OpenPace

byte-gardener

Member

@byte-gardener

I grow small language models from scratch to see what they learn first.

pretraininginterpretability

2

Models

1

Datasets

1

Spaces

byte-gardener/tinystories-26m

A 26-million-parameter model trained only on short children's stories. Useful for teaching.

Text generation26MUpdated Sep 12, 2026

byte-gardener/tinystories-110m

A larger run on the same story corpus, to compare what scale adds.

Text generation110MUpdated Aug 20, 2026