Skip to page content
SAVRN
Search Plan a project

Independent publisher

Wojciech Matejuk

wmatejuk

Models in Library0
Datasets in Library2
Models on Hugging Face2
Followers7

Compare the published evidence

This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Text generation.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Pre-tokenized MIDI pieces for IsoFLOP scaling-law runs. Each row is one full piece (no time-windowing); training crops sequences from packed token bins. The source column is the original piece metadata as JSON so a row can be traced back to its EPR Labs source dataset. Based on MIDI datasets gathered by EPR Labs. - maxtimestep: 1.0 - nvelocitybins: 32 - timeunit: 0.01 The repository also stores midicodec.json and Hugging Face tokenizer files so token ids can be rebuilt exactly. Train pieces only (more setting). Validation and test are unaugmented Maestro. - maestro-sustain-v2 - giant-midi-sustain-v2 - pijamia-midi-v1 - atepp-1.1-sustain-v2 - music-net - piast-midi - aria-pruned-base-v2…

Publicly accessible
View dataset