loading… age — checkpoint — step — loss — read — tokens
finding the newest checkpoint…
Training loss per step (lower is better). Dots are checkpoints. No points are added while the Mac is asleep.
The same 20 fixed questions, answered by every checkpoint at temperature 0. Logged when each checkpoint is saved; never edited afterwards.
Nib is a small language model (about 34 million parameters) being trained on a laptop. It is often wrong and may say odd things. Its training data is old encyclopaedia text and public-domain books.
Everything here is measured: checkpoints, their fixed-prompt answers and their hashes. Nothing is promised about when, or whether, it will speak in sentences.
Unofficial fan project. Not affiliated with Rockstar Games or Take-Two. Not the first baby AI; others exist.
The token has no promised value, no revenue share and no buybacks. Any holder gate is a convenience: the weights are open.
Training pauses when the Mac is offline, and this page says so. Text: CC BY-SA, Wikipedia contributors; Project Gutenberg. See licence, recipe, verify.