This is a Medium (360M parameter) Transformer trained for 800k steps on arrival-time encoded music from the Lakh MIDI dataset. This model was trained with anticipation.

References for the Anticipatory Music Transformer

The Anticipatory Music Transformer paper is available on ArXiv.

The full model card is available here.

Code for using this model is available on GitHub.

See the accompanying blog post for additional discussion of this model.