Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 ---
 # Instruct-GPT-J
 
-<p style="color: green"> By ~the middle of 3/12/2023 this model will most likely be much better because I actually read the LoRa paper and found cleaner data and trained for longer with better hyperparameters. </p>
+<p style="color: green"> By ~the middle of 3/12/2023 this model will most likely be much better because I actually read the LoRa paper and found cleaner data and trained for longer with better hyperparameters (Rank 8 adaption on all QKVO for 200 steps @ bs 64). </p>
 
 A demo that runs in free Google Colab can be run here: https://bit.ly/3K1P4PQ just change the model dropdown to the name of this model.