---
title: rwkv-5-music
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-music"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-music.md"
repository: AI-ModelScope/rwkv-5-music
last_updated: 2023-10-06
license: "Apache License 2.0"
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 9482
stars: 2
---

# rwkv-5-music

> rwkv-5-music - AI-ModelScope 在 ModelScope 开源的模型。Use https://github.com/BlinkDL/ChatRWKV/tree/main/music to run rwkv-music models.

AI-ModelScope/rwkv-5-music 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: AI-ModelScope/rwkv-5-music
- **License**: Apache License 2.0
- **Downloads**: 9482
- **Stars**: 2
- **Last updated**: 2023-10-06

Source: https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-music

---

Use https://github.com/BlinkDL/ChatRWKV/tree/main/music to run rwkv-music models.

https://huggingface.co/BlinkDL/rwkv-4-music

https://huggingface.co/BlinkDL/rwkv-5-music

MIDI model (RWKV-4 sounds better):

Tokenizer: https://github.com/briansemrau/MIDI-LLM-tokenizer

Training data: https://huggingface.co/datasets/breadlicker45/bread-midi-dataset

ABC model (RWKV-5 sounds better if you use topp=0.5 without topk):

Training data: ```load_dataset("sander-wood/massive_abcnotation_dataset")["train"]```

https://huggingface.co/datasets/sander-wood/massive_abcnotation_dataset