m-a-p
/

ChatMusician

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

a43992899 commited on Feb 28

Commit

875f229

•

1 Parent(s): d603a22

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -88,7 +88,8 @@ dump_wav('cm_music_piece.wav', audio, sample_rate=44100, use_int16=True)
 - The MusicThoeryBench results reported in the paper are obtained with perplexity mode. Direct generation may result in a worse performance.
 - We observe that using the current version of training data, ChatMusician presents a weak in-context-learning and chain-of-thoughts ability. The community should work on improving the music data quality.
-## Example Prompts
 ### Function: Chord Conditioned Music Generation
 ```

 - The MusicThoeryBench results reported in the paper are obtained with perplexity mode. Direct generation may result in a worse performance.
 - We observe that using the current version of training data, ChatMusician presents a weak in-context-learning and chain-of-thoughts ability. The community should work on improving the music data quality.
+## Example Stable Prompts
+We provide some of the prompts that are tested to be stable. For more prompts, please check 🤗 [MusicPile](https://huggingface.co/datasets/m-a-p/MusicPile).
 ### Function: Chord Conditioned Music Generation
 ```