Update README.md

README.md

@@ -2,10 +2,18 @@
 license: apache-2.0
 ---
 
-Use rwkv pip package 0.8.7+ for RWKV-5 inference.
+Use https://github.com/BlinkDL/ChatRWKV/tree/main/music to run rwkv-music models.
 
-Interesting fact: RWKV-5 is great at benchmarks (excellent zeroshot performance), but generates quite worse music (just like GPT models) despite lower loss.
+https://huggingface.co/BlinkDL/rwkv-4-music
 
-This fits my theory: Dot-product is good for uncreative work, while Channelwise is good for creative work.
+https://huggingface.co/BlinkDL/rwkv-5-music
 
-Therefore use https://huggingface.co/BlinkDL/rwkv-4-music for better music. Or let's see if someone can find a better sampling method to improve RWKV-5 results.
+MIDI model (RWKV-4 sounds better):
+
+Training data: https://huggingface.co/datasets/breadlicker45/bread-midi-dataset
+
+ABC model (RWKV-5 sounds better):
+
+Training data: ```load_dataset("sander-wood/massive_abcnotation_dataset")["train"]```
+
+https://huggingface.co/datasets/sander-wood/massive_abcnotation_dataset