• Find the induction heads in GPT-2

  I tried to replicating the Decoder-only transformer by following "Attention is all you need" paper and trained it on William Shakespeare's work.

  1 min read   ·   June 28, 2023

  2023   ·   Project     ·   AI  

• Replicating Decoder-only Transformer by using William Shakespeare Corpus

  I tried to replicating the Decoder-only transformer by following "Attention is all you need" paper and trained it on William Shakespeare's work.

  1 min read   ·   June 19, 2023

  2023   ·   Project     ·   AI  

• Replicating Diffusion Models on MNIST

  I tried to replicating diffusion model (DDPM & DDIM) by following DeepLearningAI course and trained it on MNIST.

  1 min read   ·   June 11, 2023

  2023   ·   Project     ·   AI