🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Fix formula typo in Relative MHA (#242)
${(\textcolor{lightgreen}{\mathbf{A + C}})}_{i,j} = Q_i^\top K_j + \textcolor{orange}{v^\top} K_j$ F
f-hy committed
5ec0f7085566bf9db9ace20e0c3ccbbd9f902170
Parent: fea91b9
Committed by GitHub <noreply@github.com>
on 3/2/2024, 8:49:06 AM