Update README.md

README.md

@@ -81,6 +81,10 @@ audio = Synthesizer().render(s, stereo=True)
 dump_wav('cm_music_piece.wav', audio, sample_rate=44100, use_int16=True)
 ```
 
+## Chat demo
+ChatMusician supports gradio web demo and multi-turn dialogue, please visit our [github](https://github.com/hf-lin/ChatMusician) for more details.
+Our web demo also supports rendering ABC scores into images.
+
 ## Limitations
 - The model currently only supports strict format and close-ended instructions for the music tasks. If we have more funding, we plan to create a more diverse multi-turn music instruction chat data for better generalization.
 - The model suffers from hallucinations, and shouldn't be used for music education. It could be improved by feeding more music textbooks, blogs, etc. And RLHF may help, too.