Update README.md

README.md

@@ -35,6 +35,6 @@ World = Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Da
 
 Training: set --my_testing "r" for latest RWKV-LM
 
-Inference: Use rwkv pip package 0.8.5+ for RWKV-5
+Inference: Use rwkv pip package 0.8.6+ for RWKV-5. Might overflow in fp16. Use fp32.
 
 inference algorithm reference: https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py