AI & ML interests

Small language models, training from scratch, and distributed training on Apple Silicon.

Recent Activity

wzebrowski  updated a Space 2 days ago
OpenSML/README
wzebrowski  updated a model 5 days ago
OpenSML/Solstice-1-175M
wzebrowski  published a model 9 days ago
OpenSML/Solstice-1-175M
View all activity

Organization Card

OpenSML

small models. bigger possibilities.

OpenSML is an independent research lab exploring the full process of building small language models—from preparing data and training tokenizers to pretraining, evaluation, and fine-tuning.

We build from scratch on Apple Silicon. Our current training setup connects five Macs for distributed training.

We share model weights, code, and research findings so others can explore, experiment, and build on the work.

Latest release

Solstice-1-175M is a 175M-parameter English chat model. We pretrained it on 42B tokens across five Macs, then fine-tuned it for short conversations, reading comprehension, and instruction following.

Solstice technical report · Source code

First release · OpenSML-150M · 150M technical report

OpenSML website

Contact: william.zebrowski@me.com

datasets 0

None public yet