Update README.md

README.md

@@ -48,7 +48,7 @@ RWKV-4-Pile-7B-20221115-8047.pth : Trained on the Pile for 332B tokens.
 * SC2016 acc 73.44%
 * Hellaswag acc_norm 65.51%
 
-### Instruct-test models: only useful if you construct your prompt following dataset templates
+### Instruct-test models (OLD): only useful if you construct your prompt following dataset templates
 
 Note I am using "Q: instruct\n\nA: result" prompt for all instructs.
 
@@ -61,7 +61,3 @@ instruct-tuned on https://huggingface.co/datasets/Muennighoff/flan & NIv2
 ### Chinese models
 
 RWKV-4-Pile-7B-EngChn-testNovel-xxx for writing Chinese novels (trained on 200G Chinese novels.)
-
-RWKV-4-Pile-7B-EngChn-testxxx for Chinese Q&A (trained on 10G Chinese text. only for testing purposes.)
-
-RWKV-4-Pile-7B-EngChn-test5 is tuned on more ChatGPT-like data and it's pretty decent. Try "+i 开题报告" "+i 世界各国美食" in latest ChatRWKV v2.