Update README.md

README.md

@@ -10,7 +10,8 @@ widget:
 This model is a GPT2 model trained to generate ancient Chinese text, with `bert-base-chinese` as tokenizer. 
 
 ## Training data
-It's trained on the classic Chinese texts fetched from ctext.org. 
+It's trained on the classic Chinese texts fetched from ctext.org. Current training data is really small scale -- all training text data together was 19Mb. 
+
 <details>
   <summary> "Reading list" of this model </summary>