100M tokens. Infinite compute. Lowest val loss wins.
Python 563 87
Pretraining Transformers Without Backpropagation
Python 189 22
Speedrun for pretraining without backpropagation
Python 37 3
Python 22 1
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
There was an error while loading. Please reload this page.