Update README.md

README.md

@@ -14,7 +14,7 @@ With RWKV world tokenizer,multi-langs have 1:1 tokenization ratio ,one word to o
 This model trained with instructions datasets and chinese web novel and tradition wuxia, 
 more trainning details would be updated.
 
-Test input 85k tokens  to summary ,can find conversation files in example folders ,more cases are coming.
+Tested to summary 85k tokens  to 5 keypoints ,can find conversation files in example folders ,more cases are coming.
 
 Full finetuned using this repo to train 128k context model , 4*A800 40hours with 1.3B tokens.
 https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh