Update README.md

README.md

@@ -18,9 +18,11 @@ datasets:
 
 These are RWKV-4-Pile 1.5/3/7/14B models finetuned on Alpaca, CodeAlpaca, Guanaco, GPT4All, ShareGPT and more. **Even the 1.5B model is surprisingly good for its size.**
 
-Gradio Demo: https://huggingface.co/spaces/BlinkDL/Raven-RWKV-7B
+Gradio Demo: https://huggingface.co/spaces/BlinkDL/Raven-RWKV-7B and https://huggingface.co/spaces/BlinkDL/ChatRWKV-gradio
 
-Use https://github.com/BlinkDL/ChatRWKV (fast CUDA) or https://github.com/saharNooby/rwkv.cpp (fast CPU, use INT8 for best results) to run them.
+RWKV models inference: https://github.com/BlinkDL/ChatRWKV (fast CUDA).
+
+Q8_0 models inference: https://github.com/saharNooby/rwkv.cpp (fast CPU).
 
 See https://github.com/BlinkDL/RWKV-LM for details on the RWKV Language Model (100% RNN).