Update README.md

README.md

@@ -18,6 +18,20 @@ remove eod, add special token, change vocabs.
 
 this model is used to QA in large texts, do some in context learning with knowledge indexed database.
 
+
+## trainning details
+
+train with this kind of format, 
+
+<s>User: <sys>xxxx\n\n</sys>xxxxx</s><s>Assistant: xxxxx\n\n</s><s>User: xxxx\n\n</s><s>Assistant: \n\n</s>
+
+so ,use User Assistant as your prefix names.
+and when inference in RWKV runner, just use the following format is fine.
+
+User: xxxx\n\nAssistant: xxxx\n\n，wnich are the test cases used.
+
+you can see Generalization ablility is great in this model
+
 --------------------------------------------
 if wanna test this model ,some effort needed, copy back-python folder to a new one ,which is in the same folder with rwkv runner exe file , then past rwkv_vocab_v20230424.txt into rwkv_pip folder to replace the vocabs file