Story Published at: June 1, 2023 at 10:15PM
Notes on training BERT from scratch on an 8GB consumer GPU
A toy example of Bayesian hyperparameter optimization on parallel cloud VMs
Story Published at: November 22, 2022 at 10:08PM
Each country as a Pokemon, using Stable Diffusion
Story Published at: September 20, 2022 at 10:15PM