB of carefully selected translation data.
+The training was done on 1 NVIDIA DGX using DeepSpeed ZeRO 3 for three epochs on roughly 4GB of carefully selected translation data. It is a full finetune of all of the model parameters.