Skip to content

Implements a GPT‑style Transformer architecture from Vaswani et al. (2017) to generate text and solve arithmetic tasks.

Notifications You must be signed in to change notification settings

treytuscai/Transformers

Repository files navigation

🔁 Transformers

Implements a GPT-style Transformer model from scratch using our modular deep learning library, DeepNeuralLib. Trains small transformers to perform arithmetic tasks and larger ones to generate Shakespearean text, showcasing attention mechanisms and positional encoding.

About

Implements a GPT‑style Transformer architecture from Vaswani et al. (2017) to generate text and solve arithmetic tasks.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •